cover
Contact Name
Hidra Amnur
Contact Email
hidra@pnp.ac.id
Phone
+6282386434344
Journal Mail Official
admjitsi@gmail.com
Editorial Address
Kampus Politeknik Negeri Padang, Jurusan Teknologi Informasi. Gedung E. Limau Manis, Pauh. Padang - Sumatera Barat. Indonesia
Location
Kota padang,
Sumatera barat
INDONESIA
JITSI : Jurnal Ilmiah Teknologi Sistem Informasi
ISSN : 27224619     EISSN : 27224600     DOI : 10.30630/jitsi
Core Subject : Science,
The journal scopes include (but not limited to) the followings: Computer Science : Artificial Intelligence, Data Mining, Database, Data Warehouse, Big Data, Machine Learning, Operating System, Algorithm Computer Engineering : Computer Architecture, Computer Network, Computer Security, Embedded system, Coud Computing, Internet of Thing, Robotics, Computer Hardware Information Technology : Information System, Internet & Mobile Computing, Geographical Information System Visualization : Virtual Reality, Augmented Reality, Multimedia, Computer Vision, Computer Graphics, Pattern & Speech Recognition, image processing Social Informatics: ICT interaction with society, ICT application in social science, ICT as a social research tool, ICT education
Articles 139 Documents
Analisis Kebergunaan, Kemudahan, dan Kepercayaan pada Intention to Use Mobile Banking Bank BUMN Gunawan, Angela Melia; Tileng, Kartika Gianina
JITSI : Jurnal Ilmiah Teknologi Sistem Informasi Vol 6 No 2 (2025)
Publisher : SOTVI - Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/jitsi.6.2.400

Abstract

State-owned banks play an important role in strengthening the mobile banking trend by providing services that are innovative and attractive to the public. State-owned banks also contribute to the State Revenue and Expenditure Budget, which influences national economic development and growth. Based on the important role of state-owned banks in strengthening the mobile banking trend and its impact on the economy, this research aims to analyze how usefulness, ease of use and trust factors influence intention to use in utilizing mobile banking services at state-owned banks. This research uses a quantitative approach with surveys as a data collection method. The data obtained was analyzed using multiple linear regression analysis to identify relationships between variables. The results show that usefulness is the main factor in encouraging the use of mobile banking in state-owned banks compared to ease of use and trust. This approach is expected to help state-owned banks develop services that are more responsive to customer needs and preferences, so that they can accelerate the adoption of mobile banking services and optimize their benefits for the national economy.
Sentimen Analisis Review Film Pada IMDb Menggunakan Algoritma Logistic Regression Faridi, Muhammad Azka; Tuzzahra, Fauzia; Al-Qadri, Adnan; Nahavira, Rhaudy; Az-Zahrah, Putri Amelia; Apriliani, Cindi; Abdiansah
JITSI : Jurnal Ilmiah Teknologi Sistem Informasi Vol 6 No 2 (2025)
Publisher : SOTVI - Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/jitsi.6.2.422

Abstract

Sentiment Analysis is a subfield of Machine Learning that focuses on analyzing opinions expressed in textual data. IMDb, as a widely used platform, provides a space for movie enthusiasts worldwide to share their thoughts and reviews. User feedback can serve as a benchmark for evaluating a film's success. This research aims to classify reviews into positive and negative categories using the Logistic Regression algorithm combined with Grid Search and Active Learning methods. The classification results show that the highest accuracy achieved is 90.90% using Logistic Regression with the combination of Grid Search and Active Learning. Meanwhile, Logistic Regression with Active Learning alone achieved an accuracy of 90.58%, Logistic Regression with Grid Search reached 90.17%, and the basic Logistic Regression model achieved an accuracy of 89.81%.
Forecasting Next Year's Health Insurance Claims Using Machine Learning Models Alkrunz, Iyad S.; Abuzaid, Ali
JITSI : Jurnal Ilmiah Teknologi Sistem Informasi Vol 6 No 2 (2025)
Publisher : SOTVI - Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/jitsi.6.2.443

Abstract

This study explores the transformative potential of big data analytics in the realm of health insurance risk management. Focusing on data sourced from Highmark Health from 2015 to 2018, the research aims to evaluate the efficacy of advanced data manipulation techniques and machine learning models in enhancing predictive accuracy. The analysis involves a comprehensive examination of Health Maintenance Organization (HMO) and Preferred Provider Organization (PPO) plans, with rigorous data preparation processes such as cleaning, aggregation, feature engineering, and outlier handling to ensure model suitability. Four distinct models were developed: an initial model utilizing raw data without outlier treatment, a model post-outlier treatment considering both HMO and PPO members, and models focusing exclusively on HMO and PPO members respectively. Results demonstrated significant improvements in predictive accuracy following outlier treatment, with Random Forest and Multivariate Adaptive Regression Splines showing superior performance. The Random Forest model achieved a Root Mean Square Error (RMSE) of 630.04 and an R-squared value of 0.757, underscoring its robust predictive capabilities. Similarly, the Multivariate Adaptive Regression Splines model exhibited strong fit with commendable metrics. The HMO-focused model yielded promising outcomes with a minimal RMSE of 675.85 and an R-squared value of 0.68. However, the PPO-focused model's suboptimal results highlight potential data quality issues and dataset limitations. This research underscores the critical role of integrating machine learning techniques in health insurance analytics, providing valuable insights for proactive risk management and decision-making, and enhancing efficiency and effectiveness within the industry,
SIG Berbasis Web untuk SDG 14 di ASEAN Menggunakan Metode Extreme Programming Salsabila, Adinda; Hadi, Setiawan; Suryana, Ino
JITSI : Jurnal Ilmiah Teknologi Sistem Informasi Vol 6 No 2 (2025)
Publisher : SOTVI - Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/jitsi.6.2.447

Abstract

Sustainable Development Goal 14 focus on sustainable development in the marine sector by emphasizing key focus areas such as Marine Protected Areas, Total Fisheries Production, Aquaculture Production, and Capture Fisheries Production. The ASEAN region, with its rich marine biodiversity, faces serious threats, including overfishing. However, no interactive platform is currently available to comprehensively visualize relevant data. This research aims to develop a web-based Geographic Information System (GIS) to visualize SDG 14 data in ASEAN using the Extreme Programming approach. This study employs the Research and Development (R&D) method with an Extreme Programming approach, allowing iterative software development. Primary data, including marine protected areas and fisheries production, were obtained from reliable sources such as the World Bank and visualized using Leaflet.js with geospatial data in GeoJSON format. System testing was conducted through Black Box Testing and the System Usability Scale (SUS), integrated into a survey form completed by 32 respondents to assess the system's accuracy and ease of access. The test results indicate that the system can provide accurate and easily accessible information, with a Black Box Testing score of 99.79%. Additionally, the Mean Absolute Percentage Error (MAPE) calculation resulted in a value of 0.21%, demonstrating a very high accuracy in system predictions. The SUS score reached 94.03%, reflecting a very high level of user satisfaction. This system successfully meets the need for SDG 14 data visualization, supports decision-making, and raises public awareness of marine ecosystem conservation in ASEAN.
Sinkronisasi Global: Taktik Koordinasi Waktu Adaptif untuk Tim IT Agile Virtual Tsani, Muhammad Rizqi; Sudiarno, Adithya
JITSI : Jurnal Ilmiah Teknologi Sistem Informasi Vol 6 No 2 (2025)
Publisher : SOTVI - Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/jitsi.6.2.458

Abstract

The global adoption of Agile methodologies in virtual IT teams presents a fundamental conflict with the principle of face-to-face communication, with temporal distance posing a primary operational barrier. This research identifies and analyzes the adaptive time-coordination tactics that globally dispersed Agile teams employ to overcome this challenge. The study utilized a qualitative, phenomenological approach, conducting semi-structured interviews with practitioners from teams spanning up to a 15-hour time zone difference. The analysis reveals that effective teams do not force full-day synchronization but instead strategically leverage a limited synchronous ‘overlap window’ for high-bandwidth collaboration. Complementing this, teams implement a disciplined ‘asynchronous handoff’ to create a continuous, 24-hour workflow, transforming temporal separation into a strategic advantage. Key findings also show that teams pragmatically reconfigure Agile ceremonies, often replacing daily stand-ups with asynchronous updates, and foster individual autonomy to maintain productivity. The study concludes that success in virtual Agile environments hinges on a flexible framework of emergent, context-aware tactics rather than rigid adherence to traditional practices. These insights provide actionable strategies for managers to enhance the temporal efficiency and coordination of virtual projects.
Zerotier Pada Home Server Menggunakan Sistem Operasi CasaOS Hidra Amnur; Putri, Widya Amda
JITSI : Jurnal Ilmiah Teknologi Sistem Informasi Vol 6 No 2 (2025)
Publisher : SOTVI - Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/jitsi.6.2.467

Abstract

Dalam era digital yang terus berkembang, kebutuhan akan ruang penyimpanan semakin meningkat baik untuk dokumen fisik maupun digital. Untuk mengatasi masalah ini, implementasi home server yang terhubung ke internet, memungkinkan akses yang lebih mudah dan fleksibel. home server adalah perangkat keras yang menjalankan perangkat lunak server dan berfungsi sebagai pusat kontrol untuk berbagai layanan rumah tangga, memfasilitasi penyimpanan dan berbagi file. Mengakses home server menggunakan ZeroTier, sebuah teknologi VPN, memungkinkan manajemen yang mudah tanpa perlu penyewaan alamat IP address public. Kombinasi antara home server, ZeroTier, dan CasaOS menjadi solusi penyimpanan data yang aman, efisien, dan hemat biaya untuk lingkungan rumah tangga. Berdasarkan perancangan dan implementasi ZeroTier pada home server menggunakan sistem operasi CasaOS, kesimpulan yang diperoleh adalah implementasi ini berhasil menciptakan penyimpanan yang aman dan efisien pada private storage home server. ZeroTier sebagai VPN(virtual private network) dengan enkripsi end-to-end memudahkan akses remote bagi pengguna, dengan adanya CasaOS dapat memberikan solusi terbaik cloud pribadi dengan biaya yang murah dibandingkan dengan penyimpanan yang lain diantaranya iCloud Sekitar 51,39% dan Google One Sekitar 67,47%. pengguna dapat mengelola penyimpanan home server di lingkungan rumah tangga. Teknologi ini sangat user-friendly sehingga relevan bagi pengguna awam, menjadikannya pilihan terbaik untuk kebutuhan penyimpanan digital di rumah.
Perancangan dan Evaluasi Aplikasi Mobile Berbasis Pengguna untuk Pengelolaan Sampah Berbasis Komunitas Asyrafil Anam, Maulana; Supriyanto
JITSI : Jurnal Ilmiah Teknologi Sistem Informasi Vol 6 No 2 (2025)
Publisher : SOTVI - Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/jitsi.6.2.469

Abstract

It is very hard to keep an eye on garbage at the village level when there is no clear information about when sorted waste will be picked up and when sales will happen, and when there is no method for documenting waste data. This lack can cause garbage to build up in places where it shouldn't and make it harder to manage waste properly. To fix these problems, Badan Usaha Milik Kalurahan needs a mobile app that is easy to use and makes waste management tasks easier. BUMKALs are very important for helping communities grow and providing important services, like trash management. This study is all about making a trash management software, with a big focus on User Interface and User Experience principles. The design process uses a User-Centered Design method, which makes sure that users are included in every step. This method makes sure that the final application fits their demands and wants very well. In Caturharjo Village, which is in the Pandak Subdistrict of Bantul Regency, the local BUMKAL has taken the lead in starting community-based garbage management. But they still have problems with keeping track of data in a systematic way and having good ways to communicate. We used the User Experience Questionnaire to find out how users felt about the design of the program and how satisfied they were with it. The evaluation results show that the mobile app had mostly good feedback on all UEQ aspects, such as how clear, beautiful, and useful it was. All of the ratings were over the positive benchmark, which is really impressive. This shows that users were very happy with the application that was made, which means it may be successfully implemented and used.
Pengaruh Augmentasi Data Terhadap Akurasi Pelatihan Model CNN untuk Klasifikasi Jenis Ikan Al-Fahrezi, Muhammad Abel
JITSI : Jurnal Ilmiah Teknologi Sistem Informasi Vol 6 No 2 (2025)
Publisher : SOTVI - Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/jitsi.6.2.471

Abstract

Sustainability of marine resources and management of aquatic ecosystems depend on accurate fish classification. CNNs have proven successful in image classification tasks; however, they often face the problem of limited data variation. The purpose of this study was to examine how data augmentation affects the training accuracy of CNN models for fish species classification. Two scenarios were studied: the first scenario involved training without data augmentation, and the second scenario involved training with data augmentation. In both scenarios, a custom CNN architecture for ten epochs was used. Experimental results showed that using data augmentation with the configuration used actually caused the model performance to deteriorate. Loss values ​​on both datasets increased, with training accuracy dropping from 76.08% to 63.81%, and validation accuracy also dropping from 91.13% to 84.55%. Overly aggressive augmentation parameters or insufficient training time for the introduced data variation could have caused this decline. Interestingly, validation accuracy was consistently higher than training accuracy in both situations, indicating that certain datasets have specific features. This study emphasizes the importance of carefully optimizing augmentation parameters and training duration to maximize the benefits of data augmentation in image classification.
Penerapan Algoritma Random Forest untuk Deteksi Phishing pada Website Fahri, Muhammad
JITSI : Jurnal Ilmiah Teknologi Sistem Informasi Vol 6 No 2 (2025)
Publisher : SOTVI - Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/jitsi.6.2.472

Abstract

Phishing attacks have become one of the most rapidly increasing cybersecurity threats in recent years. Phishing websites are designed to deceive users into divulging sensitive information such as login credentials, credit card data, and other personal details. This research proposes the implementation of the Random Forest algorithm for automated phishing website detection. The dataset used in this study comprises 10,000 classified URL samples, with 49 distinct features extracted. The research methodology includes data preprocessing, URL feature extraction, Random Forest model training, and performance evaluation. The evaluation results demonstrate that the developed Random Forest model achieved an accuracy of 98.20%, precision of 98.22%, recall of 98.22%, and an F1-score of 98.22%. This study proves that the Random Forest algorithm is highly effective for phishing detection and can be implemented as a preventive security system in internet Browse.