Puriwat Lertkrai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Puriwat Lertkrai has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Nattapong Kaewboonma
Faculty of Management Technology, Rajamangala University of Technology Srivijaya, Nakhon Si Thammarat 80110, Thailand
5 shared publications - Benjamin Chanakot
Rajamangala University of Technology Srivijaya
2 shared publications - Jutaporn Lertkrai1 shared publication
- Jutaporn Lertkrai
Faculty of Management Technology, Rajamangala University of Technology Srivijaya, Thailand
1 shared publication - Kanitsorn Suriyapaiboonwattana
Informatics Innovation Center of Excellence, School of Informatics, Walailak University, Nakhon Si Thammarat 80160, Thailand
1 shared publication - Kate Hone
Computer Science, Brunel University of London, Uxbridge UB8 3PH, UK
1 shared publication
Latest Publications
- Open Access
- 18 August 2025
- Published by MDPI AG in Informatics
- Vol. 12 (3) , 84
Marketing a Banned Remedy: A Topic Model Analysis of Health Misinformation in Thai E-Commerce
Unregulated herbal products marketed via digital platforms present escalating risks to consumer safety and regulatory effectiveness worldwide. This study positions the case of Jindamanee herbal powder—a banned substance under Thai law—as a lens through which to examine broader challenges in digital health governance. Drawing on a dataset of 1546 product listings across major platforms (Facebook, TikTok, Shopee, and Lazada), we applied Latent Dirichlet Allocation (LDA) to identify prevailing promotional themes and compliance gaps. Despite explicit platform policies, 87.6% of listings appeared on Facebook. Medical claims, particularly for pain relief, featured in 77.6% of posts, while only 18.4% included any risk disclosure. These findings suggest a systematic exploitation of regulatory blind spots and consumer health anxieties, facilitated by templated cross-platform messaging. Anchored in Information Manipulation Theory and the Health Belief Model, the analysis offers theoretical insight into how misinformation is structured and sustained within digital commerce ecosystems. The Thai case highlights urgent implications for platform accountability, policy harmonization, and the design of algorithmic surveillance systems in global health product regulation.
- 18 August 2025
- Published by MDPI AG in Informatics
- Vol. 12 (3) , 84
Open AccessMarketing a Banned Remedy: A Topic Model Analysis of Health Misinformation in Thai E-Commerce
Unregulated herbal products marketed via digital platforms present escalating risks to consumer safety and regulatory effectiveness worldwide. This study positions the case of Jindamanee herbal powder—a banned substance under Thai law—as a lens through which to examine broader challenges in digital health governance. Drawing on a dataset of 1546 product listings across major platforms (Facebook, TikTok, Shopee, and Lazada), we applied Latent Dirichlet Allocation (LDA) to identify prevailing promotional themes and compliance gaps. Despite explicit platform policies, 87.6% of listings appeared on Facebook. Medical claims, particularly for pain relief, featured in 77.6% of posts, while only 18.4% included any risk disclosure. These findings suggest a systematic exploitation of regulatory blind spots and consumer health anxieties, facilitated by templated cross-platform messaging. Anchored in Information Manipulation Theory and the Health Belief Model, the analysis offers theoretical insight into how misinformation is structured and sustained within digital commerce ecosystems. The Thai case highlights urgent implications for platform accountability, policy harmonization, and the design of algorithmic surveillance systems in global health product regulation.
- Open Access
- 1 January 2025
- Published by IACSIT Press in International Journal of Computer Theory and Engineering
- Vol. 17 (3) , 126-133
Deployment of a Deep Learning Model for the Automated Diagnosis of Thai Rubber Leaf Diseases via the LINE Platform
This research presents an approach for real-time detection of rubber leaf diseases using the YOLOv8 deep learning model, integrated with the LINE messaging platform. The system enables users to submit rubber leaf images via LINE, where they are processed by an Artificial Intelligence (AI)—powered backend hosted on Heroku, utilizing Docker and Flask for scalability and efficiency. The YOLOv8 model was trained on a dataset comprising three classes: Healthy, New Disease, and Powdery Mildew. It achieved an overall mAP50 of 57.9% and an mAP50-95 of 42.8%, demonstrating strong performance in detecting healthy leaves (mAP50: 98.3%) but lower accuracy in identifying Powdery Mildew (mAP50: 22.4%), likely due to significant class imbalance. User testing involved 50 beta testers who submitted 500 images through the chatbot, yielding a detection accuracy of 72.4%, a misclassification rate of 5.4%, and an average response time of 2.5 seconds. Key performance metrics included a macro-average precision of 78.2%, recall of 73.0%, and an F1 score of 75.5%. User feedback highlighted satisfaction with the system’s ease of use and response speed, though improvements were suggested in handling misclassifications and providing treatment recommendations. These results indicate that the system offers a robust and scalable solution for rubber leaf disease detection, with potential for further optimization.
- 1 January 2025
- Published by IACSIT Press in International Journal of Computer Theory and Engineering
- Vol. 17 (3) , 126-133
Open AccessDeployment of a Deep Learning Model for the Automated Diagnosis of Thai Rubber Leaf Diseases via the LINE Platform
This research presents an approach for real-time detection of rubber leaf diseases using the YOLOv8 deep learning model, integrated with the LINE messaging platform. The system enables users to submit rubber leaf images via LINE, where they are processed by an Artificial Intelligence (AI)—powered backend hosted on Heroku, utilizing Docker and Flask for scalability and efficiency. The YOLOv8 model was trained on a dataset comprising three classes: Healthy, New Disease, and Powdery Mildew. It achieved an overall mAP50 of 57.9% and an mAP50-95 of 42.8%, demonstrating strong performance in detecting healthy leaves (mAP50: 98.3%) but lower accuracy in identifying Powdery Mildew (mAP50: 22.4%), likely due to significant class imbalance. User testing involved 50 beta testers who submitted 500 images through the chatbot, yielding a detection accuracy of 72.4%, a misclassification rate of 5.4%, and an average response time of 2.5 seconds. Key performance metrics included a macro-average precision of 78.2%, recall of 73.0%, and an F1 score of 75.5%. User feedback highlighted satisfaction with the system’s ease of use and response speed, though improvements were suggested in handling misclassifications and providing treatment recommendations. These results indicate that the system offers a robust and scalable solution for rubber leaf disease detection, with potential for further optimization.
- Open Access
- 16 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 84-91
Thai Rubber Leaf Disease Classification Using Deep Learning Techniques
This research investigated the utilization of deep learning methodologies for the precise classification of Thai rubber leaf diseases using leaf images. The study employed a diverse set of convolutional neural network (CNN) models, including VGG16, ResNet50, EfficientNet, and YOLOv8, to accomplish this task. Data augmentation techniques were employed to address overfitting, thereby enhancing the robustness of the models. The dataset, meticulously curated and labeled by domain experts, comprised 734 high-quality rubber leaf images categorized into three distinct classes: new diseases, powdery mildew disease, and healthy leaves. The findings revealed that YOLOv8n-cls emerged as the optimal choice, demonstrating exceptional efficiency with a diminutive model size (5.5 MB) and a parsimonious parameter count (1.44 million). This model exhibited remarkable accuracy (98.68%) and an impressive F1-score of 0.98, establishing its proficiency in delivering precise and reliable predictions. Furthermore, a comparative analysis of YOLOv8 pretrained classify models underscored YoloV8s as the most favorable option, characterized by the lowest validation loss. These results highlighted the potential of deep learning methodologies in the field of agricultural disease detection, offering a cost-effective and efficient solution for rubber plantation owners and farmers. This research contributed valuable insights into the application of advanced technology to address critical challenges in the agricultural sector, particularly in the context of plant disease detection and classification.
- 16 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 84-91
Open AccessThai Rubber Leaf Disease Classification Using Deep Learning Techniques
This research investigated the utilization of deep learning methodologies for the precise classification of Thai rubber leaf diseases using leaf images. The study employed a diverse set of convolutional neural network (CNN) models, including VGG16, ResNet50, EfficientNet, and YOLOv8, to accomplish this task. Data augmentation techniques were employed to address overfitting, thereby enhancing the robustness of the models. The dataset, meticulously curated and labeled by domain experts, comprised 734 high-quality rubber leaf images categorized into three distinct classes: new diseases, powdery mildew disease, and healthy leaves. The findings revealed that YOLOv8n-cls emerged as the optimal choice, demonstrating exceptional efficiency with a diminutive model size (5.5 MB) and a parsimonious parameter count (1.44 million). This model exhibited remarkable accuracy (98.68%) and an impressive F1-score of 0.98, establishing its proficiency in delivering precise and reliable predictions. Furthermore, a comparative analysis of YOLOv8 pretrained classify models underscored YoloV8s as the most favorable option, characterized by the lowest validation loss. These results highlighted the potential of deep learning methodologies in the field of agricultural disease detection, offering a cost-effective and efficient solution for rubber plantation owners and farmers. This research contributed valuable insights into the application of advanced technology to address critical challenges in the agricultural sector, particularly in the context of plant disease detection and classification.
- 27 September 2018
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2016 (1) , 020072
Developing ontology of food and nutrition for Thai pre-school
Nutrition is very important for pre-school children age 1-5 years. At this age, they grow too fast both with body and brain. Structural damages in the body and brain may result if children are underweight or obese. In this research, we propose an ontology development of food and nutrition for pre-school that aims to assist pre-school in daily diet selections based on Thai foods menus and nutrition guidelines. This research reused existing ontologies and resources to present the ontology modeling and rules-based that focus on Thai pre-school. The methodology of this research can be summarized into four major states; data collection, ontology development, rules-based development, and evaluation. The eight main classes of this ontology are Body Mass Index (BMI) levels, Thai foods menus, Food energy levels, and knowledge base for providing the recommendation based on BMI level for Thai pre-school. In addition, the evaluation result from domain experts ensured that this ontology and rules-based can be used in Thai food menu recommendation system for Thai pre-school.
- 27 September 2018
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2016 (1) , 020072
Developing ontology of food and nutrition for Thai pre-school
Nutrition is very important for pre-school children age 1-5 years. At this age, they grow too fast both with body and brain. Structural damages in the body and brain may result if children are underweight or obese. In this research, we propose an ontology development of food and nutrition for pre-school that aims to assist pre-school in daily diet selections based on Thai foods menus and nutrition guidelines. This research reused existing ontologies and resources to present the ontology modeling and rules-based that focus on Thai pre-school. The methodology of this research can be summarized into four major states; data collection, ontology development, rules-based development, and evaluation. The eight main classes of this ontology are Body Mass Index (BMI) levels, Thai foods menus, Food energy levels, and knowledge base for providing the recommendation based on BMI level for Thai pre-school. In addition, the evaluation result from domain experts ensured that this ontology and rules-based can be used in Thai food menu recommendation system for Thai pre-school.
- 27 September 2018
- Published by AIP Publishing
- Vol. 2016 (1) , 020146
Hypertension management ontology based on Thai guidelines on the treatment of hypertension
This study aims to develop an ontology for hypertension management based on Thai guidelines on the treatment of hypertension by Thai Hypertension Society. The study and development methods were used in following steps. In the concerting stage, a qualitative research method was applied in the following steps: 1) Content analysis of the Thai Hypertension Guideline; 2) Organizing the knowledge on Thai Hypertension Guideline using the domain analytic approach; and 3) Clarification of the knowledge organization by the domain experts and modification. In the developing stage, Ontology development is composed of four steps: 1) Setting the Scope; 2) Enumerate Terms, Defining the Class and Class Hierarchy; 3) Creating Instances, and 4) Implementation and Evaluation of Ontologies. The research result provides the ontology for treatment of hypertension which comprised seven main classes. Each class is divided into sub-class in which the relationships of them are direct properties of class. The ontology can be used to give the advice for lifestyle modification and provide choice of drug therapy with the capacity of recommender system.
- 27 September 2018
- Published by AIP Publishing
- Vol. 2016 (1) , 020146
Hypertension management ontology based on Thai guidelines on the treatment of hypertension
This study aims to develop an ontology for hypertension management based on Thai guidelines on the treatment of hypertension by Thai Hypertension Society. The study and development methods were used in following steps. In the concerting stage, a qualitative research method was applied in the following steps: 1) Content analysis of the Thai Hypertension Guideline; 2) Organizing the knowledge on Thai Hypertension Guideline using the domain analytic approach; and 3) Clarification of the knowledge organization by the domain experts and modification. In the developing stage, Ontology development is composed of four steps: 1) Setting the Scope; 2) Enumerate Terms, Defining the Class and Class Hierarchy; 3) Creating Instances, and 4) Implementation and Evaluation of Ontologies. The research result provides the ontology for treatment of hypertension which comprised seven main classes. Each class is divided into sub-class in which the relationships of them are direct properties of class. The ontology can be used to give the advice for lifestyle modification and provide choice of drug therapy with the capacity of recommender system.