Article Per Year (5 Year)
p-Index From 2021 - 2026
0.718
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI) TELKOMNIKA (Telecommunication Computing Electronics and Control)
Ha Manh Toan
Vietnam Academy of Science and Technology
Computer Science & IT Engineering

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Diagnosing tuberculosis from X-ray imaging based on contrast limited adaptive histogram equalization Nguyen Trong Vinh; Lam Thanh Hien; Ha Manh Toan; Do Nang Toan
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 15, No 3: June 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v15.i3.pp2567-2580

Abstract

Tuberculosis is a serious threat, and one of the effective data types for diagnosing tuberculosis is chest X-ray data. In this paper, we hypothesize the effect of image enhancement on the effectiveness of deep learning models in the problem of diagnosing pulmonary tuberculosis from chest X-ray images. To clarify the hypothesis, we have designed a data processing process with an image enhancement step using the contrast limited adaptive histogram equalization (CLAHE) technique to enhance the quality of input chest X-ray data, and the experiments were conducted with a standard dataset that was published on the Kaggle system. The evaluation is performed comprehensively with popular convolutional neural network architectures, including DenseNet201, DenseNet121, EfficientNetB0, and MobileNetV2, compared in two scenarios with and without the image enhancement step. Experiments have shown that the image enhancement step effectively improves the classification performance of all models, clearly through important scores such as area under curve (AUC), accuracy, F1-score, precision, and recall. The best result tested is the EfficientNetB0 model with 0.925926 accuracy score, 0.970732 AUC score, 0.904762 precision score, 0.95 recall score, and 0.926829 F1-score. In addition, qualitative analysis using gradient-weighted class activation mapping (Grad-CAM) shows that the resulting models have shown a focus on the lung region, reflecting the interpretability and suitability for radiologist expertise.
SYNDIAG: an expert system for disease syndrome diagnosis of traditional Vietnamese medicine Truong Hong Thuy; Ha Manh Toan; Vu Tung Lam; Nguyen Hoang Phuong
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 22, No 5: October 2024
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v22i5.25831

Abstract

Vietnam medicine consists of traditional Vietnam medicine and Western medicine. There is a lack of experienced traditional medicine practitioners, therefore, it needs to develop an expert system supporting medical practitioners in diagnosis. In this paper, we present an overview of syndrome diagnosis (SYNDIAG), a rule-based expert system for disease syndrome diagnosis in traditional Vietnamese medicine. The system consists of five components: knowledge base, inference engine, knowledge acquisition, explanation, and user interface. The paper focuses on how the rule base is constructed, managed, and used. At present, this knowledge base contains more than 1,000 rules used for the diagnosis of 50 disease syndromes of traditional Vietnamese medicine. The inference engine of the system applies the knowledge propagation and the algebra structure of MYCIN-like systems. We also present here the first evaluation of SYNDIAG by the practitioners of traditional medicine, who have been playing a very important role by providing the system with their knowledge.
Improving efficiency of autism detection based on facial image landmarks Nguyen Trong Tung; Ngo Duc Vinh; Ha Manh Toan; Do Nang Toan
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 15, No 1: February 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v15.i1.pp766-779

Abstract

Autism is a serious mental health problem with long-term effects on life. Therefore, early diagnosis is a topical issue for effective treatment. This study proposes a novel facial landmark transformation-based data augmentation method that allows for the generation of geometric transformations related to facial geometry. This method increases the generalizability and provides a perspective on the role of facial regions in autism detection. The proposed augmentation method ensures the generation of variants that are consistent with the facial image structure and the nature of the facial image. Next, conduct a comprehensive and comparative study with EfficientNet-B0, EfficientNet-B4, ResNet-18, ResNet-50, ResNet-101, MobileNet-V2, DenseNet-121 and DenseNet-201. Also analyze the model's attention over the main regions of the face that are related to facial landmarks. The results clearly show that the models trained with the proposed method outperform the default augmentation method. Specifically, when averaging the measures across the tested models, the results are 0.905417 for accuracy, 0.962133 for area under the curve (AUC), 0.9198 for precision, 0.888333 for recall, and 0.903678 for F1-score. Furthermore, when analyzing the gradient-weighted class activation mapping (Grad CAM) heatmaps, the high-value regions are clearly concentrated on the main areas of the face. Source code is published on GitLab platform.
Co-Authors Do Nang Toan Lam Thanh Hien Ngo Duc Vinh Nguyen Hoang Phuong Nguyen Trong Tung Nguyen Trong Vinh Truong Hong Thuy Vu Tung Lam