KMITL

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

Browse

Search Results

Now showing 1 - 10 of 54

Some of the metrics are blocked by your
consent settings
Distributed compressed video sensing with multiple key frames
(2026-02-27)
Nomaguchi, Mizuki
;
Inoue, Ryota
;
Woraratpanya, Kuntpong
;
Kuroki, Yoshimitsu
Distributed Compressed Video Sensing is a video compression method utilizing Compressed Sensing and Distributed Video Coding. With this method, compressed frames are reconstructed with information obtained by applying Convolutional Sparse Coding to a non-compressed frame. In this study, we aim to increase the reconstruction accuracy by selecting multiple non-compressed frames. In addition, we use symmetric convolution in order to solve a high computational optimization problem. The experimental results show our proposed method outperforms the conventional method.
Some of the metrics are blocked by your
consent settings
L1-L1 norm-based convolutional sparse coding via Anderson-accelerated Douglas-Rachford splitting
(2026-02-27)
Take, Hiroto
;
Furusho, Riku
;
Woraratpanya, Kuntpong
;
Kuroki, Yoshimitsu
Convolutional Sparse Coding (CSC) represents a signal through the convolution of dictionary filters and sparse coefficients. While the Alternating Direction Method of Multipliers (ADMM) has conventionally been used to solve CSC problems, recent studies have demonstrated that Douglas-Rachford (DR) splitting can achieve faster convergence. In this study, we propose an accelerated CSC algorithm by applying Anderson Acceleration to the DR splitting method. Experimental results demonstrate that the proposed method significantly improves convergence speed compared to standard DR splitting.
Some of the metrics are blocked by your
consent settings
Advancing GAN Evaluation: The Advanced Mahalanobis Distance Learning Metric for Realistic Car Damage Image Assessment
(2026-01-01)
Kyu, Phyu Mar
;
Woraratpanya, Kuntpong
Generative Adversarial Networks (GANs) have demonstrated remarkable capability in synthesizing high-quality images from limited data, addressing challenges of data scarcity and diversity in deep learning (DL) training. This is particularly valuable for car damage classification, where real-world datasets are often limited. To mitigate this, we created a custom damaged-undamaged car dataset for training GAN models and generating realistic car damage images. However, evaluating the per-image realism of GAN-generated images remains challenging. Standard GAN metrics, such as Fréchet Inception Distance (FID), Kernel Inception Distance (KID), and Inception Score (IS), provide dataset-level scores but do not assess individual image quality. Meanwhile, Image Quality Assessment (IQA) metrics require reference images, rendering them unsuitable for reference-free scenarios, particularly in unpaired GAN-generated data. To address these limitations—including the practical failure of standard Mahalanobis Distance Learning (MDL) on small or high-dimensional datasets due to non-invertible covariance matrices—we propose Advanced Mahalanobis Distance Learning (AMDL), which incorporates adaptive regularization and pseudo-inverse refinement on deep feature embeddings from pre-trained CNNs. AMDL enables stable and reliable per-image realism assessment under covariance matrix instability, without requiring large datasets or ground-truth references. Our comprehensive evaluation framework involves three procedures: (1) dataset-level evaluation of four GAN models using standard GAN metrics, (2) per-image realism assessment with AMDL, and (3) classifier-based validation with CNN and Vision Transformer (ViT) models (with vs. without AMDL). Experimental results show that AMDL provides precise per-image realism assessment, outperforms existing GAN metrics across datasets, and offers a practical solution for evaluating unpaired GAN-generated images in car damage classification.
Some of the metrics are blocked by your
consent settings
Evaluating the effectiveness of facial actions features for the early detection of driver drowsiness in driving safety monitoring system
(2025-01-01)
Rahmawati, Yenny
;
Woraratpanya, Kuntpong
;
Ardiyanto, Igi
;
Nugroho, Hanung Adi
Traffic accidents caused by drowsiness remain a serious threat to driving safety. Many of these accidents can actually be prevented with an early warning system that detects the early signs of driver drowsiness. This study proposes a non-invasive system to detect drowsiness based on visual features extracted from videos recorded by a dashboard camera. The system uses facial landmarks generated by a facial network detector to identify key areas such as eyes, mouth, and head. The eye aspect ratio (EAR), mouth aspect ratio (MAR), and head rotation angle were calculated as the main features. These features were fed into three classification models: 1D-CNN, LSTM, and BiLSTM. Evaluation was conducted using 87 videos from the YawDD dataset for training and 20 videos from custom data for testing. During training, the 5-fold cross-validation was used to ensure model generalization and reduce the risk of overfitting. In addition to accuracy, other metrics such as precision, recall, and F1-score were used to provide a more comprehensive overview of the system performance. The results showed that the combination of the three facial features (EAR, MAR, and head rotation) provided a better performance than did the use of a single feature or a combination of two features, with an accuracy improvement of 5–8%. The BiLSTM model showed the best performance, with a training accuracy of 99% on the YawDD dataset and a testing accuracy of 98% on the custom data.
Some of the metrics are blocked by your
consent settings
Vision Transformer with Fractal Dimension Transformation: Effects of Resolution and Patch Size
(2025-01-01)
Ngamkham, Woramat
;
Woraratpanya, Kuntpong
;
Kuroki, Yoshimitsu
Vision Transformer (ViT) achieves strong performance in computer vision but requires substantial computational resources, particularly with high-resolution data. A key challenge lies in the quadratic complexity of self-attention with respect to the number of image patches, which is jointly determined by input size and patch size. Conventional resizing is a common strategy to reduce resolution and thus the number of patches, but it risks discarding structural details that may be important for prediction. To address this issue, this study investigates how input size, patch size, and dimensionality reduction influence ViT training time and prediction accuracy. Using the NIH Chest X-ray dataset, we compared two preprocessing methods: conventional resizing and a Fractal Dimension (FD)-based transformation. Results show that the FD-based method consistently reduced training time across all settings, demonstrating its effectiveness in lowering computational costs. In terms of accuracy, conventional resizing generally performed slightly better overall; however, the differences were not uniform, as smaller patches improved AUROC mainly at higher resolutions but not consistently at lower ones. These findings highlight a tradeoff between efficiency and accuracy, positioning FD-based representations as a practical complement to conventional resizing when computational resources are limited.
Some of the metrics are blocked by your
consent settings
Fourier Latent Transformer for Anomaly Signal with High-Frequency Reconstruction
(2025-01-01)
Chalongvorachai, Thasorn
;
Woraratpanya, Kuntpong
Anomaly-related applications play a crucial role in real-world systems. However, developing effective solutions remains challenging, particularly due to missing data caused by system errors during anomaly events. Several approaches have been proposed to address this issue, including statistical methods, autoencoders, and deep learning models such as Transformers and Latent Transformers. Despite their potential, these methods often struggle to preserve high-frequency signal characteristics or require extensive training time and computational resources. To overcome these challenges, this paper proposes the Fourier Latent Transformer for Anomaly Signal with High Frequency Reconstruction. The method integrates Fourier positional encoding, which enhances the model's ability to retain high-frequency components, with a Latent Transformer architecture that reduces the need for computational resources and shortens training time. This approach not only effectively reconstructs missing highfrequency anomaly signals, but also improves overall training efficiency. Experimental results on real-world datasets show that the proposed method tremendously reduces error in anomaly data imputation, while maintaining training time comparable to baseline models.
Some of the metrics are blocked by your
consent settings
Integrating Recurrent Neural Networks and Deep Q-Networks for Precision Irrigation Control
(2025-01-01)
Jogo, Fransiksus Serfian
;
Wahyunggoro, Oyas
;
Mustika, I. Wayan
;
Woraratpanya, Kuntpong
Agricultural irrigation accounts for a substantial portion of global water consumption, necessitating intelligent irrigation strategies. Conventional systems, such as fixed irrigation or evapotranspiration (ET)-based control, often exhibit inefficiencies due to reliance on static measurements and empirical farmer knowledge, lacking adaptive decision-making capabilities. To address this challenge, this paper presents an IoT-based framework integrating Recurrent Neural Networks (RNNs) for weather prediction and Deep Q-Networks (DQNs) for adaptive irrigation decisions. The RNN achieves high-precision forecasts for solar radiation, rainfall, and reference evapotranspiration (ETo) with determination coefficients (R<sup>2</sup>) of 0.819,0.915, and 0.892, respectively, surpassing the other two neural network models in our tests. Simultaneously, the DQN agent learns irrigation policies that reduce water consumption by 16.6-25.3% compared to conventional methods while maintaining post-irrigation soil moisture above the critical threshold (V<inf>mad</inf>=0.50) in testbed experiments. The proposed RNN-DQN architecture demonstrates significant improvements in water-use efficiency and plant health maintenance, offering a robust solution for smart agriculture in water-limited, data-scarce arid regions.
Some of the metrics are blocked by your
consent settings
Anomaly Signal Imputation Using Latent Coordination Relations
(2024-01-01)
Chalongvorachai, Thasorn
;
Woraratpanya, Kuntpong
Missing data is a critical challenge in industrial data analysis, particularly during anomaly incidents caused by system equipment malfunctions or, more critically, by cyberattacks in industrial systems. It impedes effective imputation and compromises data integrity. Existing statistical and machine learning techniques struggle with heavily missing data, often failing to restore original data characteristics. To address this, we propose Anomaly Signal Imputation Using Latent Coordination Relations, a framework employing a variational autoencoder (VAE) to learn from complete data and establish a robust imputation model based on latent space coordination points. Experimental results from a water treatment testbed show significant improvements in output signal fidelity despite substantial data loss, outperforming conventional techniques.
Some of the metrics are blocked by your
consent settings
Enhancing Thai Food Recognition Through Multimodal Fusion of Image and Fourier Spectrum
(2024-01-01)
Pasupa, Kitsuchart
;
Woraratpanya, Kuntpong
Recognizing food is a challenging task in artificial intelligence research because food items may undergo deformations during cooking or serving, and they can be partially or fully occluded, making it difficult for recognition systems to analyze their complete visual information. Therefore, in addition to evaluating object detection effectiveness, consideration must be given to the texture of the food. However, Convolutional Neural Networks may fall short in capturing textural information. In this research, we propose a method to enhance the efficiency of Thai food recognition by employing the concept of multi-modal fusion, incorporating Fourier Spectrum images to take texture representation into account and improve the model’s performance. In the fusion process, we employed the CentralNet framework and compared it with baselines (using only images and conventional concatenation fusion) on three datasets: THFOOD-50, FoodyDudy, and our newly proposed food dataset called iTHFOOD-200. This new dataset encompasses a more diverse range of food types. The experimental results demonstrate that fusion with the CentralNet framework yielded better performance than the baselines using only images (7.1% Top-1 Accuracy and 3.9% Top-5 Accuracy on average) and conventional concatenation fusion (5.0% Top-1 Accuracy and 2.4% Top-5 Accuracy on average).
Some of the metrics are blocked by your
consent settings
LSCR: Latent Space Coordination Relation for Anomaly Prediction
(2023-01-01)
Chalongvorachai, Thasorn
;
Woraratpanya, Kuntpong
Anomaly time series prediction is a crucial yet challenging task in real-world systems. Existing techniques often require a substantial amount of data to achieve satisfactory performance, posing a significant challenge as anomaly data is scarce and difficult to obtain. Despite attempts to address this issue using traditional machine learning techniques, their effectiveness remains limited, resulting in performance degradation or costly trade-offs. Therefore, in this paper, we propose a novel approach called Latent Space Coordination Relation for Anomaly Prediction to overcome these challenges. Our framework leverages the power of the Variational Autoencoder (VAE) and learns the coordination relations of points in the latent space to detect anomalies. By exploiting the latent space, our method enables effective learning and prediction of anomalies. Additionally, the decoder of the VAE aids in restoring the data, further improving the accuracy of anomaly detection. Experimental results demonstrate that our approach outperforms baseline models when training data is limited. The predicted anomalous signals exhibit lower error rates, highlighting the efficacy of our method. This improvement is attributed to the utilization of the latent space for learning and assisting in anomaly prediction, along with the signal restoration capabilities of the decoder.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results