Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal International Journal of Advances in Artificial Intelligence and Machine Learning
Hafiz Muhammad Kurniawan
INTI International University
Computer Science & IT

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Chatbot for Traditional Malay Museum Misinem Misinem; Hafiz Muhammad Kurniawan; Fadly Fadly; Muhammad Raihan Hanif
International Journal of Advances in Artificial Intelligence and Machine Learning Vol. 2 No. 3 (2025): International Journal of Advances in Artificial Intelligence and Machine Learni
Publisher : CV Media Inti Teknologi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58723/ijaaiml.v2i3.567

Abstract

Background of study: Museums play a key role in preserving cultural heritage and educating the public. In Malaysia and Indonesia, over 150 traditional Malay museums attract millions of visitors annually. Between 2015 and 2017, the Department of Museum Malaysia recorded 9.1 million visitors, while Indonesia reported over 12 million. Managing visitor inquiries manually poses challenges for museum staff, highlighting the need for an automated information system.Aims: This study aims to develop a chatbot for Muzium Adat to provide instant, accurate, and accessible information to visitors, thereby reducing dependence on staff and enhancing the visitor experience.Methods: A museum information chatbot was developed to answer frequently asked questions related to Muzium Adat. The system was tested through questionnaires distributed to 15 respondents to assess usability, accuracy, and satisfaction.Result: Findings showed that the chatbot achieved an 83.6% satisfaction and accuracy rate, indicating effective real-time interaction and reliable responses.Conclusion: The Muzium Adat chatbot improves communication efficiency, saves time, and enhances visitor engagement. It demonstrates the potential of chatbot technology to support museum operations and promote cultural heritage in Malaysia and Indonesia.
Learning from Heterogeneous Label Quality: Strategies for Robust Model Training Wu Shukun; Hafiz Muhammad Kurniawan; Adolf Asih Suprianto
International Journal of Advances in Artificial Intelligence and Machine Learning Vol. 3 No. 2 (2026): International Journal of Advances in Artificial Intelligence and Machine Learni
Publisher : CV Media Inti Teknologi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58723/ijaaiml.v3i2.799

Abstract

Background: Training data collected from crowdsourcing platforms, automated labeling systems, and multiple annotators often contain labels with unequal levels of reliability. Conventional machine-learning methods generally treat all labels as equally trustworthy, which can reduce model performance when label errors vary across samples and annotation sources.Aims: This study proposes a quality-aware training method that explicitly models the heterogeneity of label reliability. It examines whether sample-level quality weighting can improve predictive performance and robustness under synthetic and real-world label-noise conditions.Methods: The proposed method combines annotation or neighborhood agreement, loss-based confidence, and source-level reliability to estimate a continuous quality score for each training sample. The scores are incorporated into a weighted cross-entropy objective and periodically updated during training. Experiments were conducted on CIFAR-10, CIFAR-100, CIFAR-10N, and CIFAR-100N using ResNet-18. The method was compared with cross-entropy, label smoothing, generalized cross-entropy, Co-teaching, and DivideMix.Result: Under high heterogeneous noise, the proposed method achieved accuracies of 83.21% on CIFAR-10 and 54.62% on CIFAR-100, compared with 73.48% and 45.92% for conventional cross-entropy. It also achieved the highest accuracy under the evaluated real-world noisy-label conditions. Ablation and sensitivity analyses showed that the combined quality indicators were complementary and that the method remained effective under moderate quality-estimation errors.Conclusion: Explicitly modeling label reliability improves robustness when training data contain unequal annotation quality. The proposed method provides a practical and computationally efficient strategy for learning from crowdsourced, weakly supervised, and multi-source datasets.
Co-Authors Adolf Asih Suprianto Fadly Fadly Misinem Misinem Muhammad Raihan Hanif Wu Shukun