cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Supiyandi
Contact Email
supiyandiyt@gmail.com
Phone
+628111261633
Journal Mail Official
ejocsaic@gmail.com
Editorial Address
Jl. Gurilla No. 2 Sidorejo Kec. Medan Tembung Kota Medan 20222
Location
Kota medan,
Sumatera utara
INDONESIA
Journal of Computer Science Artificial Intelligence and Communications
Published by CV. Raskha Media Group
ISSN : 31093981     EISSN : 31089828     DOI : -
Core Subject : Science, Engineering,
Computer Science & IT Earth & Planetary Sciences Engineering
Journal of Computer Science Artificial Intelligence and Communications is a multidisciplinary, peer-reviewed journal dedicated to advancing research in computer science, artificial intelligence (AI), and communication technologies. The journal publishes high-quality original articles, reviews, and case studies that explore the latest innovations, theories, algorithms, and applications shaping the digital world. Focused on the intersection of computational systems, intelligent automation, and seamless communication networks, JOCSAIC aims to foster collaboration and knowledge exchange among researchers, practitioners, and academics working across diverse sectors such as data science, machine learning, telecommunications, and intelligent systems. The journal is a key resource for cutting-edge developments and trends in these transformative fields.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 28 Documents
 1   2   3 
Evaluation of the Usability of the Academic Information System Using the System Usability Scale (SUS) Method Rahardian, Rifky Lana; Khodijah, Siti; Rizki, Cindy Atika
Journal of Computer Science, Artificial Intelligence and Communications Vol 2 No 2 (2025): November 2025
Publisher : Raskha Media Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64803/jocsaic.v2i2.62

Abstract

The increasing reliance on digital platforms in higher education necessitates the evaluation of system usability to ensure effective user interaction and satisfaction. This study aims to evaluate the usability of the Academic Information System (AIS) at [University Name] using the System Usability Scale (SUS) method. SUS is a reliable, standardized tool for measuring the usability of interactive systems, providing a quick and quantitative assessment. Data were collected from a sample of 100 students and academic staff who frequently use the AIS for various academic activities, including course registration, grade checking, and academic planning. The results of the SUS analysis yielded an average score of 72.5, indicating that the system falls within the “Good” usability category. However, several usability issues were identified, such as navigation complexity and visual layout inconsistencies, which slightly reduced user satisfaction. These findings highlight the importance of continuous usability testing and user-centered design in the development of academic systems. The study recommends specific design improvements to enhance user experience and system performance. Overall, the SUS method proved effective in identifying usability strengths and weaknesses, offering valuable insights for future system optimization.
Development of an Employee Performance Monitoring Information System Using a Web-Based Interactive Dashboard Prayoga, Abil Alwi; Hasanuddin, Muhammad; Khodijah, Siti; Rizki, Cindy Atika; PA, Dahrim
Journal of Computer Science, Artificial Intelligence and Communications Vol 2 No 2 (2025): November 2025
Publisher : Raskha Media Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64803/jocsaic.v2i2.63

Abstract

This research aims to develop an employee performance monitoring information system that utilizes a web-based interactive dashboard to enhance decision-making and managerial oversight. In many organizations, traditional performance evaluation methods are often time-consuming, static, and lack real-time insight, resulting in inefficiencies in performance tracking. To address these challenges, the proposed system is designed to provide dynamic visualization of key performance indicators (KPIs), attendance records, task completion rates, and other critical metrics through an interactive and user-friendly dashboard interface. The development process follows the Waterfall methodology, encompassing stages of requirements analysis, system design, implementation, testing, and deployment. The system was built using PHP and JavaScript for front-end interactivity, with a MySQL database to manage data storage. The dashboard includes various visual tools such as graphs, charts, and progress bars to facilitate real-time monitoring and performance analysis. Testing results indicate that the system performs effectively, offering accurate and timely information that supports employee evaluation and organizational planning. User feedback also reveals a high level of satisfaction due to the dashboard's ease of use and responsiveness. Overall, the implementation of this web-based performance monitoring system is expected to improve transparency, accountability, and productivity within the organization.
Machine Learning and Deep Learning Approaches for Weather Forecasting in IoT-Based Systems: A Review Hasanur Mohammad Firdausi
Journal of Computer Science, Artificial Intelligence and Communications Vol 3 No 1 (2026): May 2026
Publisher : Raskha Media Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64803/jocsaic.v3i1.141

Abstract

Weather forecasting is important across many fields, including agriculture, transportation, energy, and disaster management. Because meteorological data is not linear or dynamic and changes over time, it is hard to predict the weather. Technological advances have made machine learning and deep learning methods more common for improving the accuracy of weather forecasts. Additionally, connectivity with the Internet of Things (IoT) enables real-time data collection through various environmental sensors. This study conducted a comprehensive literature review of machine learning, deep learning, and hybrid methodologies for IoT-based weather prediction systems. The methodologies analyzed included Random Forest, Support Vector Machine, Artificial Neural Network, Long Short-Term Memory, Gated Recurrent Unit, Convolutional Neural Network, and Transformer. The results showed that deep learning and hybrid models performed better than traditional methods, especially for finding temporal patterns and non-linear correlations. Still, other issues need to be addressed, such as data quality, model complexity, high processing requirements, and limitations on how quickly it can adapt. As a result, combining AI and IoT has significant potential to make weather forecasting systems more accurate, flexible, and timely, especially for early warning systems based on data.
Wireless Network Security Analysis Using the Penetration Testing Method in a Campus Environment Abil Alwi Prayoga; Siti Khodijah
Journal of Computer Science, Artificial Intelligence and Communications Vol 3 No 1 (2026): May 2026
Publisher : Raskha Media Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64803/jocsaic.v3i1.173

Abstract

The rapid development of information technology has increased the utilization of wireless networks in higher education environments to support academic activities, administrative services, and digital communication. However, the widespread use of wireless networks also introduces various cybersecurity risks due to the open nature of wireless communication media. This study aims to analyze the security level of campus wireless networks using the penetration testing method to identify vulnerabilities and evaluate existing security mechanisms. The research applies a systematic penetration testing approach consisting of several stages, including information gathering, scanning, vulnerability assessment, exploitation testing, and reporting. The testing process focuses on analyzing wireless configurations, authentication mechanisms, encryption implementation, and potential unauthorized access risks. The results indicate that although the campus wireless network has implemented security protocols such as WPA/WPA2 and encryption mechanisms, several vulnerabilities remain, particularly related to weak password policies, limited access control, and insufficient network monitoring. Based on the vulnerability assessment, improvements are recommended through the implementation of stronger authentication methods, enhanced password management policies, continuous network monitoring, and periodic security evaluations. This research demonstrates that penetration testing is an effective method for identifying security weaknesses and improving wireless network protection. The findings are expected to provide valuable insights for educational institutions in developing more secure, reliable, and sustainable wireless network infrastructures.
Explainable Artificial Intelligence for Student Academic Performance Prediction Using Random Forest and SHAP Wahyu Nugraha; Rabiatus Sa’adah; Muhammad Hasanuddin
Journal of Computer Science, Artificial Intelligence and Communications Vol 3 No 1 (2026): May 2026
Publisher : Raskha Media Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64803/jocsaic.v3i1.174

Abstract

Predicting student academic performance has become an important application of educational data mining because it enables educational institutions to identify students who require academic support at an early stage. Although machine learning algorithms have demonstrated high predictive capability, many predictive models operate as black-box systems, making it difficult for educators to understand the factors influencing prediction outcomes. This study proposes an Explainable Artificial Intelligence (XAI) framework for student academic performance prediction by integrating the Random Forest algorithm with SHapley Additive exPlanations (SHAP). The proposed methodology consists of data collection, data preprocessing, feature selection, model development, performance evaluation, and model interpretation. Random Forest was employed as the primary classification algorithm due to its robustness and high predictive performance, while SHAP was utilized to provide transparent explanations of both global and local prediction results. The experimental evaluation demonstrated that the proposed model achieved high classification performance, obtaining an accuracy of 91.67%, precision of 90.32%, recall of 93.33%, and an F1-score of 91.80%. Furthermore, SHAP analysis identified Previous GPA, Final Examination Score, Attendance, Assignment Score, and Study Hours as the most influential factors affecting student academic performance. The integration of Random Forest and SHAP not only improves prediction reliability but also enhances model transparency by explaining the contribution of each feature to prediction outcomes. Consequently, the proposed framework supports evidence-based academic decision-making, facilitates early identification of at-risk students, and provides educators with interpretable insights for designing effective academic intervention strategies. These findings demonstrate that Explainable Artificial Intelligence can significantly improve the practical applicability and trustworthiness of machine learning models in educational environments.
Explainable Artificial Intelligence-Based Early Warning System for Student Dropout Prediction Aan Ansen Andryadi; Samsan; Gilang Redzav Bagaswara
Journal of Computer Science, Artificial Intelligence and Communications Vol 3 No 1 (2026): May 2026
Publisher : Raskha Media Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64803/jocsaic.v3i1.177

Abstract

Student dropout remains one of the major challenges faced by higher education institutions because it negatively affects academic performance, institutional reputation, and educational sustainability. Early identification of students at risk of dropping out enables universities to implement timely interventions that improve student retention. Although machine learning models have demonstrated promising predictive performance, many of these approaches operate as black-box systems, limiting their transparency and practical adoption in educational decision-making. Therefore, this study proposes an Explainable Artificial Intelligence (XAI)-Based Early Warning System for student dropout prediction by integrating the XGBoost classification algorithm with SHapley Additive exPlanations (SHAP). The proposed framework consists of six stages: data collection, data preprocessing, feature engineering, machine learning model development, explainability analysis, and performance evaluation. To demonstrate the proposed methodology, a synthetic dataset representing higher education student records was utilized. The simulated experimental results showed that the proposed model achieved an Accuracy of 89.5%, Precision of 84.0%, Recall of 82.0%, F1-Score of 83.0%, and an ROC-AUC of 0.93. Furthermore, SHAP analysis identified Grade Point Average (GPA), Attendance Rate, Previous Semester GPA, Financial Status, and Learning Management System (LMS) activity as the most influential factors affecting student dropout prediction. By combining high predictive performance with interpretable explanations, the proposed Early Warning System provides transparent decision support for lecturers and academic advisors, facilitating data-driven interventions aimed at improving student retention in higher education institutions.
Detection of AI-Generated Text in Academic Writing Using Transformer-Based Models Cindy Atika Rizki; Nabila Khairuniza; Mel Wulandini
Journal of Computer Science, Artificial Intelligence and Communications Vol 3 No 1 (2026): May 2026
Publisher : Raskha Media Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64803/jocsaic.v3i1.178

Abstract

The rapid advancement of generative artificial intelligence (AI), particularly large language models (LLMs), has significantly transformed academic writing by enabling the automatic generation of coherent and contextually relevant text. While these technologies improve writing efficiency and accessibility, they also raise serious concerns regarding academic integrity, originality, and authorship. Conventional plagiarism detection tools are ineffective in identifying AI-generated content because such text is often original rather than copied. This study proposes a transformer-based approach for detecting AI-generated text in academic writing by evaluating the performance of four pre-trained language models: BERT, RoBERTa, DistilBERT, and DeBERTa. The research methodology consists of dataset collection, text preprocessing, dataset splitting, transformer model fine-tuning, and performance evaluation using Accuracy, Precision, Recall, F1-score, and ROC-AUC. Experimental results show that all evaluated transformer models achieved excellent classification performance, with DeBERTa producing the highest accuracy of 98.10%, followed by RoBERTa (97.20%), BERT (95.10%), and DistilBERT (93.40%). These findings demonstrate that transformer-based architectures effectively capture contextual and semantic characteristics that distinguish AI-generated text from human-authored academic writing. The proposed approach provides a reliable solution for supporting academic integrity and assisting educators, publishers, and research institutions in detecting AI-generated content within scholarly documents.
Web Scraping Design for Text Data Acquisition on Platform X in Adolescent Sexual Deviant Behavior Research Yanti Yusman; Noor Anida Zaria Mohd Noor
Journal of Computer Science, Artificial Intelligence and Communications Vol 3 No 1 (2026): May 2026
Publisher : Raskha Media Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64803/jocsaic.v3i1.182

Abstract

The increasing use of social media among adolescents has generated vast amounts of digital textual data that can be utilized to investigate online behavioral phenomena, including discussions related to sexual behavior. As one of the most active social media platforms, X provides a rich source of publicly available textual information that reflects users' interactions, opinions, and behavioral expressions. However, obtaining high-quality textual data for behavioral research requires a systematic, transparent, and reproducible data acquisition process. This study aims to design a web scraping framework for acquiring textual data from Platform X to support research on adolescent sexual behavior deviance. The research adopts a Design Science Research (DSR) approach to develop a structured data acquisition pipeline consisting of requirement analysis, keyword formulation, web scraping design, data harvesting, data preprocessing, and dataset construction. The proposed framework emphasizes methodological rigor by integrating data quality assessment, reproducibility, and ethical considerations throughout the data acquisition process. The resulting dataset comprises structured textual data and relevant metadata that are prepared for subsequent analytical stages, such as natural language processing, text mining, machine learning, and behavioral pattern analysis. Furthermore, the proposed web scraping framework provides a systematic approach for researchers to collect social media data efficiently while ensuring data consistency and traceability. This study contributes to the field of social media analytics by providing a replicable methodology for acquiring textual data from Platform X and establishing a reliable foundation for future research on adolescent online behavior and digital risk assessment. The findings are expected to facilitate the development of evidence-based analytical models for understanding behavioral patterns in digital environments while supporting future studies employing Big Data Analytics and Computational Social Science.

Page 3 of 3 | Total Record : 28

 1   2   3 

Filter by Year

2024 2026


Reset
Filter By Issues
All Issue Vol 3 No 1 (2026): May 2026 Vol 2 No 2 (2025): November 2025 Vol 2 No 1 (2025): May 2025 Vol 1 No 2 (2024): November 2024 Vol 1 No 1 (2024): May 2024