cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Heri Nurdiyanto
Contact Email
Heri Nurdiyanto
Phone
-
Journal Mail Official
internationaljournalair@gmail.com
Editorial Address
-
Location
Kota metro,
Lampung
INDONESIA
International Journal of Artificial Intelligence Research
Published by STMIK Dharma Wacana
ISSN : -     EISSN : 25797298     DOI : -
Core Subject : Science, Engineering,
Computer Science & IT Electrical & Electronics Engineering
International Journal Of Artificial Intelligence Research (IJAIR) is a peer-reviewed open-access journal. The journal invites scientists and engineers throughout the world to exchange and disseminate theoretical and practice-oriented topics of Artificial intelligent Research which covers four (4) majors areas of research that includes 1) Machine Learning and Soft Computing, 2) Data Mining & Big Data Analytics, 3) Computer Vision and Pattern Recognition, and 4) Automated reasoning. Submitted papers must be written in English for initial review stage by editors and further review process by minimum two international reviewers.
Arjuna Subject : -
Articles 650 Documents
 61   62   63   64   65 
Detection of Data Duplication and Anomalies in the Population Registration System to Improve the Quality of Public Services Mayce Novitalia; Selvi Diana Meilinda; Imelda Hutasoit; Riswati Riswati; Hendayana Hendayana; Dwi Agus Sumarno
International Journal of Artificial Intelligence Research Vol 10, No 1 (2026)
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v10i1.1722

Abstract

The consequences of data duplication and anomalies on the quality of public service in Indonesia's Civil Registration Information System (SIAK) are investigated in this study. The study analyses documented anomaly patterns and institutional reports to back up its qualitative descriptive methodology, which is based on semi structured interviews with fifteen civil registration officers from five different districts. Multiple identities, inconsistent demographic features, faulty NIK formats, duplicate geographic coordinates, unrecognised or inactive Population Identification Numbers (NIK), and duplicate addresses are among the most common data errors, according to the research. As an example, NIK entries with less than 16 digits or infants classified as married are examples of logical and format abnormalities, which constitute the majority of errors. Data update cycles that are too long, inadequate automated validation, poor inter agency synchronisation, and reliance on human data entry are the main causes of these difficulties. Not resolving these irregularities might result in failed verification, delayed social assistance delivery, and termination of BPJS Health membership, therefore their impact is substantial. According to the research, public service quality may be enhanced by moving away from reactive rectification and toward preventive data governance. This can be achieved through the use of artificial intelligence (AI) for validation, real time updates, stronger integration between agencies, increased officer capacity, and public knowledge of data updating.
Cost Optimization of Preventive Maintenance Using an Integer Linear Programming Approach Based on RCA and Markov Chain Rino Indriyanto; Maria Ulfah; Ratna Ekawati
International Journal of Artificial Intelligence Research Vol 10, No 1 (2026): June
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v10i1.1649

Abstract

In 2024, the canned slurry pump at PT. X experienced 38 failure events, resulting in a total downtime of 105 hours and maintenance costs of IDR 3,193,283,735 due to the absence of a preventive maintenance program. This study proposes an integrated preventive maintenance optimization framework combining Root Cause Analysis (RCA), Markov Chain modeling, and Integer Linear Programming (ILP). RCA identifies six dominant failure causes accounting for 89.5% of total failures, which are used to define machine condition states in the Markov Chain model for estimating expected maintenance costs and predicting system behavior. The proposed maintenance policy (P?) reduces the average expected maintenance cost from IDR 333,486,618 to IDR 187,820,157, corresponding to a reduction of 43.68%. This value yields the most economical annual expected maintenance cost of IDR 1,798,000,000 and is subsequently applied as a cost constraint in the ILP model. The optimization results show that preventive maintenance for 10 pump units in 2025 can be implemented at a total cost of IDR 1,701,000,000 while generating an estimated profit of IDR 1,520,000,000. The results demonstrate that the proposed integrated approach enables effective and cost-efficient preventive maintenance decision-making, supported by the formulation of standardized working instructions in accordance with company standards.
Implementation of Business Intelligence to Support Decision Making in Academic Information Systems Risna Risna; Muhammad Syahrani
International Journal of Artificial Intelligence Research Vol 10, No 1 (2026)
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v10i1.1754

Abstract

The rapid advancement of digital transformation has encouragedhigher education institutions to optimize the utilization of academicdata as a strategic asset for evidence-based decision-making. AlthoughAcademic Information Systems (AIS) continuously generatesubstantial volumes of academic data, these data are predominantlyused to support operational activities rather than strategic analysis andinstitutional planning. This study aims to develop a BusinessIntelligence (BI) implementation model for Academic InformationSystems by integrating a data warehouse, Extract, Transform, andLoad (ETL) processes, and interactive analytical dashboards tofacilitate data-driven decision-making
Artificial Intelligence in Vocational Education: A Bibliometric Analysis of Global Trends and Collaboration Fuad Abdillah; Dhega Febiharsa; Herry Sulendro Mangiri; Afis Pratama; Toni Setiawan
International Journal of Artificial Intelligence Research Vol 10, No 1 (2026)
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v10i1.1691

Abstract

Implementasi  Kecerdasan Buatan (AI) dalam teknologi pendidikan kejuruan telah secara signifikan mengubah lanskap pembelajaran global. Pertumbuhan publikasi ilmiah di bidang ini mencerminkan peningkatan minat penelitian dalam mengintegrasikan AI untuk meningkatkan kompetensi lulusan pendidikan kejuruan. Studi ini bertujuan untuk memetakan lanskap global penelitian Kecerdasan Buatan dalam teknologi pendidikan kejuruan melalui analisis bibliometrik yang komprehensif. Data penelitian diperoleh dari basis data Dimensions AI dengan kombinasi strategi pencarian kata kunci yang terkait dengan AI dan pendidikan kejuruan untuk periode 2000-2025. Analisis dilakukan menggunakan perangkat lunak VOSviewer untuk memvisualisasikan jaringan kolaborasi, tren publikasi, dan evolusi topik penelitian. Prosedur analisis meliputi pembersihan data, pembuatan matriks ko-sitasi, pengelompokan tematik, dan interpretasi metrik bibliometrik. Temuan menunjukkan pertumbuhan eksponensial dalam publikasi, dominasi kategori pendidikan, kolaborasi intensif antar negara maju, dan identifikasi empat klaster tematik utama yang mencerminkan evolusi penelitian dari metodologis ke aplikasi praktis. Bidang penelitian AI dalam pendidikan kejuruan berkembang pesat dengan pergeseran fokus ke arah pembelajaran adaptif, pertimbangan etis, dan integrasi teknologi yang berpusat pada nilai-nilai kemanusiaan. Penelitian ini memberikan landasan empiris untuk agenda penelitian di masa mendatang, memandu para pembuat kebijakan dalam alokasi sumber daya, dan mendorong lembaga pendidikan kejuruan untuk mengadopsi teknologi AI secara bertanggung jawab dan efektif.
Data Driven Comparison of Synthetic and Waste Based Bio-Geotextiles: A Systematic Literature Review Lusi Dwi Putri; Muhammad Usman Tariq
International Journal of Artificial Intelligence Research Vol 10, No 1 (2026): June
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v10i1.1614

Abstract

Synthetic polymer geotextiles are widely used in geotechnical engineering for separation, reinforcement, drainage, and erosion control, but their production and end of life stages often raise environmental concerns due to fossil based raw materials and persistent plastic waste. In parallel, bio geotextiles manufactured from agricultural or agro industrial waste such as coir, jute, pineapple leaves, and other natural fibres have been promoted as a more sustainable alternative, although questions remain about their mechanical performance, durability, and long term serviceability. This study conducts a systematic literature review to compare manufactured synthetic geotextiles with waste based bio geotextiles, with a primary focus on coconut coir geotextiles produced from coconut husk waste. The comparison is framed from three perspectives, namely mechanical and hydraulic performance, durability and degradation behaviour, and environmental sustainability including life cycle impacts. Scientific databases were searched using predefined keywords and inclusion criteria, resulting in a final sample of 20 core journal articles published between 2011 and 2025, most of which investigate coir based products for slope stabilization, erosion control, and low volume road applications. The findings show that coir bio geotextiles can provide comparable short term reinforcement and erosion control to conventional products in low to medium demand applications, particularly for slope stabilization and surface erosion control, although synthetic geotextiles still outperform in high load and long term applications. From an environmental perspective, coir geotextiles and other bio based products generally offer lower embodied energy and greenhouse gas emissions, but this advantage depends on local supply chains, fibre processing, and replacement frequency. The novelty of this review lies in integrating geotechnical performance evidence with environmental assessment results and highlighting how simple data driven metrics can support material selection for coir based bio geotextiles. The study concludes with a set of research gaps and design recommendations that bridge geotechnical engineering and sustainable materials science.
Building Student Confidence Through Satisfaction : The Role Of Service Quality, Education Costs And Institutional Image In A-Acreditated Muhammadiyah Senior High School Iis Dewi Fitriani; Popo Suryana; Nandan Limakrisna
International Journal of Artificial Intelligence Research Vol 10, No 1 (2026)
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v10i1.1692

Abstract

Competition among private secondary education institutions in metropolitan areas requires schools to improve service quality to build student satisfaction and trust. This study aims to analyze the influence of service quality, tuition fees, and institutional image on student satisfaction and their impact on student trust at A-accredited Muhammadiyah Senior High Schools in the Bandung Metropolitan area. This study uses a quantitative approach with an explanatory survey method . The study population was all 4,674 A-accredited Muhammadiyah Senior High School students in the Bandung Metropolitan area, with a sample of 223 grade XII students determined through a two-stage sampling technique . Data collection was carried out using a Likert-scale questionnaire, interviews, and observations. Data analysis used Structural Equation Modeling (SEM). The results showed that service quality, tuition fees, and institutional image had a positive and significant effect on student satisfaction. Furthermore, student satisfaction had a positive and significant effect on student trust. Student satisfaction was also proven to mediate the influence of service quality, tuition fees, and institutional image on student trust. These findings confirm that improving service quality, proportional management of education costs, and strengthening the institution's image are strategic factors in building student satisfaction and trust at Muhammadiyah Senior High Schools accredited A in the Bandung Metropolitan area.
A Machine Learning Approach for Pornographic Website Content Detection Using an Optimised Naïve Bayes Classifier Rahmalia Syahputri; Taufik Taufik; Aldwi Mandak; Prana Alfath Rais
International Journal of Artificial Intelligence Research Vol 10, No 1 (2026): June
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v10i1.1698

Abstract

The rapid growth of internet usage has increased concerns about exposure to pornographic content, particularly among younger users. This study proposed and developed a machine learning approach for classifying Indonesian-language website content containing pornographic material using the Naïve Bayes (NB) algorithm. A dataset comprising 50,329 website entries collected between 2019 and 2026 was processed through several preprocessing steps, including text normalisation, tokenisation, case folding, stemming, and stopword removal, to enhance the quality of textual features. To address class imbalance between pornographic and non-pornographic categories, the Synthetic Minority Oversampling Technique (SMOTE) was applied during the training phase. Model performance was evaluated using a 5-fold cross-validation strategy and was compared across three Naïve Bayes variants: Multinomial Naïve Bayes (MNB), Bernoulli Naïve Bayes (BNB), and Gaussian Naïve Bayes (GNB). Experimental results showed that the Multinomial Naïve Bayes model achieved the best performance, with an accuracy of approximately 94%, a precision of 0.92, a recall of 0.94, and an F1-score of 0.93, along with an ROC-AUC of 0.986. These findings demonstrated that the proposed approach was effective in classifying pornographic website content and could support automated web content filtering systems to protect users from harmful material. Future work could explore real-time implementation and the integration of more advanced machine learning techniques to further improve classification performance.
Regional Financial Management Accountability in the Perspective of Public Sector Accounting Yuniati Yuniati; Yuni Oktaviani; Zahra Hardyanti; Wandy Zulkarnaen
International Journal of Artificial Intelligence Research Vol 10, No 1 (2026)
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v10i1.1744

Abstract

To ensure transparency, efficiency, and accountability in the use of public funds, accountability in regional financial management is needed, which is one of the two main foundations in public sector accounting practice. In addition, the demands of the community with a government that is run in a clean and accountable manner have increased the government's need to improve the quality of financial management. The government improves the quality of financial management through the implementation of government accounting standards and an adequate internal control system. Therefore, this study aims to examine the accountability of regional financial management from the perspective of public sector accounting through a literature study approach. The method used in this study is a literature study of accredited national journals in the last five years, textbooks, and relevant laws and regulations. The results of this study show that the role, the government's internal control system, the quality of human resources, and the use of Government Accounting Standards, and the role of internal & external supervision have a significant influence on improving the level of accountability of regional financial management. However, there are still a number of structural and technical obstacles that still have the potential to be stumbling blocks to the realization of optimal accountability. Therefore, there is a need for a commitment by the government to improve financial governance that allows each public entity to be more accountable and open.
A Deep Learning Approach to Fake News Detection in Images with Text Overlay Heri Nurdiyanto; Nova Suparmanto; Beniati Lestyarini; Novan Edo Pratama
International Journal of Artificial Intelligence Research Vol 10, No 1 (2026): June
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v10i1.1701

Abstract

This study addresses the growing challenge of fake news distributed through images containing overlaid text, a format that is widely used on social media because it is visually persuasive, easy to share, and often difficult to verify. Unlike conventional text-only misinformation, this type of content combines visual and textual cues that can strengthen misleading narratives and increase public trust in false information. To respond to this problem, the study proposes a deep learning approach for detecting fake news in text-overlay images by integrating image-based and text-based feature extraction within a unified classification framework. The proposed method begins with image preprocessing and text extraction from embedded captions, followed by feature learning using deep neural architectures to capture both semantic and visual patterns associated with deceptive content. The model is trained and evaluated on a labeled dataset of images containing news-like textual overlays, with performance assessed using accuracy, precision, recall, F1-score, and confusion matrix analysis. The results indicate that the proposed approach is able to identify fake news content effectively and achieves promising classification performance compared with baseline machine learning methods. These findings indicate that combining visual representation and embedded textual information can significantly improve detection capability in multimodal misinformation settings. This study aids in the advancement of more flexible fake news detection systems, especially in digital contexts where altered or deceptive image-based content disseminates swiftly. The proposed framework is expected to support future research and practical implementation in automated content verification, social media monitoring, and digital information integrity management
Optimization of Face Tracking in Crowded Environments Using YOLOv9, Attention Mechanism and DeepSORT Teguh Budi Santoso; Fachrul Kurniawan; Mochamad Imamudin
International Journal of Artificial Intelligence Research Vol 10, No 1 (2026): June
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v10i1.1705

Abstract

Face detection and tracking in crowded environments remain challenging due to occlusion, object overlap, and high visual similarity between individuals. In tracking-by-detection systems, detection quality plays a crucial role in tracking stability, yet the relationship between detection performance and identity consistency is not fully explored. This study proposes an integrated framework combining YOLOv9, an attention mechanism, and DeepSORT to enhance feature representation and improve identity tracking in dense environments, where the attention mechanism is embedded in the detection stage to strengthen feature discriminability and enable more stable identity association across frames. The system is evaluated using three dataset partitioning scenarios (90:10, 50:50, and 10:90) to analyze the impact of training data distribution. Experimental results show that the 90:10 configuration achieves the best performance, with precision 0.9398, recall 0.8869, F1-score 0.9126, MOTA 71.0%, and IDF1 73.0%. These findings confirm that improved feature representation significantly enhances detection quality and tracking stability, and demonstrate that feature stability is more critical than adopting newer detection architectures for achieving robust tracking performance in crowded environments.

Page 65 of 65 | Total Record : 650

 61   62   63   64   65 

Filter by Year

2017 2026


Reset
Filter By Issues
All Issue Vol 10, No 1 (2026): June Vol 10, No 1 (2026) Vol 9, No 1.1 (2025) Vol 9, No 2 (2025): December Vol 9, No 1 (2025): June Vol 8, No 2 (2024): December 2024 Vol 8, No 1 (2024): June 2024 Vol 8, No 1.1 (2024) Vol 7, No 2 (2023): December 2023 Vol 7, No 1 (2023): June 2023 Vol 7, No 1.1 (2023) Vol 6, No 2 (2022): Desember 2022 Vol 6, No 1 (2022): June 2022 Vol 6, No 1.2 (2022) Vol 6, No 1.1 (2022) Vol 5, No 2 (2021): December 2021 Vol 5, No 1 (2021): June 2021 Vol 4, No 2 (2020): December 2020 Vol 4, No 1 (2020): June Vol 3, No 2 (2019): December 2019 Vol 3, No 1 (2019): June 2019 Vol 2, No 2 (2018): December 2018 Vol 2, No 1 (2018): June 2018 Vol 1, No 2 (2017): December 2017 Vol 1, No 1 (2017): June 2017 More Issue