cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Anjar Wanto
Contact Email
anjarwanto@ieee.org
Phone
+6282294365929
Journal Mail Official
jomlai.journal@gmail.com
Editorial Address
Jl. Bunga Cempaka No. 51D. Medan. Indonesia Phone: +62 822-9436-5929 | +62 812-7551-8124 
Location
Kota medan,
Sumatera utara
INDONESIA
JOMLAI: Journal of Machine Learning and Artificial Intelligence
Published by Yayasan Literasi Sains Indonesia
ISSN : 28289102     EISSN : 28289099     DOI : 10.55123/jomlai
Core Subject : Science, Engineering,
Computer Science & IT Engineering
Focus and Scope JOMLAI: Journal of Machine Learning and Artificial Intelligence is a scientific journal related to machine learning and artificial intelligence that contains scientific writings on pure research and applied research in the field of machine learning and artificial intelligence as well as an overview of the development of theories, methods, and related applied sciences. Topics cover the following areas (but are not limited to): Software engineering Hardware Engineering Information Security System Engineering Expert system Decision Support System Data Mining Artificial Intelligence System Computer network Computer Engineering Image processing Genetic Algorithm Information Systems Business Intelligence and Knowledge Management Database System Big Data Internet of Things Enterprise Computing Machine Learning Other relevant study topics Noted: Articles have primary citations and have never been published online or printed before
Arjuna Subject : Ilmu Komputer (semua kategori) - Kecerdasan Buatan
Articles 91 Documents
 6   7   8   9   10 
Public Sentiment Analysis of the Agrarian Conflict between PT TPL and the Toba Simalungun Indigenous Community Using the SVM Method Dian Yusri Andira; Deswita Maharani Harahap; Vibiola Br Damanik; Indah Frian Sari; Victor Asido Elyakim P
JOMLAI: Journal of Machine Learning and Artificial Intelligence Vol. 4 No. 3 (2025): September 2025
Publisher : Yayasan Literasi Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55123/jomlai.v4i3.6116

Abstract

The agrarian conflict between PT Toba Pulp Lestari and the Toba Simalungun indigenous community has generated diverse public opinions on social media. This study aims to analyze public sentiment regarding the conflict using the Support Vector Machine (SVM) method based on TikTok comment data. A total of 1,751 comments were collected via the TikTok API and processed through cleaning, normalization, stopword removal, and stemming. Sentiment labeling was performed automatically with a lexical-based approach, followed by feature weighting using Term Frequency-Inverse Document Frequency (TF-IDF). The SVM model was used to classify public sentiment into two main categories, namely positive and negative. The results of the testing showed that the SVM model was able to achieve an accuracy of 80%, with excellent performance in detecting negative sentiment. Additional analysis through wordcloud visualization shows the dominant words in each sentiment category, which reinforces the model's classification results. The findingsof this study provide an objective picture of public opinion patterns on social media, while also demonstrating the potential application of machine learning-based sentiment analysis methods to understand public perceptions of other social issues in the future.
Design and Development of a Web-Based Boarding House Information System Iqbal Aditya Ferryanto; Ruswanti, Diyah; Susilo, Dahlan
JOMLAI: Journal of Machine Learning and Artificial Intelligence Vol. 4 No. 3 (2025): September 2025
Publisher : Yayasan Literasi Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55123/jomlai.v4i3.6486

Abstract

Web-based information systems serve an essential function in promoting efficient and efficient information management in the digital era.  The objective of this research is to create a web-based information system for boarding houses with 6 boarding house research objects. to address challenges often encountered in manual data management, such as data inaccuracies and difficulties in accessing information. The development process employs the Waterfall methodology, which includes phases including communication, planning, planning, execution, and upkeep. The coding language applied for in creating websites is JavaScript and uses a MySQL database. Where This system offers features tailored to the needs of boarding house seeker, house owners, and administrators. Testing using the System Usability Scale (SUS) involving 38 respondents resulted in a rating of 78.16, categorized as good usability (Grade B). These results indicate that the system provides a satisfactory user experience and supports increased efficiency in managing boarding house operations.
Entropy-Regularized Nonlinear Auto-Regressive Network with eXogenous Inputs (ER-NARX): A Mathematical Framework for Scalable and Robust Big Data Forecasting Using ITL and Fractional Dynamics Zulfatri Aini; Tengku Reza Suka Alaqsa
JOMLAI: Journal of Machine Learning and Artificial Intelligence Vol. 4 No. 4 (2025): Desember 2025
Publisher : Yayasan Literasi Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55123/jomlai.v4i4.6689

Abstract

This study proposes the Entropy-Regularized NARX (ER-NARX) model, which integrates nonlinear autoregressive modeling, entropy-based regularization, and information-theoretic learning for big data forecasting. The NARX model captures temporal dependencies between past outputs and exogenous inputs, while entropy regularization is incorporated to control the uncertainty of model predictions and prevent overfitting. The innovation of this model is its ability to control information flow through entropy regularization, which helps balance predictive accuracy with uncertainty, preventing the model from becoming overly deterministic. By combining these components, the ER-NARX model enhances the stability and robustness of the forecasts and improves its generalization to complex, high-dimensional data. Additionally, fractional dynamics are employed to model long-range memory effects in temporal data to enhancing the model's ability to handle datasets with extended dependencies. The resulting ER-NARX framework provides a mathematically grounded approach to big data forecasting improved performance in a computationally efficient manner. Future research may explore advanced entropy regularization techniques and apply the model to more diverse real-world data with intricate dependencies.
Quantum-Entropy NARX (Q-ENARX): A Mathematical Framework for Forecasting Based on Quantum Information Theory and Nonlinear Dynamic Regularization Tengku Reza Suka Alaqsa; Syarifah Adriana
JOMLAI: Journal of Machine Learning and Artificial Intelligence Vol. 4 No. 4 (2025): Desember 2025
Publisher : Yayasan Literasi Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55123/jomlai.v4i4.6722

Abstract

This study addresses the limitations of conventional nonlinear autoregressive models, which struggle to maintain stability and generalization in high-dimensional, non-stationary forecasting environments. The research aims to develop a mathematical framework that integrates deterministic dynamics with probabilistic uncertainty through the proposed Quantum-Entropy NARX (Q-ENARX) model. The methodology combines nonlinear autoregressive modeling, entropy-based trust-region optimization, and quantum information theory to establish a unified formulation for dynamic forecasting. The model embeds NARX states into a quantum Hilbert space, introduces an entropy-regularized loss function to balance accuracy and uncertainty, and employs a quantum Fisher Information Matrix for curvature-aware optimization. Analytical derivations reveal that Q-ENARX achieves enhanced stability, improved generalization, and robust convergence by leveraging quantum state dynamics, entropy-energy duality, and fractional learning operators. The results shows that the integration of entropy and quantum principles transforms traditional NARX forecasting into a probabilistically interpretable and physically grounded framework capable of capturing complex temporal correlations with high mathematical precision.
Integration of Artificial Intelligence in Physical Education Learning to Improve Learning Quality Butsiarah, Butsiarah
JOMLAI: Journal of Machine Learning and Artificial Intelligence Vol. 4 No. 4 (2025): Desember 2025
Publisher : Yayasan Literasi Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55123/jomlai.v4i4.6734

Abstract

This study aims to analyze the impact of integrating Artificial Intelligence (AI) into physical education learning to enhance students’ learning quality. The research employed a quasi-experimental method with a pretest-posttest control group design involving 60 students, divided into experimental and control groups. The research instruments included a learning motivation questionnaire, a student activity observation sheet, and a physical fitness test. The results revealed a significant improvement in the experimental group that applied AI-based learning. The average learning motivation score increased from 72.3 to 88.6 (a 22.5% increase), students’ active participation rose from 68.4% to 90.2%, and physical fitness scores improved from 70.1 to 83.5. The t-test results indicated a significant difference between the experimental and control groups (p < 0.05). These findings demonstrate that the implementation of artificial intelligence technology in physical education can effectively enhance students’ motivation, participation, and learning outcomes. Therefore, integrating AI into the learning process can serve as an innovative and effective strategy to improve the quality of physical education and support the transformation of learning in the rapidly evolving digital era.
Artificial Intelligence and the Sociology of Folklore: A Comparative Study of Turkey and Indonesia Dewi Christa Kobis; Michel Farrel Tomatala
JOMLAI: Journal of Machine Learning and Artificial Intelligence Vol. 4 No. 4 (2025): Desember 2025
Publisher : Yayasan Literasi Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55123/jomlai.v4i4.7459

Abstract

This study examines how Artificial Intelligence (AI) mediates the production and circulation of folklore in Turkey and Indonesia and asks: How does AI mediate folklore production and circulation in both contexts? And What similarities and differences characterize AI–folklore interaction from a sociological perspective? Using a qualitative comparative cultural sociology design, the analysis draws on Turkish sociological theory, Ziya Gokalp’s concept of halk kültürü and Şerif Mardin’s center–periphery framework alongside documentary and digital ethnographic observation of publicly accessible folklore texts, AI-mediated outputs (retellings, translations, summaries), and platform-based circulation. Findings show that AI mediates folklore production through textual regeneration, translation, narrative standardization, and platform-oriented adaptation, while circulation is shaped by recommendation, tagging, ranking, and translation interfaces that regulate visibility, dissemination, and the dominance of particular versions. Although both countries experience algorithmic pressures on cultural memory and narrative visibility, impacts diverge by context: Turkey’s institutionally anchored cultural authority tends to constrain AI toward selective continuity, whereas Indonesia’s pluralistic and decentralized landscape allows AI and platforms to operate as stronger cultural gatekeepers, enabling more transformative reinterpretations. Overall, the study concludes that AI is a structural cultural mediator whose sociological effects are context-dependent, amplifying existing power relations rather than uniformly transforming folklore.
Student Grouping Based on Grades and Attendance Using K-Means Theresya Simanjuntak; Jelita Astrid Gulo; Sardo Pardingotan Sipayung
JOMLAI: Journal of Machine Learning and Artificial Intelligence Vol. 5 No. 1 (2026): Maret 2026
Publisher : Yayasan Literasi Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55123/jomlai.v5i1.7283

Abstract

Student grouping based on academic performance is needed to support decision-making in more targeted academic guidance programs. This research implemented K-Means Clustering algorithm to group students based on academic scores and attendance rates. The dataset consisted of 50 student samples with score and attendance percentage attributes ranging from 0-100. Optimal cluster determination used Elbow Method and Silhouette Score with K values varying from 2 to 6. Experimental results showed K=3 produced optimal separation with highest Silhouette Score of 0.72 and WCSS 8,230. Three clusters formed represented high-achieving students (30%), average-performing students (40%), and students requiring special attention (30%). The algorithm converged in average of 8-12 iterations with 90% consistency on multiple runs. Correlation analysis showed very strong relationship between scores and attendance (r=0.89). Interactive visualization system was developed using React.js and Recharts to facilitate result interpretation. This research provided practical contribution in form of clustering framework for early warning identification of at-risk students and academic intervention program recommendations.
A Convolutional Neural Network-Based Real-Time Behavioral Detection System for Preventing Cheating in Online Examinations Muktar Abubakar Muhammed; Henry Onyebuchukwu Ordu
JOMLAI: Journal of Machine Learning and Artificial Intelligence Vol. 5 No. 1 (2026): Maret 2026
Publisher : Yayasan Literasi Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55123/jomlai.v5i1.7676

Abstract

The integrity of online examinations has become a growing concern in digital education, particularly following the rapid shift to remote learning. This study presents the development of a Convolutional Neural Network (CNN)-based Real-Time Behavioral Detection System and Prevention of cheating in online examinations. Specifically, the study identifies and classifies common visual behaviors associated with cheating, such as frequent eye movement, head turning, and the presence of unauthorized individuals. A CNN model was designed and trained on a curated dataset of annotated behavioral frames. The model achieved a classification accuracy of 91.7%, precision of 89.5%, recall of 92.3%, and an F1-score of 90.9%, demonstrating strong performance in real-time cheating behavior detection. A working prototype was developed using Python, TensorFlow, and OpenCV, and successfully integrated into a live monitoring interface capable of issuing alerts, logging incidents, and generating post-exam reports. The system's performance was evaluated across various test scenarios, showing consistent results with an average latency of 0.72 seconds per frame, making it suitable for real-time deployment.. Its implementation offers significant value to educational institutions, exam regulators, and EdTech platforms seeking to ensure fairness and trust in digital examinations.
Development of an Enhanced Predictive Model for Road Accident Occurrence in Nigeria Chukwudi Ugbaja; Friday E. Onuodu; Henry Onyebuchukwu Ordu; Emmanuel J. Izionworu
JOMLAI: Journal of Machine Learning and Artificial Intelligence Vol. 5 No. 1 (2026): Maret 2026
Publisher : Yayasan Literasi Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55123/jomlai.v5i1.7700

Abstract

Road accidents in Nigeria rank as the second highest globally, with 33.7% of deaths per 100,000 persons occurring annually. This study developed and tested a predictive model for road accident occurrence using Artificial Neural Networks (ANN) to address the technological gap in Nigeria's road safety management systems. A feed-forward neural network architecture comprising 52 input neurons, three hidden layers (32, 16, and 8 neurons) with ReLU activation, and a single sigmoid output neuron was designed. Dropout (0.3, 0.3, 0.2) and L2 regularization (0.001, 0.001, 0.0005) were incorporated to address sample size constraints. The dataset comprised 2,847 records from FRSC, NEMA, and NBS (2018-2023) across twelve Nigerian states, with 24 features spanning road, environmental, driver, and vehicle factors. Stratified random splitting yielded 1,994 training, 570 validation, and 283 temporally distinct test records. The model achieved 84.5% accuracy (95% CI: 79.8%-88.5%), 77.0% recall, 89.4% specificity, and 0.89 AUC on independent test data—a 13.5 percentage point improvement over the existing K-modes system (p<0.0001). Five-fold cross-validation confirmed stability (84.3%±0.6%). Feature importance analysis identified speeding (18.4%), alcohol impairment (15.2%), wet roads (11.8%), night driving (9.4%), and lane discipline (8.1%) as dominant predictors, with human factors accounting for 45.3% of predictive power. This study provides the first evidence-validated ANN-based accident prediction model calibrated for Nigeria, establishing a reproducible methodological template for developing contextually-adapted predictive systems in data-constrained environments while demonstrating statistically significant and practically meaningful improvement over existing approaches.
Development of a Content Creation Model Using Natural Language Generation Paul-Odeli Jonathan Ateko; Constance I. Amannah; Henry Onyebuchukwu Ordu; Izionworu, Emmanuel J.
JOMLAI: Journal of Machine Learning and Artificial Intelligence Vol. 5 No. 1 (2026): Maret 2026
Publisher : Yayasan Literasi Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55123/jomlai.v5i1.7726

Abstract

The increasing demand for scalable, high-quality digital content has exposed the limitations of manual content creation and existing Natural Language Generation (NLG) systems, particularly in terms of domain specificity, ethical reliability, and readiness for optimization. This study addresses this gap by developing NLG-ACCO, a transformer-based model for automated content creation and optimization in educational, media, and digital marketing applications. Transformer-XL was selected over newer architectures like Llama-3 or Mistral because it models longer contextual dependencies beyond fixed-length segments—essential for coherent paragraph-level content—while offering a better trade-off between performance, computational efficiency, and transparency under resource-constrained conditions. The model integrates domain-aware fine-tuning, reinforcement learning, SEO optimization, and ethical safeguards, including bias detection and factual verification. Evaluation used BLEU, ROUGE, readability indices, and Perplexity. NLG-ACCO achieved a BLEU score of 0.79 (baseline: 0.61) and ROUGE-L of 0.76 (baseline: 0.36). Perplexity dropped from 45.2 to 27.8, indicating more coherent predictions. Readability improved by 24%, post-editing time decreased by 38.5%, and bias detection mitigated 87% of flagged cases. These results demonstrate that integrating optimization and ethical controls within Transformer-XL frameworks significantly enhances content quality and reliability.

Page 9 of 10 | Total Record : 91

 6   7   8   9   10 

Filter by Year

2022 2026


Reset
Filter By Issues
All Issue Vol. 5 No. 1 (2026): Maret 2026 Vol. 4 No. 4 (2025): Desember 2025 Vol. 4 No. 3 (2025): September 2025 Vol. 4 No. 2 (2025): Juni 2025 Vol. 4 No. 1 (2025): Maret 2025 Vol. 2 No. 3 (2023): September Vol. 2 No. 2 (2023): June Vol. 2 No. 1 (2023): March Vol. 1 No. 4 (2022): December Vol. 1 No. 3 (2022): September Vol. 1 No. 2 (2022): June Vol. 1 No. 1 (2022): March More Issue