KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Search Results

Now showing 1 - 10 of 15

Some of the metrics are blocked by your
consent settings
Mammogram Analysis with YOLO Models on an Affordable Embedded System
(2026-01-01)
Intasam, Anongnat
;
Piyawattanametha, Nicholas
;
Promworn, Yuttachon
;
Jiranantanakorn, Titipon
;
Thawornwanchai, Soonthorn
Background/Objectives: Breast cancer persists as a leading cause of female mortality globally. Mammograms are a key screening tool for early detection, although many resource-limited hospitals lack access to skilled radiologists and advanced diagnostic tools. Deep learning-based computer-aided detection (CAD) systems can assist radiologists by automating lesion detection and classification. This study investigates the performance of various You Only Look Once (YOLO) models and a Hybrid Convolutional-Transformer Architecture (YOLOv5, YOLOv8, YOLOv10, YOLOv11, and Real-Time-DEtection Transformer (RT-DETR)) for detecting mammographic lesions on an affordable embedded system. Methods: We developed a custom web-based annotation tool to enhance mammogram labeling accuracy, using a dataset of 3169 patients from Thailand and expert annotations from three radiologists. Lesions were classified into six categories: Masses Benign (MB), Calcifications Benign (CB), Associated Features Benign (AFB), Masses Malignant (MM), Calcifications Malignant (CM), and Associated Features Malignant (AFM). Results: Our results show that the YOLOv11n model is the optimal choice for the NVIDIA Jetson Nano, achieving an accuracy of 0.86 and an inference speed of 6.16 ± 0.31 frames per second. A comparative analysis with a graphics processing unit (GPU)-powered system revealed that the Jetson Nano achieves comparable detection performance at a fraction of the cost. Conclusions: The current research landscape has not yet integrated advanced YOLO versions for embedded deployment in mammography. This method could facilitate screening in clinics without high-end workstations, demonstrating the feasibility of deploying CAD systems in low-resource environments and underscoring its potential for real-world clinical applications.
Some of the metrics are blocked by your
consent settings
An artificial intelligence model for the diagnosis of otitis media with effusion in children
(2026-01-01)
Ungkanont, Kitirat
;
Udomchaiporn, Akadej
;
Sriphoonga, Nopavit
;
Wannarong, Thanakrit
;
Rugsujrit, Thaweewat
Background: The diagnosis of otitis media with effusion (OME) requires substantial training and experience in otoscopic examination of children. Objective: This study developed an artificial intelligence (AI) model to predict OME diagnosis in children. Methods: The source data were images of pediatric patients’ tympanic membranes obtained by otoendoscopy. A convolutional neural network was used in machine learning. The diagnostic features of the tympanic membrane, as labelled by the experts, and the surgical findings served as the ground truth. InceptionV4 built the final model. The model was trained using the Adaptive Moment Estimation optimizer with an initial learning rate of 0.0001 and a total duration of 100 epochs. The batch size was 32. The Categorical Cross-Entropy loss function was employed for the internal validation. The outcome was to distinguish between OME and normal tympanic membrane. A confusion matrix was used to assess the model’s performance. The model was tested for agreement with otolaryngologists and implemented as a web application. Results: The initial sample size was 320 pictures. For OME, the model achieved an accuracy of 94.7% (95% CI 0.88, 1). The F1 score was 96% (95% CI 0.89, 1), and the area under the receiver operating characteristic curve was 0.98 (95% CI 0.93, 1). The kappa agreement between AI and experienced otolaryngologists was 0.627 (p < 0.001). Conclusion: An AI diagnostic model for otitis media with effusion had good accuracy and moderate agreement with otolaryngologists. The model should be helpful for preliminary diagnosis, telemedicine, or educational purposes.
Some of the metrics are blocked by your
consent settings
Unlocking the Future of Orthopaedic Imaging: A Comprehensive Update on the Role and Benefits of The Medical Open Network for AI (MONAI)
(2025-12-31)
Angthong, Chayanin
;
Angthong, Wirana
;
Pongsakonpruttikul, Napat
BACKGROUND: Deep learning (DL) has revolutionized orthopaedic imaging, transitioning from traditional radiomics-based analysis to powerful, data-driven diagnostic and prognostic models. However, a persistent lack of methodological standardization has limited clinical translation. The Medical Open Network for AI (MONAI), an open-source PyTorch-based framework, addresses this gap by providing domain-specific tools optimized for medical imaging. This review evaluates MONAI's role and benefits in orthopaedics across diagnosis, treatment planning, and outcomes prediction. MATERIAL AND METHODS: A comprehensive literature synthesis was conducted, examining studies utilizing MONAI for musculoskeletal imaging. We assessed technical attributes including architecture, data handling, loss functions, and multimodal integration and their applications in fracture detection, disease grading, surgical planning, and prognostic modeling. RESULTS: MONAI demonstrated superior efficiency in handling 3D/4D orthopaedic imaging data and managing class imbalance using specialized medical loss functions (e.g., Dice and Tversky). Diagnostic models achieved near-expert accuracy in fracture detection and quantitative osteoarthritis grading, providing explainable, and reproducible outputs. MONAI enabled automated, high-fidelity 3D reconstruction for personalized implant design and 3D printing integration. Prognostically, it outperformed surgeons in predicting arthroplasty complications, revealing latent imaging biomarkers. The framework's evolution into MONAI Multimodal - with agentic AI and radiomics integration - enhanced personalized, multimodal risk assessment. CONCLUSIONS: 1. MONAI establishes a standardized, transparent infrastructure that accelerates orthopaedic AI research and clinical translation. Its integration of domain-optimized architectures, multimodal data fusion, and explainable AI tools enables accurate diagnosis, individualized surgical planning, and reliable outcome prediction. 2. Adoption of MONAI-based pipelines is strongly recommended to promote reproducibility, regulatory readiness, and clinician trust in next generation of precision orthopaedic care.
Some of the metrics are blocked by your
consent settings
AI Chatbot for Post-Operative Oral Surgery Information and Support
(2025-08-07)
Warin, Kritsasith
;
Taetragoo, Unchalisa
;
Trachoo, Vorapat
;
Khanijoh, Chanon
;
Saepong, Pechdanai
This study presented the development of an AI chatbot specifically designed to address oral surgery-related inquiries. The chatbot, trained on a dataset of 240 questions, utilized machine learning algorithms to predict the corresponding operation for each question. The best model achieved accuracy of 0.906 in responding to questions. In conclusion, this AI chatbot has the potential to improve patient care by providing clear information to enhance post-operative outcomes.
Some of the metrics are blocked by your
consent settings
Early Diagnosis of Knee Osteoarthritis With a Natural Language Processing–Driven Approach Based on Clinician Notes: Development and Validation Study
(2025-01-01)
Thanyakunsajja, Narathip
;
Jitkajornwanich, Kulsawasd
;
Xu, Shan
;
Shin, Donghee
;
Charoenporn, Pattama
Background: Knee osteoarthritis (OA) is a common form of knee arthritis that can cause significant disability and affect a patient’s quality of life. Although this disease is chronic and irreversible, the patient’s condition can be improved and the progression of the disease can be prevented if the disease is diagnosed early and the patient receives appropriate treatment immediately. Therefore, the prediction of knee OA is considered one of the essential steps to effectively diagnose and prevent further severe OA conditions. Knee OA is commonly diagnosed by medical experts or physicians, and the diagnosis of OA is mainly based on patients’ laboratory results and medical images, including x-ray and magnetic resonance images. However, diagnosis through such data is often time-consuming. Moreover, the diagnosis results can vary among physicians depending on their expertise. Previous studies mostly focused on using approaches, such as those involving artificial intelligence, to automatically detect knee OA through such data. However, these studies did not incorporate clinicians’ or doctors’ notes (text data) into the analysis, although these data involving reported symptoms and behaviors are already available and easier to collect and access than laboratory data and image data. Objective: We propose a novel natural language processing–driven approach based on clinicians’ or doctors’ notes of patient-reported symptoms (text data only) for diagnosing knee OA. Methods: The textual information from clinicians’ or doctors’ notes was first preprocessed using text analysis algorithms with respect to natural language processing. We then incorporated deep learning models, including convolutional neural networks, bidirectional long short-term memory (BiLSTM), and gated recurrent units. Lastly, a disease-specific standard questionnaire called WOMAC (Western Ontario and McMaster Universities Arthritis Index) was taken into account to improve the overall performance of the models. Results: Our experiment included 5849 records (OA: 3455; non-OA: 2394). Before applying our WOMAC-based processing approach, the best-performing model was BiLSTM (area under the curve, 0.85; accuracy, 0.87; precision, 0.85; sensitivity, 0.95; specificity, 0.76; F<inf>1</inf>-score, 0.90), and there was an improvement in the results with BiLSTM after applying our approach (area under the curve, 0.91; accuracy, 0.91; precision, 0.91; sensitivity, 0.94; specificity, 0.87; F<inf>1</inf>-score, 0.93). Conclusions: Our proposed method for predicting the occurrence of knee OA showed better performance than other conventional methods that use image data and statistical laboratory data. The findings indicate the feasibility of using text data (symptom descriptions reported by patients and recorded by doctors) to predict knee OA. Medical notes of symptom reports can be considered a valuable data source for predicting whether a particular knee is likely to experience OA progression.
Some of the metrics are blocked by your
consent settings
Integrating Machine Learning for Automated Root Cause Analysis of Critical-to-Quality (CTQ) in Hard Disk Drive Manufacturing
(2025-01-01)
Inpang, Mullika
;
Thanasopon, Bundit
This research was studying the process of analyzing key factors that significantly impact the quality of Head Stack Assembly (HSA) in the production of Hard Disk Drives (HDDs). Various factors are considered, such as production machine, testing equipment, lot numbers of raw materials, production time and testing times etc. The assembly of the Head Stack is a critical step in Hard Disk Drives manufacturing. As the number of heads increases, the process requires greater precision and careful consideration of multiple factors. The use of artificial Intelligence technology in research is to be able to analyze the causal factors that affect the assembly of Head Stack more quickly and accurately in order to help reduce damage that will affect the production process and the quality of the Hard Disk Drives. It also increases the reliability of the product and raises the production standards, including quality control for the Hard Disk Drives manufacturing industry.
Some of the metrics are blocked by your
consent settings
PREDICTION OF AIR POLLUTION FROM POWER GENERATION USING MACHINE LEARNING
(2024-01-31)
Photsathian, Thongchai
;
Suttikul, Thitiporn
;
Tangsrirat, Worapong
Electrical energy is now widely recognized as an essential part of life for humans, as it powers many daily amenities and devices that people cannot function without. Examples of these include traffic signals, medical equipment in hospitals, electrical appliances used in homes and offices, and public transportation. The process that generates electricity can pollute the air. Even though natural gas used in power plants is derived from fossil fuels, it can nevertheless produce air pollutants involving particulate matter (PM), nitrogen oxides (NO<inf>x</inf>), and carbon monoxide (CO), which affect human health and cause environmental problems. Numerous researchers have devoted significant efforts to developing methods that not only facilitate the monitoring of current air quality but also possess the capability to predict the impacts of this increasing rise. The primary cause of air pollution issues associated with electricity generation is the combustion of fossil fuels. The objective of this study was to create three multiple linear regression models using artificial intelligence (AI) technology and data collected from sensors positioned around the energy generator. The objective was to precisely predict the amount of air pollution that electricity generation would produce. The highly accurate forecasted data proved valuable in determining operational parameters that resulted in minimal air pollution emissions. The predicted values were accurate with the mean squared error (MSE) of 0.008, the mean absolute error (MAE) of 0.071, and the mean absolute percentage error (MAPE) of 0.006 for the turbine energy yield (TEY). For the CO, the MSE was 2.029, the MAE was 0.791, and the MAPE was 0.934. For the NO<inf>x</inf>, the MSE was 69.479, the MAE was 6.148, and the MAPE was 0.096. The results demonstrate that the models developed have a high level of accuracy in identifying operational conditions that result in minimal air pollution emissions, with the exception of NO<inf>x</inf>. The accuracy of the NO<inf>x</inf> model is relatively lower, but it may still be used to estimate the pattern of NO<inf>x</inf> emissions.
Some of the metrics are blocked by your
consent settings
DETERMINANTS OF AI-BASED APPLICATIONS ADOPTION IN THE AGRICULTURAL SECTOR – MULTI-GROUP ANALYSIS
(2024-01-01)
Keerativutisest, Vasu
;
Chaiyasoonthorn, Wornchanok
;
Khalid, Bilal
;
Ślusarczyk, Beata
;
Chaveesuk, Singha
This research investigated the factors determining the adoption of AI-based applications in Thailand and Poland’s agricultural sectors. The study explored the sector’s adoption of AI technology and its contributions to driving the market and business performance. Despite the potential of AI in the agricultural sector, its adoption rate still needs to be clarified, and its potential needs to be better understood, hence the need for the study. The research applied primary data collected from respondents working in the agricultural sector in Thailand and Poland using a structured questionnaire. A sample of 356 and 377 respondents were representative samples in Thailand and Poland, respectively. The research was driven by the hypotheses evaluated using the Structural Equation Model (SEM). The findings indicated that organizational size was the most influential determinant of AI-based applications in both countries. Another significant determinant was technological competence in both countries. Additionally, social influence was a significant determinant in Thailand, while facilitating conditions and effort expectancy were significant determinants in Poland. The multi-group analysis revealed that the two countries were not invariant; hence, the effect of independent variables on behavioral intention to adopt AI between the two countries was different. The research recommended that each country’s policymakers consider its contexts differently in AI-based application adoption policies. However, improving the organizational size and technological competence would enhance the adoption of AI-based applications across the board.
Some of the metrics are blocked by your
consent settings
Enhancing Odor Classification of Essential Oils with Electronic Nose Data
(2024-01-01)
Grodniyomchai, Boonyawee
;
Satcharoen, Kleddao
;
Tangtisanon, Pikulkaew
In the current business landscape, the fragrance industry has gained substantial prominence. In this context, there is a requirement to create the most compact and sufficiently accurate model possible, suitable for deployment on a portable device. The aim is to develop a model capable of effectively classifying various fragrance types based on data pertaining to air properties and fragrance component attributes. This paper presents the feature extraction from the dataset electronic node to classify odor types using a machine learning model compared before and after the feature extraction of the dataset. In our investigation, we employed datasets of varying sizes, including small datasets (composed of 1000 samples), large datasets (composed of 10000 samples), and raw datasets (composed of 21000 samples). This methodology was employed to discern disparities in model performance, average accuracy, and computational runtime across these different dataset sizes. We observed that the decision tree model, post-training with principal component analysis, showed a performance improvement when compared to the basic machine learning model. Specifically, the decision tree model achieved accuracy rates of 100.00%, 99.97%, and 97.00% respectively.
Some of the metrics are blocked by your
consent settings
Proximal Policy Optimization for Crowd Evacuation in Complex Environments - A Metaverse Approach at Krung Thep Aphiwat Central Terminal, Thailand
(2024-01-01)
Chaudhary, Sushank
;
Sinpan, Nitinun
;
Sasithong, Pruk
;
Khichar, Sunita
;
La-Aiddee, Panithan
Efficient crowd evacuation from railway platforms is critical for passenger safety during emergencies. This study introduces a novel dynamic emergency evacuation route generator using the Proximal Policy Optimization (PPO) algorithm within a custom-built 3D simulation environment developed in Unity. We independently created a detailed digital twin of Krung Thep Aphiwat Central Terminal, Thailand's largest train station, and implemented all elements of the simulation, including the Social Force Model, to accurately replicate crowd behaviors and interactions during evacuation scenarios. Through extensive training over 3,000,000 episodes, our PPO-based model achieved significant improvements in evacuation efficiency. The results indicate that in a major emergency scenario, increasing the number of agents in the station reduced the number of remaining passengers from 111 to just 6, highlighting the model's effectiveness. Similarly, in a minor emergency scenario, the average number of remaining passengers dropped from 38 to 1 with the addition of more agents. These findings confirm the model's ability to adapt to different emergency conditions, offering a practical and scalable solution for enhancing evacuation strategies in high-density environments. Furthermore, increasing the agents' sight range also improved evacuation efficiency, with a 20-meter sight range yielding the best results.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results