Conference Programs

and Abstract

nd2019 2 INTERNATIONAL CONFERENCE AND WORKSHOP

ON TELECOMMUNICATION, COMPUTING, ELECTRICAL,

ELECTRONICS AND CONTROL

November 19-21, 2019

at Royal Ambarrukmo Hotel,

Yogyakarta, Indonesia

Conference Programs And

Abstract

2019 2nd International Conference and Workshop on Telecommunication, Computing, Electrical, Electronics,

and Control (ICW-TELKOMNIKA 2019)

19-20 November 2019

YOGYAKARTA, INDONESIA

iii

Foreword from the Conference Chair

Assalamu'alaikum warahmatullahi wabarakatuh. To our distinguished guests, ladies, and gentlemen, Welcome to 2019 2nd International Conference and Workshop on Telecommunication, Computing, Electrical, Electronics, and Control (ICW-TELKOMNIKA 2019). We welcome all the attendees to Yogyakarta, the city of culture and education. ICW-TELKOMNIKA is an annual international conference and workshop where experts come to present and share their latest works in the field of telecommunication, computing, electrical, electronics, and control. This year’s conference theme is “Computational Intelligence Techniques in the Context of Industry 4.0: Present Findings & Future Directions for Living a Better Life”. In ICW-TELKOMNIKA 2019, only high quality selected papers are accepted to be presented. It was successfully held with the selected 173 papers among 475 submissions. Thus the acceptance rate was 36.4%. We would like to express our gratitude to all participants presenting your experiences in this vast conference. We are also thankful to all the international reviewers, steering committee, TPC members, and organizing a committee for their valuable work. We would like to give a compliment to all partners in publications and sponsorships for their valuable supports. We hope you enjoy your stay with us.

Wassalamu'alaikum warahmatullahi wabarakatuh.

Nuryono Satya Widodo Executive Chair

Anton Yudhana, Ph.D. Executive Chair

iv

Foreword from the General Chair

In the name of Allah, Most Gracious, Most Merciful. Welcome to 2019 2nd International Conference and Workshop on Telecommunication, Computing, Electrical, Electronics, and Control (ICW-TELKOMNIKA 2019) in the Special Region of Yogyakarta, a centre of Javanese culture as well as the centre of learning which is marked by the existence of 120 state and private education institutions. ICW-TELKOMNIKA is an annual international conference and workshop where all experts from home and abroad come together to present and share their latest works. They will share new ideas and visions for achieving future telecommunication, computing, electrical, electronics, and control to the world. In this event, there is a one-day scientific writing workshop guided by highly qualified experts. The objective of this workshop is to provide guidelines on how to write a good paper, mainly how to write clear and concise papers, edit for structure and clarity, edit for spelling and grammar and add the finishing touches. In addition to the workshop, the authors will also be guided specifically and technically by experts in the field in parallel sessions to finalise and polish the final presentation. Organizing such a prestigious conference was incredibly challenging and would have been impossible without or outstanding committee, so we would like to extend our sincere appreciation to all committees and volunteers from Universitas Ahmad Dahlan (UAD) as the host, and Institute of Advanced Engineering and Science (IAES) and Smart Grid Indonesia (PJCI) for providing us with much needed support, advice, and assistance on all aspects of the conference. Especially, we would like to express our hearty gratitude to all participants for coming, sharing, and presenting your experiences in this vast conference. We are also thankful to all the international reviewers, steering committee, TPC members, and the organizing committee for their valuable work. We would like to give a compliment to all partners in publications and sponsorships for their valuable supports. We do hope that this event will encourage collaboration among us now and in the future. We wish you all find unique opportunity to get a rewarding technical program, intellectual ideas and innovations, and chance to forge new friendships; and that everyone enjoys some of what in Yogyakarta, one of the historical cities in Indonesia, known for its friendly people, historical building and temples, culture, and delicate food. We hope you enjoy your stay here!

Tole Sutikno, Ph.D. General Chair Editor-in-Chief, TELKOMNIKA Director, Institute of Scientific Publication and UAD Press (LPPI) Universitas Ahmad Dahlan (UAD) Yogyakarta, Indonesia

v

Foreword from the Rector of Universitas Ahmad Dahlan

It is our great pleasure to join and welcome all participants of 2019 2nd International Conference and Workshop on Telecommunication, Computing, Electrical, Electronics, and Control (ICW-TELKOMNIKA 2019) in Yogyakarta. Universitas Ahmad Dahlan (UAD) fully supports development four core areas: research, education, communication of research results, and knowledge sharing. I am happy to see this great work as part of a collaboration between Universitas Ahmad Dahlan, Smart Grid Indonesia (PJCI), and the Institute of Advanced Engineering and Science (IAES). On this occasion, I would like to congratulate all participants for their scientific involvement and willingness to share their findings at this conference. I believe that this conference can play an important role in encouraging and embrace cooperative, collaborative, and interdisciplinary research among engineers and scientists. I do expect that this kind of similar event will be held in the future as part of activities in education research and social responsibilities of universities, research institutions, and industries internationally. My heartful gratitude is dedicated to organizing committee members and the staffs of Universitas Ahmad Dahlan for their generous effort and contribution toward the success of ICW-TELKOMNIKA 2019.

Dr. Muchlas, M.T.

Rector Universitas Ahmad Dahlan (UAD)

Yogyakarta, Indonesia

vi

Organizers

Universitas Ahmad Dahlan (UAD) is a development of the institute of Teacher Training and Education (Teacher’s Training Collage) Muhammadiyah Yogyakarta. The latter institute is a development institution of Higher Education Guidance and Counseling Branch of Muhammadiyah in Yogyakarta established on 18th November 1960. UAD is located in Yogyakarta, a special district in The southern part of Central Java renowned as a center of education and classical Javanese fine art and culture. UAD is one of the leading world private universities and rated as one of the top 50 Promising universities in Indonesia by Directorate General of Higher Education in 2011. Since its establishment, the university has sustained a strong tradition of academic integrity and gained an excellent reputation for its educational programs, research and student’s service. Besides, now UAD has five campuses spread on strategic location in Yogyakarta that known as city of student and city of culture. UAD offers community service programs from which students can draw authentic experience as well as invaluable insights into Indonesian Traditional culture and everyday life of local communities.

Institute of Advanced Engineering and Science (IAES) is a non-profit international scientific association of distinguished scholars engaged in engineering and science devoted to promoting researches and technologies in engineering and science field through digital technology. IAES is a fast growing organization that aims to benefit the world, as much as possible, via technological innovations. The mission of IAES is to encourage and conduct collaborative research in “state of the art” methodologies and technologies within its areas of expertise. IAES publishes high quality international journals in engineering and science area. It will also organize multidisciplinary conferences and workshop for academics and professionals and to get sponsors for supporting the activities. In addition, IAES is involved in many international projects and welcomes collaborative work. The IAES members include research excellent scientist, engineers, scholars, research and development center heads, faculty deans, department heads, professors, university postgraduate engineering and science student, experienced hardware and software development directors, managers and engineers, etc.

vii

Prakarsa Jaringan Cerdas Indonesia (Smart Grid Indonesia) is a non-governmental organization that is independent, professional, and transparent, that prioritizes the interest of the Indonesian people and is not affiliated with any political party. Smart Grid Indonesia aims to provide technology, regulation, education, and entrepreneurship and also provide various ways to realize intelligent networks, which are the infrastructure for the realization of Smart Indonesia.

viii

Organizing Committee 2019 2nd International Conference and Workshop on Telecommunication, Computing, Electrical, Electronics and Control (ICW-TELKOMNIKA 2019)

Advisors Faycal Djeffal, University of Batna, Batna, Algeria Franco Frattolillo, University of Sannio, Italy Frede Blaabjerg, Aalborg University, Esbjerg, Denmark Leo P. Ligthart, Delft University of Technology, Netherlands Luis Paulo Reis, University of Minho, Portugal Muchlas, Universitas Ahmad Dahlan, Indonesia Nidhal Bouaynaya, Rowan University, United States Nik Rumzi Nik Idris, Universiti Teknologi Malaysia, Malaysia Sanjeevikumar Padmanaban, Aalborg University, Denmark Sunardi, Universitas Ahmad Dahlan, Indonesia Tarek Bouktir, Ferhat Abbes University, Setif, Algeria Wanquan Liu, Curtin University of Technology, Australia

General Chair & Editor-in-Chief Tole Sutikno, Universitas Ahmad Dahlan, Indonesia

Executive Chairs Anton Yudhana, Universitas Ahmad Dahlan, Indonesia Nuryono Satya Widodo, Universitas Ahmad Dahlan, Indonesia

Associate Editors Achmad Widodo, Universitas Diponegoro, Indonesia Achmad Widodo, Universitas Diponegoro, Indonesia Ahmad Saudi Samosir, Lampung University, Indonesia Ahmet Teke, Cukurova University, Turkey Arianna Mencattini, University of Rome "Tor Vergata", Italy Assoc. Prof. Jumril Yunas, Universiti Kebangsaan Malaysia, Malaysia Asst. Prof. Dr. Andrea Francesco Morabito, University of Reggio Calabria, Italy Asst. Prof. Dr. Supavadee Aramvith, Chulalongkorn University, Thailand Auzani Jidin, Universiti Teknikal Malaysia Melaka, Malaysia D. Jude Hemanth, Karunya University, India Deris Stiawan, Universitas Sriwijaya, Indonesia Francis C.M. Lau, The University of Hong Kong, Hong Kong Franco Frattolillo, University of Sannio, Italy G.A. Papakostas, Eastern Macedonia and Thrace Institute of Technology, Greece Haruna Chiroma, Federal College of Education (Technical), Nigeria Huchang Liao, Sichuan University, China Hussain Al-Ahmad, Khalifa University, United Arab Emirates Ing. Mario Versaci, Mediterranea University of Reggio Calabria, Italy Jacek Stando, Technical University of Lodz, Poland Longquan Yong, Shaanxi University of Technology, China Lunchakorn Wuttisittikulkij, Chulalongkorn University, Thailand Mark S Hooper, Analog/RF IC Design Engineer (Consultant) at Microsemi, United States Mirosław Swiercz, Politechnika Bialostocka, Poland Mochammad Facta, Diponegoro University, Indonesia Mohamed Arezki Mellal, M'Hamed Bougara University, Algeria Munawar A Riyadi, Universitas Diponegoro, Indonesia

ix

Omar Lengerke, Universidad Autónoma de Bucaramanga, Colombia Shahrin Md Ayob, Universiti Teknologi Malaysia, Malaysia Srinivasan Alavandar, CK College of Engineering and Technology, India Surinder Singh, SLIET Longowal, India Tutut Herawan, Universiti Malaya, Malaysia Yang Han, University of Electronic Science and Technology of China, China Yin Liu, Symantec Research Labs’ Core Research group, United States Youssef Said, National Engineering School of Tunis (ENIT), Tunisia Yutthapong Tuppadung, Provincial Electricity Authority (PEA), Thailand Zahriladha Zakaria, Universiti Teknikal Malaysia Melaka, Malaysia Zhixiong Li, China University of Mining and Technology, China

Technical Program Committee Aditi Sharma, MBM Engineering College Jodhpur & Jai Narayan Vyas University, India Ahmad Azhari, Universitas Ahmad Dahlan, Indonesia Ahmed Toaha Mobashsher, The University of Queensland & LicenSys Pty Ltd., Australia Ahmed-Foitih Zoubir, University of Sciences and Technology of Oran, Algeria Akbar Sheikh-Akbari, Leeds Beckett University, United Kingdom Arif Rahman, Ahmad Dahlan University, Indonesia Benoît Muth, Benoît Muth, France Bidyut Mahato, IIT(ISM), DHANBAD, India Dat Vo, Australian Communications and Media Authority, Australia Dawam Dwi Jatmiko Suwawi, Telkom University, Indonesia Deepti Prakash Theng, G.H. Raisoni College of Engineering & RTMNU, India Der-Feng Tseng, National Taiwan University of Science and Technology, Taiwan Dimitrios Kallergis, University of Piraeus, Greece Divya Rishi Shrivastava, Manipal University Jaipur, India Domenico Ciuonzo, University of Naples, Italy Eduard Babulak, National Science Foundation, United States & Graduate Fellowship

Research Programs, Canada Eduardo Pinos, Universidad Politécnica Salesiana, Ecuador Evgeny Markin, United States, Russia & Richemar LLC, United States Fairul Azhar Abdul Shukor, Universiti Teknikal Malaysia Melaka, Malaysia Farrukh Arslan, Purdue University, United States Galandaru Swalaganata, Institut Agama Islam Negeri Tulungagung, Indonesia Gen Motoyoshi, NEC Corporation, Japan Giuseppe Di Lucca, University of Sannio, Italy Hamid Alasadi, Basra University, Iraq Haniza Nahar, Universiti Teknikal Malaysia, Malaysia Hao Wu, ZTE Corporation, China Harry Prabowo, Universitas Gadjah Mada, Indonesia Hasan Ali Khattak, COMSATS University, Islamabad, Pakistan Hengky Susanto, Huawei Technology, Hong Kong Hossein Jafari, Prairie View A&M University, United States Hsg Supreeth, SJB Institute of Technology, India Inung Wijayanto, Telkom University, Indonesia Iwan Riyadi Yanto, Universitas Ahmad Dahlan, Indonesia Jing-Sin Liu, Academia Sinica, Taiwan Junaid A Qayyum, Universiti Teknologi PETRONAS, Malaysia Junfei Qiu, University of York, United Kingdom Kaiying Sun, State University of New York (SUNY) at Buffalo, United States Kashif Sharif, Beijing Institute of Technology, China Keh-Kim Kee, University College of Technology Sarawak, Malaysia Kittipong Kan Tripetch, Rajamangala University of Technology, Thailand Konstantinos Giannakis, Ionian University, Greece

x

Krzysztof Kulpa, Warsaw University of Technology, Poland Longquan Yong, Shaanxi University of Technology, China Mahdi Imani, Texas A&M University, United States Malaoui Abdessamad, Sultan Moulay Slimane University of Beni Mellal, Morocco Manoj Riyal, VCSG Uttarakhand University of Horticulture and Forestry, India Marco Guazzone, University of Piemonte Orientale, Italy Maxime Leclerc, Thales Canada Inc, Canada Mayank Chaturvedi, Graphic Era University, India Md. Mehedi Hasan, University of Saskatchewan & Bangladesh University, Canada Md. Moidul Islam, Friedrich Schiller University Jena, Germany & American International,

University-Bangladesh, Bangladesh Mehran Alidoost Nia, University of Tehran, Iran Mohamed Hussein Moharam, Misr University For Science and Technology, Egypt Mohammed I. Younis, University of Baghdad & College of Engineering, Iraq Mohd Helmy Abd Wahab, Universiti Tun Hussein Onn Malaysia, Malaysia Mohsin Masood, University of Strathclyde, United Kingdom Muftah Fraifer, IDC-CSIS-UL, Ireland Muhamad Fadli Ghani, Universiti Kuala Lumpur Malaysian Institute of Marine Engineering

Technology, Malaysia Muhammad Hafidz Fazli Bin Md Fauadi, Universiti Teknikal Malaysia Melaka, Malaysia Muhammad Ishtiaq Ahmad, Beijing Institute of Technology, China Nemanja Zdravkovic, Norwegian University of Science and Techonlogy, Norway Nico Saputro, Florida International University, United States & Parahyangan Catholic

University, Indonesia Nisha Mithal, General Management, United States Nurdin Nurdin, Institut Agama Islam Negeri (IAIN) Palu & STMIK Bina Mulia Palu, Indonesia Nuryono Satya Widodo, Universitas Ahmad Dahlan, Indonesia Octavian Adrian Postolache, Instituto de Telecomunicações, Portugal Op Pal, UPTU, Lucknow & AICTE, India Padmanabhan Balasubramanian, Nanyang Technological University, Singapore Paolo Crippa, Università Politecnica delle Marche, Italy Pedro Luiz Teixeira de Moura, Instituto de Pesquisas Tecnológicas de São Paulo & HCL

Technologies, Brazil Prashant Verma, Amazon, United States Pujianto Yugopuspito, Universitas Pelita Harapan, Indonesia Pushpendra Singh, JK Lakshmipat University, Jaipur, India Qammer H Abbasi, University of Glasgow, United Kingdom Rajeev Mathur, Geetanjali Instt of Tech Studies, Udaipur & RTU, India Rajesh M Pindoriya, Indian Institute of Technology Mandi & IIT Mandi, India Ratheesh Kumar Meleppat, University of California Davis, United States Ravi Subban, Pondicherry University, Pondicherry, India Rodrigo Campos Bortoletto, São Paulo Federal Institute of Education, Science and

Technology & Federal, University of the ABC, Brazil Rodrigo Montufar-Chaveznava, Universidad Nacional Autonoma de Mexico, Mexico Ronald Mulinde, University of South Australia, Australia Roslina Mohamad, Universiti Teknologi Mara, Malaysia S. Vijaykumar, 6TH SENSE, An Advanced Research and Scientific Experiment Foundation,

India Sandeep Kakde, Y C College of Engineering, India Sayantam Sarkar, Vijaya Vittala Institute of Technology, India Senthil Sivakumar, St. Joseph University, Tanzania Seyed Hossein Hosseini, Sahand University of Technology, Iran Seyed Sahand Mohammadi Ziabari, Vrije University of Amsterdam, The Netherlands Sharad W. Mohod, SGB Amravati University Amravati, India Shashikant Shantilal Patil, SVKM NMIMS Mumbai India, India

xi

Shuvendu Rana, University of Strathclyde, United Kingdom Soufiana Mekouar, Mohammed V University Rabat, Morocco Srinivasulu Tadisetty, Kakatiya University College of Engineering and Technology, India Sudha T, University of Calicut, India Sumita Mishra, Amity University Lucknow, India Tapas Kumar Maiti, Hiroshima University, Japan TC Manjunath, Visvesvaraya Technological University, India Tuğçe Bilen, Istanbul Technical University, Turkey Veeru Talreja, West Virginia University, United States Vivek B. Kute, St Vincent Pallotti College of Engg and Tech, India Xia Li, Qualcomm, United States Xiangguo Li, Henan University of Technology, China Yongchuan Tang, Northwestern Polytechnical University, China Zhengwei Hao, MathWorks, United States

Reviewers Abhineet Anand, University of Petroleum and Energy Studies, India Agus Eko Minarno, Universitas Muhammadiyah Malang, Indonesia Agustinus Noertjahyana, Petra Christian University, Indonesia Ahmed Chitnalah, Cadi Ayyad University EST Laboratory, Morocco Ahmed Riadh Rebai, Qatar Foundation (QF), Qatar Ai-ichiro Sasaki, Kindai University, Japan Akhil Gupta, Lovely Professional University, India Alberto Fernandez Hilario, University of Granada, Spain Alfian Maarif, Universitas Ahmad Dahlan, Indonesia Alireza Ghasempour, ICT Faculty, United States Allam Mousa, An Najah University, Palestine Amir Mahdiyar, Universiti Sains Malaysia, Malaysia Amir Rezagholi, Shiraz University, Iran Amirah 'Aisha Badrul Hisham, University of Nottingham Malaysia, Malaysia Amit Prakash Singh, Guru Gobind Singh Indraprastha University, India Amrit Mukherjee, Jiangsu University, China Andrews Samraj, Mahendra Engineering College, India Ankur Dumka, UPES, India Anshul Pandey, Indian Institute of Information Technology Allahabad, India Antonios Gasteratos, Democritus University of Thrace, Greece Antonius Cahya Prihandoko, University of Jember, Indonesia Areej M. Abduldaim Al-Alwash, University of Technology, Iraq Artis Mednis, Institute of Electronics and Computer Science, Latvia Asif Iqbal, KTH Royal Institute of Technology, Sweden Asrul Izam Azmi, Universiti Teknologi Malaysia, Malaysia Athul Shaji, Indian Institute of Science, India Attuluri R Vijay Babu, Vignan University, India Ayoub Bahnasse, University Hassan II Casablanca, Morocco Azura Che Soh, Universiti Putra Malaysia, Malaysia Bayu Erfianto, Telkom University, Indonesia Bilal Munir Mughal, Universiti Teknologi Petronas, Malaysia Boonsit Yimwadsana, Mahidol University, Thailand Brij Gupta, National Institute of Technology Kurukshetra, India Bruno Miranda Henrique, University of Brasília, Brazil Carlos Gómez-Calero, Airbus Defence and Space, Spain Cathryn Peoples, Ulster University, United Kingdom César Hernando Valencia, Pontifical Catholic University of Rio de Janeiro, Brazil Chao-Hsien Lee, National Taipei University of Technology, Taiwan Cheruku Sandesh Kumar, Amity University Rajasthan, India

xii

Christina Gnanamani, Coimbatore Institute of Technology, India Christos J Bouras, University of Patras, Greece Chutisant Kerdvibulvech, National Institute of Development Administration, Thailand D Ganeshkumar, Anna University, India Daowen Qiu, Instituto Superior Técnico, Portugal David Reiser, University of Hohenheim, Germany Davood Toghraie, Islamic Azad University, Iran Deepti Prakash Theng, G. H. Raisoni College of Engineering, India Devi Vinayak Siva Rama Krishna Koilada, NetrixLLC, United States Dharmendra G. Ganage, Savitribai Phule Pune University, India Dijana Karuovic, University of Novi Sad, Serbia Dinesh Bhatia, North Eastern Hill University, India Dipesh G Kamdar, VVP Engineering College, India Duy C Huynh, Ho Chi Minh City University of Technology (HUTECH), Vietnam Eduard Babulak, Liberty University, United States Efil Yusrianto, UIN Imam Bonjol Padang, Indonesia Elias Aboutanios, University of New South Wales, Australia Elisha Tadiwa Nyamasvisva, Infrastructure University Kuala Lumpur, Malaysia Elyas Rakhshani, Delft University of Technology, The Netherlands Ezra Morris A Gnanamuthu, Universiti Tunku Abdul Rahman, Malaysia Farrukh Arslan, Purdue University, United States Fat'hah Noor Prawita, Telkom University, Indonesia Felix Albu, Valahia University of Targoviste, Romania Feng Liu, Shanghai Maritime University, China Ferdows B. Zarrabi, Islamic Azad University, Iran Gabriel Vasile, National Center for Scientific Research, France Gabriela Florescu, National Institute for Research and Development in Informatics, Romania Gaurav Bhatia, Technical University Darmstadt, Germany Gen Motoyoshi, NEC Corporation, Japan Gerino P Mappatao, De La Salle University, Philippines Guanping Lu, Shanghai Jiaotong University, China Gustavo Galegale, Universidade de São Paulo, Brazil GV. Nagesh Kumar, GITAM University, India Hadeel N. Abdullah, University of Technology, Iraq Hafedh Trigui, Reverb Networks, United States Haijun Pan, New Jersey Institute of Technology, United States Haitham Hassan Mahmoud, Birmingham City University (BCU), United Kingdom Hamid Alasadi, Basra University, Iraq Hardik A Vyas, Uka Tarsadia University, India Hasan Amca, Eastern Mediterranean University, Turkey Hazlee Azil Illias, University of Malaya, Malaysia Heba Hassan, Cairo University, Egypt Hengky Susanto, Hong Kong University of Science and Technology, Hong Kong Huai-Kuei Wu, Oriental Institute of Technology, Taiwan Hussain Saleem, University of Karachi, Pakistan I Made Murwantara, Universitas Pelita Harapan, Indonesia Ion Iancu, University of Craiova, Romania J. Ballestrín, CIEMAT-Plataforma Solar de Almería, Spain Jami Venkata Suman, GMR Institute of Technology, India Jarutas Pattanaphanchai, Prince of Songkla University, Thailand Jatin Sharma, Microsoft Research, United States Jiann-Der Lee, Chang Gung University, Taiwan Joao M. Felicio, Instituto de Telecomunicações, Portugal Juan Carlos Cuevas Martínez, University of Jaen, Spain Junfei Qiu, University of York, United Kingdom

xiii

Jyoti Prakash Singh, National Institute of Technology Patna, India K.-L. Du, Concordia University, Canada Karim Hashim Al-Saedi, Mustansiriyah University, Iraq Kartika Firdausy, Universitas Ahmad Dahlan, Indonesia Keh-Kim Kee, UCTS, Malaysia Kennedy E Ehimwenma, Sheffield Hallam University, United Kingdom Kerry Sado, University of Duhok, Iraq Kesavaraja D, Dr Sivanthi Aditanar College of Engineering, India Khairilmizal Samsudin, Universiti Sains Malaysia, Malaysia Khairul Anuar Mohamad, Universiti Tun Hussein Onn Malaysia, Malaysia Khalid Isa, Universiti Sains Malaysia, Malaysia Khalil Hassan Sayidmarie, Ninevah University, Iraq Lakshmi Yamujala, Centre for Development of Telematics, India Leo Yi Chen, Glasgow Caledonian University, United Kingdom Leon A. Abdillah, Bina Darma University, Indonesia M. Udin Harun Al Rasyid, Politeknik Elektronika Negeri Surabaya (PENS), Indonesia Maamar Bougherara, LIMPAF Laboratory Bouira University, Algeria Madan Kumar Lakshmanan, CSIR-CEERI, India Madan Singh, RITES Limited, India Mahdi Imani, George Washington University, United States Mahdieh Babaiasl, University of Tabriz, Iran Mahmood Mosleh, Middle Technical University, Iraq Mahmoud Moghavvemi, University of Malaya, Malaysia Mahmoud Rokaya, Taif University, Saudi Arabia Mahmoudreza Tahmassebpour, Islamic Azad University, Iran Manojkumar Somabhai Parmar, Robert Bosch Engineering and Business Solutions Private

Limited, India Marcelo A. Oliveira, Universidade do Minho, Brazil Marco Guazzone, University of Piemonte Orientale, Italy Mario Barbati, Riello UPS, Italy Marta Kuźma, Military University of Technology, Poland Massudi Mahmuddin, Universiti Utara Malaysia, Malaysia Mauricio Donatti, University of Campinas, Brazil Melany M Ciampi, Safety, Health and Environment Research Organization, Portugal Michele Fiorini, SELEX Sistemi Integrati, Italy Mihai Gavrilas, Technical University of Iasi, Romania Min Qiu, University of New South Wales, Australia Mittapalle Kiran Reddy, Indian Institute of Technology Kharagpur, India Mohamed EL-Shimy, Ain Shams University, Egypt Mohamed Hussein, Universiti Teknologi Malaysia, Malaysia Mohammad Al-Shabi, University of Sharjah, United Arab Emirates Mohammad Hossein Rezvani, Iran University of Science and Technology, Iran Mohammad Sadegh Kayhani Pirdeh, University of Oulu, Finland Mohammed El-Abd, American University of Kuwait, Kuwait Mohammed I. Younis, University of Baghdad, Iraq Mohammed Jawad Mohammed, University of Technology, Iraq Mohammed K A Kaabar, Moreno Valley College, United States Mohammed Kdair Abd, University of Technology, Iraq Mohd Zamri Hasan, University Malaysia Perlis, Malaysia Moirangthem Marjit Singh, North Eastern Regional Institute of Science and Technology, India Muchharla Suresh, National Institute of Science and Technology, India Muhamad Yusnorizam Ma'arif, The National University of Malaysia (UKM), Malaysia Muhammad Izuan Fahmi Romli, University Malaysia Perlis, Malaysia Muhammad Mokhzaini Azizan, Universiti Malaysia Perlis, Malaysia Muthana Hamd, Al Mustansirya University, Australia

xiv

Nadheer A. Shalash, Al-Mamon University College, Iraq Nanda Kishore Chavali, Mathworks India Pvt Ltd., India Nasrin Amiri, Islamic Azad University, Iran Navid Tafaghodi Khajavi, University of Hawaii at Manoa, United States Nemuel Daniel Pah, Universitas Surabaya, Indonesia Nibal Fadel Farman, Univrsity of Baghdad, Iraq Nitish Paliwal, Intel Corp., United States Nitish Sehgal, Netaji Subhas University of Technology, India Nurdin Nurdin, Institut Agama Islam Negeri (IAIN) Palu, Indonesia Onur Günlü, Technische Universität Berlin, Germany Orion Sky Lawlor, University of Alaska Fairbanks, United States Otavio P. Lavor, UFERSA, Brazil P. Janik, University of Silesia in Katowice, Poland Pablo Menoni, ITU & Antel, Uruguay Pablo Sendín-Raña, University of Vigo, Spain Padmavathy N, Jawaharlal Nehru Technological University Kakinada, India Pai Chet Ng, Hong Kong University of Science and Technology, Hong Kong Pakawan Pugsee, Chulalongkorn University, Thailand Paramate Horkaew, Suranaree University of Technology, Thailand Parameshachari Bidare Divakarachari, Visvesvaraya Technological University, India Partha Pratim Ray, Sikkim University, India Paweł Pędzich, Warsaw University of Technology, Poland Pedro Marinho R. de Oliveira, University Côte d'Azur, France Pehr Söderman, KTH Royal Institute of Technology, Sweden Peter Riegl, Ingolstadt University of Applied Sciences, Germany Peter Roessler, University of Applied Sciences Technikum Wien, Austria Praveen Kumar Malik, Lovely Professional University Jalandhar, India Preecha Somwang, Rajamangala University of Technology Isan, Thailand Pujianto Yugopuspito, Universitas Pelita Harapan, Indonesia Puput Dani Prasetyo Adi, University of Merdeka Malang, Indonesia Quan Chen, National University of Defense Technology, China Radu A. Vasiu, Politehnica University of Timisoara, Romania Rahmat Sanudin, Universiti Tun Hussien Onn Malaysia, Malaysia Raid Daoud, Northern Technical University/Al-Hawija Institute, Iraq Raja Waseem Anwar, Universiti Teknologi Malaysia, Malaysia Rajeev Sobti, Lovely Professional University, India Ramkumar Jaganathan, VLB Janakiammal College of Arts and Science, India Ratheesh Kumar Meleppat, University of California Davis, United States Raul de Lacerda, CentraleSupelec, France Raveendranathan Kalathil Chellappan, Rajadhani Institute of Engineering and

Technology, India Rayane El Sibai, Sorbonne Université, France Reza Pulungan, Universitas Gadjah Mada, Indonesia Riko Arlando Saragih, Maranatha Christian University, Indonesia Rini Nur Hasanah, Brawijaya University, Indonesia Riza Muhida, Surya University, Indonesia Robert K Pucher, University of Applied Sciences Technikum Wien, Austria Rodrigo Campos Bortoletto, Instituto Federal de São Paulo, Brazil Rosaura Palma-Orozco, Instituto Politécnico Nacional, Mexico Rostam Affendi Hamzah, Universiti Teknikal Malaysia Melaka, Malaysia Rostyslav Sklyar, Independent Professional, Ukraine Rubita Sudirman, Universiti Teknologi Malaysia, Malaysia Rui Santos Cruz, Universidade de Lisboa, Portugal S. M. Salim Reza, Universiti Kebangsaan Malaysia (UKM), Malaysia Sachin Sharma, Gujarat Technological University, India

xv

Safanah M Raafat, University of Technology Baghdad, Iraq Saifullah Khalid, Civil Aviation Research Organisation, India Sakchai Muangsrinoon, Southeast Asia University, Thailand Salvatore Serrano, University of Messina, Italy Samuel Ndueso John, Nigerian Defence Academy, Nigeria Samy Sayed Abdou Ghoniemy, The British University in Egypt (BUE), Egypt Sandeep Kakde, Y C College of Engineering, India Sandeep Saxena, AKTU Lucknow India, India Sang Van Doan, Vietnam Naval Academy, Vietnam Satya Kumara, Udayana University, Indonesia Seyedehnafiseh Mirniaharikandehi, University of Oklahoma, United States Shahram Shah Heydari, University of Ontario Institute of Technology, Canada Shahrum Shah Abdullah, Universiti Teknologi Malaysia, Malaysia Shashikant Shantilal Patil, SVKM NMIMS Mumbai India, India Shilpi Birla, Manipal University, India Shipra Shukla, Gautam Budh Technical University, India Siddharth Aphale, K. K. Wagh Institute of Engineering Education and Research, India Siong Lee Koh, Tunku Abdul Rahman University, Malaysia Sritrusta Sukaridhoto, Politeknik Elektronika Negeri Surabaya, Indonesia Sudhir K Routray, CMR Institute of Technology, Bangalore, India Sumit Waghmare, Utopus Insights, India Sunitha George, Netaji Subhas University of Technology, India Supriya Dubey, Motilal Nehru National Institute of Technology, India Suriani Mohd Sam, University Technology Malaysia, Malaysia Syed Ahmed Raza Naqvi, University of Western Ontario, Canada Tapodhir Acharjee, Assam University, India TC Manjunath, Dayananda Sagar College of Engineering, India Tomi Tristono, Universitas Merdeka Madiun, Indonesia Tomo Popović, University of Donja Gorica, Montenegro Tomonobu Senjyu, University of the Ryukyus, Japan Tong Li, Beijing University of Technology, China Tow Leong Tiang, Universiti Malaysia Perlis, Malaysia Tresna Dewi, Politeknik Negeri Sriwijaya, Indonesia Triwiyanto Triwiyanto, Poltekkes Kemenkes Surabaya, Indonesia Tusar Kanti Mishra, Gayatri Vidya Parishad, India Ucuk Darusalam, Universitas Nasional, Indonesia V Santhosh, National Institiute of Technology, India Vigneshwar Manokar, Karpagam Academy of Higher Education, India Vijaykumar Selvam, An Advanced Research and Scientific Experiment Foundation, India Vivek Kumar Sehgal, Jaypee University of Information Technology, India Vivek Sharma, Graphic Era University Dehradun, India Weihuang Fu, Google, United States Widodo Widodo, University of Indonesia, Indonesia Winai Wongthai, Naresuan University, Thailand Wolfgang Frohberg, Gesellschaft fuer Internationale Zusammenarbeit (GIZ), Germany Xiaoling Luo, Harbin Institute of Technology, China Yaareb M.Basheer Ismael Al-Khashab, Ministry of Water Resources/Badush Dam, Iraq Ying-Khai Teh, San Diego State University, United States Yogi Muliandi, Muliandi Holdings Limited, Indonesia Young Mo Chung, Hansung University, Korea Zaher Haddad, Alaqsa University, Palestine Zahra Pezeshki, Shahrood University of Technology, Iran Zainudin Kornain, Royal Commission Yanbu Colleges and Institutes, Saudi Arabia Zeashan Hameed Khan, National University of Science and Technology (NUST), Pakistan Zeyad Al-Shibaany, Cardiff University, United Kingdom

xvi

Local Arrangement Members Lina Handayani, Universitas Ahmad Dahlan, Indonesia Ahmad Azhari, Universitas Ahmad Dahlan, Indonesia Ahmad Raditya Cahya Baswara, Universitas Ahmad Dahlan, Indonesia Alfian Ma’arif, Universitas Ahmad Dahlan, Indonesia Phisca Aditya Rosyady, Universitas Ahmad Dahlan, Indonesia Riky Dwi Puriyanto, Universitas Ahmad Dahlan, Indonesia Son Ali Akbar, Universitas Ahmad Dahlan, Indonesia

Publicity

Dian Dwi Vaputra, Institute of Advanced Engineering and Science, Indonesia Fathur Rahmawanto, Institute of Advanced Engineering and Science, Indonesia

Treasurers Lila W Saputri, Universitas Ahmad Dahlan, Indonesia Ninu Novia Pinasthi, Institute of Advanced Engineering and Science, Indonesia Yekti Nur Hasanah, Institute of Advanced Engineering and Science, Indonesia

Secretariat Radita Apriana, Institute of Advanced Engineering and Science, Indonesia Hany Safitry F., Institute of Advanced Engineering and Science, Indonesia Mita Dewi Suryani, Institute of Advanced Engineering and Science, Indonesia Septian Dwi Cahyo, Institute of Advanced Engineering and Science, Indonesia Azidanti Saufi, Institute of Advanced Engineering and Science, Indonesia Zly Wahyuni, Institute of Advanced Engineering and Science, Indonesia Fakhrunnisa, Institute of Advanced Engineering and Science, Indonesia Arif Hidayat, Institute of Advanced Engineering and Science, Indonesia Evrynda Widyasari P.D., Institute of Advanced Engineering and Science, Indonesia Fadhila Fatma Pramasti, Institute of Advanced Engineering and Science, Indonesia Amir Fuad Asy’ari, Institute of Advanced Engineering and Science, Indonesia Milzam Adang Rusdianto, Institute of Advanced Engineering and Science, Indonesia Niko Firman Saputra, Institute of Advanced Engineering and Science, Indonesia Nila Rezha Diyestia Rakhma, Institute of Advanced Engineering and Science, Indonesia Syifa Khoirunnisa, Universitas Ahmad Dahlan, Indonesia

Office LPPI Room, 9th Floor, Campus 4 of Universitas Ahmad Dahlan (UAD) South Ring Road, Tamanan, Banguntapan, Bantul, Yogyakarta 55191, Indonesia Phone: +62 274 563515, 511830, 379418, 371120, ext. 4902, Fax: +62 274 564604 E-mail: icwt1@ee.uad.ac.id, cc: lppi@uad.ac.id

xvii

Programs

DAY 1 — TUESDAY, 19 NOVEMBER 2019

Time Agenda

07:30-08:00 Registration

08:00-08:30

Opening Ceremony 1. Opening 2. Quran Recitation 3. Indonesia Raya 4. Speech

a. Tole Sutikno (General Chair) b. Rector of Universitas Ahmad Dahlan

5. Dance Performance (UAD) 6. Photo session

08:30-09:15 Keynote Speech Session: Keynote Speaker 1

M. Nadzir Marsono Universiti Teknologi Malaysia, Malaysia

09:15-10:00 Keynote Speech Session: Keynote Speaker 2

Nur Pamudji Indonesia Solar Association, Indonesia

10:00-10:30 Coffee Break, Moving Room

10:30-12:10 Parallel Session + Manuscript Mentoring and Coaching

12:10-13:00 Lunch Break

13:00-17:40 Parallel Session + Manuscript Mentoring and Coaching

DAY 2 — WEDNESDAY, 20 NOVEMBER 2019

Time Agenda

07:30-08:00 Registration

08:00-08:45 Keynote speech session: Keynote speaker 3

Teddy Mantoro Sampoerna University, Indonesia

08:45-09:30 A One Day Workshop on Preparing High Quality Journal Article

Zainal Salam Universiti Teknologi Malaysia

09:30-10:00 Coffee break

10:00-12:00 A One Day Workshop on Preparing High Quality Journal Article

Zainal Salam Universiti Teknologi Malaysia

12:00-13:00 Lunch break

13:00-15:00 A One Day Workshop on Preparing High Quality Journal Article

Zainal Salam Universiti Teknologi Malaysia

15:00-15:30 Coffee Break and Closing

xviii

Table of Contents

Foreword from the Conference Chair iii Foreword from the General Chair iv Foreword from the Rector of Universitas Ahmad Dahlan v Organizers vi Organizing Committee viii Programs xvii

ROOM 1

R1-1 UNet-VGG16 with Transfer Learning for MRI-Based Brain Tumor Segmentation 1 Anindya Apriliyanti Pravitasari, Nur Iriawan, Mawanda Almuhayar, Taufik Azmi, Irhamah, Kartika Fithriasari, Santi Wulan Purnami, Widiana Ferriastuti

R1-2 Throughput in Cooperative Wireless Networks 1 Diego Giral, Cesar Hernandez, Fredy Martinez

R1-3 Failed Handoffs in Collaborative Wi-Fi Networks 2 Cesar Hernandez, Diego Giral, C. Salgado

R1-4 Performance of Wi-Fi Networks in Coexistence with LTE in Non-Licensed Band 2 Elvis E. Gaona-Garcia, Felipe A. Zarta, David G. Rosero-Bernal

R1-5 Design and Performance Study of Free Space Optical Communication System 3 Suman Malik, Prasant Kumar Sahu

R1-6 ILC Combined with a PI regulator for Wastewater Treatment Plants 3 Lanh Van Nguyen, Nam Van Bach, Hai Trung Do, Minh Tuan Nguyen

R1-7 Use of Closed Loop System Using Arduino for Different Parameters in Farming 4 Saifur Rahman

R1-8 Scheme for Motion Estimation Based on Adaptive Fuzzy Neural Network 4 Fredy Martínez, Cristian Penagos, Luis Pacheco

R1-9 Design of Deep Hypersphere Embedding for Real-Time Face Recognition 5 Ryann Alimuin, Elmer Dadios, Jonathan Dayao, Shearyl Arenas

R1-10 COA Learning Module Uses an 8-bit CPU Architecture to Analyze the Undergraduate Learning Outcomes 5 Mochammad Hannats Hanafi Ichsan, Wijaya Kurniawan

R1-11 Noise on Near Infrared Sensor for Glucose Solution Measurement 6 Kiki Prawiroredjo, Engelin Shintadewi Julian

R1-12 Effect of Dye pH Variation on Blueberry Anthocyanin Based Dye Sensitized Solar Cell (DSSC) 6 Zainul Abidin, Eka Maulana, Panca Mudjirahardjo, M. Ivan Fadillah

R1-13 BPF Comparison of Hairpin Line and Square Open-Loop Resonator Method 7 Yuyun Siti Rohmah, Budi Prasetya, Dwi Andi Nurmantris, Sarah Mulyawati, Reza Dipayana

R1-14 Analysis of Lambertian Order to Determine The Ideal Angle and Position of Photodetector for VLC 7 Dwi Astharini, Heri Kurniawan, Ary Syahriar

xix

R1-15 Audio Watermarking Based on LWT-DCT-SVD with Compressive Sampling Framework 8 Ledya Novamizanti, Gelar Budiman, Elsa Nur Fitri Astuti

R1-16 Accurate Characterizations of Material Using T-ring Microwave Resonator for Bio-sensing Applications 8 Rammah A. Alahnomi, Z. Zakaria, Zulkalnain Mohd Yussof, Tole Sutikno, H. Sariera, Amyrul Azuan Mohd Bahar

R1-17 Buck Converter Optimization Using P&O Algorithm for PV System Based Battery Charger 9 Zainul Abidin, Adharul Muttaqin, Eka Maulana, M. Gilang Ramadhan

R1-18 Water Bath Sonicator Integrated with PID-Based Temperature Controller for Flavonoid Extraction 9 Zainul Abidin, M. Aziz Muslim, Muhammad Muqorrobin, Warsito

ROOM 2

R2-1 Insomnia Analysis Based on Internet of Things Using Electrocardiography and Electromyography 10 Novi Azman, Mohd Khanapi Bin Abd Ghani, S.R. Wicaksono, Barru Kurniawan, Viktor Vekky Ronald Repi

R2-2 MILA: Mobile IoT for Low Cost BCI Framework 10 Rolly Maulana Awangga, Syafrial Fachri Panea, Dzikri Ahmad Ghifaria, Moch Yusuf Asyharib

R2-3 Classification of Pneumonia from X-ray Images Using Siamese Convolutional Network 11 Kennard Alcander Prayogo, Alethea Suryadibrata, Julio Christian Young

R2-4 Identification of Gram-Negative Bacteria Using Convolutional Neural Network 11 Budi Dwi Satoto, Imam Utoyo, Riries Rulaningtyas, Eko Budi Koendhori

R2-5 Low Frequency Response Test Device of Electret Condenser Microphone 12 Erni Yudaningtyas, Achsanul Khabib, Waru Djuriatno, Zakiyah Amalia, Ramadhani Kurniawan Subroto

R2-6 Genomic Repeats Detection Using Boyer-Moore Algorithm on Apache Spark Streaming 12 Lala Septem Riza, Farhan Dhiyaa Pratama, Erna Piantari, Mahmoud Fahsi

R2-7 Performance Measurement of A High Performance Programmable Logic Controller on FPGA 13 Zulfakar Aspar, Mohamed Khalil-Hani, and Ahmad Zuri Sha’ameri

R2-8 Bershca: Bringing Chatbot into Hotel Industry in Indonesia 13 Dennis Gunawan, Farica Perdana Putri, Hira Meidia

R2-9 Comparison of Search Algorithms in Javanese-Indonesian Dictionary Application 14 Yana Aditia Gerhana, Nur Lukman, Arief Fatchul Huda, Cecep Nurul Alam, Undang Syaripudin, Devi Novitasari

R2-10 Breakdown Movie Script Uses the Parsing Algorithm 14 Agung Wahana, Diena Rauda Ramdania, Dhanis Al Ghifari, Ichsan Taufik, Faiz M Kaffah, Yana Aditia Gerhana

xx

R2-11 Artificial Neural Network for Modelling The Removal of Pollutants: A Review 15 Siti Fatimah, Wiharto

R2-12 Knowing Group Motivation Based On Plagiarism Regression 15 M Zainal Arifin, Naim Che Pee, Nanna Suryana Herman

R2-13 Low-Cost and Open-Source Anthropomorphic Prosthetics Hand Using Linear Actuators 16 Triwiyanto Triwiyanto, I Putu Alit Pawana, Torib Hamzah, Sari Luthfiyah

R2-14 The Complexity of Traffic Lights Control Systems Based on The Petri Net Model 16 Tomi Tristono, Setiyo Daru Cahyono, Candra Budi Susila, Pradityo Utomo, Fendi Hary Yanto, Martin Lukito, Kartikadyota Kusumaningtyas, Ari Kusuma Wardana

R2-15 User Stories Collection via Interactive Chatbot to Support Requirements Gathering 17 Ferliana Dwitama, Andre Rusli

R2-16 Combined Scaled Manhattan Distance and Mean of Horner’s Rules for Keystroke Dynamic Authentication 17 Didih Rizki Chandranegara, Hardianto Wibowo, Agus Eko Minarno

R2-17 Application of Recommendation System with AHP Method and Sentiment Analysis 18 Ira Prasetyaningrum, Kholid Fathoni, Tri Tangguh Jiwo Priyantoro

ROOM 3

R3-1 A Robust Method for VR-Based Hand Gesture Recognition Using Density-Based CNN 19 Liliana, Ji-Hun Chae, Joon-Jae Lee, Byung-Gook Lee

R3-2 Voronoi Diagram with Fuzzy Number and Sensor Data in an Indoor Navigation for Emergency Situation 19 Nanna Suryana, Fandy Setyo Utomo, Mohd Fairuz Iskandar Othman, Mohd Nazrin Muhammad

R3-3 Basic Principles of Blind Write Protocol 20 Khairul Anshar, Nanna Suryana, Noraswaliza

R3-4 Comparative Analysis of Iris Template Matching Techniques for Motion-Blurred Images 20 Rohayanti Hassan, Shahreen Kasim, Dyia Sarah Md Shukri, Rohaizan Ramlan

R3-5 The Enhancement of Logging System Accuracy for Infrastructure as a Service Cloud 21 Surapong Wiriya, Winai Wongthai, Thanathorn Phoka

R3-6 Artificial Intelligence in Education: A Review of the State of the Art 21 Balqis Al Braiki, Saad Harous, Nazar Zaki, Fady Alnajjar

R3-7 Predicting Machine Failure using Time Series Data through Recurrent Neural Network-Gated Recurrent Unit (RNN-GRU) 22 Zainuddin Z, P. Akhir E.A., Hasan M.H.

R3-8 Digital Addiction: Online Game Addiction Impact to Adolescent Physical Health 22 Norshakirah Aziz, Muhammad Muhaimin, Md Jan Nordin, Norharlina Bahar

xxi

R3-9 Knowledge Internalization in e-Learning Management System (eLMS) 23 Zahraa Abed Aljasim Muhisn, Mazida Ahmad, Mazni Omar, Sinan Adnan Muhisn

R3-10 Semi-Supervised AutoEncoder for Facial Attributes Recognition 23 Soumaya Zaghbani, Noureddine Boujnah, Med Salim Bouhlel

R3-11 Readiness Measurement of IT Implementation in Higher Education Institutions in Indonesia 24 Mohamad Irfan, Syopiansyah Jaya Putra

R3-12 Benchmarking Level Interactivity of Indonesia Government University Websites 24 Nurdin Nurdin, Zana Chobita Aratusa

R3-13 The Designing of Interactive Learning Media at Yogyakarta’s Sandi Museum Based on Augmented Reality 25 Prita Haryani, Joko Triyono

R3-14 Fisher-Yates and Fuzzy Sugeno in Game for Special Children Needs 25 Diena Rauda Ramdania, Mohamad Irfan, Salma Nuralisa Habsah, Cepy Slamet

R3-15 IoT and Chatbot Integration Using Natural Language Processing for Aquaculture 26 M. Udin Harun Al Rasyid, Sritrusta Sukaridhoto, Muhammad Iskandar Dzulqornain, Ahmad Rifai

R3-16 Fuzzy Transform for High-Resolution Satellite Images Compression 26 Donna Monica, Ayom Widipaminto

R3-17 Machinery Signal Separation Using NMF with Real Mixing 27 Anindita Adikaputri Vinaya, Sefri Yulianto, Qurrotin A’yunina Maulida Okta Arifianti, Dhany Arifianto, Aulia Siti Aisjah

R3-18 An Investigation of Load Balancing in SDN with Distributed Gateway 27 Halimah Tussyadiah, Ridha Muldina Negara, Danu Dwi Sanjoyo

ROOM 4

R4-1 Sensorless Dual Axis Solar Tracker Using Improved Sun Position Algorithm 28 Chan Men Loon, Muhamad Zalani Daud

R4-2 Computer-Based Solar Tracking System for PV Energy Yield Improvement 28 Rini Nur Hasanah, Aditya Bagus Setyawan, Eka Maulana, Tri Nurwati, Taufik Taufik

R4-3 Application of Direct MRAC in PI Controller for Boost DC/DC Converter 29 Lunde Ardhenta, Ramadhani Kurniawan Subroto

R4-4 An Improved MPPT Controller for Photovoltaic System Using Fuzzy Logic-Particle Swarm Optimization 29 Aji Akbar Firdaus, Riky Tri Yunardi, Eva Inaiyah Agustin

R4-5 A Performance Comparison of Transformer-less Grid Tied PV System Using Diode Clamped and Neutral Point Shorted Inverters 30 Suroso, Hari Siswantoro

R4-6 Design of 4-Stage Marx Generator Using Gas Discharge Tube 30 Wijono, Zainul Abidin, Waru Djuriatno, Eka Maulana, Nola Ribath

xxii

R4-7 Short-term Photovoltaics Power Forecasting Using Jordan Recurrent Neural Network in Surabaya 31 Aji Akbar Firdaus, Riky Tri Yunardi, Eva Inaiyah Agustin, Tesa Eranti Putri, Sisca D. N. Nahdliyah, Elsyea Adia Tunggadewi, Dimas Okky Agriawan, Dimas Fajar Uman P.

R4-8 Three-Level Modified Sine Wave Inverter Equipped with Online Temperature Monitoring System 31 Suroso, Ahmad Khafidz, Winasis, Hari Siswantoro

R4-9 MPPT Control Based on PSO of PV System Using Adaptive Controller 32 Totok Winarno, Lucky Nindya Palupi, Agus Pracoyo, Lunde Ardhenta

R4-10 Design and Fabrication of Vehicle Gust Turn Powered Turbine 32 Dichi Syahbana, Putri Wulandari, Ary Syahriar

R4-11 Linear Quadratic Regulator and Pole Placement for Stabilising a Cart Inverted Pendulum System 33 Mila Fauziyah, Zakiyah Amalia, Indrazno Siradjuddin, Denda Dewatama, Erni Yudaningtyas

R4-12 Neural Network Based Smart Home System Controller for Energy Efficiency 33 Puji Catur Siswipraptini, Rosida Nur Aziza, Iriansyah Sangadji, Indrianto

R4-13 Fault Tolerant Sliding Mode Control for Anti-lock Braking in a Quarter Electric Vehicle 34 Katherin Indriawati, Bambang L. Widjiantoro

R4-14 Compensation of Time-Varying Clock-Offset in a Long Baseline Navigation 34 Yohannes S M Simamora, Harijono A. Tjokronegoro, Edi Leksono, Irsan S. Brodjonegoro

R4-15 Obstacle Avoidance using Timed Elastic Band Path Planning on 3D Point Cloud Data 35 Eko P. Wahyono, Endah S. Ningrum, Raden S. Dewanto, Dadet Pramadihanto

R4-16 Dynamic Control for ROV Using Integral SMC with PSO Optimization 35 Syadza Atika Rahmah, Eko Henfri Binugroho, Raden Sanggar Dewanto, Dadet Pramadihanto

R4-17 Implementation of Camera-Based Depth Control for Micro Class ROV 36 Simon Siregar, Muhammad Ikhsan Sani, Sintong Tua Parlindungan Silalahi

R4-18 Towards Cognitive Artificial Intelligence Devices: Processor Based on Human Thinking Emulation 36 Catherine Olivia Sereati, Arwin Datumaya Wahyudi Sumari, Trio Adiono, Adang Suwandi Ahmad

ROOM 5

R5-1 Vision: A Convolutional Network for Real-Time Face Recognition Web Service 37 Akino Archilles, Arya Wicaksana

R5-2 Cleveree: An Artificial Intelligence Web Service for Jacob Voice Chatbot 37 Octavany, Arya Wicaksana

R5-3 SSA-Based Hybrid Forecasting Models and Applications 38 Winita Sulandari, Subanar, Suhartono, Herni Utami, Muhammad Hisyam Lee, Paulo Canas Rodrigues

xxiii

R5-4 Application of Neural Network Method for Road Crack Detection 38 Yuslena Sari, Puguh Budi Prakoso, Andreyan Rizky Baskara

R5-5 PSO Optimization on Backpropagation for Fish Catch Production Prediction 39 Yuslena Sari, Eka Setya Wijaya, Andreyan Rizky Baskara, Rico Silas Dwi Kasanda

R5-6 Rice Leaf Classification using Fuzzy Logic and Hue Saturation Value (HSV) to Determine Fertilizer Dosage 39 Yuslena Sari, Muhammad Alkaff, Andreyan Rizky Baskara, Fungky Arya

R5-7 Evaluation of Distance-Based K-Means Method for Detecting Moving Vehicles 40 Yuslena Sari, Puguh Budi Prakoso, Andreyan Rizky Baskara

R5-8 Precipitation Prediction Model Using Recurrent Neural Networks and Long Short-Term Memory 40 Mishka Alditya Priatna, Esmeralda Contessa Djamal, Elvan Panca Prasetya

R5-9 Framework for Developing Algorithmic Fairness 41 Dedy Prasetya Kristiadi, Po Abas Sunarya, Melvin Ismanto, Joshua Dylan, Ignasius Raffael Santoso, Harco Leslie Hendric Spits Warnars

R5-10 Matching Algorithm Performance Analysis for Autocalibration Method of Stereo Vision 41 Raden Arief Setyawan, Rudy Sunoko, Moch Agus Choiron, Panca Mudjirahardjo

R5-11 The Fish Movement on Madura Island Using Gaussian Mixture Model 42 Wahjoe Tjatur Sesulihatien, Achmad Basuki, Citra Nurina Prabiantissa

R5-12 3D Reconstruction Using Convolution Smooth Method 42 Sofyan Arifianto, Hardianto Wibowo, Wildan Suharso, Raditya Novidianto, Agus Eko Minarno, Dani Harmanto

R5-13 Ground Motion Vulnerability Analysis on Road Geometric Based on Remote Sensing 43 Niswah Selmi Kaffa, Bangun Muljo Sukojo

R5-14 Vision-Base Perception for Biological Feature Extraction of Similar Genera in Mosquito: Case Study Aedes Aegepty and Culex 43 Wahjoe Tjatur Sesulihatien, Tri Harsono, Akhmad Alimudin, Dia Bitari Mei Yuana, Etik Ainun Rohmah

R5-15 Classification of Ictal and Ocular Artifact Signals Using Time-frequency Features and Its Ratio Parameters 44 Yoga Prastya Irfandi, Santi Wulan Purnami, Irhamah, Wardah Rahmatul Islamiyah, Diah Puspito Wulandari, Anda Iviana Juniani

R5-16 Adaptive Threshold for Moving Objects Detection Using Gaussian Mixture Model 44 Moch Arief Soeleman, Aris Nurhindarto, Muslih, Karis W, Muljono, R. Anggi Pramunendar, Farikh Al Zami

R5-17 Mobile Cloud Game in High Performance Computing Environment 45 Dedy Prasetya Kristiadi, Ferry Sudarto, Evan Fabian Rahardja, Naufal Rayfi Hafizh, Christopher Samuel, Harco Leslie Hendric Spits Warnars

xxiv

ROOM 6

R6-1 Identification The Number of Mycobacterium Tuberculosis Based on Sputum Image Using Local Linear Estimator 46 Nur Chamidah, Yolanda Swastika Yonani, Elly Ana, Budi Lestari

R6-2 Quality and Size Assessment of Quantized Images Using K-Means++ Clustering 46 Davin Ongkadinata, Farica Perdana Putri

R6-3 JPG, PNG and BMP Image Compression Using Discrete Cosine Transform 47 Rostam Affendi Hamzah, MM Md Roslan, MGY Wei, AF Kadmin, SFA Gani, KA Aziz

R6-4 A Study on Edge Preserving Filter in Image Matching 47 Rostam Affendi Hamzah, AF Kadmin, SFA Gani, KA Aziz, TMFT Wook, N Mohamood, MGY Wei

R6-5 Contour Evolution Method for Precise Boundary Delineation of Medical Images 48 Friska Natalia, Hira Meidia, Nunik Afriliana, Julio Christian Young, Sud Sudirman

R6-6 Triple Layer Image Security Using Bit-Shift, Chaos, and Stream Encryption 48 Ajib Susanto, De Rosal Ignatius Moses Setiadi, Eko Hari Rachmawanto, Ibnu Utomo Wahyu Mulyono, Christy Atika Sari, Md Kamruzzaman Sarker, Musfiqur Rahman Sazal

R6-7 BCI of Focus and Motor Imagery Using Wavelet and RNN 49 Rifqi Dania Putra, Esmeralda C. Djamal

R6-8 Incident and Reflected Two Waves Correlation with Cancellous Bone Structure 49 Muhamad Amin Abd Wahab, Rubita Sudirman, Mohd Azhar Abdul Razak, Fauzan Khairi Che Harun, Nurul Ashikin Abdul Kadir

R6-9 QR Code Based Authentication Method for IoT Applications 50 Abbas M. Al-Ghaili, Hairoladenan Kasim, Marini Othman, Wahidah Hashim

R6-10 A Review of Anomaly Detection Techniques in Advanced Metering Infrastructure 51 Abbas M. Al-Ghaili, Fiza Abdul Rahim, Zul-Azri Ibrahim, Syazwani Arissa Shah Hairi, Hasventhran Baskaran, Noor Afiza Mohd Ariffin

R6-11 Data Falsification Attacks in Advanced Metering Infrastructure 52 Hasventhran Baskaran, Abbas M. Al-Ghaili, Zul-Azri Ibrahim, Fiza Abdul Rahim, Saravanan Muthaiyah

R6-12 Patterns of Sidemount Four-Bay FM Antenna System 52 Gerino P. Mappatao

R6-13 Requirements Identification for Distributed Agile Team Communication 53 Nor Hidayah Zainal Abidin, Pathiah Abdul Samat

R6-14 A Lightweight Middleware for Personalized IoT Applications 53 A. Karim Mohamed Ibrahim, Rozeha A. Rashid, A.H.F.A. Hamid, M. Adib Sarijari, S. Imroze, A. Shahidan Abdullah, Omar A. Aziz, Samura Ali, Angga Rusdinar

R6-15 Machine Learning based Lightweight Interference Mitigation Scheme for Wireless Sensor Network 54 Ali Suzain, Rozeha A. Rashid, A. Karim Mohamed Ibrahim, M. A. Sarijari, A. Shahidan Abdullah, Omar A. Aziz, Samura Ali, Teruji Ide, Angga Rusdinar

xxv

R6-16 A Review on Region of Interest Based Hybrid Medical Image Compression Algorithms 54 Suhaila Ab Aziz, Suriani Mohd Sam, Norliza Mohamed-, Salwani Mohd Daud, Siti Zaleha Abdul Rashid, Hafiza Abas, Muhammad Fathi Yusof, Rudzidatul Akmam Dziyauddin

R6-17 Vulnerabilities Detection Using Attack Recognition Technique in Multi-Factor Authentication 55 Noor Afiza Mohd Ariffin, Fiza Abdul Rahim, Aziah Asmawi, Zul-Azri Ibrahim

R6-18 Characterization of FM Broadcast Channel in Office Locations 55 Marco G. Domingo, Prince Kendrick E. Estebal, Geraldine A. Tongco, Gerino P. Mappatao

ROOM 7

R7-1 Web-App Realization of Shor’s Quantum Factoring Algorithm and Grover’s Quantum Search Algorithm 56 Arya Wicaksana

R7-2 Detection of Water Quality in Crayfish Ponds with IoT 56 Abdurrasyid Abdurrasyid, Indrianto Indrianto, Meilia Nur Indah Susanti, Yudhi S. Purwanto

R7-3 Hoax Classification and Sentiment Analysis of Indonesian News using Naive Bayes Optimization 57 Heru Agus Santoso, Eko Hari Rachmawanto, Adhitya Nugraha, Akbar Aji Nugroho, De Rosal Ignatius Moses Setiadi, Ruri Suko Basuki

R7-4 The Best Discretization Method on Bayesian Network in Disaster 57 Devni Prima Sari, Dedi Rosadi, Adhitya Ronnie Effendie, Danardono

R7-5 Multicore Development Environment for Embedded Processor in Arduino IDE 58 Stefanus Kurniawan, Dareen K. Halim, Dicky H., Tang C.M.

R7-6 Area Calculation Based on GADM Geographic Information System Database 58 Adi Setiawan, Eko Sediyono

R7-7 Indoor Positioning System Using BLE Beacon to Improve Knowledge about Museum Visitors 59 Andreas Handojo, Tanti Octavia, Resmana Lim, Jonathan Kurnia Anggita

R7-8 Latent Semantic Analysis and Cosine Similarity for Hadith Searching Engine 59 Wahyudin Darmalaksana, Cepy Slamet, Wildan Budiawan Zulfikar, Imam Fahmi Fadillah, Dian Sa’adillah Maylawati, Hapid Ali

R7-9 Teacher and Student Readiness Using E-Learning and m-Learning in Samarinda 60 Ramadiani Ramadiani, Azainil Azainil, Acmad Nizar Hidayanto, Dyna Marissa Khairina, Muhammad Labib Jundillah

R7-10 Cloud based Middleware for Supporting Batch and Stream Access over Smart Healthcare Wearable Device 61 Adhitya Bhawiyuga, Bagus Jati Santoso, Satria Adi Kharisma, Dani Primanita Kartikasari, Annisa Puspa Kirana

xxvi

R7-11 The IoT Implementation for the Lamps Control Using the Infrared Sensor with Arduino and Raspberry Pi 61 Arif Ainur Rafiq

R7-12 Performance Evaluation of Low-Cost IoT Based Chlorophyll Meter 62 Heri Andrianto, Suhardi, Ahmad Faizal

R7-13 Image Transmission Using Visible Light Communication in Data Communication 62 Alfajri Tsaqifurrasyid, Mia Rosmiati, Moch. Fachru Rizal

R7-14 Smart Parking Management System Using SSEA MQTT with Real-Time Database 63 Putri Sandika Juwita, Radya Fadhil, Tri Nopiani Damayanti, Dadan Nur Ramadan

R7-15 A Survey of Defense Mechanisms against Sybil Attacks on IoT with Wireless Ad-hoc Networks 63 Agria Rhamdhan, Fadhil Hidayat

R7-16 Decision Support System for Determining Chili Land Using Weighted Product Method 64 Ramadiani Ramadiani, Bayu Ramadhani, Zainal Arifin, Heliza Rahmania Hatta, Muhammad Labib Jundillah, Azainil Azainil

R7-17 A Lightweight Security Scheme for Smart Meter Communication in Smart Grid 64 S M Salim Reza, Afida Ayob, Mohd Hanif Md Saad, Aini Hussain, Nowshad Amin, Md Murshedul Arifeen, Mohammad Shakeri, Sieh Kiong Tiong, Md Akhteruzzaman

ROOM 8

R8-1 Stabilized Controller of A Two Wheels Robot 65 Ahmad Fahmi, Marizan bin Sulaiaman, Indrazno Siradjuddin, I Made Wirawan, Abdul Syukor Mohamad Jaya, Mahfud Jiono, Zakiyah Amalia

R8-2 Identifier of Human Emotions Based on Convolutional Neuronal Network for Assistant Robot 65 Fredy Martínez, César Hernández, Angélica Rendón

R8-3 Controlling a Knee CPM Machine Using PID and Iterative Learning Control Algorithm 66 Dechrit Maneetham, Petrus Sutyasadi

R8-4 2D Mapping Using Omni-Directional Mobile Robot Equipped with LiDAR 66 Muhammad Rivai, Dony Hutabarat, Zishwa Muhammad Jauhar Nafis

R8-5 Performance Evaluation of Deep Neural Network Architectures in the Identification of Bone Fissures 67 Fredy Martínez, César Hernández, Fernando Martínez

R8-6 Using Bacterial Interaction and Stereoscopic Images for the Location of Obstacles on Autonomous RobotS 67 Fredy Martínez, Edwar Jacinto, Fernando Martínez

R8-7 Design and Implementation OPC Server on Communication between PLC Different Platforms 68 Ignatius Deradjad Pranowo, YB Theo Bagastama, Thomas AF Wibisono

xxvii

R8-8 The Study of Attention Estimation for Child-Robot Interaction Scenarios 68 Muhammad Attamimi, Takashi Omori

R8-9 Deep Learning Based Facial Expressions Recognition System Implemented on a Wearable Device for Assisting Visually Impaired Persons 69 Hendra Kusuma, Muhammad Attamimi, Hasby Fahrudin

R8-10 Power Characteristic of Wireless Sensor Network for Illegal Cutting Tree 69 Giva Andriana Mutiara, Nanna Suryana, Othman Mohd

R8-11 Wireless Sensor Network for Monitoring Irrigation 70 Gita Indah Hapsari, Giva Andriana Mutiara, Luky Rohendi, Aldy Mulia

R8-12 LHCP and RHCP Triangular Array Eight Patches Antennas for CP-SAR 70 Muhammad Fauzan Edy Purnomo, Vita Kusumasari, Edi Supriana, Rusmi Ambarwati, Akio Kitagawa

R8-13 Salinity Monitoring and pH Control System on Guppy Fish Farming Based on IoT 71 Periyadi, Gita Indah Hapsari, Zahir Wakid, Sobran Mudopar

R8-14 Mobile Based Monitoring System for an Automatic Cat Feeder 71 Nenny Anggraini, Dzul Fadli Rahman, Luh Kesuma Wardhani, Nashrul Hakiem

R8-15 Computer Vision and Robotics Integration Based Student’s Programming Comprehension Improvement 72 Nova Eka Budiyanta, Catherine Olivia Sereati, Lukas

R8-16 Joint Control of a Robotic Arm Using Particle Swarm Optimization Based H2/H∞ Robust Control on Arduino 72 Petrus Sutyasadi, Martinus Bagus Wicaksono

ROOM 9

R9-1 Predicting Student Performance Using Data Mining 73 Leo Willyanto Santoso, Yulia

R9-2 Pulmonary Rontgen Classification to Detect Pneumonia Disease Using Convolutional Neural Networks (CNNs) 73 Zuherman Rustam, Rivan Pratama Yuda, Hamimah Alatas, Chelvian Aroef

R9-3 Recognition of Hanacaraka Characters in Old Manuscripts Using Feed-Forward Networks and Elman Recurrent Networks 74 Gregorius Satia Budhi, Hans Christian Indrayana, Liliana, Yulia, Rudy Adipranata

R9-4 The Application of Machine Learning for Earthquake Prediction in Indonesia 74 I Made Murwantara, Pujianto Yugopuspito, Rickhen Hermawan

R9-5 Hybrid Approach Redefinition-Multiclass Imbalance (HAR-MI) Method for Multi-class Imbalanced Datasets 75 H Hartono, Erianto Ongko, Dahlan Abdullah, Yeni Risyani

R9-6 Reconfiguration Layers of Convolutional Neural Network for Fundus Patches Classification 75 Wahyudi Setiawan, Moh. Imam Utoyo, Riries Rulaningtyas

R9-7 HistoriAR: Experience Indonesian History through Interactive Game and Augmented Reality 76 Shintia Trista, Andre Rusli

xxviii

R9-8 Transfer Learning with Multiple Pre-Trained Network for Fundus Classification 76 Wahyudi Setiawan, Moh. Imam Utoyo, Riries Rulaningtyas

R9-9 Augmented Reality using Features Accelerated Segment Test for Learning Tajweed 77 Adi Putra Andriyandi, Wahyudin Darmalaksana, Dian Sa’adillah Maylawati, Ferli Septi Irwansyah, Teddy Mantoro, Muhammad Ali Ramdhani

R9-10 Marketplace Affiliates Potential Analysis Using Cosine Similarity and Vision-Based Page Segmentation 77 Wildan Budiawan Zulfikar, Mohamad Irfan, Muhammad Ghufron, Jumadi

R9-11 Performance Analysis of Multi Services on Container Docker, LXC and LXD 78 Adinda Riztia Putri, Rendy Munadi, Ridha Muldina Negara

R9-12 Prediction Schizophrenia Using Random Forest 78 Zuherman Rustam, Glori Stephani Saragih

R9-13 An Intelligent Agent Model for Learning Group Development in the Digital Learning Environment (DLE): A Systematic Literature Review 79 Budi Laksono Putro, Yusep Rosmansyah, Suhardi

R9-14 Development of Online Learning Groups Based on MBTI Learning Style and Fuzzy Algorithm 79 Budi Laksono Putro, Yusep Rosmansyah, Suhardi

R9-15 Vector Space Model (VSM) for the Search of Qur’an and Hadiths Verses on Science and Technology 80 Ichsan Taufik, Mohamad Jaenudin, Fatimah Ulwiyatul Badriyah, Beki Subaeki

R9-16 Convolutional Neural Network for Maize Leaf Disease Image Classification 80 Mohammad Syarief, Novi Prastiti, Wahyudi Setiawan

R9-17 Single Object Detection to Support Requirements Modeling Using Faster R-CNN 81 Nathanael Gilbert, Andre Rusli

ROOM 10

R10-1 Cerebral Infarction Classification Using Multiple Support Vector Machine with Information Gain Feature Selection 82 Zuherman Rustam, Arfiani, Jacub Pandelaki

R10-2 Kernel KC-means and Support Vector Machines in the Classification of Schizophrenia 82 Zuherman Rustam, Sri Hartini

R10-3 Random Forest and Support Vector Machine for Breast Cancer Classification 83 Chelvian Aroef, Yuda Rivan, Zuherman Rustam

R10-4 Various and Multilevel of Mother Wavelet for Classification Misalignment on Induction Motor with Linear and Quadratic Discriminant Analysis 83 P.P.S. Saputra, Misbah, Eliyani, Rifqi Firmansyah, FD Murdianto, Kukuh Widarsono

R10-5 Classification of Batik Patterns Using K-Nearest Neighbor and Support Vector Machine 84 Agus Eko Minarno, Fauzi Dwi Setiawan Sumadi, Hardianto Wibowo, Yuda Munarko

xxix

R10-6 DWT-SMM-based Audio Steganography with RSA Encryption and Compressive Sampling 84 Fikri Adhanadi, Ledya Novamizanti, Gelar Budiman

R10-7 Identification of Post-Stroke EEG Signal Using Wavelet and 1D Convolutional Neural Networks 85 Rizkia Ilham Ramadhan, Esmeralda C. Djamal, Miranti I. Mandasari

R10-8 Hand Gesture Recognition Using Discrete Wavelet Transform and Convolutional Neural Network 85 Muhammad Biyan Priatama, Ledya Novamizanti, Suci Aulia

R10-9 OFDM Synchronization System Using Wavelet Transform for Symbol Rate Detection 86 Masaru Sawada, Quang Ngoc Nguyen, Mohammed Mustafa Alhasani, Cutifa Safitri, Takuro Sato

R10-10 Deep Convolutional Neural Network for Hand Sign Language Recognition Using Model E 86 Yohanssen Pratama, Ester Marbun, Yonatan Parapat, Anastasya Manullang

R10-11 New Feature Selection Based on Kernel 87 Zuherman Rustam, Sri Hartini

R10-12 Temperature Effect in Optical Fiber Interleaver Based on Cascaded MZI Structure 87 Rahmat Alamtaha, Ary Syahriar, Zulkifli Alamtaha

R10-13 Extended Systematic Clustering: Microdata Protection by Distributing Sensitive Values 88 Widodo, Wahyu Catur Wibowo, Eko K. Budiardjo, Harry T. Yani Achsan

R10-14 A Performance of Radio Frequency and Signal Strength of LoRa with BME280 Sensor 88 Puput Dani Prasetyo Adi, Akio Kitagawa

R10-15 The Flow of Baseline Estimation Using A Single Omnidirectional Camera 89 Sukma Meganova Effendi, Dadet Pramadihanto, Riyanto Sigit

R10-16 Hybrid Optical Communications for Supporting the Palapa Ring Network 89 Ucuk Darusalam, Fitri Yuli Zulkifli, Purnomo Sidi Priambodo, Eko Tjipto Rahardjo

R10-17 VLC Based Infant’s Room Monitoring System For RFFree Hospital 90 Senna Dwi Prasetyo, Ardianto Dzaky Ramzy, Dika Novansyah, Rizki Ardianto Priramadhi, Denny Darlis

1

ABSTRACTS

ROOM 1

R1-1

UNet-VGG16 with Transfer Learning for MRI-Based Brain Tumor Segmentation

Anindya Apriliyanti Pravitasari*1, Nur Iriawan*2, Mawanda Almuhayar3, Taufik Azmi4,

Irhamah5, Kartika Fithriasari6, Santi Wulan Purnami7, Widiana Ferriastuti8 1,2,3,4,5,6,7Department of Statistics, Faculty of Mathematics, Computing, and Data Science,

Institut Teknologi Sepuluh Nopember, 60111 Surabaya, Indonesia 1Department of Statistics, Faculty of Mathematics and Natural Sciences,

Universitas Padjajaran, 45363 Bandung, Indonesia 8Department of Radiology, Faculty of Medicine, Universitas Airlangga, 60115 Surabaya, Indonesia

*Corresponding author, e-mail: anindya.apriliyanti@unpad.ac.id1, nur_i@statistika.its.ac.id2

A brain tumor is one of a deadly disease that needs high accuracy in its medical surgery. Brain tumor detection can be done through Magnetic Resonance Imaging (MRI). Image segmentation for the MRI brain tumor aims to separate the tumor area (as the Region of Interest or ROI) with a healthy brain and provide a clear boundary of the tumor. This study classifies the ROI and Non-ROI using Fully Convolutional Network with new architecture, namely UNet-VGG16. This model or architecture is a hybrid of U-Net and VGG16 with transfer Learning to simplifying the U-Net architecture. This method has a high accuracy of about 96.1% in the testing dataset. The validation is done by calculating the Correct Classification Ratio (CCR) to comparing the segmentation result with the ground truth. The CCR value shows that this UNet-VGG16 could recognize the brain tumor area with a mean of CCR value is about 95.69%.

R1-2

Throughput in Cooperative Wireless Networks

Diego Giral1, Cesar Hernandez*2, Fredy Martinez3

Technological Faculty, Universidad Distrital Francisco Jose de Caldas Calle 68D Bis A Sur # 49F – 70, Bogotá D.C., 111941, Colombia

*Corresponding author, e-mail: dagiralr@correo.udistrital.edu.co1, cahernandezs@udistrital.edu.co2, fhmartinezs@udistrital.edu.co3

Cognitive radio networks emerge as a solution to fixed allocation issues and spectrum scarcity through the dynamic access to spectrum. In cognitive networks, users must make intelligent decisions based on spectrum variation and actions taken by other users. Under this dynamic, cooperative systems can significantly improve quality of service parameters. This article presents the comparative study of the multi-criteria decision-making algorithms SAW and FFAHP through four levels of cooperation (10%, 20%, 50%, 80% y 100%) established between secondary users. The results show the performance evaluation obtained through of simulations and experimental measurements. The analysis is carried out based on throughput, depending on the class of service and the type of traffic.

2

R1-3

Failed Handoffs in Collaborative Wi-Fi Networks

Cesar Hernandez*1, Diego Giral2, C. Salgado3

Technological Faculty, Universidad Distrital Francisco Jose de Caldas Calle 68D Bis A Sur # 49F – 70, Bogotá D.C., 111941, Colombia

*Corresponding author, e-mail: cahernandezs@udistrital.edu.co1, dagiralr@correo.udistrital.edu.co2, lcsalgadof@correo.udistrital.edu.co3

Cognitive radio networks allow a more efficient use of the radioelectric spectrum through dynamic access. Descentralized cognitive radio networks have gained popularity due to the advantages over centralized networks. The purpose of this article is to propose the collaboration between secondary users for cognitive Wi-Fi networks, in the form of two multi-criteria decision-making algorithms TOPSIS and VIKOR, and assess the performance in terms of failed handoffs. The comparison is established under four different scenarios, according to the service class and the traffic level, within the Wi-Fi frequency band. The results show the performance evaluation obtained through of simulations and experimental measurements, where the VIKOR algorithm has a better performance in failed handoffs under different scenarios and collaboration levels.

R1-4

Performance of Wi-Fi Networks in Coexistence with LTE in Non-Licensed Band

Elvis E. Gaona-Garcia*, Felipe A. Zarta, David G. Rosero-Bernal

Facultad de Ingeniería, Universidad Distrital Francisco José de Caldas Carrera 7 N° 40B-53, Bogotá D.C, 110311, Colombia

*Corresponding author, e-mail: egaona@udistrital.edu.co

Currently, LTE transmission initiatives in the 5 GHz unlicensed band are subject of discussion because they could not only represent an increase in capacity for LTE mobile operators of almost 500 MHz but could also mean a potential degradation in the performance of technologies that operate in unlicensed bands as is the case of Wi- Fi, a technology that, despite having more than 15 years in the market, still represents one of the fastest growing wireless technologies. In this article, the performance of a Wi-Fi network in coexistence with the LTE network over an unlicensed band is evaluated using the quantitative degradations index for the performance and latency of the network obtained through simulation results. To evaluate the performance, a coexistence simulation in the 5 GHz band for indoor scenario was carried out following the recommendations of the 3GPP-TR089 for UDP and TCP FTP transmissions. In all the cases analyzed, degradation of performance and network latency was found on the Wi-Fi operator during its coexistence with the LTE operator.

3

R1-5

Design and Performance Study of Free Space Optical Communication System

Suman Malik*1, Prasant Kumar Sahu2

School of Electrical Sciences, Indian Institute of Technology Bhubaneswar, Bhubaneswar, Odisha, India

*Corresponding author, e-mail: sm38@iitbbs.ac.in1, pks@iitbbs.ac.in2

We demonstrate the performance of the Free Space Optical Communication (FSO) system and proposes an optimized FSO system model for data rates of 1Gbps, and 10Gbps respectively. The system performance evaluation has been carried out on the basis of acceptable Q-factor and output power for different data rates signals. Proposed model covers different cases concerning transmitter and receiver characteristics. The presented work aims at optimizing Q-factor, link distance, beam divergence angle and receiver aperture diameter. It is found that the signal with 1Gbps data rate offers a longer link availability for different beam divergence angle and receiver aperture diameter. The impact of the transceiver parameters on FSO system has been investigated. In order, to provide an insight into the impact of various system parameters a detailed analysis has been carried out in this paper.

R1-6

ILC Combined with a PI regulator for Wastewater Treatment Plants

Lanh Van Nguyen*1, Nam Van Bach2, Hai Trung Do3, Minh Tuan Nguyen4

Thai Nguyen University of Technology, Thai Nguyen city, Vietnam *Corresponding author, e-mail: lanhnguyen@tnut.edu.vn1, bachvannam@tnut.edu.vn2,

dotrunghai@tnut.edu.vn3, nguyentuanminh@tnut.edu.vn4

Due to high nonlinearity with features of large time constants, delays, and interaction among variables, control of the Wastewater treatment plants (WWTPs) is a very challenging task. Modern control strategies such as model predictive controllers or artificial neural networks can be used to deal with the non-linearity. Another characteristic of this system should be considered is that it works repetitively. Iterative Learning Control (ILC) is a potential candidate for such a demanding task. This paper proposes a method using ILC for WWTPs to achieve new results. By exploiting data from the previous iterations, the learning control algorithm can improve gradually tracking control performance for the next runs, and hence outperforms conventional control approaches such as feedback controller and Model Predictive Control (MPC). The Benchmark Simulation Model No.1-BSM1 has been used as a standard for performance assessment and evaluation of the control strategy. Control of the Dissolved Oxygen in the aerated reactors has been performed using the PD-type ILC algorithms. The obtained results show the advantages of ILC over a classical PI control concerning the control quality indexes, IEA and ISE, of the system. Besides, the conventional feedback regulator is designed in a combination with the iterative learning control to deal with uncertainty. Simulation results demonstrate the potential benefits of the proposed method.

4

R1-7

Use of Closed Loop System Using Arduino for Different Parameters in Farming

Saifur Rahman

Department of EE, Faculty of Engineering, Najran University King Abdul Aziz Road, Najran-1988, Saudi Arabia

*Corresponding author, e-mail: srrahman@nu.edu.sa

The GDP (Gross Domestic Product) of most countries in the world are based on the agriculture contribution of that particular country. The current weather conditions in the world and crop loss are the main reason for its contribution to GDP. New technologies and advanced fertilizers are now used in the farming though these technologies and advanced fertilizers do not reach to farmers till now. In this paper, a concept for the automated watering system in farming is introduced which uses wireless sensors technology for detection of moisture in the soil suitable for agriculture using a smartphone application which will play the critical role for agriculture. The automatic watering to plant using the Arduino system and android application is used. Even this application of Android will provide information to the farmers related to agriculture like costs of seeds, level of moisture required, amount of water needed, which type of soil required, forecast weather, fertilizers to be used and pesticides required.

R1-8

Scheme for Motion Estimation Based on Adaptive Fuzzy Neural Network

Fredy Martínez*1, Cristian Penagos2, Luis Pacheco3

Facultad Tecnológica, Universidad Distrital Francisco José de Caldas, Bogotá, Colombia *Corresponding author, e-mail: fhmartinezs@udistrital.edu.co1,

cfpenagosb@correo.udistrital.edu.co2, lapachecor@correo.udistrital.edu.co3

Many applications of robots in collaboration with humans require the robot to follow the person autonomously. Depending on the tasks and their context, this type of tracking can be a complex problem. The paper proposes and evaluates a principle of control of autonomous robots for applications of services to people, with the capacity of prediction and adaptation for the problem of following people without the use of cameras (high level of privacy) and with a low computational cost. A robot can easily have a wide set of sensors for different variables, one of the classic sensors in a mobile robot is the distance sensor. Some of these sensors are capable of collecting a large amount of information sufficient to precisely define the positions of objects (and therefore people) around the robot, providing objective and quantitative data that can be very useful for a wide range of tasks, in particular, to perform autonomous tasks of following people. This paper uses the estimated distance from a person to a service robot to predict the behavior of a person, and thus improve performance in autonomous person following tasks. For this, we use an Adaptive Fuzzy Neural Network (AFNN) which includes a fuzzy neural network based on Takagi-Sugeno fuzzy inference, and an adaptive learning algorithm to update the membership functions and the rule base. The validity of the proposal is verified both by simulation and on a real prototype.

5

R1-9

Design of Deep Hypersphere Embedding for Real-Time Face Recognition

Ryann Alimuin1, Elmer Dadios2, Jonathan Dayao3, Shearyl Arenas4

Technological Institute of the Philippines – Quezon City, De La Salle University - Manila tel: (+632) 911-0964 loc. 334

*Corresponding author, e-mail: ryann.alimuin@tip.edu.ph1, elmer.dadios@dlsu.edu.ph2, jonathan.dayao@tip.edu.ph3, shearyl.arenas@tip.edu.ph4

With the advancement of human-computer interaction capabilities of Robots, computer vision surveillance systems involving security yields a large impact in the research industry by helping in digitalization of certain security processes. Recognizing a face in the computer vision involves identification and classification of which faces belongs to the same person by means of comparing face embedding vectors. In an organization that has a large and diverse labelled datasets on a large number of epoch, oftentimes, creates a training difficulties involving incompatibility in different versions of face embedding that leads to poor Face Recognition accuracy. In this paper, we will design and implement robotic vision security surveillance system incorporating hybrid combination of MTCNN for face detection, and FaceNet as the unified embedding for face recognition and clustering.

R1-10

COA Learning Module Uses an 8-bit CPU Architecture to Analyze the Undergraduate Learning Outcomes

Mochammad Hannats Hanafi Ichsan1, Wijaya Kurniawan*2

Computer Engineering, Faculty of Computer Science, Brawijaya University 8th Veteran Road, Malang, Indonesia, tel: (0341) 577-911

*Corresponding author, e-mail: hanas.hanafi@ub.ac.id1, wjaykurnia@ub.ac.id2

Computer Organization and Architecture (COA) is a basic course that must be understood by students in the field of Computer Engineering (CE). This COA course offers basic principle about how computer works, which can be simply represented on the design of an 8-bit CPU. To achieve these objectives, it should be supported by a good learning media. Learning media are not only made to convey material but must provide better understanding to students. This research is divided into several stages. There was some previous researches to identify the needs of students, make a selection of related software, and carry out a simulation design with an 8-bit CPU architecture. Based on those researches, it is found that the simplest computer architecture for learning is the Mic-1 architecture. This study will be focused on conducting an analysis related to student achievement on the ability to understand the COA subject to Learning Outcome (LO). Students is asessed before getting material using other media (books, slide shows and e-learning) and then some comparation with students who got material from simulators will be made. The objective is to analyze which students will get the better scores between those teaching media.

6

R1-11

Noise on Near Infrared Sensor for Glucose Solution Measurement

Kiki Prawiroredjo*, Engelin Shintadewi Julian

Electrical Engineering Department, Faculty of Industrial Technology, Trisakti University Jalan Kiai Tapa No. 1, Jakarta 11440, Indonesia, tel: 021-5663232

*Corresponding author, e-mail: kiki.prawiroredjo@trisakti.ac.id

This paper proposed the method of measuring glucose concentrations in solution using near infrared light (NIR) and photodiode sensor in three different environment conditions in order to find out noise sources on the sensor. We studied noises that occurred on the output signal of NIR sensor in three different room conditions. We measured the sensor output voltages every five minutes in an hour for air media, water media, and glucose solution media to observe the output voltage stability. The first room was near a main transformer and with translucent glass windows, the second room was near a main transformer without window, and the third room was a room with translucent windows. The sensor’s circuit consisted of a 1450 nm NIR light emitting diode, a photodiode as the receiver, transimpedance amplifier, a notch filter, and a 4th order low pass filter to reduce high frequency noises and 50 Hertz noise from power line induction. The results showed that the sun light passing through the windows was the most influenced sensor work and made the sensor output voltages did not stable. The filters removed the AC voltages and the DC output voltages of the sensor varied depend on room conditions. Based on the average voltage difference of the output sensor from the three room with water and glucose solution media, the sensor had the potential to be a glucose solution meter.

R1-12

Effect of Dye pH Variation on Blueberry Anthocyanin Based Dye Sensitized Solar Cell (DSSC)

Zainul Abidin*, Eka Maulana, Panca Mudjirahardjo, M. Ivan Fadillah

Electrical Engineering Dept. of Universitas Brawijaya Jl. MT Haryono 167 Malang, Indonesia, tel/fax: +62 341 554166

*Corresponding author, e-mail: zainulabidin@ub.ac.id

Anthocyanin is a type of natural pigment that gives color to plants and can be used to absorb visible light with wavelength of 400-600 nm. The absorption ability is very useful for dye in designing Dye Sensitized Solar Cell (DSSC). The anthocyanin can be extracted from blueberry and has unique characteristic of high stability when it reaches low pH. In this paper, design of DSSC with dye made of blueberry anthocyanin and its performance related to pH variation is presented. The performance was evaluated experimentally according to output voltage and current generated by 4 fabricated samples (pH of 1,5; 2; 2,6; 4,4) from A.M 1.5 sunlight and 10 watt LED. Experiment results show that for both light sources, dye with pH of 1,5 has the highest output voltage and current among the others. Since the output voltage and current are very small, the exsisting design of DSSC is suitable to be developed for optical sensor.

7

R1-13

BPF Comparison of Hairpin Line and Square Open-Loop Resonator Method

Yuyun Siti Rohmah1, Budi Prasetya2, Dwi Andi Nurmantris3,

Sarah Mulyawati4, Reza Dipayana5

Telkom University, Jl. Telekomunikasi, Bandung, 40257, Indonesia tel: +62 22 7564108, fax: +62 22 756 5200

*Corresponding author, e-mail: yuyunsitirohmah@telkomuniversity.ac.id1, budiprasetya@telkomuniversity.ac.id2, dwiandi@tass.telkomuniversity.ac.id3,

sarahmulya98@gmail.com4, rezadipayana.rd@gmail.com5

This paper presents the comparison of two methods of bandpass filter (BPF) design using hairpin-line and square open loop resonator. Both methods were applied to obtain filter designs that can work at television broadcasting system. Bandpass filter was simulated using design software and fabricated using epoxy FR-4 substrate. The results of simulation and measurement showed return loss value at 27.3 dB for hairpin line BPF and 25.901 for square open loop resonator BPF. Meanwhile, VSWR parameter values were 1.09 and 1.1067 for hairpin line and square open loop BPF respectively. The insertion loss values for the Hairpin line BPF and square open loop BPF were 6.9 and 5.9511 dB, respectively. Fractional bandwidth (FBW), for hairpin line BPF was 6.7% while for square open loop BPF was 4.8%. Regarding the size, the dimension of square open loop resonator was approximately three times larger than that of hairpin-line band pass filter.

R1-14

Analysis of Lambertian Order to Determine The Ideal Angle and Position of Photodetector for VLC

Dwi Astharini1, Heri Kurniawan*2, Ary Syahriar3

University of Al Azhar Indonesia, Jl. Sisingamangaraja No.2, RT.2/RW.1, Selong, Kec. Kebayoran. Baru, Kota Jakarta Selatan, Daerah Khusus Ibu Kota Jakarta, tel: (021) 72792753

*Corresponding author, e-mail: Astharini@uai.ac.id1, herikurniawan220996@gmail.com2, Arysyahriar@uai.ac.id3

Visible Light Communication is one of the light-based communication technologies that is currently being developed. In simple terms in this communication system, information will be sent via LED with a range of 430 THz-790 THz frequency and will be received by the receiver side using a photodetector. However, there are several problems in the system visible transmission of communication between the LED and the Photodetector. The LED light that reaches a room at each corner does not have the same power. If the Photodetector is moved in just a few corners, the power received is not the same as the previously received power. In this paper, a simulation will be made using MATLAB to find out the LED gain against the angle 0o - 90o. So it will be found which angle is the most ideal to put the photodiode. By using the Line of Sight method and analysis at Lambertian, the ideal angle for placing the photodetector is in the range 30o-60o. The angle reaches a more stable LED transmission area. Stability is measured using gain at the angle mentioned above. While at an angle of 70o-90o there is a need for a physical amplifier to maintain gain on the LED transmission.

8

R1-15

Audio Watermarking Based on LWT-DCT-SVD with Compressive Sampling Framework

Ledya Novamizanti1, Gelar Budiman2, Elsa Nur Fitri Astuti3

School of Electrical Engineering, Telkom University, Bandung, Indonesia *Corresponding author, e-mail: ledyaldn@telkomuniversity.ac.id1,

gelarbudiman@telkomuniversity.ac.id2

Digital audio watermarking is one of a solution to protect the copyright of an audio from copyright infringement. Audio watermarking should be implemented in such a way as to be its imperceptibility is high, its robustness is good, and it has high payload. In this paper, we design an audio watermarking method which is robust also to delay attack with high payload. The synchronization bit added on an audio host. After the audio host is decomposed by LWT, then choose a subband from the output of LWT to be transformed by DCT. Next, the matrix of the signal from DCT is selected for the SVD process, so that is obtained U, S and V matrix. S matrix is embedded with the watermark. Before the embedding process, the watermark is compressed by CS acquisition. The results indicate that the proposed watermarking system is highly robust against a kind attack of LPF, resampling, and linear speed change which its BER is zero.

R1-16

Accurate Characterizations of Material Using T-ring Microwave Resonator for Bio-sensing Applications

Rammah A. Alahnomi*1, Z. Zakaria2, Zulkalnain Mohd Yussof3, Tole Sutikno4,

H. Sariera5, Amyrul Azuan Mohd Bahar6

1,2,3,5Centre for Telecommunication Research and Innovation (CeTRI), Universiti Teknikal Malaysia Melaka (UTeM), 76100 Durian Tunggal, Melaka, Malaysia

4Department of Electrical Engineering, Universitas Ahmad Dahlan, Yogyakarta, Indonesia 6Intel Microelectronics, Bayan Lepas Free Industrial Zone, 11900 Penang, Malaysia

*Corresponding author, e-mail: alrammah89@gmail.com1, zahriladha@utem.edu.my3

The topic of microwave sensors in enclosures is one of the most active areas in material characterization research today due to its wide applications in various industries. Surprisingly, a microwave sensor technology has been comprehensively investigated and there is an industry demand for an accurate instrument of material characterization such as food industry, quality control, chemical composition analysis and bio-sensing. These accurate instruments have the ability to understand the properties of materials composition based on chemical, physical, magnetic, and electric characteristics. Therefore, a design of the T-ring resonator has been introduced and investigated for an accurate measurement of material properties characterizations. This sensor is designed and fabricated on a 0.787 mm-thickness Roger 5880 substrate for the first resonant frequency to resonate at 2.4 GHz under unloaded conditions. Various standard dielectric of the sample under test (SUT) are tested to validate the sensitivity which making it a promising low-cost, compact in size, ease of fabrication and small SUT preparation for applications requiring novel sensing techniques in quality and control industries.

9

R1-17

Buck Converter Optimization Using P&O Algorithm for PV System Based Battery Charger

Zainul Abidin*, Adharul Muttaqin, Eka Maulana, M. Gilang Ramadhan

Electrical Engineering Dept. of Universitas Brawijaya Jl. MT Haryono 167 Malang, Indonesia, tel/fax: +62 341 554166

*Corresponding author, e-mail: zainulabidin@ub.ac.id

In this research, battery charger based on Photovoltaic (PV) system consists of buck converter as useful PV module interface was fabricated. Since output power of PV module changes quickly due to changing solar radiation, optimization is required. One of the easy and cheap optimization techniques is by implementing Perturb and Observe (P&O) algorithm for controlling switch of the buck converter. The P&O algorithm tracks maximum power point by generating suitable duty cycle for switching of the buck converter. The objective of this paper is to present the experimental proof of the P&O algorithm implementation in optimizing performance of the buck converter. The experimental results prove that the P&O algorithm can optimize the work of the buck converter and support shorter charging time by producing higher output voltage and power.

R1-18

Water Bath Sonicator Integrated with PID-Based Temperature Controller for Flavonoid Extraction

Zainul Abidin*1, M. Aziz Muslim2, Muhammad Muqorrobin3, Warsito4

1,2,3Electrical Eng. Dept. of Universitas Brawijaya

4Chemistry Dept. of Universitas Brawijaya Jl. Veteran, Malang, Indonesia, tel/fax: +62 341 554166 *Corresponding author, e-mail: zainulabidin@ub.ac.id

In this research, water bath sonicator was fabricated to extract bioactive compound of plants material using sound energy (ultrasonic waves) and heater. The bioactive compound, flavonoid, has high sensitivity to temperature and extraction time and previous research stated best treatment with combination of 45˚C and 20 minutes. Therefore, fabricated water bath sonicator was equipped with Proportional Integral Derivative (PID) based temperature controller and timer. Based on a calculation using the Ziegler-Nichols tuning method, Kp, Ki, Kd parameters are 16.59, 0.0279, and 2463.6, respectively. The experimental result shows that the PID controller can perform as design specification with overshoot 1.39%, error steady-state 0.688% and settling time 37.2 minutes. Furthermore, it was proven that the PID controller has contribution to extract more flavonoid.

10

ROOM 2

R2-1

Insomnia Analysis Based on Internet of Things Using Electrocardiography and Electromyography

Novi Azman*1, Mohd Khanapi Bin Abd Ghani2, S.R. Wicaksono3,

Barru Kurniawan4, Viktor Vekky Ronald Repi*5 1,2Fakulti Teknologi Maklumat dan Komunikasi (FTMK), Universiti Teknikal Malaysia Melaka

Hang Tuah Jaya, 76100 Durian Tunggal, Melaka, Malaysia 1,3,4,5Faculty Engineering and Science, Universitas Nasional

Jalan Sawo Manila, Jakarta Selatan 12520, DKI Jakarta, Indonesia *Corresponding author, e-mail: novi.azman@civitas.unas.ac.id1, vekky_repi@civitas.unas.ac.id5

Insomnia as a disorder to start, maintain, and wake up from sleep, has many sufferers in the world. For patients in remote locations who suffer from Insomnia, which requires testing the gold standard performed requires patients to take the time and travel to the health care center. By making alternatives to remote sleep insomnia testing using electrocardiography and electromyography connected to the Internet of Things, it is hoped that this problem can be resolved. Delivery of patient data to the server is done to make observations from the visualization of patient data real-time. Furthermore, by using Artificial Neural Networks to classify the Insomnia has resulted in errors in testing patient data of 0.2% to 2.7%.

R2-2

MILA: Mobile IoT for Low Cost BCI Framework

Rolly Maulana Awangga*1, Syafrial Fachri Panea2, Dzikri Ahmad Ghifaria3, Moch Yusuf Asyharib4

1,2,3Applied Bachelor Program of Informatics Engineering, Politeknik Pos Indonesia 4Magister Program of Informatics Engineering, Universitas Islam Indonesia

*Corresponding author, e-mail: awangga@poltekpos.ac.id

The Human brain is a vital organ in the body that acts as the centre of the human nervous system. Brain-Computer Interface (BCI) use Electroencephalography (EEG) signal as information from the brain activity. EEG generally used as medical equipment in the hospital, which is not wearable and high-cost equipment. Combining EEG as part of IoT (Internet of Things) with high mobility is challenging research. This study tries to make a low-cost wearable BCI on motorcycle riders. An EEG data is used to analyze brain activity and predict the transitions generated when riding a motorcycle when conditions are turning right or left. Therefore, a further installation method must produce the right features to get the precise and accurate brain wave characteristics of the EEG signal. This study used IoT concept combine with software engineering to avoid an accident in motorcycle driver. The purpose of this research to create a low-cost BCI framework for mobile IoT.

11

R2-3

Classification of Pneumonia from X-ray Images Using Siamese Convolutional Network

Kennard Alcander Prayogo1, Alethea Suryadibrata*2, Julio Christian Young3 Department of Information and Technology, Universitas Multimedia Nusantara

Jl. Scientia Boulevard, Gading Serpong, Tangerang, Banten 15811, Indonesia, tel: +6221 54220808 *Corresponding author, e-mail: kennard.prayogo@student.umn.ac.id1,

alethea@umn.ac.id2, julio.christian@umn.ac.id3

Pneumonia is one of the highest global causes of deaths especially for children under 5 years old. This happened mainly because of the difficulties in identifying the cause of pneumonia. As a result, the treatment given may not be suitable for each pneumonia case. Recent studies have used deep learning approaches to obtain better classification within the cause of pneumonia. In this research, we used siamese convolutional network (SCN) to classify chest x-ray pneumonia image into 3 classes, namely normal conditions, bacterial pneumonia, and viral pneumonia. Siamese convolutional network is a neural network architecture that learns similarity knowledge between pairs of image inputs based on the differences between its features. One benefit of classifying data with SCN is the availability of comparable images that can be used as a reference when determining class. Using SCN, our best model achieved 80.03% accuracy and 79.59% f1 score.

R2-4

Identification of Gram-Negative Bacteria Using Convolutional Neural Network

Budi Dwi Satoto*1, Imam Utoyo2, Riries Rulaningtyas3, Eko Budi Koendhori4

1Information System Department, Engineering Faculty, Trunojoyo University of Madura Raya Telang Street PO BOX 2 Kamal, Bangkalan, tel: +6231-3011146

2Mathematic Department, Sains and Technology Faculty, Airlangga University of Surabaya

3Physic Department, Sains and Technology Faculty, Airlangga University of Surabaya

4Microbiology Department, Medical Faculty, Airlangga University of Surabaya Kampus C Mulyorejo, Surabaya PO BOX 60115, Indonesia, tel: +62031-5914042

*Corresponding author, e-mail: budids@trunojoyo.ac.id1, m.i.utoyo@fst.unair.ac.id2

Damage to the lung lobes is mostly caused by Gram-negative bacteria. Bacterial samples were obtained through the sputum of the patient. Bacteria distinguished by the Gram staining process. The problem faced is that the process of identifying bacterial objects is still done manually under a fluorescence microscope. The solution proposed in this research is the identification pattern approached using image processing with the Graphics Processing Unit. The observations focused on observing bacterial morphology for the process of selecting shape features. In the test scenario, a convolutional neural network with the VGG-16 architecture is used. The choice of method is influenced by a high degree of accuracy. This research uses a sample of 2520 images from 2 different classes. The number of the data used in training, testing and validation are 840 images with a resolution of 256x256 pixels. The accuracy ofthe results obtained after the fitting process is 99.20%.

Insomnia Analysis based on Internet of Things using Electrocardiography and Electromyography

Novi Azman*1, Mohd Khanapi Bin Abd Ghani2, S. R. Wicaksono3, Barru Kurniawan4, Viktor Vekky Ronald Repi*5

1,2Fakulti Teknologi Maklumat dan Komunikasi (FTMK), Universiti Teknikal Malaysia Melaka Hang Tuah Jaya, 76100 Durian Tunggal, Melaka, Malaysia 1,3,4,5Faculty Engineering and Science, Universitas Nasional

Jalan Sawo Manila, Jakarta Selatan 12520, DKI Jakarta, Indonesia e-mail: vekky_repi@civitas.unas.ac.id5, novi.azman@civitas.unas.ac.id1

Abstract Insomnia as a disorder to start, maintain, and wake up from sleep, has many sufferers

in the world. For patients in remote locations who suffer from Insomnia, which requires testing the gold standard performed requires patients to take the time and travel to the health care center. By making alternatives to remote sleep insomnia testing using electrocardiography and electromyography connected to the Internet of Things, it is hoped that this problem can be resolved. Delivery of patient data to the server is done to make observations from the visualization of patient data real-time. Furthermore, by using Artificial Neural Networks to classify the Insomnia has resulted in errors in testing patient data of 0.2% to 2.7%.

Keywords: Electrocardiography, Electromyography, insomnia, internet of things 1. Introduction

Sleep is a mandatory requirement that humans need and affect human health. Poor sleep quality can result in sleep disorders that have a direct and indirect impact on daily activities. There is a tendency that patients who have sleep disorders are more prone to suffer from chronic diseases such as diabetes, obesity, and hypertension. Several studies have found an association between sleep quality and the risk of chronic obesity and diabetes [1], while Obstructive Sleep Apnea is a risk factor for systemic hypertension [2].

The most common sleep disease is Insomnia. Insomnia is a sleep disorder that is often overlooked and missed by primary care physicians until or unless requested by the patient, with a prevalence of about one in three subjects in the study that has a sleep disorder insomnia. Prevalence of people with chronic Insomnia has increased significantly in the urban area. The urban lifestyle, requirements, and other socio-economy demands are some of the cause for this increment [3–8]. These have an indirect effect on the socio-economy factors in a country, where about 60 percent of people in developing countries living in an urban area.

Polysomnography is the gold standard to measurement and collection of those factor for the sleep study. However, due to the routine of clinical assessment, the polysomnography is impractical and limited to be used in a specific place [9]. A proposed Actigraph could be used to increase accuracy and mobility from polysomnography for sleep pattern measurement. Unfortunately, the limitation of this device and complexity in its installation, along with polysomnography become their restriction [10]. The advantage of using this polysomnography is that it produces accurate data, but it has constraints in terms of time and cost needed by patients to be able to get insomnia treatment as well as obstacles for patients who find it challenging to carry out routine treatment to the hospital. However, this conventional approach has been considered more costly and technically complex and may present appointing schedule difficulties when there is high demand [11]. One of the most problems of sleep disorder is access to diagnosis. The demand of the diagnosis is influenced by prevalence and incidence of the disease, cost and patient reimbursement policies, patient and primary physician awareness and wait times where the capacity of the treatment dictate by availability of sleep laboratory beds determined by funding policies, availability of sleep specialists, and policies about order or interpret diagnostic polysomnography studies [12]. Treatments and assessments of Insomnia using polysomnographic turn out to have socio-economic problems, but for some cases is not

good enough in patients who are difficult to mobility [13,14]. So we need a tool with a method of use that can make it easier for patients to undergo treatment that is cheap and easy to apply daily.

The use of Internet-based telemonitoring with the advantage of remote data measurement as one of the right solutions to solve the problems faced by insomnia patients. The problem of Insomnia patients in terms of time, cost, and routine care that requires patients to come to the hospital. Many IoT application was using in medical area, such as, ECG IoT based Centralized Insomnia system [15], IoT for real-time cardiac monitoring [16], IoT for diabetes management [17], Drowsiness Detection and Monitoring using IoT and brainwaves [18], IoT for chronic metabolic disorder [19], IoT-based upper limb rehabilitation assessment [20], HRV monitoring using IoT [21], and even for elderly monitoring using IoT [22].

Problems that occur regarding access to insomnia sleep disorders testing with high costs and time consuming are expected to be resolved with the help of the Internet of Things, wherein this study case studies were carried out in remote monitoring of vital organs of the heart using ECG sensors and vital organs of the muscles by using EMG sensors. The results of the data are transmitted using the concept of the Internet of Things to store data. Furthermore, vital patient data visualized graphically and analyzed for the classification of insomnia sleep disorders. It is also increasing the effectiveness of sending data between patients and medical services.

The contribution of our study is to provide a new system approach to diagnose Insomnia sleep disorders. By using some biomedical sensors from Polysomnography devices, Electrocardiography, Electromyography and by applying the concept of the Internet of Things that is used so that diagnosis can be done anywhere by sending data to the medical center. In this study, it is expected to reduce the cost and time of patients compared to the way the diagnosis of the conventional insomnia sleep disorder nowadays. 2. Research Method

This section will explain how the system created can be useful to perform functions such as the objectives stated in the introduction. Overall the system in this study is divided into four major parts. This system consists of a hardware system, a software system, communication between them, and the data classification step. In this paper, we will explain how each hardware component is connected. Also explained the process of how the communication between hardware and software data exchange. So finally, how to classification patients with insomnia sleep disorders.

2.1. Hardware Systems Architecture

The hardware part involved in the system in the study conducted in this paper involves several hardware devices. The hardware made compact so that it makes it easy for the hardware to move from one location to another. Therefore, the hardware made with some lightweight components and small size. Overall the hardware components that are compiling into a hardware system used in this study are shown in Figure 1.

Figure 1. Hardware Systems Architecture

In Figure 1, we can see that we can group them into four parts. The part is Microcontroller and Shield, Medical Sensor, Interface, and Supply. In the Microcontroller and Shield section, the ESP32 microcontroller hardware used as the central control of the hardware. The ability of ESP32 [23] using Xtensa® LX6 microprocessors and 448 KB ROM and 520 SRAM also with built-in WiFi 802.11 b/g/n connectivity and Bluetooth v4.2 and Bluetooth Low

Energy is sufficient to process from the Internet of Things to the system carried out on the study. Shields made for ESP32 microcontrollers are custom made that is used to connect them to sensors. This section serves to receive data from sensors and send data to the server using internet connectivity.

In the Medical Sensor section, there are two medical sensors, namely Electrocardiography and Electromyography sensors. For sensors that record heart activity, the AD8232 Electrocardiography medical sensor used. Meanwhile, to record the activity of the body's movements used electromyography medical sensors from BITalino. BITalino is one of the medical sensors used to carry out physiological computing [24,25].

The interface part displays the status of the hardware system in the system used in this study. LCD 5110 used as a hardware component whose job is to display the status of the hardware system.

The Supply Section is responsible for providing power for the entire hardware system, and a Li-Po battery is used to deliver and distribute power. 2.2. Software Embedded

Software embedded in the hardware system is carried out using the Arduino IDE program. The process flow is shown in Figure 2. It can seem that at the beginning of the initials, the program is calling the library from the sensor, declaring WiFi profiles, server addresses, and other global variables.

Arduino IDE setting the baud rate speed of 115200 bits per second to download the program on the ESP32 microcontroller and logging the processes that occur. Next is to connect to a WiFi network. If the ESP32 microcontroller is not connecting to a WiFi network, it will be re-connecting.

If it is successfully connecting to a WiFi network, continuous data reading is performing on the “void loop()” function on the Arduino programming. Patient vital data readings are from electrocardiography and electromyography sensors with float data types. After the data obtained, then try to connect to the server. If it is not connected, it will reread the patient's vital data and re-connect with the server. If it is connected, the patient's vital data will convert into a form of data string which is carried out for sending data to the server using the "POST" method from REST (Representational State Transfer) API (Application Program Interface) prepared on the server-side. The process of the loop() function will repeat until it doesn’t get power back.

Figure 2. Hardware Processing Flowchart

2.3. Communication This section is communication between systems located in remote areas and servers using interconnection networks. The system is conducting communication between systems located in remote areas sending data to a server where the server acts as a REST API. The connection flow process of the device system at a remote location with a server is shown in Figure 3.

Figure 3. File Request Data Process Flowchart

The process in Figure 3 starts from the initiation of the user and the website host to log

in to the database. Data received through the REQUEST method in REST API will then stored in each table in the MySQL database that is set depending on the type of sensor type used by using the INSERT command in the database. Furthermore, using the API for each table by taking data from the database which convert into the JSON format.

The schematic process flow for creating the API is shown in Figure 4. The schematic is to explain how the patient data flow is taken from the database preparing the data used to be the JSON format. First, initiating website users and hosts who then log in to the database on the web service. Retrieve data from each sensor table from the database using the GET command on MySQL. After the patient data took, then the next step sorts the data according to needs and makes an array of patient data lines. Next is to convert the data array created previously into data in the form of the JSON format.

Figure 4. API Process Flowchart

3. Results and Analysis 3.1. Effectiveness of sending data

The effectiveness of sending data needs to be examined further because in some cases in remote locations, signal strength may be worse than in urban locations; therefore testing with varying signal strengths appears in this study. We can see in Table 1, a comparison of data with varying signal strengths. Table 1 is the data sent from the ESP32 microcontroller which has been set up by sending two data per second (7200 data per hour) with the condition that the tested signal strengths range from -81 dBm to -108 dBm. Delivery time starts from 30 minutes to 120 minutes. It is seen that the accuracy of the signal transmission reaches 100% at the signal strength of -81 dBm, -89 dBm and -97 dBm. While the signal strength of -108 dBm has an accuracy of sending data above 97%. From this data shows that the quality of internet connectivity used must be stable.

Table 1. Sending Data Accuracy

The effectiveness of sending data is useful for performing patient vital data from

Electrocardiography and Electromyography sensors in real-time. The patient real-time data store in a database. The visualization is a dynamic graph, where this graph will only display the latest data when the device system that is in a remote location is running. So that when it is not running, no graph is displayed. Because the dynamic graph that is displayed is a real-time graph, the use of stable internet connectivity is a must. An example of a real-time image on this device system shown in Figure 5.

Figure 5. Realtime ECG-EMG visualization in web service 3.2. Insomnia Classification

Data stored on the server in addition to visualization by making dynamic charts also the data is useful for classifying Insomnia, whether the patient has Insomnia or not. By using artificial intelligence through Artificial Neural Network methods performed on the server. Patient data will be test data and compared with training data derived from verified medical device data. There are three stages of the process of using Artificial Neural Networks to obtain patient classification results.

In the Artificial Neural Network that uses, there is an input layer and target output, where there are ten arrays of data from three patients which are training data that become the input layer and one expected output target. With the initiation of the number of layers used in the form of ten input layers, ten hidden layers, and one output layer. Test data from the sensor as much as ten arrays of data from the training data compare with ten arrays of test data, which is the input layer. One in ten hidden layers consists of neurons that receive each data from ten

No

Signal Strength-108 dBm -97 dBm -89 dBm -81 dBm

Accuracy Accuracy Accuracy Accuracy

1 0,5 3600 3560 98,80% 3600 100,00% 3600 100,00% 3600 100,00%2 1 7200 7020 97,50% 7200 100,00% 7200 100,00% 7200 100,00%3 1,5 10800 10580 97,90% 10800 100,00% 10800 100,00% 10800 100,00%4 2 14400 14080 97,70% 14400 100,00% 14400 100,00% 14400 100,00%

Sending time (in hours)

Amount of packet Data Data

receivedData

receivedData

receivedData

received

input layers. The results in the output layer are a calculation of the value of the input layer to be the target output.

Training data used to train training data, where the training data used is data from medical devices. There are three training data inputs from medical devices provided that two data are not insomnia data, and one is insomnia sufferer data. Each input value will classify with the output value agreed with the specialist doctor. Later the training data will go through a training process until corrections to the agreed, and expected output values are reaches. The value of training used is 350, where the value of this training has the smallest error of the whole tested. These results are shown in Table 2.

No Train error output No Train error output1 10 25.8 % 9 300 3.1 %2 30 22.6 % 10 350 1.0 %3 50 22.3 % 11 400 8.4 %4 80 15.2 % 12 450 9.1 %5 100 11.9 % 13 500 9.9 %6 150 11.9 % 14 550 8.0 %7 200 6.2 % 15 600 8.8 %8 250 3.2 %

Table 2. Data training and error of output

In classifying patients suffering from insomnia sleep disorders, the process of testing

the data with the first Artificial Neural Network aims to compare the patient's cardiac activity test data obtained from electrocardiography sensors with training data from medical devices. The second process is to test data with Artificial Neural Networks that compare the patient's movement data during sleep conditions from electromyography sensors with data from medical devices. The predicted output is the result of comparison with actual output. If the predicted output approaches the value of one of the actual outputs with the smallest error value, then it can be concluded that the predicted output is classifying according to specified conditions. These two processes are shown in Figure 6, the process of comparing data using Artificial Neural Networks.

Figure 6. Comparison process of training and testing data using Artificial Neural Network

ECG analysis is shown in Figure 7. Figure 7 is a conclusion from the results of the analysis of patient biosignal data using the BioSppy library, graphs are filtered, analyzed for cardiac activity and reviewed with the PQRST signal pattern displayed in the "Templates" image column.

Table 3 is the result of testing ten test data from the device used in this study, namely the electrocardiography sensor, which compares with medical training data. Actual output is the result of the training from the expected output. The predicted output of the device used in this study is compared with the actual output to find the closest data with the smallest error in one of the target values. There are four out of ten test data that are classified as having cardiac abnormalities but have not been confirmed to suffer from Insomnia. The error value of this test is between 0.4% and 1.2%.

Figure 7. ECG Graph Analysis in web services Table 3. ECG Analysis using Artificial Neural Network

Figure 9 shows the conclusions of the EMG conducted by the BioSppy library. In Figure

9, the upper part is the image before filtering by the BioSppy library while at the bottom is the image that has been filtered by the BioSppy library.

Table 4 is the result of testing ten test data from the device used in this study, namely the Electromyography sensor, which compares with medical training data. Actual output is the result of the training from the expected output. The predicted output of the device used in this study is compared with the actual output to find the closest data with the smallest error in one of the target values. There two of ten test data are classified experiencing tense muscles but has

NoMedical Device Data

TrainTraining Reuslt

ErrorHealty Heart Healty Heart Heart Trouble

1 350 0,961 0.6% Healty Heart

2 350 0,935 0.6% Healty Heart

3 350 0,991 1.0%

4 350 0,97 1.2%

5 350 0,99 0,90%

6 350 0,967 1.2% Healty Heart

7 350 0,947 0.8% Healty Heart

8 350 0,951 0.5% Healty Heart

9 350 0,959 0.4% Healty Heart

10 350 0,993 1.2%

Obtained Data

Classification ResultActual

OutputPredicted

Output[1.1,1.2,2.4,0.9,1.3,1.4,1.3,1.3,1.3,1.3]

[1.5,1.2,2.4,0.8,1.5,1.6,1.7,1.5,1.5,1.2]

[1.3,1.4,2.4,1.0,1.3,1.4,1.3,1.3,1.4,1.4]

[1.8,1.7,2.9,1.2,1.6,1.7,1.8,1.7,1.5,1.8]

0.940,0.955,0.

981[1.4,1.2,2.4,1.0,1.3,1.4,1.3,1.3,1.5,1.5]

[1.5,1.2,2.4,0.8,1.5,1.6,1.7,1.5,1.5,1.2]

[1.3,1.4,2.4,1.0,1.3,1.4,1.3,1.3,1.4,1.4]

[1.8,1.7,2.9,1.2,1.6,1.7,1.8,1.7,1.5,1.8]

0.940,0.955,0.

981[1.8,1.6,2.9,1.2,1.6,1.8,1.8,1.7,1.6,1.5]

[1.5,1.2,2.4,0.8,1.5,1.6,1.7,1.5,1.5,1.2]

[1.3,1.4,2.4,1.0,1.3,1.4,1.3,1.3,1.4,1.4]

[1.8,1.7,2.9,1.2,1.6,1.7,1.8,1.7,1.5,1.8]

0.940,0.955,0.

981

Heart Problem

[1.6,1.8,2.8,1.2,1.6,1.7,1.8,1.7,1.5,1.8]

[1.5,1.2,2.4,0.8,1.5,1.6,1.7,1.5,1.5,1.2]

[1.3,1.4,2.4,1.0,1.3,1.4,1.3,1.3,1.4,1.4]

[1.8,1.7,2.9,1.2,1.6,1.7,1.8,1.7,1.5,1.8]

0.940,0.955,0.

981

Heart Problem

[1.7,1.7,2.8,1.2,1.5,1.6,1.8,1.7,1.7,1.7]

[1.5,1.2,2.4,0.8,1.5,1.6,1.7,1.5,1.5,1.2]

[1.3,1.4,2.4,1.0,1.3,1.4,1.3,1.3,1.4,1.4]

[1.8,1.7,2.9,1.2,1.6,1.7,1.8,1.7,1.5,1.8]

0.940,0.955,0.

981

Heart Problem

[1.2,1.2,1.6,1.6,2.0,2.3,2.0,1.4,1.7,1.2]

[1.5,1.2,2.4,0.8,1.5,1.6,1.7,1.5,1.5,1.2]

[1.3,1.4,2.4,1.0,1.3,1.4,1.3,1.3,1.4,1.4]

[1.8,1.7,2.9,1.2,1.6,1.7,1.8,1.7,1.5,1.8]

0.940,0.955,0.

981[1.4,1.4,2.2,2.4,2.4,1.9,1.4,1.4,1.4,1.3]

[1.5,1.2,2.4,0.8,1.5,1.6,1.7,1.5,1.5,1.2]

[1.3,1.4,2.4,1.0,1.3,1.4,1.3,1.3,1.4,1.4]

[1.8,1.7,2.9,1.2,1.6,1.7,1.8,1.7,1.5,1.8]

0.940,0.955,0.

981[1.1,1.2,2.4,1.0,1.3,1.4,1.3,1.3,1.2,1.4]

[1.5,1.2,2.4,0.8,1.5,1.6,1.7,1.5,1.5,1.2]

[1.3,1.4,2.4,1.0,1.3,1.4,1.3,1.3,1.4,1.4]

[1.8,1.7,2.9,1.2,1.6,1.7,1.8,1.7,1.5,1.8]

0.940,0.955,0.

981[1.4,1.4,2.3,0.9,1.3,1.4,1.3,1.3,1.4,1.2]

[1.5,1.2,2.4,0.8,1.5,1.6,1.7,1.5,1.5,1.2]

[1.3,1.4,2.4,1.0,1.3,1.4,1.3,1.3,1.4,1.4]

[1.8,1.7,2.9,1.2,1.6,1.7,1.8,1.7,1.5,1.8]

0.940,0.955,0.

981[1.6,1.8,2.8,1.1,1.6,1.7,1.8,1.7,1.6,1.6]

[1.5,1.2,2.4,0.8,1.5,1.6,1.7,1.5,1.5,1.2]

[1.3,1.4,2.4,1.0,1.3,1.4,1.3,1.3,1.4,1.4]

[1.8,1.7,2.9,1.2,1.6,1.7,1.8,1.7,1.5,1.8]

0.940,0.955,0.

981

Heart Problem

not been confirmed to suffer from Insomnia. The error value of this test is between 0.1% to 1.8%.

Figure 9. EMG Graph Analysis in web service

Table 4. EMG Analysis using Artificial Neural Network

Furthermore, the last process is to classify Insomnia. Insomnia classification derives

from two combined data between the predicted output from ECG and EMG data compared with actual output from medical data. If the results obtained from patients approach one of the values of the actual output with the smallest error value, then the conclusions of the measured patient data can be included in the classification according to the specified conditions. The process in classification shown in Figure 11.

Table 5 is the result of testing ten test data from the device used in this study, namely the Electrocardiography sensor, which compares with medical training data. Actual output is the result of the training from the expected output. The predicted output of the device used in this study is compared with the actual output to find the closest data with the smallest error in one of the target values. The range of actual output values of 50 to 65 is insomnia sufferers while in the range of 35 to 45 is insomnia sufferers. The results obtained that there are four out of ten test

NoMedical Device Data

TrainTraining Result

ErrorRelax Relax Tense

1 350 0,91 0.1% Relax Muscle

2 350 0,929 1.0% Relax Muscle

3 350 0,92 1.0% Relax Muscle

4 350 0,98 0.6% Tense Muscle

5 350 0,993 0,7% Tense Muscle

6 350 0,908 1.2% Relax Muscle

7 350 0,922 0.3% Relax Muscle

8 350 0,934 0.5% Relax Muscle

9 350 0,902 1.8% Relax Muscle

10 350 0,928 1.1% Relax Muscle

Obtained Data

Classification ResultActual

OutputPredicted

Output[1.1,1.3,1.9,2.4,2.4,2.3,1.9,1.3,1.3,1.7]

[1.8,1.7,2.1,2.4,2.4,2.0,1.8,1.7,1.8,1.7]

[1.3,1.4,2.2,2.4,2.4,1.9,1.3,1.3,1.3,1.3]

[1.8,1.7,1.8,2.7,2.8,2.5,1.8,1.7,1.8,1.7]

0.938,0.919,0.983

[1.8,1.8,2.0,2.6,2.3,2.2,1.8,1.7,1.8,1.7]

[1.8,1.7,2.1,2.4,2.4,2.0,1.8,1.7,1.8,1.7]

[1.3,1.4,2.2,2.4,2.4,1.9,1.3,1.3,1.3,1.3]

[1.8,1.7,1.8,2.7,2.8,2.5,1.8,1.7,1.8,1.7]

0.938,0.919,0.983

[1.4,1.4,2.2,2.3,2.4,1.7,1.3,1.3,1.3,1.3]

[1.8,1.7,2.1,2.4,2.4,2.0,1.8,1.7,1.8,1.7]

[1.3,1.4,2.2,2.4,2.4,1.9,1.3,1.3,1.3,1.3]

[1.8,1.7,1.8,2.7,2.8,2.5,1.8,1.7,1.8,1.7]

0.938,0.919,0.983

[1.8,1.7,1.8,2.7,2.8,2.5,1.8,1.7,1.8,1.7]

[1.8,1.7,2.1,2.4,2.4,2.0,1.8,1.7,1.8,1.7]

[1.3,1.4,2.2,2.4,2.4,1.9,1.3,1.3,1.3,1.3]

[1.8,1.7,1.8,2.7,2.8,2.5,1.8,1.7,1.8,1.7]

0.938,0.919,0.983

[1.9,1.7,2.0,2.7,2.8,2.5,1.9,1.7,1.8,1.7]

[1.8,1.7,2.1,2.4,2.4,2.0,1.8,1.7,1.8,1.7]

[1.3,1.4,2.2,2.4,2.4,1.9,1.3,1.3,1.3,1.3]

[1.8,1.7,1.8,2.7,2.8,2.5,1.8,1.7,1.8,1.7]

0.938,0.919,0.983

[1.4,1.4,1.6,1.8,2.0,2.4,2.0,1.4,1.7,1.2]

[1.8,1.7,2.1,2.4,2.4,2.0,1.8,1.7,1.8,1.7]

[1.3,1.4,2.2,2.4,2.4,1.9,1.3,1.3,1.3,1.3]

[1.8,1.7,1.8,2.7,2.8,2.5,1.8,1.7,1.8,1.7]

0.938,0.919,0.983

[1.3,1.4,2.2,2.4,2.4,1.9,1.4,1.5,1.3,1.4]

[1.8,1.7,2.1,2.4,2.4,2.0,1.8,1.7,1.8,1.7]

[1.3,1.4,2.2,2.4,2.4,1.9,1.3,1.3,1.3,1.3]

[1.8,1.7,1.8,2.7,2.8,2.5,1.8,1.7,1.8,1.7]

0.938,0.919,0.983

[1.7,1.8,2.0,2.2,2.4,2.3,1.8,1.8,1.7,1.7]

[1.8,1.7,2.1,2.4,2.4,2.0,1.8,1.7,1.8,1.7]

[1.3,1.4,2.2,2.4,2.4,1.9,1.3,1.3,1.3,1.3]

[1.8,1.7,1.8,2.7,2.8,2.5,1.8,1.7,1.8,1.7]

0.938,0.919,0.983

[1.0,1.1,1.8,2.2,2.3,2.0,1.7,1.3,1.3,1.3]

[1.8,1.7,2.1,2.4,2.4,2.0,1.8,1.7,1.8,1.7]

[1.3,1.4,2.2,2.4,2.4,1.9,1.3,1.3,1.3,1.3]

[1.8,1.7,1.8,2.7,2.8,2.5,1.8,1.7,1.8,1.7]

0.938,0.919,0.983

[1.6,1.8,1.6,1.8,2.0,2.4,2.0,1.8,1.7,1.7]

[1.8,1.7,2.1,2.4,2.4,2.0,1.8,1.7,1.8,1.7]

[1.3,1.4,2.2,2.4,2.4,1.9,1.3,1.3,1.3,1.3]

[1.8,1.7,1.8,2.7,2.8,2.5,1.8,1.7,1.8,1.7]

0.938,0.919,0.983

data classified as suffering from insomnia sleep disorders. Errors of this classification that occur between 0.2% to 2.7%.

Figure 11. Insomnia classification’ process using Artificial Neural Network

Table 5. Insomnia Classification using Artificial Neural Network

One of the results of insomnia classification using Artificial Neural Networks, shown in

Figure 12. These results appear in a web-based form with the hope that these results can reach patients in remote locations and doctors in large cities can see data from patients in order to be able to right treatment.

No TrainTraining Result

ErrorActual Output

1 350 [65], [60], [55], [50], [45], [40], [35] 63,2 2.7% non insomnia

2 350 [65], [60], [55], [50], [45], [40], [35] 60,9 1.5% non insomnia

3 350 [65], [60], [55], [50], [45], [40], [35] 44,1 2.0%

4 350 [65], [60], [55], [50], [45], [40], [35] 39,8 0.5%

5 350 [65], [60], [55], [50], [45], [40], [35] 40,4 1.0%

6 350 [65], [60], [55], [50], [45], [40], [35] 54,2 1.5% non insomnia

7 350 [65], [60], [55], [50], [45], [40], [35] 59,1 1.5%

8 350 [65], [60], [55], [50], [45], [40], [35] 58,9 1.9% non insomnia

9 350 [65], [60], [55], [50], [45], [40], [35] 60,7 1.1% non insomnia

10 350 [65], [60], [55], [50], [45], [40], [35] 40,1 0.2%

Classification ResultPredicted

Output

Person with Insomnia

Person with Insomnia

Person with Insomnia

Person with Insomnia

Person with Insomnia

Figure 12. Classification result in web service

4. Conclusion

Based on the results obtained in this study, we can conclude the following. Signal strength is very influential in sending data sent from the microcontroller to the server. Where in this study, the results obtained with the signal strength of -81 dBm to -97dBm to get 100% accuracy of data transmission. While testing at -108 dBm gets an accuracy above 97%. From the analysis of patient data obtained, it takes about 350 training data, which produces the smallest error. Prediction results from 10 EMG sensor test data, there are 2 out of 10 data that suffer from tense muscles. The resulting accuracy level is 100%, with the most significant error value of 1.8%, and the smallest error is 0.1%. Prediction results from 10 ECG sensor test data, there are 4 out of 10 data that suffer from heart problems. The resulting accuracy level is 100%, with the most significant error value of 1.2%, and the smallest error is 0.4%. The accuracy of classification of people with Insomnia with Neural Network reaches 100%. There are 4 out of 10 data that are predicted to suffer from Insomnia. The smallest error value is 0.2%, and the most significant error value is 2.7%. With these results, the diagnosis of insomnia using our system in this study can provide a solution to make a remote Insomnia diagnosis that is more cost effective and less time-consuming. For further studies, it is recommended to use other biomedical sensors that are more complete and more equal than the gold standard for testing insomnia such as adding medical sensors EEG, EOG, and other medical sensors that can equal specification with Polysomnography device. References [1] Spiegel K, Knutson K, Leproult R, Tasali E, Cauter E Van. Sleep loss: a novel risk factor for

insulin resistance and Type 2 diabetes. J Appl Physiol. 2005; 99(5): 2008–2019. [2] Brooks D, Horner RL, Kozar LF, Render-Teixeira CL, Phillipson EA. Obstructive sleep

apnea as a cause of systemic hypertension Evidence from a canine model. J Clin Invest. 1997; 99(1): 106–109.

[3] Liu X, Liu L. Sleep habits and insomnia in a sample of elderly persons in China. Sleep. 2005; 28(12): 1579–1587.

[4] Liu X, Liu L, Owens JA, Kaplan DL. Sleep patterns and sleep problems among schoolchildren in the United States and China. Pediatrics. 2005; 115(Supplement 1): 241–249.

[5] Xiang Y-T, Ma X, Cai Z-J, Li S-R, Xiang Y-Q, Guo H-L, et al. The prevalence of insomnia, its sociodemographic and clinical correlates, and treatment in rural and urban regions of Beijing, China: a general population-based survey. Sleep. 2008; 31(12): 1655–1662.

[6] Asghari A, Farhadi M, Kamrava SK, Ghalehbaghi B. Subjective sleep quality in urban population. Arch Iran Med. 2012; 15(2): 95.

[7] Zailinawati A-H, Mazza D, Teng CL. Prevalence of insomnia and its impact on daily function amongst Malaysian primary care patients. Asia Pac Fam Med. 2012; 11(1): 9.

[8] Zailinawati AH, Ariff KM, Nurjahan MI, Teng CL. Epidemiology of insomnia in Malaysian adults: a community-based survey in 4 urban areas. Asia Pacific J Public Heal. 2008; 20(3): 224–233.

[9] Littner M, Hirshkowitz M, Kramer M, Kapen S, Anderson WM, Bailey D, et al. Practice Parameters for Using Polysomnography to Evaluate Insomnia: An Update. Sleep. 2003; 6(6): 754–760.

[10] Marino M, Li Y, Rueschman MN, Winkelman JW, Ellenbogen JM, Solet JM, et al. Measuring Sleep: Accuracy, Sensitivity, and Specificity of Wrist Actigraphy Compared to Polysomnography. Sleep. 2013; 36(11): 1747–1755.

[11] Sartori DE, Tufik S, Bittencourt LRA, Santos-Silva R, Alonso FFFD, Truksinas V, et al. Validation of a Portable Monitoring System for the Diagnosis of Obstructive Sleep Apnea Syndrome. Sleep. 2009; 32(5): 629–636.

[12] Flemons WW, Douglas NJ, Kuna ST, Rodenstein DO, Wheatley J. Access to Diagnosis and Treatment of Patients with Suspected Sleep Apnea. Am J Respir Crit Care Med. 2004; 169(6): 668–672.

[13] He K, Kim R, Kapur VK. Home- vs. Laboratory-Based Management Of OSA: An Economic Review. Curr Sleep Med Reports. 2016; 2(2): 107–113.

[14] Kundel V, Shah N. Impact of Portable Sleep Testing. Sleep Med Clin. 2017; 12(1): 137–147.

[15] Azman N, Satria MH, Mukaram MZ, Ghani MKA. Development of Embedded System for Centralized Insomnia System. 2018 5th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI). Malang. 2018: 451–455.

[16] Lin C-T, Prasad M, Chung C-H, Puthal D, El-Sayed H, S S, et al. IoT-based Wireless Polysomnography Intelligent System for Sleep Monitoring. IEEE Access. 2018; 6: 405–414.

[17] Alelyani S, Ibrahim A. Internet-of-things in telemedicine for diabetes management. 2018 15th learning and technology conference (L&T). Jeddah. 2018: 20–23.

[18] Borulkar N, Pandey P, Davda C, Chettiar J. Drowsiness Detection and Monitoring the Sleeping Pattern using Brainwaves Technology and IoT. 2018 2nd International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud). Tamil Nadu. 2018: 703–706.

[19] Patti E, Donatelli M, Macii E, Acquaviva A. IoT Software Infrastructure for Remote Monitoring of Patients with Chronic Metabolic Disorders. 2018 IEEE 6th International Conference on Future Internet of Things and Cloud (FiCloud). Barcelona. 2018: 311–317.

[20] Jiang Y, Qin Y, Kim I, Wang Y. Towards an IoT-based upper limb rehabilitation assessment system. 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Jeju Island. 2017: 2414–2417.

[21] Kirtana RN, Lokeswari Y V. An IoT based remote HRV monitoring system for hypertensive patients. 2017 International Conference on Computer, Communication and Signal Processing (ICCCSP). Tamil Nadu. 2017: 1–6.

[22] Ling THY, Wong LJ. Sensors for Everyday Life. Springer. 1. Sidney: Springer International Publishing. 2017: 103–20.

[23] Espressif. ESP32 Series Datasheet. Espressif Systems. 2019. Available from: https://www.espressif.com/sites/default/files/documentation/esp32_datasheet_en.pdf.

[24] Guerreiro J, Martins R, Plácido da Silva H, Lourenco A, Fred A. BITalino: A Multimodal Platform for Physiological Computing. 10th International Conference on Informatics in Control, Automation and Robotics. Reykjavik. 2013; 1: 500–506.

[25] Plácido da Silva H, Guerreiro J, Lourenco A, Fred A, Martins R. BITalino: A Novel Hardware Framework for Physiological Computing. International Conference on Physiological Computing Systems. Lisbon. 2014: .246–253.