cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Ramdani Dwi Pamuji
Contact Email
jocsit.publine@gmail.com
Phone
+6285945340977
Journal Mail Official
jocsit.publine@gmail.com
Editorial Address
Jl. Tawak-tawak No.5 Karang Sukun, Kel. Mataram Timur, Kec. Mataram, Kota Mataram - NTB, Indonesia 83121
Location
Kota mataram,
Nusa tenggara barat
INDONESIA
Journal of Computer Science and Information Technology
Published by Lembaga Publikasi Ilmiah Nusantara
ISSN : -     EISSN : 3090787X     DOI : https://doi.org/10.70716/jocsit
Core Subject : Science,
Computer Science & IT
Journal of Computer Science and Information Technology (JOCSIT) is a scientific journal in computers that contains research results and literature studies, managed by Lembaga Publikasi Ilmiah Nusantara. JOCSIT journal provides a platform for researchers, academics, professionals, practitioners and students to embed and share knowledge in the form of empirical and theoretical research papers, case studies, literature reviews and book reviews related to computer science and information technology research, and or related to it with a range of themes such as Biomedical Application Computer Network and Architecture, Data Mining, E-Business, E-Commerce, E-Government E-Learning, Embedded Systems, Environmental Systems, Fuzzy Logics, Genetic Algorithms, Geographic Information System, High-Performance Computing, Human-Computer Interaction, Image Processing, Internet of Things (IoT), Computer Vision, Information Security, Information Retrieval, Modeling System and Control, Mobile Technology, Neural Networks, Pattern Recognition, Remote Sensing, Robotics, Signal Processing, Smart Home, Smart Sensor Networks. This journal will process all receipts of the script in a double-anonymized review by Bestari partners.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 30 Documents
 1   2   3 
Design and Development of a Mobile-Based E-Tourism Application for Promoting Tourism Destinations in Lombok Irwan Prasetya; Mei Lin Chen; Ahmad Fauzi
Journal of Computer Science and Information Technology Vol. 2 No. 2 (2026): Journal of Computer Science and Information Technology, June 2026
Publisher : Lembaga Publikasi Ilmiah Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70716/jocsit.v2i2.552

Abstract

The advancement of mobile technology has driven digital transformation in the tourism sector, including Lombok Island, which has high tourism potential but still faces limitations in information access and integrated services. This study aims to design and develop a mobile-based e-tourism application to enhance the promotion and accessibility of tourist destinations in Lombok. The research method employs a software engineering approach using the waterfall model, including requirement analysis, system design, implementation, and testing. Data were collected through literature studies and observation of user needs. The results indicate that the developed application provides features such as GPS-based location search, tourism recommendations, multimedia information, and integration with local services. System testing shows good usability and potential to increase tourist visits. In conclusion, mobile-based e-tourism applications can serve as an effective solution to support digital and sustainable tourism promotion in Lombok.
Design and Development of an IoT-Based Smart Farming System for Corn Plant Monitoring in Sumbawa Bayu Pratama; Satria Wijaya; Faiza Irfan
Journal of Computer Science and Information Technology Vol. 2 No. 2 (2026): Journal of Computer Science and Information Technology, June 2026
Publisher : Lembaga Publikasi Ilmiah Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70716/jocsit.v2i2.557

Abstract

The development of Internet of Things (IoT) technology has provided significant opportunities to improve agricultural efficiency, particularly in corn farming in Sumbawa, which faces challenges related to climate variability and irrigation management. This study aims to design and implement an IoT-based smart farming system capable of monitoring environmental conditions in real-time. The research employs a prototyping approach by integrating soil moisture, temperature, and pH sensors connected to a cloud-based platform. The results indicate that the system improves water usage efficiency by up to 25% and achieves sensor accuracy of approximately 95%. Additionally, the system enables farmers to make data-driven decisions more effectively. Therefore, the implementation of IoT in corn farming in Sumbawa has proven to enhance productivity and resource efficiency.
Early Warning System for Forest and Land Fires in Sumatra Using Computer Vision and Remote Sensing Data Satria Dwi Nanda; Nur Aisyah Ahmad
Journal of Computer Science and Information Technology Vol. 2 No. 2 (2026): Journal of Computer Science and Information Technology, June 2026
Publisher : Lembaga Publikasi Ilmiah Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70716/jocsit.v2i2.592

Abstract

Forest and land fires in Sumatra pose significant environmental, health, and economic challenges. This study aims to develop an early warning system by integrating computer vision and remote sensing data to improve real-time fire detection accuracy. The method utilizes image processing techniques based on YOLO and CNN algorithms, combined with MODIS and Landsat satellite data for hotspot monitoring. Data analysis is conducted using machine learning approaches and multi-source data integration. The results indicate that the proposed system achieves detection accuracy above 90% and provides earlier warnings compared to conventional methods. The integration of drone imagery and satellite data proves effective in detecting fires at an early stage. This research contributes to the advancement of intelligent fire monitoring systems to support disaster mitigation efforts in Indonesia.
Development of a Web-Based Geographic Information System for Mapping MSME Locations Aditya Dwi Ramadhan; Nabila Iskandar; Muhammad Aiman Hakim
Journal of Computer Science and Information Technology Vol. 2 No. 2 (2026): Journal of Computer Science and Information Technology, June 2026
Publisher : Lembaga Publikasi Ilmiah Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70716/jocsit.v2i2.608

Abstract

The advancement of information technology has encouraged the utilization of web-based Geographic Information Systems (GIS) to support the management and promotion of Micro, Small, and Medium Enterprises (MSMEs). This study aims to develop a web-based GIS capable of mapping MSME locations interactively, informatively, and accessibly. The research method adopts the waterfall software development model, including requirement analysis, system design, implementation, and testing. Data were collected through observation, interviews, and literature review. The system was developed using web technologies such as PHP, Laravel framework, and digital map integration with Leaflet and Mapbox. The results indicate that the system effectively presents spatial and non-spatial MSME information, equipped with search features, category filters, and navigation tools. System testing shows a high success rate and positive user responses. Therefore, this system can improve accessibility of MSME information and support location-based decision-making.
Prediksi Kebutuhan Rawat Inap Pasien Berdasarkan Data Hematologi Menggunakan Random Forest dengan Hyperparameter Optimization dan SHAP Explainability Milla Akbarany Baktiar Putri Putri; Hana Titania Sastrian; Muhammad Erlangga Kurniawan; Andri Fauzan Adziima; Kartika Maulida Hindrayani; Muhammad Zulhaj Aliansyah
Journal of Computer Science and Information Technology Vol. 2 No. 2 (2026): Journal of Computer Science and Information Technology, June 2026
Publisher : Lembaga Publikasi Ilmiah Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70716/jocsit.v2i2.650

Abstract

Determining whether a patient requires inpatient or outpatient care is one of the most critical clinical decisions in healthcare facility management. Complete blood count (CBC) parameters provide routine and rapidly available physiological indicators, making them strong candidates for machine learning-based clinical decision support systems. This study aims to develop a prediction model for patient hospitalization needs using the Random Forest algorithm optimized through RandomizedSearchCV, combined with SHAP (SHapley Additive exPlanations) for model interpretability. The dataset consists of 4,412 patient records from an Indonesian private hospital available on Kaggle, containing nine hematological parameters and two demographic attributes. Feature engineering was applied by constructing three derived variables: leucocyte-thrombocyte ratio (leu_throm_ratio), hemoglobin-hematocrit ratio (hb_hct_ratio), and thrombocyte-age interaction (platelet_age). Two models were compared: a baseline Random Forest with manually configured hyperparameters and an optimized model using RandomizedSearchCV with Stratified 5-Fold Cross Validation. The baseline model achieved accuracy of .7633 and ROC AUC of .8097, while the optimized model yielded accuracy of .7644 and ROC AUC of .8131 on the test set. Feature importance analysis identified thrombocyte (.1655) and leu_throm_ratio (.1525) as the dominant predictors, together contributing over 31% of the model's predictive information. SHAP analysis confirmed that low thrombocyte values and high leucocyte values were the primary drivers of inpatient predictions, consistent with clinical indicators of infection and systemic inflammation. These findings demonstrate that Random Forest with clinically grounded feature engineering and SHAP interpretability provides a transparent and reasonably accurate approach for supporting hospital admission triage decisions.
Analysis of Student Engagement Levels in E-Learning Using Clustering Methods Aoni Aslihatin; Nisreen Alzahrani; Alejandro Mozo Quesada
Journal of Computer Science and Information Technology Vol. 2 No. 3 (2026): Journal of Computer Science and Information Technology, September 2026
Publisher : Lembaga Publikasi Ilmiah Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70716/jocsit.v2i3.550

Abstract

The rapid growth of e-learning has increased the need to analyze student engagement levels in online learning environments. This study aims to analyze student activity levels using a clustering method based on activity log data from a Learning Management System (LMS). The approach applied is K-Means Clustering with an exploratory method on student activity data, including frequency of access to learning materials, discussion forum participation, assignment submission, and duration of learning activities. The sample consisted of 200 Informatics Engineering students selected through purposive sampling, with data collected over one academic semester. The optimal number of clusters was determined using the elbow method, while cluster quality was evaluated using the Silhouette Score. The results show that students can be grouped into three main clusters: high, medium, and low engagement levels. The high-engagement cluster showed consistent participation and potential correlation with better academic performance, while the low-engagement cluster indicated a higher risk of academic difficulty. These findings are consistent with previous studies showing that interaction levels are strongly correlated with academic performance. Clustering methods proved effective in automatically identifying student behavior patterns, thereby supporting the development of data-driven adaptive learning strategies.
Adaptive AI Guardian: An Explainable Deep Learning System for Real-Time Cyber Threat Detection Fauzan Rahman; Michael James Anderson; Lucas Wei Chen
Journal of Computer Science and Information Technology Vol. 2 No. 3 (2026): Journal of Computer Science and Information Technology, September 2026
Publisher : Lembaga Publikasi Ilmiah Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70716/jocsit.v2i3.824

Abstract

The increasing complexity, frequency, and adaptability of cyber threats require intrusion detection systems (IDSs) that can identify malicious activity rapidly while providing interpretable evidence for security analysts. Conventional machine-learning and deep-learning IDSs have demonstrated strong detection capabilities, but their black-box nature can limit operational trust, particularly when security decisions must be made in real time. This study develops Adaptive AI Guardian, an explainable deep-learning framework designed to integrate adaptive threat detection with post-hoc model interpretation. The proposed framework combines network traffic preprocessing, deep-learning-based intrusion classification, adaptive threat profiling, and Explainable Artificial Intelligence (XAI) using SHAP and LIME. The study adopts a design-and-development research approach based on publicly available cybersecurity datasets, with a multidimensional evaluation covering accuracy, precision, recall, F1-score, false-positive rate, inference latency, throughput, and explanation consistency. The proposed architecture is designed to distinguish normal from malicious traffic while identifying the principal features contributing to each prediction. The framework addresses limitations identified in prior studies concerning explainability, evolving attacks, false positives, scalability, and real-time deployment. The manuscript does not yet report empirical measurements for these indicators; therefore, the study does not claim quantitative superiority over existing IDS approaches. Instead, its main contribution is the development of an integrated architecture and evaluation framework ready for subsequent empirical validation, including cross-dataset testing, concept-drift analysis, adversarial robustness, and real-time deployment assessment. The framework is expected to serve as a foundation for developing trustworthy adaptive IDSs for enterprise networks, Internet of Things environments, and emerging cyber-physical infrastructures.
EduAI Personalized Learning System: A Large Language Model-Based Adaptive Learning System to Enhance the Effectiveness of Digital Education Ahmad Fauzan Saputra; Muhammad Rizky Pratama; Daniel James Anderson
Journal of Computer Science and Information Technology Vol. 2 No. 3 (2026): Journal of Computer Science and Information Technology, September 2026
Publisher : Lembaga Publikasi Ilmiah Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70716/jocsit.v2i3.830

Abstract

Digital education has expanded access to learning resources, but conventional digital learning environments frequently provide standardized content that does not adequately accommodate differences in learners' knowledge, learning pace, interests, and proficiency levels. Recent advances in large language models (LLMs) provide opportunities to develop adaptive educational systems capable of dynamically generating learning materials, explanations, feedback, and learning pathways. This study aims to develop the conceptual architecture of EduAI Personalized Learning System, an LLM-based adaptive learning system designed to support individualized digital learning. The study employed a design-oriented developmental approach consisting of needs identification, literature-informed system design, adaptive learning architecture development, and functional analysis. The proposed system integrates learner profiling, learning-path recommendation, LLM-based content generation, formative assessment, personalized feedback, and continuous learner-model updating. The analysis indicates that LLMs can provide a flexible interaction layer for adaptive learning while analytics and learner models provide the personalization mechanism. However, issues concerning hallucination, bias, privacy, pedagogical alignment, and excessive dependence on automated tutoring require explicit governance mechanisms. The proposed EduAI architecture therefore combines generative capabilities with learner analytics, knowledge representation, assessment, and human oversight. The study contributes an integrated conceptual framework for implementing LLM-powered personalized learning in digital education and provides a foundation for subsequent empirical evaluation.
Application of Machine Learning for Anomaly Detection in Network Traffic to Enhance Cybersecurity Fajar Maulana Putra; Kevin Jonathan; Ahmad Fauzan Ramadhan
Journal of Computer Science and Information Technology Vol. 2 No. 3 (2026): Journal of Computer Science and Information Technology, September 2026
Publisher : Lembaga Publikasi Ilmiah Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70716/jocsit.v2i3.841

Abstract

The increasing volume and complexity of network traffic have created significant challenges for cybersecurity, particularly in identifying abnormal activities that may indicate security threats. Machine learning has emerged as an important approach for network anomaly detection because it can identify complex traffic patterns and support automated threat detection. This study aims to examine the application of machine learning for anomaly detection in network traffic and analyze its contribution to cybersecurity. The study employed a structured literature review and comparative qualitative synthesis based on 27 scientific publications published between 2024 and 2026. The analysis focused on conventional machine learning, deep learning, ensemble learning, hybrid approaches, real-time detection, adaptive detection, and scalable network anomaly detection. The empirical evidence shows that algorithm performance varies according to the dataset and evaluation context. Pai et al. (2025) reported accuracies of 98.28% for K-nearest neighbors, 97.00% for random forest, 96.62% for gradient boosting, 87.95% for support vector machine, and 85.59% for logistic regression on the CICIDS2017 dataset. Their hybrid ensemble stacking approach achieved 98.79% accuracy. Ness et al. (2025) reported 1.00 training accuracy and 0.85 test accuracy for LightGBM, demonstrating the importance of evaluating model generalization. The study concludes that machine learning can strengthen network anomaly detection, but model selection must consider data characteristics, feature complexity, class imbalance, scalability, and real-time processing requirements.
Waste Detection and Classification Using Computer Vision to Support Smart Waste Management Systems Fikri Maulana; Anissa Fitri Hapsari; Daniel Kwame Mensah
Journal of Computer Science and Information Technology Vol. 2 No. 3 (2026): Journal of Computer Science and Information Technology, September 2026
Publisher : Lembaga Publikasi Ilmiah Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70716/jocsit.v2i3.848

Abstract

The increasing complexity of solid waste requires intelligent and efficient systems to support waste detection, classification, and management. This study aims to synthesize the development of computer vision-based waste detection and classification technologies and examine their contribution to smart waste management systems. The study employed a structured literature-based design using 19 scientific publications published between 2018 and 2026. The selected publications were analyzed through qualitative content analysis and comparative synthesis based on technological orientation, computational approach, primary task, implementation context, and reported contribution. The findings indicate a technological progression from convolutional neural network-based image classification and transfer learning toward object localization, real-time detection, and YOLO-based approaches. Recent studies also demonstrate increasing integration between computer vision, Internet of Things infrastructure, embedded computing, automated sorting, and cloud-based deployment. The analysis identifies dataset diversity, environmental variability, object overlap, computational efficiency, and deployment architecture as recurring challenges affecting practical implementation. The findings suggest that computer vision should be developed as an integrated component of smart waste management systems rather than as an isolated classification model. Effective implementation requires alignment between visual recognition capability, computational resources, communication infrastructure, and operational requirements. This study provides a structured synthesis of technological developments and highlights directions for developing more adaptive, scalable, and practically applicable computer vision-based waste management systems.

Page 3 of 3 | Total Record : 30

 1   2   3 

Filter by Year

2025 2026


Reset
Filter By Issues
All Issue Vol. 2 No. 3 (2026): Journal of Computer Science and Information Technology, September 2026 Vol. 2 No. 2 (2026): Journal of Computer Science and Information Technology, June 2026 Vol. 2 No. 1 (2026): Journal of Computer Science and Information Technology, March 2026 Vol. 1 No. 3 (2025): Journal of Computer Science and Information Technology, December 2025 Vol. 1 No. 2 (2025): Journal of Computer Science and Information Technology, September 2025 Vol. 1 No. 1 (2025): Journal of Computer Science and Information Technology, June 2025