International Journal on Information and Communication Technology (IJoICT) <p align="justify">International Journal on Information and Communication Technology (IJoICT) is a peer-reviewed journal in the field of computing that published twice a year; scheduled in December and June.</p> <p align="justify">IJoICT includes novel ideas on ICT, state of the art technique implementations, and study cases on developing countries. Each article is featured with details of the proposed method including dataset and external link for program or codes. The journal is published for those who wish to share information about their research and innovations and for those who want to know the latest results in the field of Information and Communication Technology (ICT).&nbsp;&nbsp;The Journal is published by the <a href="" target="_blank" rel="noopener">School of Computing</a>, Telkom University, Bandung, Indonesia. Accepted paper will be immediately available online (open access) without any publication fee.</p> School of Computing, Telkom University en-US International Journal on Information and Communication Technology (IJoICT) 2527-9599 <p>Manuscript submitted to IJoICT has to be an original work of the author(s), contains no element of plagiarism, and has never been published or is not being considered for publication in other journals. Author(s) shall agree to assign all copyright of published article to IJoICT. Requests related to future re-use and re-publication of major or substantial parts of the article must be consulted with the editors of IJoICT.</p> Web-based Application for Diagnosis of Diabetes using Learning Vector Quantization (LVQ) <p>Diabetes is a chronic disease that causes the most deaths in the world. This disease can cause long-term complications that develop gradually, such as heart attacks, strokes, and problems with the kidneys, eyes, skin, and blood vessels. Therefore, early diagnosis of diabetes is crucial for patients to know their diabetes status. In this study, we designed a web-based application for diabetes diagnosis using Learning Vector Quantization (LVQ). The dataset was collected from Kaggle's Diabetes Dataset which contains eight attributes, namely pregnancy, glucose, blood pressure, insulin, skin thickness, BMI, diabetes lineage function, and age, with two classes, namely negative diabetes (healthy) and positive diabetes. The results show that the best accuracy is 73.1% with a learning rate of 0.001. These findings can help patients detect diabetes problems early.</p> Juni Wijayanti Puspita Kevin Jieventius Yanto Andi Moh. Ridho Pettalolo Moh. Ali Akbar Dg. Matona Handayani Lilies Copyright (c) 2024 2024-07-03 2024-07-03 10 1 10.21108/ijoict.v10i1.941 Application of Singular Spectrum Analysis (SSA) Decomposition in Artificial Neural Network (ANN) Forecasting <p>Over time, various forecasting methods have been introduced. An example is the Hybrid model. This model can enhance the forecast accuracy compared to a single model. The Hybrid Singular Spectrum Analysis (SSA)-Artificial Neural Network (ANN) model combines the concepts of decomposition and forecasting. The Hybrid SSA-ANN forecasting works through two stages. Firstly, SSA decomposes the data into trend, seasonal, noise, and residue components. Secondly, the decomposed data is predicted using the ANN model, specifically the LSTM and GRU models. The Hybrid SSA-ANN model has been proven to improve forecasting accuracy. The Hybrid SSA-LSTM model improves the forecast accuracy by 78% compared to the single LSTM forecasting model. This can be seen from the respective RMSE values of 4.36 changing to 0.97 and MAPE values of 5.2% changing to 1.16%. Similarly, the Hybrid SSA-GRU model improves the forecast accuracy by 79% compared to the single GRU forecasting model. This can be observed from the respective RMSE values of 4.86 changing to 1.01 and MAPE values of 6.33% changing to 1.36%. In a case study using weekly data of crude oil's opening prices, the application of SSA decomposition can enhance the forecast accuracy by 78-79% in ANN forecasting</p> Annisa Martina Irwan Girana Copyright (c) 2024 2024-06-24 2024-06-24 10 1 13 27 10.21108/ijoict.v10i1.870 AgroSense: An IoT-Based Manual Crops Selection Farming <p>This capstone project introduces an Intelligent Irri-gation System leveraging IoT technology to enhance agriculture. Using the ESP32 microcontroller and various sensors for soil moisture, water levels, and environmental conditions, the system automates irrigation based on real-time data. It communicates through the Blynk platform, allowing remote monitoring via a mobile app. The project includes a smart algorithm for crop selection and irrigation control, displayed on an LCD and acces- sible through the Blynk app. By considering soil moisture and water availability, the system adapts to different crops like rice, wheat, potato, and corn. The project promotes sustainability by optimizing water usage and encourages efficient crop growth. The integration of a manual crop count for field feedback enhances decision-making. Overall, this system presents a user-friendly and innovative solution for precision agriculture, showcasing the transformative potential of IoT, data analytics, and machine learning in modernizing farming practices.</p> Safaet Hossain Md. Payer Hamid Bijoy Chowdhury Copyright (c) 2024 2024-06-29 2024-06-29 10 1 53 61 10.21108/ijoict.v10i1.918 The Re-development of Proxsis Workspace with Responsive Design and Multiplatform approaches using Flutter Framework <p>Most of previous studies implemented the responsive design approach for the web-based application platform only since it had several difficulties to apply in the mobile-based application platform. In addition, the mobile application required different codebases since there were several platforms like Android and iOS. However, this study tried to redevelopment the Proxsis Workspace website to mobile application with responsive design and multiplatform approaches using Flutter Framework, in order to explore the potentials and counter the difficulties these two approaches for mobile development. In addition, we provide the detailed improvement, and the software testing results of our redevelopment app. Eight participants were participated in this study to measure the improvement of the redevelopment application. The results showed that the redevelopment version of the Proxsis Workspace could implement the responsive design and multiplatform approaches well. Furthermore, the software testing found that the redevelopment version passed the responsive design and multiplatform testing. In addition, there was significant different and enhancement of the usability score from 52.50 with marginal category to 72.81 with acceptable category. Hence, the authors suggest implementing the responsive design and multiplatform with Flutter Framework to enhance and make efficient with single code base only.</p> Shinta Yulia Puspitasari Iqbal Abdul Ra'uf Rio Nurtantyana Cahyo Tri Satrio Copyright (c) 2024 2024-06-29 2024-06-29 10 1 41 52 10.21108/ijoict.v10i1.919 The Implementation of Titian for Data Provenance on DISC Systems Automated Debugging <p>Data-Intensive Scalable Computing (DISC) systems are critical for managing large datasets while prioritizing fault tolerance, cost effectiveness, and user accessibility. However, the presence of input errors in processed data presents considerable hurdles to programmers. The Snowfall Analysis program, which is well-known for its anomalous data that causes forecasting failures, serves as a key case study in this research. To solve this problem, this study leverages Titian, an extended library designed to speed debugging by methodically tracing the provenance of incorrect data back to its original source. Through thorough analysis, we analyzed Titian's accuracy using confusion matrix and compared its efficiency to standard manual debugging approaches, showing solid evidence of its utility in improving data provenance in DISC systems.</p> Agista Putri Nungki Selviandro Gia Septiana Wulandari Copyright (c) 2024 2024-07-03 2024-07-03 10 1 10.21108/ijoict.v10i1.929 Analysis of Factors Affecting the Use of Digital Paylater Transactions Using the Hedonic-Motivation System Adoption Model (HMSAM) <p>The use of paylater digital transaction methods is a major trend in the current era of digitalization. This study aims to analyze the factors of Continuance Intention of paylater digital transactions. Employing a quantitative approach with Partial Least Square Structural Equation Modeling (SEM-PLS), the research focuses on individuals aged 18 and above who have made digital paylater transactions. The sampling technique chosen was a purposive sampling technique, while data collection was conducted through questionnaires. This research proposes a modified Hedonic-Motivation System Adoption Model (HMSAM) and formulates hypotheses to test the relationship between variables. Data analysis was conducted by measuring the validity and reliability of the model and applying SEM-PLS to analyze variable relationships and test hypotheses. This model integrates elements from HMSAM developed by previous researchers. The six main variables include perceived ease of use, curiosity, joy, control, satisfaction, and Continuance Intention. The results revealed that the hypothesis testing conducted for 6 from 7 hypotheses shows the value of T-Statistics&gt; 1.96, the value of P-Values &lt;0.05, and the value of R-Square in low and moderate indicates moderate and small classification of the influence of Factors Affecting the Use of Digital Paylater Transactions Using the Hedonic-Motivation System Adoption Model (HMSAM).</p> Muhammad Zahwan Latif Rio Guntur Utomo Copyright (c) 2024 2024-06-29 2024-06-29 10 1 28 40 10.21108/ijoict.v10i1.896 An Impact Analysis of Damage Level caused by Malware with Dynamic Analysis Approach <p>Malware, short for malicious software, is software or code specifically designed to damage, disrupt <br>computer systems, or gain unauthorized access to sensitive information. Based on type <br>classification, one of the well-known types of malware is ransomware. Usually, ransomware will <br>encrypt the files on a computer system and then demand a ransom from the owner of the computer <br>system so that the owner can regain access to the encrypted files. Sometimes in some cases, <br>ransomware is able to delete files without input from the computer system owner. This research <br>includes the analysis process of three ransomware samples that are known for successfully causing <br>losses to many computer systems throughout the world, namely WannaCry, Locky, and Jigsaw, <br>using a dynamic approach and the use of tools to track the processes carried out by the ransomware. <br>The purpose of this research is to determine which of the three samples has the highest to lowest <br>level of damage based on metrics based on file access capabilities and file modification capabilities <br>for various types of files such as system files, boot-related files, program files, etc. The findings of <br>this research indicate that WannaCry has the highest impact followed by Locky and then Jigsaw.</p> Christopher Arden Anugerah Erwid Musthofa Jadied Niken Cahyani Copyright (c) 2024 2024-07-03 2024-07-03 10 1 10.21108/ijoict.v10i1.940 Optimizing Hyperparameters of CNN and DNN for Emotion Classification Based on EEG Signals <p>EEG emotion is a research topic that has gained significant attention in the development of emotion classification systems. This study focuses on optimizing the hyperparameters of CNN (Convolutional Neural Network) and DNN (Deep Neural Network) for classifying EEG emotion signals. The data is divided into three train-test data ratio scenarios: 80:20, 70:30, and 60:40. After modeling and the classification process, hyperparameter tuning was conducted on both models to achieve the best results. Experimental results showed the highest accuracy of 98.36% for CNN, while DNN reached 98.18% in the 80:20 data ratio scenario. Despite the high accuracy, the differences in the loss curves between CNN and DNN reflect the complexity of the performance of both models. The train-test data ratio was also found to significantly impact the performance of both models, with the 80:20 data split yielding the best results, while the 70:30 and 60:40 splits resulted in slightly lower accuracies.</p> Dian Palupi Rini Winda Kurnia Sari Copyright (c) 2024 2024-06-24 2024-06-24 10 1 1 12 10.21108/ijoict.v10i1.857 Sentiment Analysis on Social Media Using Word2Vec and Gated Recurrent Unit (GRU) with Genetic Algorithm Optimization <p>The evolution of information technology has changed the function of social media from a mere information repository to a platform for expressing opinions and aspirations. One of the most used social media is Twitter. Twitter users can express opinions according to their conscience. Therefore, a sentiment analysis process is needed to classify the opinion as positive or negative. Sentiment analysis on social media is important to understand user opinions, monitor public perception, measure campaign performance, identify trends and opportunities, and improve customer service. This research builds a model to perform sentiment analysis on the topic the president election with a total dataset of 39,791 with GRU method, TF-IDF feature extraction, Word2Vec feature expansion with 142,545 corpus from IndoNews, and Genetic Algorithm optimization. The test results show that the highest accuracy achieved is 83.39%, which shows an improvement of 1.42% compared to the baseline. This performance was achieved when combining of TF-IDF with a 5,000 maximum features, applying Word2Vec at top 1 similarity, and applying Genetic Algorithm for feature optimization. This study proves the relationship between the use of Word2Vec feature expansion and Genetic Algorithms as optimization in improving the accuracy of the model created.</p> Syafa Fahreza Erwin Budi Setiawan Copyright (c) 2024 2024-06-29 2024-06-29 10 1 62 77 10.21108/ijoict.v10i1.903 Sentiment Analysis on Social Media Using Fasttext Feature Expansion and Recurrent Neural Network (RNN) with Genetic Algorithm Optimization <p>Social media is a place to express opinions or feelings, both positive and negative. One of them is to express opinions or feelings about a topic that is currently being discussed. The number of opinions or sentiments related to a topic can be challenging to assess if it leans towards positivity or negativity. Therefore, Sentiment analysis is essential for examining the viewpoints or sentiments on the topic. In this study, 37,391 Twitter user comments on the 2024 Indonesian presidential election were tested. This research employs the RNN methodology, TF-IDF feature extraction, and FastText feature expansion utilizing an IndoNews corpus of as much as 142,545 data and using Genetic Algorithm optimization. The outcomes of this study yielded the highest accuracy when combining TF-IDF feature extraction with max 7000 features, FastText feature expansion on top 5 features, and implementing Genetic Algorithm optimization with a value of 82.72%, accuracy increased by 3.4% from the baseline.</p> Inggit Restu Illahi Erwin Budi Setiawan Copyright (c) 2024 2024-06-29 2024-06-29 10 1 78 89 10.21108/ijoict.v10i1.905