Chonlameth Arpnikanondt
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Chonlameth Arpnikanondt has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
- Debajyoti Pal
School of Information Technology, KMUTT, Thungkru, Bangkok, Thailand
3 shared publications - Bunyarit Puangthamawathanakun
Dublin City University, IE
2 shared publications - Cathal Gurrin
Dublin City University, Dublin, Ireland
2 shared publications - Graham Healy
School of Computing, Dublin City University, Dublin, Ireland
2 shared publications - Tuul Triyason
School of Information Technology, KMUTT, Thungkru, Bangkok, Thailand
2 shared publications Adi Wibowo
1 shared publication
Latest Publications
- Open Access
- 16 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Thai Threat News Classification Using Open-Source LLMs: A Comparative Evaluation of Models and Prompt Strategies
- 16 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Open AccessThai Threat News Classification Using Open-Source LLMs: A Comparative Evaluation of Models and Prompt Strategies
- Open Access
- 16 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Geometry-Aware Foundation Makeup Simulation Using Radiative Transfer Models
This research details a simulation pipeline methodology for applying a physics-based foundation simulation pipeline that leverages both full-spectrum Kubelka–Munk theory and the four-flux radiative transfer model. Unlike traditional alpha-blending, image-processing techniques, or contemporary deep learning methods such as GAN-based makeup transfer and neural style transfer, this approach simulates the actual physical light transport within a translucent cosmetic layer applied to human skin. While generative AI models often provide visually plausible results, they frequently lack physical consistency, fail to satisfy optical energy conservation (light transport) constraints, and cannot accurately account for complex 3D lighting interactions. By operating in a physically linear color space and reconstructing full-wavelength spectral reflectances from RGB data, this system ensures rigorous color accuracy and robustness under varying environmental lighting. This work focuses on the cohesive system-level synthesis of these physics-based components and provides a comparative empirical evaluation under professional DSLR and consumer mobile imaging environments. This provides a practical end-to-end pipeline that achieves physically consistent virtual try-on while remaining grounded in optical physics.
- 16 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Open AccessGeometry-Aware Foundation Makeup Simulation Using Radiative Transfer Models
This research details a simulation pipeline methodology for applying a physics-based foundation simulation pipeline that leverages both full-spectrum Kubelka–Munk theory and the four-flux radiative transfer model. Unlike traditional alpha-blending, image-processing techniques, or contemporary deep learning methods such as GAN-based makeup transfer and neural style transfer, this approach simulates the actual physical light transport within a translucent cosmetic layer applied to human skin. While generative AI models often provide visually plausible results, they frequently lack physical consistency, fail to satisfy optical energy conservation (light transport) constraints, and cannot accurately account for complex 3D lighting interactions. By operating in a physically linear color space and reconstructing full-wavelength spectral reflectances from RGB data, this system ensures rigorous color accuracy and robustness under varying environmental lighting. This work focuses on the cohesive system-level synthesis of these physics-based components and provides a comparative empirical evaluation under professional DSLR and consumer mobile imaging environments. This provides a practical end-to-end pipeline that achieves physically consistent virtual try-on while remaining grounded in optical physics.
- Open Access
- 5 March 2026
- Published by MDPI AG in Environments
- Vol. 13 (3) , 141
Geospatial Optimization of Field Engineer Deployment for Sustainable Telecommunication Tower Maintenance: A Case Study in West Java, Indonesia
The rapid expansion of telecommunication infrastructure in developing countries has increased the demand for sustainable strategies to deploy field engineers in tower maintenance operations. Traditional approaches often neglect spatial factors, resulting in inefficient workforce allocation, excessive travel, and higher carbon emissions. This study develops an applied geospatial deployment framework that integrates spatial analysis with sustainable supply chain management (SSCM) principles to support operational decision-making in resource-constrained telecommunication maintenance environments. Using publicly available tools, tower and homebase coordinates were mapped and analyzed through Haversine-based geodesic distance calculations, with a comparative assessment against Euclidean approximation, while incorporating operational constraints such as service time per tower, available personnel, and work-hour limitations. The results indicate that the existing two-homebase deployment strategy leads to unbalanced workloads and unnecessary travel distances. By introducing a cluster-based restructuring using k-means to identify four sub-homebases, the proposed approach reduces total round-trip travel distance from 9120 km to 5913 km per maintenance cycle, representing a 35.2% reduction. This distance reduction corresponds to an estimated saving of approximately 593 kg of CO2 emissions per maintenance cycle, representing an operational-scale reduction in travel-related emissions based on distance-derived fuel consumption modeling and assuming typical fuel efficiency for service vehicles. In addition, the optimized spatial configuration enables a more equitable distribution of engineers and reduces travel-related fatigue. These findings demonstrate the value of integrating geospatial optimization with sustainable supply chain management by aligning operational efficiency with quantifiable environmental and social sustainability outcomes. The proposed framework offers a replicable, low-cost, and data-driven solution for telecommunication infrastructure providers seeking to enhance the sustainability of field service operations in resource-constrained environments.
- 5 March 2026
- Published by MDPI AG in Environments
- Vol. 13 (3) , 141
Open AccessGeospatial Optimization of Field Engineer Deployment for Sustainable Telecommunication Tower Maintenance: A Case Study in West Java, Indonesia
The rapid expansion of telecommunication infrastructure in developing countries has increased the demand for sustainable strategies to deploy field engineers in tower maintenance operations. Traditional approaches often neglect spatial factors, resulting in inefficient workforce allocation, excessive travel, and higher carbon emissions. This study develops an applied geospatial deployment framework that integrates spatial analysis with sustainable supply chain management (SSCM) principles to support operational decision-making in resource-constrained telecommunication maintenance environments. Using publicly available tools, tower and homebase coordinates were mapped and analyzed through Haversine-based geodesic distance calculations, with a comparative assessment against Euclidean approximation, while incorporating operational constraints such as service time per tower, available personnel, and work-hour limitations. The results indicate that the existing two-homebase deployment strategy leads to unbalanced workloads and unnecessary travel distances. By introducing a cluster-based restructuring using k-means to identify four sub-homebases, the proposed approach reduces total round-trip travel distance from 9120 km to 5913 km per maintenance cycle, representing a 35.2% reduction. This distance reduction corresponds to an estimated saving of approximately 593 kg of CO2 emissions per maintenance cycle, representing an operational-scale reduction in travel-related emissions based on distance-derived fuel consumption modeling and assuming typical fuel efficiency for service vehicles. In addition, the optimized spatial configuration enables a more equitable distribution of engineers and reduces travel-related fatigue. These findings demonstrate the value of integrating geospatial optimization with sustainable supply chain management by aligning operational efficiency with quantifiable environmental and social sustainability outcomes. The proposed framework offers a replicable, low-cost, and data-driven solution for telecommunication infrastructure providers seeking to enhance the sustainability of field service operations in resource-constrained environments.
- Open Access
- 1 January 2026
- Published by Tech Science Press in Computers, Materials & Continua
- Vol. 89 (3) , 1-10
A Robustness Aware Intrusion Detection Framework Using Ensemble Learning and Imbalance Aware Preprocessing for Smart Home IoT Networks
The proliferation of smart home Internet of Things (IoT) devices has introduced critical security vulnerabilities that demand robust and efficient intrusion detection mechanisms. Existing machine learning-based Intrusion Detection Systems (IDS) often suffer from class imbalance bias, limited cross domain generalization, and insufficient robustness evaluation under adversarial conditions. This study proposes a robustness-aware intrusion detection framework that systematically integrates imbalance-aware preprocessing and ensemble machine learning into a unified pipeline specifically designed for resource-constrained smart home IoT environments. The framework employs Min Max normalization and Synthetic Minority Over sampling Technique (SMOTE) with strict train-test separation to prevent data leakage, operating directly on the seven packet-level traffic features available in the capture rather than on a reduced subset. Three machine learning models Decision Tree (DT), Random Forest (RF), and XGBoost are systematically compared against deep learning baselines (CNN and LSTM) across three benchmark IoT datasets: COMNETS Smart Home, IoT-23, and TON IoT. Under a conventional random-split evaluation, XGBoost achieves the highest detection performance (97.8% accuracy, 97.0% F1) at substantially lower computational cost than the deep-learning alternatives; a leakage-controlled evaluation, however, shows that much of this reflects evaluation artifacts, with the honest macro-F1 falling to 0.558 and reliable detection of the scarce benign (minority) class remaining unverified. Cross-dataset experiments are reported as a preliminary analysis; because the feature spaces could only be approximately harmonized, these results are indicative rather than conclusive evidence of cross-domain generalization. Robustness analysis under Gaussian noise injection (5%–15%) and random feature perturbation (not gradient-based adversarial attacks) reveals that ensemble models exhibit significantly lower performance degradation compared to single-tree approaches. Statistical significance testing (paired t-test, p < 0.05) validates that the observed improvements are not attributable to random variation. These results show that, once evaluation artifacts are controlled for, the honest performance of these lightweight models is modest, underscoring the importance of leakage-aware evaluation for smart-home IoT intrusion detection.
- 1 January 2026
- Published by Tech Science Press in Computers, Materials & Continua
- Vol. 89 (3) , 1-10
Open AccessA Robustness Aware Intrusion Detection Framework Using Ensemble Learning and Imbalance Aware Preprocessing for Smart Home IoT Networks
The proliferation of smart home Internet of Things (IoT) devices has introduced critical security vulnerabilities that demand robust and efficient intrusion detection mechanisms. Existing machine learning-based Intrusion Detection Systems (IDS) often suffer from class imbalance bias, limited cross domain generalization, and insufficient robustness evaluation under adversarial conditions. This study proposes a robustness-aware intrusion detection framework that systematically integrates imbalance-aware preprocessing and ensemble machine learning into a unified pipeline specifically designed for resource-constrained smart home IoT environments. The framework employs Min Max normalization and Synthetic Minority Over sampling Technique (SMOTE) with strict train-test separation to prevent data leakage, operating directly on the seven packet-level traffic features available in the capture rather than on a reduced subset. Three machine learning models Decision Tree (DT), Random Forest (RF), and XGBoost are systematically compared against deep learning baselines (CNN and LSTM) across three benchmark IoT datasets: COMNETS Smart Home, IoT-23, and TON IoT. Under a conventional random-split evaluation, XGBoost achieves the highest detection performance (97.8% accuracy, 97.0% F1) at substantially lower computational cost than the deep-learning alternatives; a leakage-controlled evaluation, however, shows that much of this reflects evaluation artifacts, with the honest macro-F1 falling to 0.558 and reliable detection of the scarce benign (minority) class remaining unverified. Cross-dataset experiments are reported as a preliminary analysis; because the feature spaces could only be approximately harmonized, these results are indicative rather than conclusive evidence of cross-domain generalization. Robustness analysis under Gaussian noise injection (5%–15%) and random feature perturbation (not gradient-based adversarial attacks) reveals that ensemble models exhibit significantly lower performance degradation compared to single-tree approaches. Statistical significance testing (paired t-test, p < 0.05) validates that the observed improvements are not attributable to random variation. These results show that, once evaluation artifacts are controlled for, the honest performance of these lightweight models is modest, underscoring the importance of leakage-aware evaluation for smart-home IoT intrusion detection.
- Open Access
- 20 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 168-172
Efficient Search with an Interactive Video Retrieval System for Novice Users in IVR4B
In this paper, we present the second release of VideoCLIP, an interactive CLIP-based video retrieval system that participated in the Video Browser Showdown 2023. While we continue to use the underlying architecture to map the content between image and text, we concentrate on improving the user experience for novice users. Specifically, we have implemented three different query modalities and redesigned the user interface in order to adapt to the context of the Interactive Video Retrieval for Beginners (IVR4B) workshop. These modifications ultimately aim to provide newcomers with a simple and efficient user experience to locate the desired videos.
- 20 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 168-172
Open AccessEfficient Search with an Interactive Video Retrieval System for Novice Users in IVR4B
In this paper, we present the second release of VideoCLIP, an interactive CLIP-based video retrieval system that participated in the Video Browser Showdown 2023. While we continue to use the underlying architecture to map the content between image and text, we concentrate on improving the user experience for novice users. Specifically, we have implemented three different query modalities and redesigned the user interface in order to adapt to the context of the Interactive Video Retrieval for Beginners (IVR4B) workshop. These modifications ultimately aim to provide newcomers with a simple and efficient user experience to locate the desired videos.
- Open Access
- 20 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 210-216
Towards Face De-identification for Wearable Cameras
Wearable cameras provide valuable new sources of data for health and wellness monitoring, however, such visual data brings privacy concerns. This paper proposes a prototype egocentric face de-identification system for wearable camera images by swapping the original faces with synthetic faces. The motivation of this paper is to: (1) de-identify faces in egocentric images and (2) preserve the existence of each identity in images where the source identity is altered. The system incorporates our proposed method, which promises a privacy-aware and cost-effective approach. We evaluated the system on the Ego4D audio-visual PoV diarization training set by analysing six activities where faces are visible in wearable camera data. The results show promising de-identification on the source faces while most existences remain.
- 20 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 210-216
Open AccessTowards Face De-identification for Wearable Cameras
Wearable cameras provide valuable new sources of data for health and wellness monitoring, however, such visual data brings privacy concerns. This paper proposes a prototype egocentric face de-identification system for wearable camera images by swapping the original faces with synthetic faces. The motivation of this paper is to: (1) de-identify faces in egocentric images and (2) preserve the existence of each identity in images where the source identity is altered. The system incorporates our proposed method, which promises a privacy-aware and cost-effective approach. We evaluated the system on the Ego4D audio-visual PoV diarization training set by analysing six activities where faces are visible in wearable camera data. The results show promising de-identification on the source faces while most existences remain.
- Open Access
- 14 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 143481-143494
Digital Diagnosis of Hand, Foot, and Mouth Disease Using Hybrid Deep Neural Networks
Hand, Foot and Mouth Disease (HFMD) is a highly contagious paediatric disease showing up symptoms like fever, diarrhoea, oral ulcers and rashes on the hands and foot, and even in the mouth. This disease has become an epidemic with several outbreaks in many Asian-Pacific countries with the basic reproduction number $R_{0} > 1$ . HFMD’s diagnosis is very challenging as its lesion pattern may appear quite similar to other skin diseases such as herpangina, aseptic meningitis, and poliomyelitis. Therefore, clinical symptoms are essential besides skin lesion’s pattern and position for precise diagnose of this disease. A deep learning-based HFMD detection system can play a significant role in the digital diagnosis of this disease. Various machine learning and deep learning architectures have been proposed for skin disease diagnosis and classification. However, these models are limited to the image classification problem. The diagnosis of similar appearing skin diseases using the image classification approach may result in misclassification or misdiagnosis of the disease. Parallel integration of clinical symptoms and images can improve disease diagnosis and classification performance. However, no deep learning architecture has been developed to diagnose HFMD disease from images and clinical data. This paper has proposed a novel Hybrid Deep Neural Networks integrating Multi-Layer Perceptron (MLP) network and Convolutional Neural Network into a single framework for the diagnosis of HFMD using the integrated features from clinical and image data. The proposed Hybrid Deep Neural Networks is particularly a multi branched model comprising of Multi-Layer Perceptron (MLP) network in the first branch to extract the clinical features and the modified pre-trained CNN architecture: MobileNet or NasNetMobile in the second branch to extract the features from skin disease lesion images. The features learnt from both the branches are merged to form an integrated feature from clinical data and images, which is fed to the subsequent classification network. We conducted several experiments employing image data only, clinical data only and both sources of data. The analyses compared and evaluated the performance of a typical MLP model and CNN model with our proposed Hybrid Deep Neural Networks. The novel approach promotes the existing image classification model and clinical symptoms based disease classification model, particularly the MLP model. From the cross-validated experiments, the results reveal that the proposed Hybrid Deep Neural Networks can diagnose the disease 99%-100% accurately.
- 14 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 143481-143494
Open AccessDigital Diagnosis of Hand, Foot, and Mouth Disease Using Hybrid Deep Neural Networks
Hand, Foot and Mouth Disease (HFMD) is a highly contagious paediatric disease showing up symptoms like fever, diarrhoea, oral ulcers and rashes on the hands and foot, and even in the mouth. This disease has become an epidemic with several outbreaks in many Asian-Pacific countries with the basic reproduction number $R_{0} > 1$ . HFMD’s diagnosis is very challenging as its lesion pattern may appear quite similar to other skin diseases such as herpangina, aseptic meningitis, and poliomyelitis. Therefore, clinical symptoms are essential besides skin lesion’s pattern and position for precise diagnose of this disease. A deep learning-based HFMD detection system can play a significant role in the digital diagnosis of this disease. Various machine learning and deep learning architectures have been proposed for skin disease diagnosis and classification. However, these models are limited to the image classification problem. The diagnosis of similar appearing skin diseases using the image classification approach may result in misclassification or misdiagnosis of the disease. Parallel integration of clinical symptoms and images can improve disease diagnosis and classification performance. However, no deep learning architecture has been developed to diagnose HFMD disease from images and clinical data. This paper has proposed a novel Hybrid Deep Neural Networks integrating Multi-Layer Perceptron (MLP) network and Convolutional Neural Network into a single framework for the diagnosis of HFMD using the integrated features from clinical and image data. The proposed Hybrid Deep Neural Networks is particularly a multi branched model comprising of Multi-Layer Perceptron (MLP) network in the first branch to extract the clinical features and the modified pre-trained CNN architecture: MobileNet or NasNetMobile in the second branch to extract the features from skin disease lesion images. The features learnt from both the branches are merged to form an integrated feature from clinical data and images, which is fed to the subsequent classification network. We conducted several experiments employing image data only, clinical data only and both sources of data. The analyses compared and evaluated the performance of a typical MLP model and CNN model with our proposed Hybrid Deep Neural Networks. The novel approach promotes the existing image classification model and clinical symptoms based disease classification model, particularly the MLP model. From the cross-validated experiments, the results reveal that the proposed Hybrid Deep Neural Networks can diagnose the disease 99%-100% accurately.
- 19 July 2021
- Published by River Publishers in Journal of Web Engineering
- Vol. 20 (5) , 1425-1464
Unified Model for Learning Style Recommendation
Studying computer programming requires not only an understanding of theories and concepts but also coding adeptness. Success in studying or conducting such a course is definitely a challenge. This paper proposes a systematic learning style recommendation. The model is designed to evaluate students’ attributes and ongoing or formative learning outcomes for suggesting the effective style-fit strategy that facilitates learners to enhance their learning performances in terms of knowledge and skill. A two-stage association analysis was designed and conducted on a dataset collected from IT major students who enrolled in the Introduction to Computer Programming course. The first stage of association rules is to analyze and discover important relationships amongst learning styles, students’ attribute, and learning performance. The second stage of moderation analysis is then applied to probe the moderation effect of the different learning preferences on the relationship between student attributes and learning achievement. Experiments expose many insights, for example, mathematics and logical thinking are powerful assets of success in computer programming study. Association rules can effectively identify associations of learning styles and the learning performance in terms of knowledge or skills. By moderation analysis, students in the “Excellent” cluster have a broad learning style than other students. Two types of significant moderators, the universal and specific, exemplify how lecturers can flexibly post style-fit teaching strategies for a class-wide and specific group, respectively.
- 19 July 2021
- Published by River Publishers in Journal of Web Engineering
- Vol. 20 (5) , 1425-1464
Unified Model for Learning Style Recommendation
Studying computer programming requires not only an understanding of theories and concepts but also coding adeptness. Success in studying or conducting such a course is definitely a challenge. This paper proposes a systematic learning style recommendation. The model is designed to evaluate students’ attributes and ongoing or formative learning outcomes for suggesting the effective style-fit strategy that facilitates learners to enhance their learning performances in terms of knowledge and skill. A two-stage association analysis was designed and conducted on a dataset collected from IT major students who enrolled in the Introduction to Computer Programming course. The first stage of association rules is to analyze and discover important relationships amongst learning styles, students’ attribute, and learning performance. The second stage of moderation analysis is then applied to probe the moderation effect of the different learning preferences on the relationship between student attributes and learning achievement. Experiments expose many insights, for example, mathematics and logical thinking are powerful assets of success in computer programming study. Association rules can effectively identify associations of learning styles and the learning performance in terms of knowledge or skills. By moderation analysis, students in the “Excellent” cluster have a broad learning style than other students. Two types of significant moderators, the universal and specific, exemplify how lecturers can flexibly post style-fit teaching strategies for a class-wide and specific group, respectively.
- 17 February 2021
- Published by Springer Nature in Wireless Personal Communications
- Vol. 119 (2) , 1065-1092
An Integrated TAM/ISS Model Based PLS-SEM Approach for Evaluating the Continuous Usage of Voice Enabled IoT Systems
- 17 February 2021
- Published by Springer Nature in Wireless Personal Communications
- Vol. 119 (2) , 1065-1092
An Integrated TAM/ISS Model Based PLS-SEM Approach for Evaluating the Continuous Usage of Voice Enabled IoT Systems