cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Jamaluddin
Contact Email
hengkitamando26@gmail.com
Phone
+6281397181985
Journal Mail Official
publication.aptikomsumut@gmail.com
Editorial Address
Jl. Alumni No.3, Padang Bulan, Kec. Medan Baru, Kota Medan, Sumatera Utara 20155
Location
Kota medan,
Sumatera utara
INDONESIA
Journal of Computer Science and Research
Published by Asosiasi Perguruan Tinggi Informatika dan Ilmu Komputer Provinsi Sumatera Utara
ISSN : -     EISSN : 29862337     DOI : -
Core Subject : Economy, Science, Engineering,
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Library & Information Science
Journal of Computer Science and Research (JoCoSiR) is aimed to publish research articles on theoretical foundations of information and computation, and of practical techniques for their implementation and application in computer systems. Journal of Computer Science and Research (JoCoSiR) published quarterly and is a peer reviewed journal covers the latest and most compelling research of the time. Journal of Computer Science and Research (JoCoSiR) is managed and published by APTIKOM Wilayah 1 Sumatera Utara.
Arjuna Subject : Ilmu Komputer (semua kategori) - Kecerdasan Buatan
Articles 63 Documents
 3   4   5   6   7 
Comparative Analysis of Dijkstra and A* Algorithms for Determining the Shortest Route from SMKN 9 Medan to Gramedia Gajah Mada Ardiansyah, Ardiansyah
Journal of Computer Science and Research (JoCoSiR) Vol. 3 No. 2 (2025): April: Artificial Intelligence
Publisher : Asosiasi Perguruan Tinggi Informatika dan Ilmu Komputer (APTIKOM) Provinsi Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Determining the shortest route is an important problem in navigation system development, especially in urban environments with complex road networks. This study aims to compare the performance of the Dijkstra algorithm and the A* algorithm in finding the shortest route from SMKN 9 Medan to Gramedia Gajah Mada. Distance data between nodes and heuristic values were obtained from Google Maps and represented in a graph structure for route computation. Both algorithms were applied to three predetermined route alternatives. The results show that Dijkstra and A* produced the same optimal route, namely A–B–E–G, with a total distance of 5.7 km. However, the A* algorithm demonstrated higher efficiency by exploring fewer nodes and requiring less computational time due to the use of a heuristic function. Therefore, the A* algorithm is more suitable for intelligent navigation systems requiring faster computation, while the Dijkstra algorithm is more appropriate for smaller networks without heuristic considerations.
Machine Learning-Based Customer Segmentation and Behavioral Analysis Using K-Means Clustering Ade Guna Suteja
Journal of Computer Science and Research (JoCoSiR) Vol. 3 No. 2 (2025): April: Artificial Intelligence
Publisher : Asosiasi Perguruan Tinggi Informatika dan Ilmu Komputer (APTIKOM) Provinsi Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The rapid growth of transactional data in retail and e-commerce has created opportunities to understand customer purchasing behavior through Market Basket Analysis (MBA). This study applies the Apriori algorithm to identify product association patterns within transactional databases and evaluates the effectiveness of including product category parameters to enhance product package recommendations. A quantitative approach with an applied experimental method is used to systematically process and analyze transactional data. The study involves data preprocessing, application of the Apriori algorithm to generate frequent itemsets and association rules, and visualization of the results. Findings indicate that the algorithm successfully discovers frequently co-purchased product combinations, and the inclusion of product categories improves the relevance and quality of the resulting recommendations. This research provides practical benefits for businesses, such as guiding cross-selling strategies, optimizing inventory management, and enhancing customer satisfaction. Additionally, it contributes to the theoretical development of data mining applications in retail. The results suggest that leveraging association rules with enhanced parameters can support more effective marketing strategies and evidence-based decision-making in dynamic transactional environments.  
Sentiment Analysis of Indonesian TikTok Comments Using TF‑IDF with Naive Bayes and SVM Rambe, Rezkinah; Iqbal, Muhammad
Journal of Computer Science and Research (JoCoSiR) Vol. 3 No. 2 (2025): April: Artificial Intelligence
Publisher : Asosiasi Perguruan Tinggi Informatika dan Ilmu Komputer (APTIKOM) Provinsi Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This study aims to develop an automatic sentiment classification model for Indonesian TikTok comments using Term Frequency–Inverse Document Frequency (TF‑IDF) with Naive Bayes and Support Vector Machine (SVM). Fifteen thousand comments were collected from public TikTok videos and manually labeled as positive, negative, and neutral. Data preprocessing included case folding, tokenization, stopword removal, and stemming (Nazief‑Adriani algorithm). TF‑IDF weighting transformed text into vectors, then used to train both classifiers. Performance was evaluated using accuracy, precision, recall, and F1-score trough 5-fold cross-validation. Result show SVM outperforms Naive Bayes with 92.8% accuracy versus 83%. Findings confirm that TF-IDF combined with SVM produces more relieble result for short Indonesian text classification, offering valuable insights for social media monitoring applications.
Multivariate Analysis and Neural Network-Based Prediction of Compression Molding Behavior in Plantain–Bamboo Fiber Reinforced HDPE Composites Obiora Jeremiah Obiafudo; Joseph Achebo; Kessington Obahiagbon; Frank. O. Uwoghiren; Callistus Nkemjika Chukwu
Journal of Computer Science and Research (JoCoSiR) Vol. 3 No. 1 (2025): Jan: Computer Science
Publisher : Asosiasi Perguruan Tinggi Informatika dan Ilmu Komputer (APTIKOM) Provinsi Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The compression molding behavior of plantain–bamboo fiber reinforced high-density polyethylene (HDPE) composites was studied through an integrated multivariate analysis and neural network modelling framework. The study utilized materials for fiber extraction and composite production, including water, alkali (NaOH), acetic acid, acetic anhydride, maleic anhydride grafted PE, hydrogen peroxide, hypochlorite, and caustic soda. The composite matrix was high-density polyethylene with density (0.96 g/cm³), reinforced with activated plantain and bamboo fibers. Methods involved mechanical extraction, chemical treatment using alkali solutions, neutralization, bleaching, and stabilization. Fibers were oven-dried, milled, and sieved to (75 μm) before composite formation. Process variables such as fiber fraction (10–50%) and temperature (150–190°C) informed the experimental design. A feed-forward neural network (5-5-5) was used for modelling system performance. The multivariate analysis used predictive neural network models to study combined process-variable effects during compression molding. Interaction plots were generated by varying fiber volume fraction (VF) against other variables. Results showed that high yield stress near (90 MPa) occurred at low VF (10–20%) when bamboo fiber ratio (BFR) was maintained at (40–60%). Pure plantain fiber outperformed pure bamboo at (0) and (1.0 BFR). Optimal molding temperature ranged (166–174°C), producing high yield stress even at VF (10%). At low temperatures (150°C) and VF (30%), yield stress exceeded (80 MPa). Maximum strength required holding times (>17 min) and low clamping force (<1900 N). Neural network predictions aligned closely with experimental data, demonstrating strong predictive reliability. This integrated statistical–computational approach provides valuable insights for optimizing natural fiber composite manufacturing and reducing experimental cost.
The use of Artificial Intelligence (AI) tool by lecturers in the teaching and learning of English language in Federal College of Education (Technical) Omoku and Federal College of Education (Technical) Umunze Assimonye, Augusta Chiedu; Chinasa Florence Okoh
Journal of Computer Science and Research (JoCoSiR) Vol. 2 No. 4 (2024): October: Artificial Intelligence
Publisher : Asosiasi Perguruan Tinggi Informatika dan Ilmu Komputer (APTIKOM) Provinsi Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

In recent years, the integration of Artificial Intelligence (AI) in education has transformed how teachers and students interact with learning materials. However, in many teacher education institutions in Nigeria, the use of AI tools in language instruction remains limited and uneven. Lecturers often rely on traditional methods, which restrict students’ exposure to innovative learning technologies that could enhance writing, grammar, comprehension, and communication skills. This gap raises concern about how effectively lecturers are adopting AI to support English Language teaching and learning in Colleges of Education. The study used a descriptive survey design to explore how lecturers and students perceived the use of artificial intelligence in teaching English Language. It was conducted in the Federal Colleges of Education (Technical) at Omoku in Rivers State and Umunze in Anambra State, involving forty-four participants—seventeen lecturers and twenty-seven final-year students. Data were collected through a validated and reliable structured questionnaire analyzed using mean and standard deviation to determine agreement levels on issues relating to AI use in English Language education. The results revealed that lecturers moderately used artificial intelligence (AI) tools in teaching English Language in the Federal Colleges of Education (Technical) at Omoku and Umunze. Findings showed strong agreement that AI supported grammar and punctuation correction (Mean = 3.57, SD = 0.78) and provided instant feedback on assignments (Mean = 2.96, SD = 0.52). The grand mean (3.02, SD = 0.74) indicated moderate adoption. Similarly, AI usage extent was modest (Grand Mean = 2.64, SD = 0.85), mainly in grammar (Mean = 2.50) and listening comprehension (Mean = 2.60), suggesting gradual but growing integration. The study concluded that while AI has begun to improve teaching effectiveness, its application remains limited. It recommended increased institutional support, lecturer training, and infrastructure development to promote full AI integration in English Language education.
Text Summarization of Online News Articles Using the Text Rank Algorithm Indra Marto Silaban
Journal of Computer Science and Research (JoCoSiR) Vol. 2 No. 4 (2024): October: Artificial Intelligence
Publisher : Asosiasi Perguruan Tinggi Informatika dan Ilmu Komputer (APTIKOM) Provinsi Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Text Summarization in online news media is useful for helping readers to get the essence of a news story. Summarization will be less effective if it is done manually by humans, so we need an application that can do summaries quickly and precisely. By utilizing preprocessing technics with sastrawi python library and the implementation of TextRank algorithm which is part of the extraction method, news that was previously long can be presented in a very concise form. This application is developed using the Python programming language with sastrawi libraries, nltk and StemmerFactory. While the framework used is Django as the backend and bootstrap as the frontend framework.
Trend Analysis and Job Classification in the Field of Artificial Intelligence Using the Support Vector Machine (SVM) Method Helmy, Ahmad; Muhammad Iqbal
Journal of Computer Science and Research (JoCoSiR) Vol. 2 No. 3 (2024): July: Artificial Intelligence
Publisher : Asosiasi Perguruan Tinggi Informatika dan Ilmu Komputer (APTIKOM) Provinsi Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The rapid advancement of Artificial Intelligence (AI) has significantly transformed the global job landscape, creating new opportunities while redefining existing roles. This study aims to analyze emerging trends and classify job roles in the AI domain using the Support Vector Machine (SVM) method. A dataset was collected from various online job marketplaces and professional platforms to identify key skills, qualifications, and job categories associated with AI-related professions. The data preprocessing involved text normalization, feature extraction using TF-IDF, and classification modeling through SVM. The experimental results demonstrate that the SVM model achieved high accuracy in categorizing AI-related occupations into predefined job clusters, such as Data Scientist, Machine Learning Engineer, AI Researcher, and AI Product Manager. Furthermore, the trend analysis revealed a growing demand for AI professionals with strong interdisciplinary skills combining data analytics, programming, and domain expertise. These findings provide insights for educational institutions, job seekers, and policymakers to align skill development strategies with the evolving needs of the AI workforce.
Predicting Public Health Risks Based on Lifestyle Factors Using the Support Vector Machine Andri, Andri Ismail Sitepu; Muhammad Iqbal
Journal of Computer Science and Research (JoCoSiR) Vol. 3 No. 3 (2025): July: Health Science Informatic
Publisher : Asosiasi Perguruan Tinggi Informatika dan Ilmu Komputer (APTIKOM) Provinsi Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Public health risks are often influenced by multiple lifestyle factors, such as age, diet, exercise, smoking, and alcohol consumption. This study aims to develop a predictive model for assessing individual health risks using the Support Vector Machine (SVM) algorithm. The dataset used consists of lifestyle attributes, including age, weight, height, exercise frequency, sleep duration, sugar intake, smoking habits, alcohol consumption, marital status, profession, and body mass index (BMI). The data were preprocessed through normalization and label encoding, followed by training and testing using a 70:30 data split. The SVM model employed the Radial Basis Function (RBF) kernel to capture non-linear relationships between variables. Experimental results show that the proposed SVM model achieved an accuracy of approximately 89%, demonstrating strong predictive capability. The confusion matrix analysis revealed that the model effectively distinguishes between high and low health risk categories, while the PCA visualization confirmed clear clustering of classified data. Moreover, the feature importance analysis indicated that age, smoking habits, BMI, and alcohol consumption were the most significant contributors to health risk prediction. Overall, the results suggest that the SVM algorithm is a robust and efficient approach for predicting public health risks based on lifestyle factors. This model can serve as a foundation for preventive health monitoring systems, providing valuable insights for promoting healthier lifestyles and supporting data-driven public health strategies.
Heart Disease Prediction Using Logistic Regression and Random Forest with SHAP Explainability Dimas Prayogi
Journal of Computer Science and Research (JoCoSiR) Vol. 3 No. 3 (2025): July: Health Science Informatic
Publisher : Asosiasi Perguruan Tinggi Informatika dan Ilmu Komputer (APTIKOM) Provinsi Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This study presents a web-based Heart Disease Prediction System developed using Logistic Regression and Random Forest algorithms, enhanced with SHAP explainability. The system predicts the likelihood of heart disease based on key clinical parameters such as age, sex, chest pain type, blood pressure, cholesterol, and heart rate. SHAP values are integrated to provide transparent and interpretable explanations of model predictions. The Random Forest model demonstrated superior performance in capturing nonlinear relationships compared to Logistic Regression. The web application offers an interactive and user-friendly interface that displays correlation heatmaps, feature importance plots, and SHAP visualizations to aid in clinical interpretation. The results indicate that chest pain type, ST depression, and exercise-induced angina are among the most influential predictors. The proposed system successfully achieves accurate and explainable heart disease prediction, contributing to early diagnosis and decision support in healthcare.
Comparative Study of Machine Learning Approaches Based on Artificial Neural Network, Regression, and Clustering for Diabetes Prediction Nauval Alfarizi; Adi Putra; Prima Lydia Yosophin Batubara; Satria Sinurat
Journal of Computer Science and Research (JoCoSiR) Vol. 3 No. 3 (2025): July: Health Science Informatic
Publisher : Asosiasi Perguruan Tinggi Informatika dan Ilmu Komputer (APTIKOM) Provinsi Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This study presents a comparative analysis of three machine learning model and algorithms Artificial Neural Network (ANN), Logistic Regression, and K-Means Clustering using the Pima Indians Diabetes dataset. The main objective is to evaluate the performance of supervised and unsupervised methods in predicting diabetes based on physiological and clinical features. he ANN model was developed using a feedforward and backpropagation approach, Logistic Regression applied the fundamental logit equation, and K-Means Clustering was employed as an unsupervised reference. Model performance was assessed using Accuracy, Precision, Recall, and F1-score for supervised models, and Adjusted Rand Index (ARI) for clustering. Experimental results indicate that Logistic Regression achieved the best accuracy of 0.7573, followed by ANN with 0.7078, while K-Means obtained an ARI of 0.1614. The heatmap comparison shows that supervised models outperform unsupervised approaches, with Logistic Regression offering better interpretability and stability, and ANN demonstrating the ability to model nonlinear relationships. K-Means, though less accurate, provided valuable insight into data structure and natural grouping. Overall, the findings confirm that supervised learning models, particularly Logistic Regression and ANN, are more effective for medical prediction tasks. Future research may explore hybrid or ensemble models that combine the interpretability of Logistic Regression, the adaptability of ANN, and the exploratory capability of clustering to enhance medical diagnostic performance.

Page 5 of 7 | Total Record : 63

 3   4   5   6   7 

Filter by Year

2023 2025


Reset
Filter By Issues
All Issue Vol. 3 No. 4 (2025): Research of Biotechnology Vol. 3 No. 3 (2025): July: Health Science Informatic Vol. 3 No. 2 (2025): April: Artificial Intelligence Vol. 3 No. 1 (2025): Jan: Computer Science Vol. 2 No. 4 (2024): October: Artificial Intelligence Vol. 2 No. 3 (2024): July: Artificial Intelligence Vol. 2 No. 2 (2024): April: Computer Science Vol. 2 No. 1 (2024): Jan: CNN and Artificial Vol. 1 No. 4 (2023): Oct: Computing Quantum and Related Fields Vol. 1 No. 3 (2023): July: Computer Science and Research Vol. 1 No. 2 (2023): April: Article Computer Science and Research Vol. 1 No. 1 (2023): January: Article Computer Science and Research More Issue