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 658 Documents
 62   63   64   65   66 
Enterprise Resource Planning Implementation to Improve Business Efficiency: An Information Systems Perspective Using the Nursobah Model Akhira Akhira; Muhammad Syahrani; Ahmad Soni Adiffa
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.v10i1.1755

Abstract

Enterprise Resource Planning (ERP) has emerged as one of the most significant technological innovations supporting organizational digital transformation by integrating various business functions into a unified information system. Despite the increasing adoption of ERP across different industries, many organizations continue to experience implementation challenges related not only to technological complexity but also to organizational communication, stakeholder engagement, and strategic management. Consequently, successful ERP implementation requires a comprehensive approach that integrates technological infrastructure with managerial and communication dimensions
Evaluation Of K3 Management And Risk Analysis In The Factory Environment Herotje Siwi; Jedithjah Naapia Tamedi Papia; Meike Negawati Kesek
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.v10i1.1732

Abstract

This study aims to evaluate the implementation of K3 management and analyze the level of occupational risk in a manufacturing plant. The implementation of an K3 management system is a crucial aspect in maintaining worker safety, increasing productivity, and minimizing the potential for workplace accidents that could harm both the company and workers. The study used a descriptive quantitative approach, employing field observations, interviews, documentation, and questionnaires distributed to 150 respondents, including production operators, technical staff, and factory supervisors. Risk analysis was conducted using the Hazard Identification, Risk Assessment, and Risk Control (HIRARC) method to identify potential hazards and determine the level of risk for each work activity.The results indicate that the implementation of K3 management in the factory environment has been quite successful. However, several weaknesses remain in the supervision of personal protective equipment (PPE) use, compliance with work procedures, and risk control of production machinery. Based on the hazard identification results, several dominant risks with high levels of risk were identified, namely noise exposure, accidents caused by production machinery, potential fires, and fatigue due to excessive workload. The evaluation revealed that the lack of regular training and low worker awareness were the main factors affecting the effectiveness of K3 implementation.This study also found that the implementation of administrative and technical risk controls can significantly reduce the potential for workplace accidents if implemented consistently. Furthermore, company management involvement in routine monitoring and evaluation is a crucial factor in improving occupational safety culture in industrial environments. This study recommends improving K3 training programs, strengthening monitoring systems, and optimizing the implementation of standard operating procedures (SOPs) to minimize occupational risks in the factory environment. With effective implementation of K3 management, companies can create a safe, healthy, and productive work environment for all workers.
Identify the Usability of the Netraku Application System Using the Usability Testing Method Amarria Dila Sari
International Journal of Artificial Intelligence Research Vol 8, No 1.1 (2024)
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v8i1.1123

Abstract

The Netraku application is aimed at the visually impaired who want to know the name of an object or the writing of an object or printed media, as well as knowing the nominal currency conveyed via voice in the application. The application works by pointing the camera at the object or currency you want to see the name or amount of. The Netraku application will detect it, and a voice will appear stating the information you want to convey. The problem found is that the Netraku application has not carried out usability testing for blind users. Therefore, it is necessary to develop usability testing to obtain user needs from the Netraku application, determine the effectiveness and efficiency values, and provide recommendations that can be applied to the Netraku application. The methods used in usability testing are performance measurement, focus group discussion, and participatory design. The results obtained on the effectiveness value received a success rate of 83.33% and a failure rate of 16.7%, concluding that the user can complete the task effectively. The efficiency value obtained from the average processing time is 10.34 seconds.
Comparative Study of IndoBERT and IndoBERT-BiLSTM Models Across Three Text Preprocessing Frameworks for Aspect-Based Sentiment Analysis on MyTelkomsel App Reviews Antonius Wahyu Sudrajat; Iis Pradesan Pradesan; Yulistia Yulistia Yulistia
International Journal of Artificial Intelligence Research Vol 10, No 2 (2026): December
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v10i2.1751

Abstract

This study examines how text preprocessing depth and model architecture jointly affect aspect-based sentiment analysis (ABSA) of MyTelkomsel application reviews. A total of 850 cleaned Google Play reviews were weakly labeled into 1,036 aspect-sentiment instances covering package price, network signal, and customer service using a keyword lexicon and a rating-derived heuristic. Three preprocessing frameworks of increasing complexity (transformer-oriented, hybrid, and augmented hybrid with class-imbalance handling) were each evaluated on three IndoBERT-based architectures (a frozen baseline, full fine-tuning, and an IndoBERT+BiLSTM hybrid) under an identical evaluation protocol. The augmented hybrid framework combined with full fine-tuning achieved the best performance (accuracy 92.16%, macro F1-score 0.7406), ahead of the transformer-oriented (macro F1 = 0.6219) and hybrid (macro F1 = 0.6404) frameworks, and its advantage for the fine-tuned model was consistent across three random seeds, although these differences do not survive correction for multiple comparisons at three seeds. Fine-tuning consistently outperformed both the frozen baseline and the BiLSTM extension, while the customer service aspect remained the hardest to classify because of class imbalance and weak-label noise. A post-hoc audit found that 61.5% of test instances share near-identical text with training instances, an artifact of splitting multi-aspect reviews at the row level; absolute scores are therefore upper bounds, and although all conditions share one split, the interaction between this overlap and the augmented framework's oversampling remains untested. Unlike prior Indonesian IndoBERT-based ABSA studies that fix a single preprocessing pipeline, this study isolates the separate contributions of preprocessing depth and model architecture.
Minimal Gated Recurrent Unit with Temporal Convolution Based Acoustic Modeling on Speech Recognition System for Evaluating the Recitation of Quran Isjhar Kautsar; Dessi Puji Lestari; Aulia Rahmawati
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.v10i1.1613

Abstract

The use of future context in acoustic modeling seems to give an impact on system performance such us Bidirectional Long Short-Term Memory (BLSTM). It has been used as an acoustic model on Speech Recognition System for Quran recitation and show better result than Hidden Markov Model - Gaussian mixture model (HMM-GMM) with average Word Error Rate (WER) value 4.6%. but, the architectural complexity of BLSTM make the latency during decoding process is high.  To reduce the latency, Minimal Gated Recurrent Unit with Temporal Convolution (mGRUIPTC) acoustic model was used. Text data such as transcription, lexicon, and corpus used in training are represented at phone level to handle phone level detection. The transcription is generated using modified QScript to handle reciting rules in detail. In the test, the system can reduce decode process latency by up to 11 seconds with Phone Error Rate (PER) difference of up to 1.46% compared to BLSTM. However, our model still needs to be trained with more data to detect error recitation better.
Global Research Trends, Collaboration Networks, and Emerging Topics in Geotechnical Engineering: A Data-Driven Bibliometric Analysis Komang Arya Utama; Milawaty Waris; Muhammad Ikbal; Susanto Susanto
International Journal of Artificial Intelligence Research Vol 10, No 2 (2026): December
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v10i2.1746

Abstract

Geotechnical Geotechnical engineering has evolved into an increasingly diverse and multidisciplinary field, yet a comprehensive, data-driven mapping of its global publication trends, collaboration networks, and emerging research themes as an integrated discipline remains limited. This study aims to (1) analyze global publication trends and scientific developments in geotechnical engineering, (2) identify collaboration networks among countries, institutions, and authors, and (3) examine emerging topics and future research directions through bibliometric visualization. A bibliometric review was conducted on 245 Scopus-indexed publications (2016–2026), selected through a PRISMA-based screening process and analyzed using VOSviewer and Bibliometrix-R. The results show a consistent growth in publications, with a sharp acceleration during 2023–2025, driven by three dominant thematic clusters: artificial intelligence and digitalization, bio-based and sustainable geotechnics, and energy geotechnics. Collaboration network analysis reveals that China (35 publications) and the United States (33 publications) lead global output, followed by Australia, the United Kingdom, and Brazil, while developing regions, including Southeast Asia, Africa, and most of Latin America, remain underrepresented. Author-level analysis identifies Phoon, K.-K. as the most productive and influential researcher, reflecting a pronounced Matthew effect within the field. Keyword co-occurrence, overlay, and density visualizations further confirm that artificial intelligence and data-centric approaches represent the most rapidly accelerating research frontier, while sustainable geotechnics remains a stable, well-established research stream. These findings provide a comprehensive evidence base for guiding future research agendas, strengthening international collaboration, and directing geotechnical innovation toward more sustainable and technologically advanced solutions.
Web-Based Complaint Handling System:A Pre-Post Cohort Evaluation of E-Service Quality Melati Oktafiyani; Etika Kartikadarma; Handy Nur Cahya; Wikan Isthika; Dayangku Azriani binti Awang Ismail
International Journal of Artificial Intelligence Research Vol 10, No 2 (2026): December
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v10i2.1753

Abstract

Customer complaint management remains a critical challenge because fragmented communication channels act as an informational “black box” for consumers, increasing uncertainty and weakening organizational trust. While prior studies focus primarily on technical deployment or post-adoption satisfaction, empirical evidence isolating how system-driven transparency drives trust recovery remains scarce. This study designs and evaluates a web-based Customer Complaint Handling System (CCHS) built on a three-tier Model–View–Controller (MVC) architecture to address this gap. Methodologically, a single-cohort longitudinal pretest–posttest design was executed involving 84 identical participants tracked over two sequential 30-day operational periods. Data were collected using a 20-item instrument covering five dimensions adapted from Electronic Service Quality (E-S-QUAL) and Information Systems Success frameworks. Reliability was confirmed via Cronbach’s alpha (?pre = 0.842; ?post = 0.891). Quantitative tracking revealed highly significant positive shifts across all dimensions (p < 0.001) following system implementation. Notably, Transparency & Information achieved the most substantial growth (? = +3.09; 213.1%), heavily driven by real-time status visibility (? = +3.40), while Satisfaction & Trust increased by +2.44 points (120.8%). Conversely, Fairness & Resolution Quality exhibited bounded improvement (? = +1.10), proving that automated architectures act as operational facilitators rather than replacements for human judgment. These findings demonstrate that digital process visibility operates as an independent driver of trust recovery, offering actionable guidance for digital service governance. 
Decision Support System for Student Attrition Risk Using Financial Trajectory Index and Survival Analysis Yulistia - Yulistia; Antonius Wahyu Sudrajat; Mardiani Mardiani; Nadya Angelia
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.v10i1.1776

Abstract

Student attrition remains a persistent problem in Indonesian higher education, but institutional decision-support tools rarely combine time-to-event modeling with longitudinal financial data. Prior dropout studies rely on single-point-in-time machine-learning classifiers such as Random Forest, XGBoost, and CatBoost, which ignore attrition timing and treat financial status as static, while existing multilevel survival studies capture program-level heterogeneity without individual financial trajectories. This study proposes the Student Financial Trajectory Index (SFTI), a semester-level composite of payment ratio, arrears ratio, arrears trend, and cumulative late-payment fines, and integrates it into a multilevel discrete-time survival analysis. Administrative panel data from 2,528 students in the 2021/2022 through 2025/2026 cohorts, across seven study programs at a private Indonesian university, were restructured into a person-period dataset. Dropout was defined both administratively and operationally (two consecutive inactive semesters), with the study program as a random-intercept cluster. Preliminary analysis shows that students in the higher-risk SFTI group have a dropout hazard of 0.51% per semester at risk, compared with 0.08% in the lower-risk group, suggesting that financial trajectory carries an early-warning signal beyond academic performance. Formal multilevel modeling shows academic predictors (GPA and cumulative leave) as the dominant predictors of dropout hazard: the SFTI coefficient in the combined model was positive but not statistically significant (? = 0.10, SE = 0.41, p = 0.80). Model B achieved a marginal QIC improvement over the academic-only model (95.246 vs 95.255) and identical held-out performance (AUC = 0.960; Brier = 0.002). The final model produces a semester-by-semester early-warning risk score to support institutional decision-making.

Page 66 of 66 | Total Record : 658

 62   63   64   65   66 

Filter by Year

2017 2026


Reset
Filter By Issues
All Issue Vol 10, No 2 (2026): December 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