CONTENTS
WELCOME MESSAGE FROM GENERAL CHAIR 2
ABOUT IPB UNIVERSITY 3
ABOUT DEPARTMENT OF COMPUTER SCIENCE, IPB UNIVERSITY 5
COMMITTEES 6
Steering Committee 6
Conference Committee 6
Technical Program Committee 7
Reviewers 7
CONFERENCE SCHEDULE 10
VIRTUAL CONFERENCE GUIDELINES 12
General Information 12
For Paper Presenter 13
For Attendees 15
For Keynote/Invited Speakers 16
Emergency Contacts and Assistance 17
INVITED SPEAKERS 18
TECHNICAL PARALLEL SESSION SCHEDULE 20
Appendix A. Using Webex in Virtual Conference 25
WELCOME MESSAGE FROM GENERAL CHAIR
On behalf of the Organizing and Program Committee, it is my great pleasure to welcome you all to the 1
stInternational Conference in Computer Science and Its Application in Agriculture (ICOSICA) 2020 on 17
thSeptember 2020. The 1
stICOSICA 2020 is organized by the Department of Computer Science, IPB University, in association with the IEEE Indonesia Section. This is the first conference that brings together all the researchers in computer science and its applications in agriculture to be held by IPB University internationally. In this conference, the researchers share and present the latest research, issues, and recent developments in the application of computer science in agriculture.
The technical program of the conference consists of five keynotes and four tracks. The tracks are (1) Software Engineering and Information Science, (2) Computational Intelligence and Optimization, (3) Computer Systems and Networks, and (4) Innovative Computer Technology in Veterinary, Fishery and Agromaritime, Animal Science, Forestry, and Agricultural Engineering. The conference received 101 papers from 10 countries, out of which 49 papers have been accepted (acceptance rate of 48,51%). All papers have undergone a meticulous peer-review process based on their significance, novelty, and technical quality. Every paper was reviewed by at least three independent experts, with many experiencing even more reviews. The accepted papers will be proposed to be published in IEEE Xplore and indexed in Scopus.
Due to the Corona Virus 2019 Outbreak, we decided to deliver the conference virtually.
The organizing committee had been working relentlessly to create a virtual conference that will be worthy and engaging for both presenters and attendees. The full conference format is a mix of pre-recorded and asynchronous engagement, and live engagement through discussion and in-person video calls.
I would like to especially thank the Organizing Committee, without the enthusiastic and hard work of a number of colleagues, the 1
stICOSICA 2020 would not have been realized.
I wish to express my sincere appreciation to the Technical Program Committee members and the reviewers for their commitment and contribution. I would also like to thank the Keynote and Invited Speakers for contributing to this indispensable part of the program.
We also thank the IEEE Indonesia Section for their great support and mentorship as technical sponsor of the conference. Last, but certainly not least, my thanks go to all the authors who had submitted papers and all the attendees. I hope that you will find the program is encouraging and a source of brilliant ideas for future research. I thank you for virtually attending the 1
stICOSICA 2020. I extend my warmest congratulations and wish the 1
stICOSICA 2020 to be a great success.
Irman Hermadi, PhD | General Chair of ICOSICA 2020
ABOUT IPB UNIVERSITY
IPB has a long history of struggle. Started from the University of Indonesia in Bogor, the university became the forerunner of the first agricultural higher education in the country in 1940. Furthermore, based on the Decree of the Minister of Higher Education and Science No. 91/1963 and ratified by Presidential Decree of the Republic of Indonesia No. 279/1965 on 1 September 1963, IPB secede from its parent university to become the Agricultural Institute in Bogor.At this time IPB is the only college in Indonesia that bears the name of "institute" same level as university that given full trust by the government to pursue and develop tropical agricultural sciences in the country.
Since 53 years ago, IPB has grown and developed into a college that has a good reputation and plays an important role in the national development and higher education in Indonesia. IPB’s growth and development has gone through three periods of time: the colonial era, the period of struggle for independence, and the period after the proclamation of independence. In the three periods there was a consistent thread that consists of the striving, nationality, patriotism and leadership of the predecessors. These are the values that have always been held firmly from time to time.
The tradition of community service, which is an integral part of higher education’s Tridharma (three main responsibilities), was also born from this campus. The action research that began in 1963 in Karawang and in cooperation with various universities and other institutions has led the Indonesia nation to significantly increase rice production and even achieve self-sufficiency in rice.
Meanwhile, IPB’s strength in the establishment of general competence turns out to have led the students to become graduates who are ready to play a role in many areas of life. The values that can be learned from a wide range of teaching and learning in IPB are familiarity of managing complexity and uncertainty, excellence in numerical and scalable solutions, always thinking of systems and caring for the environment, always thinking and acting systemically, complying to the regulations, and always caring for farmers as well as readily helping others.
Now at the age of 53 years, IPB has nine faculties: the Faculty of Agriculture, Faculty
of Veterinary Medicine, Faculty of Fisheries and Marine Sciences, Faculty of Animal
Science, Faculty of Forestry, Faculty of Agriculture, Faculty of Mathematics and Natural
Sciences, Faculty of Economics and Management, Faculty of Human Ecology, Business School, Graduate School and Vocational School.
IPB currently has 36 departments, 21 Study Centers, 159 undergraduate and graduate programs and 18 diploma (vocational) educational programs. And until January 2016, IPB has graduated 133,778 students.
IPB University Main Campus, Bogor, Indonesia.
Contacts
Jl. Raya Dramaga
Kampus IPB Dramaga Bogor 16680 West Java, Indonesia +62 251 8622642
[email protected] ipb.ac.id
ABOUT DEPARTMENT OF COMPUTER SCIENCE, IPB UNIVERSITY
The Computer Science Study Program in FMIPA IPB was opened in the 1993/1994 academic year. Then, on September 17, 1998 the Computer Science Study Program was established as the Department of Computer Science under the Faculty of Mathematics and Natural Sciences IPB through IPB Rector's Decree No. 095/K.13/HK/OT/1998. The mandate given to the Department of Computer Science is the development of computer science and its application in the field of information and communication technology (ICT). In September 2004, the office of the Department of Computer Science FMIPA IPB which was previously located on the IPB Baranangsiang Campus was moved to the IPB Darmaga Campus. Currently, the department consists of bachelor, master, and doctoral programs in computer science.
Contacts
Departemen Ilmu Komputer
Jl Meranti Wing 20 Level 5 Kampus IPB Darmaga 16680 +62 251-8625584
[email protected] cs.ipb.ac.id
COMMITTEES
Steering Committee
Prof. Dr. Ir. Agus Buono, M.Si., M.Kom, IPB University, Indonesia.
Dr. Azwirman Gusrialdi, Tampere University of Technology, Finlandia.
Conference Committee
General ChairDr. Irman Hermadi, M.S., IPB University, Indonesia.
General Co-Chair
Auzi Asfarian, S.Komp., M.Kom., IPB University, Indonesia.
Financial and Sponsorship Chair
Dr. Karlisa Priandana, M.Eng., IPB University, Indonesia.
Meuthia Rachmaniah, M.Sc., IPB University, Indonesia.
Lailan S Hasibuan, M.Kom., IPB University, Indonesia.
Wulandari, M.Eng., IPB University, Indonesia
Program Chair
Dr. Sony H Wijaya, M.Kom., IPB University, Indonesia.
Wulandari, M.Eng., IPB University, Indonesia.
Publication Chair
Dr. Yani Nurhadryani, M.T., IPB University, Indonesia.
Publicity and Public Relationship Chair Firman Ardiansyah, M.Si., IPB University, Indonesia.
Auriza R Akbar, M.Kom., IPB University, Indonesia.
Local Committee
Dean A Ramadhan, M.Kom., IPB University, Indonesia.
Irvan Y Ramdhan, IPB University, Indonesia.
Technical Program Committee
Technical Program ChairsDr. Medria K Hardienata, IPB University, Indonesia.
TPC Member
Dr. Mohd Noor Bin Derahman, Universiti Putra Malaysia, Malaysia.
Dr. Yani Nurhadryani, IPB University, Indonesia
Dr.Eng Wisnu Ananta Kusuma, IPB University, Indonesia.
Dr. Hendra Rahmawan, IPB University, Indonesia.
Dr. Karlisa Priandana, M.Eng., IPB University, Indonesia.
Reviewers
A Afiahayati, Gadjah Mada University (UGM), Indonesia Abdullah bin Muhammed, Universiti Putra Malaysia, Malaysia Achmad Solichin, Budi Luhur University, Indonesia
Adzkia Salima, Wageningen University, Netherlands Afia Hayati, Gadjah Mada University (UGM), Indonesia Agus Buono, IPB University, Indonesia
Agustami Sitorus, Indonesian Institute of Sciences (LIPI), Indonesia Ahmad Ridha, IPB University, Indonesia
Albert Yosua, Tokyo Institute of Technology, Japan
Andrew Schauf, Nanyang Technological University, Singapore Annisa Annisa, IPB University, Indonesia
Aries Fitriawan, University of Indonesia, Indonesia
Arli Aditya Parikesit, Indonesia International Institute for Life Sciences (i3L), Indonesia Asem Kasem, Universiti Teknologi Brunei, Brunei
Asif Zaman, University of Rajshahi , Bangladesh Auriza Rahmad Akbar, IPB University, Indonesia Auzi Asfarian, IPB University, Indonesia
Ayu Purwarianti, Bandung Institute of Technology (ITB), Indonesia Bayu Erfianto, Telkom University, Indonesia
Chastine Fatichah, Sepuluh Nopember Institute of Technology (ITS), Indonesia Dean Apriana Ramadhan, IPB University, Indonesia
Deshinta Arrova Dewi, INTI International University, Malaysia
Didik Utomo, Nagoya University, Japan
Dilini Samarasinghe Widana Arachchige, University of New South Wales (ADFA), Australia
Endah Ratna Arumi, Muhammadiyah University, Magelang, Indonesia
Erandi Lakshika, University of New South Wales, Canberra (UNSW Canberra)., Australia Fahren Bukhari, IPB University, Indonesia
Fatimah Abdul Razak, Universiti Kebangsaan Malaysia, Malaysia
Ferry Astika Saputra, Electronic Engineering Polytechnic Institute of Surabaya (PENS), Indonesia
Firman Ardiansyah, IPB University, Indonesia Firman Sasongko, Rolls-Royce@NTU, Singapore
Gede Indrawan, Ganesha University of Education, Indonesia Hari Agung Adrianto, IPB University, United Kingdom Harry Budi Santoso, University of Indonesia, Indonesia Hendra Rahmawan, IPB University, Indonesia
Heru Sukoco, IPB University, Indonesia
Hjh Nor Zainah binti Hj Siau, Universiti Teknologi Brunei, Brunei Ibrahim Umar, Institute of Marine Research, Norway
Imas Sukaesih Sitanggang, IPB University, Indonesia Ionia Veritawati, Pancasila University, Indonesia Irman Hermadi, IPB University, Indonesia
Jaziar Radianti, University of Agder, Centre for Integrated Emergency Management, Norway
Julio Adisantoso, IPB University, Indonesia Karlisa Priandana, IPB University, Indonesia
Khaironi Yatim bin Sharif, Universiti Putra Malaysia, Malaysia Lailan Sahrina Hasibuan, IPB University, Indonesia
Leon A. Abdillah, LAA, Bina Darma University, Indonesia Lukmanul Hakim Zaini, IPB University, Indonesia
Mahardhika Pratama, Nanyang Technological University, Singapore Mahirah binti Jahari, Universiti Putra Malaysia, Malaysia
Maria Susan Anggreainy, IPB University, Indonesia Marimin Marimin, IPB University, Indonesia Markus Santoso, University of Florida, USA
Mayanda Mega Santoni, Universitas Pembangunan Nasional Veteran (UPNV) Jakarta,
Indonesia
Md. Altaf-Ul-Amin, Nara Institute of Science and Technology, Japan Medria Kusuma Dewi Hardhienata, IPB University, Indonesia Melinda Melinda, Syiah Kuala University, Indonesia
Meuthia Rachmaniah, IPB University, Indonesia Mochamad Asri, Facebook, USA
Mohammad Saiful bin Haji Omar, Universiti Teknologi Brunei, Brunei Mohd Helmy Abd Wahab, Universiti Tun Hussein Onn Malaysia, Malaysia Mohd Noor Bin Derahman, University Putra Malaysia, Malaysia
Mohd Taufik bin Abdullah, Universiti Putra Malaysia, Malaysia Muhammad Asyhar Agmalaro, IPB University, Indonesia
Muhammad Fadli Prathama, PLN Institute of Technology (formerly STT-PLN), Indonesia Muhammad Hasannudin Yusa, BIG Indonesia, Indonesia
Muhammad Irwan Padli Nasution, State Islamic Univeristy, Sumatera Utara, Indonesia Muhammad Rasyid Aqmar, Rakunten Institute of Technology, Japan
Muharfiza Muharfiza, Indonesian Polytechnic of Agricultural Engineering, Indonesia Muqtafi Akhmad, Tokyo Institute of Technology, Japan
Mushthofa Mushthofa, IPB University, Indonesia
Mutsawashe Gahadza, Econet Wireless Zimbabwe, Zimbabwe Noor Akhmad Setiawan, Gadjah Mada University (UGM), Indonesia Noor Cholis Basjaruddin, Bandung State Polytechnic, Indonesia Novanto Yudistira, Brawijaya University, Indonesia
Nur Afny Catur Andryani, Tanri Abeng University, Indonesia Nur Hasanah, IPB University, Indonesia
Nurulhuda Khairudin, Universiti Putra Malaysia, Malaysia Riko Arlando Saragih, Maranatha Christian University, Indonesia Rina Trisminingsih, IPB University, Indonesia
Rudolf Jason, Tokyo Institute of Technology, Japan S H Shah Newaz, Universiti Teknologi Brunei, Brunei Sabita Maharjan, University of Oslo, Norway
Setiawan Hadi, Padjadjaran University, Indonesia Setyanto Tri Wahyudi, IPB University, Indonesia
Shadi Abpeikar, University of New South Wales (ADFA), Australia Shelvie Nidya Neyman, IPB university , Indonesia
Shuo Yang, University of New South Wales (ADFA), Australia
Sony Hartono Wijaya, IPB University, Indonesia Sri Wahjuni, IPB University, Indonesia
Sritrusta Sukaridhoto, Electronic Engineering Polytechnic Institute of Surabaya (PENS), Indonesia
Sunu Wibirama, Gadjah Mada University (UGM), Indonesia Supriyanto Supriyanto, IPB University, Indonesia
Suyanto Suyanto, Telkom University, Indonesia Taufik Djatna, TDJ, IPB University, Indonesia
Temmy Hendrawan, Bandung Institute of Technology (ITB), Indonesia
Tenia Wahyuningrum, Telkom Institute of Technology, Purwokerto, Indonesia Teny Handhayani, University of York, USA
Terje Gjosaeter, Oslomet University, Norway
Teuku Muhammad Roffi, Pertamina University, Indonesia Toto Haryanto, IPB University, Indonesia
Triwiyanto Triwiyanto, Health Polytechnic Ministry of Health Surabaya, Department of Electromedical Engineering, Indonesia
Tutun Juhana, Bandung Institute of Technology (ITB), Indonesia Uky Yudatama, Muhammadiyah University, Magelang, Indonesia Vektor Dewanto, University of Queensland, Australia
Wida Susanty Haji Suhaili, Universiti Teknologi Brunei, Brunei Widodo Widodo, Jakarta State University (UNJ), Indonesia Wisnu Ananta Kusuma, IPB University, Indonesia
Wiwin Suwarningsih, Indonesian Institute of Sciences (LIPI), Indonesia Wulandari Wulandari, IPB University, Indonesia
Yani Nurhadryani, IPB University, Indonesia Yeni Herdiyeni, IPB University, Indonesia Yus Sholva, Tanjungpura University, Indonesia
CONFERENCE SCHEDULE
All time in the program schedule is in Western Indonesia Time / Waktu Indonesia Barat (WIB; GMT+7). Please pay attention and adjust it to your local time. Current time in WIB can be found on http://time.bmkg.go.id.
Time Agenda
(GMT +7)
07.30 – 08.15 Registration
08.15 – 08.45 Opening Remarks (@ 10 mins) Prof. Dr. Ir. Agus Buono, M.Si., M.Kom
Chair, Dept. of Computer Science, IPB University Dr. Ir. Sri Nurdiati, M. Sc
Dean, Faculty of Mathematics and Natural Sciences, IPB University Prof. Dr. Arif Satria SP, M.Si
Rector, IPB University 08.45 – 09.15 Keynote Speech
Dr. Fadjry Djufry
(Head of Indonesian Agency for Agricultural Research and Development) 09.15 – 09.25 Break
09.25 - 10.05 Invited Speakers (30 mins presentation, 10 mins QA)
Professor Dr. Rusli Bin Haji Abdullah, University Putra Malaysia, Malaysia 10.05 - 10.45 Invited Speakers (30 mins presentation, 10 mins QA)
Prof. Naoshi Kondo, Kyoto University, Japan
10.45 - 11.25 Invited Speakers (30 mins presentation, 10 mins QA)
Dr Wida Susanty binti Haji Suhaili, Universiti Teknologi Brunei, Brunei Darussalam
11.25 - 12.05 Invited Speakers (30 mins presentation, 10 mins QA) Dr Wisnu Ananta Kusuma, IPB University, Indonesia
12.05 - 13.00 Break
13.00 - 15.20 Parallel Session 15.20 - 16.00 Break
16.00 - 16.30 Closing
INVITED SPEAKERS
Prof. Naoshi Kondo
Prof. Naoshi Kondo is currently a professor, Graduate School of Agriculture, Kyoto University and is working on automation and sensing systems in agriculture, livestock and aquaculture aiming precision farming. He graduated from undergraduate and graduate schools (Department of Agricultural Engineering), Kyoto University in 1982 and 1984 respectively, and was engaged at Okayama University in 1985 as an assistant professor for 15 years.
He has received many academic awards for his works from many kinds of societies: JSAM, JSME, SHITA, ASAE, SAS, AABEA, JSABE, JAICABE, MAFF, JATAFF, AJASS. He was given the Japan Prize of Agricultural Science, which is one of the oldest and top awards in agricultural fields from AJASS and the Yomiuri Shimbun on April 5, 2017. His achievement was “Sensing System Based Bio-Production Intelligent Robots.”
Prof. Rusli Abdullah
Prof. Rusli Abdullah is currently Professor of Knowledge Management at Software Engineering and Information System Department, as well as the Dean of Faculty of Computer Science and Information Technology, Universiti Putra Malaysia (UPM).
Specialized in Knowledge Management, he has completed his PhD in Computer Science at Universiti Teknologi Malaysia (UTM), Johor, Malaysia in 2006. Starting his career as a lecturer in 2006 after serving as System Analyst for 8 years at UPM. He has published over 14 books and over 100 journal papers, conference publications and other academic research publications. He has also received numerous awards and recognitions throughout his career that includes Silver Medal for University Research Invention in 2008 and 2009, Gold Medal for University Research Invention 2005, Silver Medal for Invention of Technology and Exposition I-TEX (2009), Silver Medal for Malaysian Research Invention and Exposition – MTE (2010, 2012
& 2014) and Certification of University Excellent Services of Lecturer Service for
many years since 1999.
Dr. Wida Susanty Haji Suhaili
Dr. Wida Susanty Haji Suhaili is the Assistant Professor at the School of Computing and Informatics, the Universiti Teknologi Brunei (UTB). She started her career in UTB on 2nd November 2004 upon completion of her Masters and later completed her PhD in 2015. Within the university, she is the project coordinator for the School of Computing and Informatics where she foresees all the students’ projects from the Computing group, Final year and Master research. She is currently the thrust’s lead for Digital and Creativity research thrust in the University.
Her works revolves around the concept of research, development and deployment where she puts research beyond development towards deployment in an actual setting. She has focused on SMART Initiative project involving Internet of Things and has started working on peatland projects since 2016. She has received support from various stakeholders from government agencies and industries and is an active member of Brunei Shell Joint Venture, Biodiversity Action Plan (BAP). She also focused on the adoption of Science, Technology and Innovation in the improvement of paddy plantation in Brunei which then continued as her fellowship engagement to represent Brunei in the ASEAN S&T Fellowship for 2019/2020. Her fellowship is in close collaboration with Department of Agriculture and Agrifood, Ministry of Primary Resources and Tourism, Brunei.
She is the national finalist representing Brunei in the ASEAN-US Science Prize for Women supported by UL and USAID 2020 under the theme of preventive healthcare with her research on the mitigation of forest fire in particular peatland through the use of Internet of Things. With her focus and committed involvement to the aforementioned projects, she has been actively invited as speaker and panelist for conference, forum and symposium locally and regionally where she has taken the opportunity to advocate the use of IoT in the advancement of technology in Brunei towards IR4.0.
Dr. Wisnu Ananta Kusuma
Dr Wisnu Ananta Kusuma is a prominent researcher in the
Department of Computer Science, Faculty of Mathematics and
Natural Sciences, IPB University. He also acts as an executive
secretary of the Tropical Biopharmaca Research Center, IPB
University and works on research related to bioinformatics and
herbal medicine. He is also pioneering two web-based applications
for bioinformatics: ISNIP for Single Nucleotide Polymorphism
Identification and IJAH Analytics a prediction system for the
formula of herbal medicine (Jamu) based on machine learning and
network pharmacology approach. Recently, he also participates as
a part of the team who implement the machine learning technique for virtual screening
on Indonesia herbal compounds as COVID-19 supportive therapy.
TECHNICAL PARALLEL SESSION SCHEDULE
Parallel 1
Software Engineering and Information Science
Time Title and Authors
13.00-13.20 Design of Green ERP System Reverse Logistic Module Based on Odoo in Leather Tanning Industry
Hennry Syahreza Arifin, Ari Yanuar Ridwan, Muhardi Saputra
13.20-13.40 Supply Chain Management Application System for Recording Chili Production and Distribution
Meuthia Rachmaniah
13.40-14.00 Metaphor Design in Localising User Interface for Farmers in Malaysia Using User-Centered Approach
Novia Indriaty Admodisastro
14.00-14.20 Preliminary User Studies on Consumer Perception Towards Blockchain-Based Livestock Traceability Platform in Indonesia: An Implication to Design Auzi Asfarian, Kautsar I Hilmi, Irman Hermadi
14.20-14.40 A Proof-of-Concept of Farmer-to-Consumer Food Traceability on Blockchain for Local Communities
Jiranuwat Jaiyen, Suporn Pongnumkul, Pimwadee Chaovalit 14.40-15.00 Tokocabai Marketplace Application Based on Web Using Extreme
Programming Method Meuthia Rachmaniah
15.00-15.20 Web Service-Based Automata Testing: A Case Study of Online Airline Reservation
Amir Rizaan Abdul Rahiman, Temitope Betty Williams, Izuka Joseph Iheanocho
Parallel 2
Computational Intelligence and Optimization
Time Title and Authors
13.00-13.20 GPUs Utilization of Residual Network Training for Colon Histopathological Images Classification
Toto Haryanto, Heru Suhartanto, Aniati M. Arymurthy, Kusmardi 13.20-13.40 Development of GPU-Accelerated Pre-Processing Chain for LAPAN-A2
Multispectral Imagery
Kamirul Kamirul, Wahyudi Hasbi, A. Hadi Syafrudin
13.40-14.00 Implementation of Breadth-First Search Parallel to Predict Drug-Target Interaction in Plant-Disease Graph
Alvin Reinaldo, Wisnu Ananta Kusuma, Hendra Rahmawan, Yeni Herdiyeni
14.00-14.20 Dynamic Route Optimization for Waste Collection Using Genetic Algorithm Abdullah Alwabli, Ivica N. Kostanic
14.20-14.40 Application of Skyline Query on Route Selection (the Case Study of Bogor City Roadway)
Lilis Gumilang Asri, Annisa Annisa
14.40-15.00 Recommendation System Based on Skyline Query: Current and Future Research
Ruhul Amin, Taufik Djatna, Annisa Annisa, Imas Sukaesih Sitanggang 15.00-15.20 Association of Single Nucleotide Polymorphism and Phenotypes in Type 2
Diabetes Mellitus Using Genetic Algorithm and CatBoost
Hilmi Farhan Ramadhani, Wisnu Ananta Kusuma, Lailan Hasibuan, Rudi Heryanto
Parallel 3
Computational Intelligence and Optimization
Time Title and Authors
13.00-13.20 Enhancing Crops Production Based on Environmental Status Using Machine Learning Techniques
Shiyam Talukder, Habiba Jannat, Sukanta Saha, Katha Sengupta, Muhammad Iqbal Hossain
13.20-13.40 Comparison of Machine Learning Models for Rainfall Forecasting Nazli Mohd Khairudin, Norwati Mustapha, Teh N M Aris, Maslina Zolkepli 13.40-14.00 Implementation of Borda Clustering to Form Zakat Receiving Villages
Clusters Based on Region Potency in Indonesia Dony Rahmad Agung Saputro, Annisa Annisa
14.00-14.20 A Design of Traceability System in Coffee Supply Chain Based on Hierarchical Cluster Analysis Approach
I Gusti Made Teddy Pradana, Taufik Djatna
14.20-14.40 Supply Chain Sustainability Assessment System Based on Supervised Machine Learning Techniques: The Case for Sugarcane Agroindustry Sri Mursidah, Taufik Djatna, Marimin Marimin, Anas Fauzi
14.40-15.00 Artificial Neural Network for Estimation Nutrient Utilization Based on Chemical Composition on Ruminant Animal Feed
Toto Haryanto, Dias Febrisahrozi, Anuraga Jayanegara, Aziz Kustiyo
15.00-15.20 Ensemble Learning for Predictive Maintenance on Wafer Stick Machine Using IoT Sensor Data
Achmad Mujib, Taufik Djatna
Parallel 4
Innovative Computer Technology in Veterinary, Fishery, Animal Science, Forestry, and Agricultural Engineering & Software Engineering and Information Systems
Time Title and Authors
13.00-13.20 IoT-Based Environmental Monitoring System for Brunei Peat Swamp Forest Syazwan Essa, Rafidah Petra, Mohammad Rakib Uddin, Nur Ikram Ilmi and Wida Haji Suhaili
13.20-13.40 VIRTUAL KIOSK: TAMAN HERBA
Muhamad Nazmi Said, Norhalina Senan, Muhammad Fakri Othman, Mohd Helmy Abd Wahab, Mohd Derahman
13.40-14.00 Development of an Aircraft Type Portable Autonomous Drone for Agricultural Applications
Kazi Mahmud Hasan, Wida Haji Suhaili, Md. Shamim Ahsan, S H Shah Newaz 14.00-14.20 Predicting Methane Emission from Paddy Fields with Limited Soil Data by
Artificial Neural Networks
Chusnul Arif, Budi Setiawan, Nur Hasanah
14.20-14.40 Experimental Evaluation of IoT Connectivity Using LoRaWAN for Vending Machine NetworkRatna Mayasari, Renaldi Permana Putra, Aditya Kurniawan, Farhan Fathir Lanang, Ibnu Alinursafa, Budi Syihabuddin
14.40-15.00 The Potential for Implementing a Big Data Analytic-Based Smart Village in Indonesia
Eneng Tita Tosida, Yeni Herdiyeni, Marimin Marimin and Suprehatin Suprehatin
15.00-15.20 Drug-Target Visualization on IJAH Analytics Using Sankey Diagram
Muhammad Fadhil Al-Haaq Ginoga, Rina Trisminingsih, Wisnu Ananta Kusuma
Parallel 5
Computational Intelligence and Optimization
Time Title and Authors
13.00-13.20 Image Processing for Diagnosis Rice Plant Diseases Using the Fuzzy System Anwar Rifai, Deni Mahdiana
13.20-13.40 Chilli Quality Classification Using Deep Learning
Sudianto Sudianto, Anggra Haristu, Yeni Herdiyeni, Medria Hardhienata
13.40-14.00 CNN with Multi Stage Image Data Augmentation Methods for Indonesia Rare and Protected Orchids Classification
Dimas Sony Dewantara, Rachmat Hidayat, Heru Susanto, Aniati M. Arymurthy
14.00-14.20 Detection and Classification of Diseased Mangoes
Akshay Koushik H, Ritanya B Bharadwaj, Ram Prasad E Naik, Ramesh G, Yogesh M J, Sana Habeeb
14.20-14.40 Estimating Crop Water Stress of Sugarcane in Indonesia Using Landsat 8 Restu Triadi, Yeni Herdiyeni, Suria Darma Tarigan
14.40-15.00 Development of Landslide Victim Detection System Using Thermal Imaging and Histogram of Oriented Gradients on E-PUCK2 Robot
Wulandari Wulandari, Muhammad Arrazi, Karlisa Priandana
15.00-15.20 Sentinel-1A Image Classification for Identification of Garlic Plants Using a Decision Tree Algorithm
Risa Intan Komaraasih, Imas Sukaesih Sitanggang, Muhammad Agmalaro
Parallel 6
Computer System and Networks & Software Engineering and Information Systems
Time Title and Authors
13.00-13.20 High Availability Bidirectional Forwarding Detection (BFD): Fast Recovery Mechanism Provide Multi-Circuit Service Provider
Hillman Akhyar Damanik
13.20-13.40 Study and Experiment of Generalized Frequency Division Multiplexing Implementation Using USRP and LabVIEW
Ajib S. Arifin
13.40-14.00 Development of Autonomous UAV Quadcopters Using Pixhawk Controller and Its Flight Data Acquisition
Karlisa Priandana, Muhammad Hazim, Wulandari, Benyamin Kusumoputro 14.00-14.20 An Initial Framework of Dynamic Software Product Line Engineering for
Adaptive Service Robot I Made Murwantara
14.20-14.40 Smart Governance for One-Stop-Shop Services of Bio-Business Licensing in Indonesia: a Literature Review
Muhammad Mahreza Maulana, Arif Suroso, Yani Nurhadryani, Kudang Seminar
14.40-15.00 Design of Smart System for Fruit Packinghouse Management in Supply Chain Ali Khumaidi, Yohanes Purwanto, Heru Sukoco, Sony Hartono Wijaya, Risanto Darmawan
15.00-15.20 Development of Back-End of a Rural Participation Based Knowledge Management System of Smallholder Palm Plantation
Irman Hermadi, Andi Muhammad Chaerul Hafidz, Auzi Asfarian, Yani Nurhadryani, Nadya Farchana Fidaroina
Parallel 7
Computational Intelligence and Optimization
Time Title and Authors
13.00-13.20 Intelligent Spatial Decision Support System Concept in the Potato Agro- Industry Supply Chain
Rindra Yusianto
13.20-13.40 Multi-UAV Coordination for Crop Field Surveillance and Fertilization Leonardi Fabianto, Karlisa Priandana, Medria Hardhienata
13.40-14.00 Implementation of Recursive Least Square for Basic Piano Chords Noise Reduction
Bobby Jonathan, Agus Buono
14.00-14.20 Application of Ant Colony Optimization for the Selection of Multi-UAV Coalition in Agriculture
Vito M. M. O. Ompusunggu, Medria Hardhienata, Karlisa Priandana
14.20-14.40 Temporal Prediction Model for CO and CO2 Pollutants Using Long Short Term Memory
Muhammad Iqbal Shiddiq, Imas Sukaesih Sitanggang, Muhammad Agmalaro 14.40-15.00 Application of Gravitational Search Algorithm on the Modified
Compartmental Absorption and Transit Model for Predicting Oral Drug Absorption
Nurfaizah Nurfaizah, Agus Kartono, Tony Sumaryada
15.00-15.20 Prediction of Therapeutic Usage of Jamu Based on the Composition of Metabolites Using Convolutional Neural Network
Sony Hartono Wijaya, Wafa Azyati, Lailan Hasibuan, Dean Apriana Ramadhan
The Potential for Implementing a Big Data Analytic-based Smart Village in Indonesia
Eneng Tita Tosida Computer Science Dept.
IPB University Bogor, Indonesia [email protected]
Yeni Herdiyeni Computer Science Dept.
IPB University Bogor, Indonesia [email protected] Suprehatin Suprehatin
Agrobusiness Dept.
IPB University Bogor, Indonesia [email protected]
Marimin
Industrial Technology Dept.
IPB University Bogor, Indonesia [email protected]
Abstract— Smart village is one of the solutions to reduce poverty in rural areas. The main objective of this research is to map the potential implementation of the concept of smart villages based on big data analytics in Indonesia. This research was conducted through the elaboration of text mining-based Systematic Literature Review (SLR) with multiple regression analysis of the 2018 Village Potential Data in Indonesia. The contribution of this study is the production of a map describing the potential for implementing smart villages based on big data analytics in Indonesia. SLR cluster analysis produces a dendrogram that maps the basic terminology of smart villages based on big data analytic. Indonesia has quite substantial economic and social capital resources, which has a positive effect on the poor and farmers/fishermen (R2 = 0.9759 and 0.9482) in the villages. This occurs through a mix of regional budget revenue (APBD) and local self-subsistent (Swadaya) funding schemes in the management of agricultural and non-agricultural small businesses in the village. Indonesia also has sufficient capital for managing information and communication technology (ICT) in the village for the development of big data analytic smart villages. There is a relatively strong influence on the poor and farmers/fishermen (R2 = 0.5946 and 0.6006). Therefore, the challenge for future research to develop a smart village model based on big data analytics that is appropriate to the territory of Indonesia. This model needs to be elaborated with diverse factors including economic, social, cultural and smart educational potential as well should include indicators of the potential for data technology available on various media, through the framework of agriculture big data analytic.
Keywords— Big data analytic, Clustering, Multiple regression Smart village, Systematic Literature Review
I. INTRODUCTION
Indonesia is an archipelago and is strengthened by rural areas in which a percentage of agricultural land use more than urban areas. In 2018 the Central Bureau of Statistics (BPS) reported that Indonesia had 74,517 villages. In addition, there are 919 Nagari in West Sumatra, 8,444 subdistricts, and 51 Transmigration Settlement Units (UPT) in Indonesia.
Development disparities in cities and villages still occur in Indonesia. This occurred due to factors influencing, the increasingly massive urbanization process. In part, due to the higher attractiveness of the city compared to the monotonous village. The disparity in village development in Indonesia was addressed in legislation with the issuing of the Village Law No. 6 of 2014. The law places a priority on development starting from in the village and the periphery. This law was reinforced by the issuance of Permendesa No. 6 2020, which gave the Village Budget (APBDesa) the power to prioritize developments in the village.
Government policy support is certainly not capable of increasing development in villages and reducing the disparity between rural and urban areas. One of the reasons is there remains a significant gap in allocating resources. The resource gap in question includes human resources and infrastructure, which are still very low in rural areas when compared to those resources allocated to the city. This condition can be described comprehensively through Indonesian Village Potential Data.
One of the methods that have been investigated by researchers to reduce the disparity between villages and cities is by the implementation of smart villages [1][2].
The concept of smart villages implemented in several countries is based on the smart city development concept. This concept certainly needs to be adjusted to the conditions and potential factors present in these villages. Essential factors that support the success of smart villages in various countries include: resources, technology, infrastructure, and four-parties synergy (academic, business, community, government). Four- parties synergies are crucial to designing, building, implementing, controlling, and maintaining the sustainability of smart village programs [1][2][3]. The development for implementing smart villages is increasing, along with the rapid growth of information and communication technology (ICT). ICT factor that is crucial to the success of smart villages in several countries. ICT support is regulated by Permendesa No. 6 of 2020, because it outlines the strategic areas, to prioritise for rural development in Indonesia. Especially in the era of data disruption, the readiness of ICTs systems provides greater opportunities for the development of smart villages based on big data analytics [4][5][6]. Research shows implementing big data analytics has been successful in climate-smart agriculture (CSA) based village programs [7][8]. CSA programs that have been adopted in the smart village models are mostly used for on-farm processes.
Research on the application of big data analytics in the smart village for the post-harvest process and analysis of the potential of the smart village has not done much. In contrast, the factors of resources, infrastructure, and technology that are presented in Indonesian villages can mostly be portrayed through Village Potential Data published by BPS [9].
Implementation of big data, data analytic, data mining, sensors, virtual reality, augmented reality, 5G technologies are a need for future smart village research that is collaborated as an ICT enrichment strategy [5][6]. This strategy needs to be synergized with a policy framework according to the conditions of local village wisdom.
Therefore, the main challenge for future smart village 2020 International Conference on Computer Science and Its Application in Agriculture (ICOSICA)
research is how to increase the ICT literacy of the villagers, so that the smart village program is optimal. The strategies to increase the ICT literacy of villagers is closely related to citizen science [10][11]. The core of big data analytic that will be implemented in the smart village program must require at least three basic principles of big data (volume, velocity dan variety) [12][13][14].
The big data-based smart village has also been successfully carried out through the provision of electricity and clean water, which is equipped with an IoT-based control system [11][15][16]. This program is able to increase the productivity of villagers. This productivity includes agricultural, entrepreneurial, education, and health activities.
The implementation of smart transportation in the village area has been done by using big data analytic concept [17]. Smart transportation has collaborated with smart tourism, which is claimed as the smart village innovation in Liaoning Province.
Implementation of a big data-based smart village must be adjusted to the basic needs of the villagers. The development of the big data-based smart village in Indonesia has a wide variety of opportunities. This is influenced by the condition of infrastructure, policies, and institutions of the economic, social, cultural, and also political value in each village. These conditions can be represented by secondary data through Village Potential Data Indonesia.
Therefore, the main objective of this research is to analyze the potential of implementing big data analytics-based smart villages in Indonesia. The analysis of the smart village's potential was carried out using the stages of Systematic Literature Review (SLR) and integrated to multiple regression. In this paper, we report an analysis of smart villages based on big data analytic and the 2018 Village Potential Data in Indonesia. Our smart village SLR's is integrated with descriptive statistical analysis and clustering of smart village research and citizen science. Using descriptive multiple regression analysis, we report the significant findings from the SLR about smart villages based on 2018 Village Potential Data.
II. METHOD
This research was carried out according to the stages of the SLR and multiple regression method, as shown in Fig. 1.
The SLR process was carried out with the NVivo 12 Plus tools and this process also refer to [18]. The use of 44 papers related to the smart village and 33 papers related to citizen science also refer to [18]. We analyzed the hierarchy of attributes and a hierarchy of the research domain [19] related to the smart village and citizen science.
The research attributes hierarchy that is related to the smart village and citizen science will produce dendogram structure. This dendogram will map the density of smart village research that is integrated into citizen science research. The map constructed by hierarchical form included year publication, Sustainable Development Goals (SDGs) area, method and technology. This hierarchy will produce the basic terminology of smart village integrated citizen science as a foundation of the next model research. This basic terminology will be used as reference to determine the variable selected from the 2018 Village Potential Data of Indonesia. SLR results are discussed with big data analytic framework components, followed by further discussion, about our analyses of 2018 Village Potential Data using multiple regression techniques.
Fig. 1 Stages of research
The instrumentation of this research limited by using the secondary data. The data used is the 2018 Village Potential Data that is produced by BPS. This data consists of potential variables in village development that exist around of the administratively village area. Some of these variables are:
ICT, management of program, sources of funds for the programs, agriculture and small-scale non-agricultural businesses and beneficiary villagers. The selection of these variable refers to [1][2][20]. The selected variable then manage by multiple regression technique to map the potential of big data analytic-based smart village in Indonesia.
III. RESULT AND DISCUSSION
A. Descriptive analysis of hierarchical attributes and domains of smart village and citizen science research The global condition of smart village research is illustrated using an analysis of attribute hierarchies. We conducted our analyses using NVivo 12 Plus tool, and the results are shown in Fig 2. The analysis of a hierarchy among the attributes of smart village research are arranged by year;
areas of Sustainable Development Goals (SDGs), followed by research methods and technology. The process of our research on the hierarchy in the smart village domain that integrates with citizen science research is shown in Fig. 3.
The SLR result that represented in Fig 2 and Fig 3 refer to [18], which is managing the paper of smart village and citizen science research by descriptive analysis through hierarchical attributes and domain research.
Based on our findings, it can be concluded that the smart village research agenda in the future will have a potential to be developed towards the construction, implementation and comprehensive analysis of big data analytic technology. This statement is supported by the availability of data and technology that are becoming cheaper. Another support is related to increasing access to various ICTs in rural areas, demonstrated by an increase in ICT literacy in these areas.
One example of the uptake of ICT in Indonesia is the increasing use of social media for sale and purchase transactions in rural areas that is higher than in cities. The rate of usage of social media to sell online in the village 69.9%
compared to the city, 62.3%. Using social media to buy online in villages is 57.2%, while in cities 42.1% [21]. Even internet usage by farmers in Indonesia has reached 10% of total farmers in Indonesia [22].
This condition has a real potential opportunity for the development of smart villages based on big data analytics.
Socialization through social media and the promotion of smart villages has also become a research agenda for progress, so that many parties can reproduce the success of smart villages. There is research that proposes this will be able to narrow urban and rural disparities, but with synergistic and sustainable four-parties support [1][2][3][5][20][23]
[24][25][26].
2020 International Conference on Computer Science and Its Application in Agriculture (ICOSICA)
Fig. 2. Attributes Hierarchical Analysis of Smart Village Researches
Fig. 3. Attributes and Domain Hierarchical Analysis of Smart Village Researches
Fig 3 shows that the potential for developing smart village research based on big data analytic is still very potential. The results of the hierarchy analysis of the smart village research domain and citizen science illustrate an area of research that is still narrow when compared to other research areas. Smart village research is still dominated by reviews related to social science (citizen science & crowdsourcing) and infrastructure (ICT and non-ICT facilities, and policies). There are relatively less comments related to institutions in smart village research, compared to other areas of research. We propose, this shows that the development of smart village research using big data analytics and integration with social science, computer science and infrastructure; has significant potential to be carried out especially in relation to institutional collaboration.
B. Cluster analysis of smart village and citizen science research
Smart village research cannot be separated from citizen science research. Based on research finding [1][26] more than 70% of smart village research is comprehensively discussed through the citizen science approach. Therefore, in this study, cluster analysis is done through the investigation using the word frequency technique of various text mining approaches in citizen science research, and the integration of smart village research with citizen science research. The results of
cluster analysis of citizen science research are shown in Fig 4. The results of cluster analysis of the integration of smart village research in citizen science are shown in Fig 5.
Cluster analysis through word frequency techniques were also carried out on 33 citizen science research papers to produce results as five dominant words at the first level of the dendrogram, as shown in Fig 4. The focus of citizen science research is very closely related to smart village research.This is evidenced by the dominant use of the words project and data which are also dominant in the smart village research dendogram. The word project belongs to the same family as a citizen. In this case, it shows that the reported citizen project activities [27][28]. The word data is closely related to quality, its finding shows that citizen science research needs high quality data. Especially, for the formation of citizens as a scientist [29][30], this requires ICT and quality data optimization techniques, to produce citizen science projects that have high validity [29][31][32][33]. What is very interesting about this word frequency technique is the emergence of the farmer as a dominant word in the process of citizen science research because it is implemented on farmer residents, most of whom live in villages [34][35].
There are exciting findings from the results of our cluster analysis using word frequency techniques in the integration of smart village research and citizen science, with the results 2020 International Conference on Computer Science and Its Application in Agriculture (ICOSICA)
of the dendrogram structure, shown in Figure 5. Terminology dominating the first level are the words smart and village.
Word frequency techniques have good potential and ability for SLR, particularly in this application to smart village research.
Fig. 4. The Dendrogram structure of citizen science's research
Fig. 5. Dendrogram structure of integration of smart village and citizen science research
As described, this condition is strengthened by the findings presented in the dendrogram of the integration of smart village research and citizen science with a particular focus on the terms : smart and village (first level); citizen and projects (second level); and model (third level). This case illustrates that most of the critical factors for the success of smart villages are part of the building blocks of citizen science. Other research reports, the development of citizen science is also very responsive to the development of ICT [8][36][37][38][39][40].
In Fig 5, at the sixth level is crowdsourcing, which is a branch shared with the words community and model. This interpreted to mean crowdsourcing an essential factor for the success of smart villages implemented through a citizen science project. The level of knowledge related to the role of its citizens can be divided into four levels : 1) crowdsourcing, citizens acting as sensors; 2) distributed intelligence, citizens as interpreter bases; 3) participatory science, citizens participating in the process of problem definition and data collection, 4) extreme or collaborative science, citizens play a role in the process of problem definition, data collection and data analysis [41][42]. Therefore, those who will be involved in a citizen science project can include professional scientists, credentialed scientists, academic scientists, residents, hobbyists, community members, volunteers, native villagers, and human sensors [42][43][44].
C. Integration of smart village domain SLR and big data management framework
Hierarchical analysis of the attributes and domains of smart villages shows that the area of research related to big data analytics being implemented and analyzed through the integration of citizen science and infrastructure remains a narrow field of research. This condition means there are potential opportunities for development using this research method. Moreover, it is strengthened by the results of a descriptive analysis of the level ICT implemented. In particular, the integration of big data analytics for the Opinion Mining sub-sector, which is still minimal [5]. However, due to the era of data disruption, data optimization using big data analytic technology has been widely used in various fields and is adopted in rural areas. The available data’s potential is abundant, being accessible through social media, online news, various government and private institutions' websites and other on-line sources. The data in question are related to agricultural commodity price, agricultural market potential and other data that can be optimized using big data analytics.
The principle of big data management is built from a strong data foundation and develops according to the procedure in Fig 6. The big data management concept which is an integrates concepts described in [4]. Entities in smart villages that involve four-parties : 1) academics, 2) villagers (community, cooperatives, micro small medium enterprises (MSMEs), and farmers), 3) government (ranging from villages level to nasional) and 4) businesses (entities from upstream to downstream).
These entities can be optimized for developing smart village big data management. An example of strong support for the development of smart villages in Indonesia is Law No. 6 of 2014. This legislates that villages can be used as a basis for descriptive and predictive data to develop the concept of big data analytics. The integration of the conceptual framework indicated in Fig 6 with agriculture
management framework, that implemented in big data analytics by [12] is shown in Fig 7. This case can be used to identify and analyzed the components involved and influence the implementation of the big data concept in smart villages.
The framework (Fig 7) shows that business processes are focused on the use of big data in the management of agricultural processes.
2020 International Conference on Computer Science and Its Application in Agriculture (ICOSICA)
Fig. 6. Conceptual of big data management
Fig. 7. The framework of a big data application system
There are three parts in business processes: 1) data chain, 2) agricultural management, and 3) agricultural processes.
Through various decisions, data chains interact with agricultural processes and agricultural management processes. The stakeholder network includes all stakeholders involved with this process, not only significant data users but other actors such as the community, MSME cooperatives, and the government. Network management is the organizational structure and technology of the network that facilitates coordination and management of processes carried out by stakeholder in the network management. The technology component focuses on an infrastructure of information that supports the data chain, while the organizational component focuses on governance and business models.
Data chain refers to the sequence data capture decision making and marketing of data [13][14]. The data chain includes all activities needed to manage data for agricultural management. Fig 6 illustrates the main steps in this chain that are combined with the four components in the big data framework. The big data analytic levels are descriptive, diagnostic, predictive and prescriptive.
The ideal concept in the big data analytic framework is very potential to be implemented in the smart village. This smart village concept integrates components of social sciences, computer science and infrastructure. The establishment of the concept of smart villages based on big data analytics can be reviewed more comprehensively through a portrait of the potential of villages in Indonesia.
D. Descriptive analysis of Smart Villages Based on Big Data Analytic Potencies in Indonesia
In this study, the potential of villages in Indonesia is portrayed according to : readiness of their infrastructure directly related to ICT; sources of funding for ICT activities
and the development of MSMEs; the involvement of villagers in ICT management activities. The ICT infrastructure and MSME potential studied in this study are limited to the results from source data the 2018 Village Potential Data elaboration in Indonesia [9].
Readiness to apply the concept of big data analytics for smart villages can be mapped through the conditions of basic needs, such as, the existence of a computer or laptop in the village. The presence of computers in the village office has a significant influence on the readiness of the village to become a smart village. According to the availability of computers in the village as an indication of readiness, there are only two provinces with villages that are not equipped with computers (80% of village offices have no computers). The provinces are located in West Papua and Papua. More than 60% of village offices in 32 other provinces have been equipped with computers. This reflects on the outcome from Indonesia's initial capital to develop smart villages; initial capital to implement big data analytics [26]; and to focus strengthening smart government [2][45][46].
Internet functionality for the development of big data analytics has a vital role. The readiness of villages in Indonesia shows very diverse conditions. Villages that have more than 50% internet functionality are presence in the provinces of Central Java, DI Yogyakarta, East Java and Bali.
This condition is following the accelerated development of smart villages that have been initiated by DI Yogyakarta [2].
Villages in the provinces of West Java, Banten, West Nusa Tenggara, Gorontalo and West Sumatra have internet functionality ranging from 20-30%. Even though West Java already has a Jabar Cyber Province (JCV) program that began in 2013 and many ICT activities that collaboration in village [47] . The conditions for village internet development are still low. The conditions for internet functionality in West Java are as follows: in 30% of functioning internet villages, 30% in other villages internet conditions are rarely functioning, as well as 30% of other villages the condition of the internet is not functioning even the rest has no internet. Villages with no internet available still dominate the provinces of West Papua and Papua, and internet functionality in villages in other provinces is still below 20%. This condition can be a reference for mapping the development of smart villages based on big data analytics [2] [5][48].
Internet functionality is certainly strongly supported by the condition of internet signals that have entered the village.
Six provinces have 4G internet signals spread over more than 40% of their villages, namely the Bangka Belitung Islands, West Java, Central Java, DI Yogyakarta, Banten and Bali.
The distribution of 3G internet signals with an average distribution in more than 30% of the villages has covered 20 provinces in Indonesia. The authorized capital of 3G and 4G signals can be optimized for the application of big data analytics related to the development of smart villages in Indonesia. Although currently, 5G technology has become a smart village research agenda [5], the availability of 3G and 4G technology can still be optimized with four-partiet integration [45][49].
The most critical ICT infrastructure related to the availability of computers and the internet will not reach their potential to develop smart villages based on big data analytics, if not supported by useful ICT management.
Potential villages in Indonesia show that there are nine provinces where the percentage of villages is more than 50%
2020 International Conference on Computer Science and Its Application in Agriculture (ICOSICA)
has been managing ICT. The provinces are West Sumatra, Riau, Bangka Belitung Islands, West Java, Central Java, DI Yogyakarta, East Java, Bali and West Nusa Tenggara. This condition is critical because the contribution of ICT management is an essential requirement in the development of smart villages based on big data analytics [2][50][51][52].
The availability of infrastructure and management of ICTs as the basis for implementing the concept of big data analytics in smart villages in Indonesia also needs to be supported by robust funding. Funding sources for ICT management in villages have been strengthened by various schemes. The 2018 Village Potential Data in Indonesia confirms there are 18 provinces that implemented Swadaya funding schemes for ICT management, in the range from 5-25%. This independent funding source shows the principle of independence and very high public awareness of the development of smart villages, especially in the face of an era of data disruption and the application of the concept of big data analytics [1][2]. This condition can be used as a powerful initial capital and is following the principle of smart village sustainability.
Provinces of Yogyakarta, Bali, Aceh, Central Java, Central Sulawesi and West Java have implemented more than 10%
Swadaya schemes. The Yogyakarta Province shows the full potential and readiness for the application of the concept of smart villages based on big data analytics compared with other provinces. In Yogyakarta, there has been a successful implementation of smart villages in four village areas [2].
Community independence and government support through funding are also vital assets for the sustainability of big data analytic smart villages. Indonesia has the potential to implement smart villages based on big data analytics, because 27 provinces have already implemented a mixed scheme of Regional Budget Revenue (APBD) and Swadaya, in the range 25-80%. The sustainability of smart villages based on big data analytics in Indonesia can be strengthened by the increasing number of provinces implementing funding sourced from Village Original Revenue (PAD), although the range 2-12%
is still low. The ten provinces : Jambi, Bengkulu, Bangka Belitung Islands, Central Java, West Nusa Tenggara, East Nusa Tenggara, West Kalimantan, Central Sulawesi, West Sulawesi and Maluku manage village ICT through a PAD scheme of more than 10%. This situation is interpreted as powerful capital and effort from the village manager in order to face the challenges in the era of data disruption. This situation can be used as the foundation of guaranteeing the sustainability of the smart village concept based on big data analytics.
Government and community synergy are a very effective strategy to ensure the sustainability of the concept of smart villages based on big data analytics. All provinces in Indonesia have adopted this strategy to strengthen management of ICT in villages. This strategy is demonstrated through the implementation (8-58%) of APBD funding scheme and the mixed APBD-PAD scheme in all provinces.
This situation also occurs in the development of productive agricultural businesses and non-agricultural small businesses.
All provinces in Indonesia have implemented this type of development by relying on mixed sources of regional Swadaya funds in the range 30-95%. When combined data sources of ICT management funds and the development of productive agricultural businesses and non-agricultural small businesses, shows high relevance among provinces that apply Swadaya funding sources to business development; who also
apply this scheme to ICT management in their villages. This finding reinforces understanding that agriculture and non- agricultural small businesses are supported by good ICT management in the village [53]. This situation becomes very important for the basic capital in the application of smart villages based on big data analytics.
The involvement of villagers in ICT management activities is a form of social capital that needs to be strengthened. This potential possessed by Indonesians, is confirmed by high rates of participation among citizens, poor and farmers to contribute to various activities of ICT management. Likewise, the beneficiaries of ICT management have been absorbed by various elements of villagers, including farmers and poor people spread across 22 provinces with a percentage in the range 5-96%. This condition is in line with the primary objective of the concept of smart villages that are focused on reducing poverty levels in the village.
The potential application of a big data analytic smart village is also assessed from the relationship between the source of funds for managing agricultural businesses and non- agricultural small businesses in the village and the program beneficiaries. The study was conducted using multiple regression analysis, and the results are shown in Table 1.
TABLE I. MULTIPLE REGRESSION ANALYSIS OF AGRICULTURE
& NON-AGRICULTURE SME'S MANAGEMENT AND FUND SOURCES TO BENEFICIARIES IN THE VILLAGE*
APBD PAD Swadaya Others
Poor citizen
Adjusted R Square 0.7040
Anova Signific. F 3.8800E-7
Anova P-value 0.0004 0.0106 0.0429 0.0692 Farmer / Fisherman
Adjusted R Square 0.9759
Anova Signific. F 7.7317E-24
Anova P-value 0.00002 0.0044 0.2291 0.5058 Community business group
Adjusted R Square 0.9482
Anova Signific. F 5.1609E-19
Anova P-value 0.0126 0.0024 0.0107 0.0023 Private / Businessman
Adjusted R Square 0.8567
Anova Signific. F 1.2138E-12
Anova P-value 0.4171 0.3142 0.0428 0.8539 *Source data processed from the 2018 Village Potential Data
Table 1 shows our results from the villages analysed in financial support from various schemes, and opportunities of development smart villages based on big data analytics. This is indicated by the high value of Adjusted R Square. Even the beneficiaries of the group of farmers/fishermen have a powerful influence compared to other beneficiaries in villages in Indonesia. This situation is relevant to the objectives of the smart village program, which is more focused on reducing poverty levels of farmers/fishermen [7][53]. The effect of funding sources of this program has a differing when examined in detail using ANOVA analysis.
Other sources of funds for the management of agricultural businesses and rural non-agricultural small businesses have 2020 International Conference on Computer Science and Its Application in Agriculture (ICOSICA)
