Woraratpanya, Kuntpong

Preferred name

Alternative Name

Weraratpanya, Kuntpong

Main Affiliation

School of Information Technology

kuntpong.wo@kmitl.ac.th

Now showing 1 - 10 of 14

Some of the metrics are blocked by your
consent settings
A compact optimal learning machine
(2019-01-01)
Sae-Pae, Kanathip
;
Woraratpanya, Kuntpong
Artificial neural networks (ANNs) have been developed and applied to a variety of problems, such as pattern recognition, clustering, function approximation, forecasting, optimization, etc. However, existing ANNs have a high computational cost, since their learning methods are mostly based on a parameter tuning approach. Extreme learning machine (ELM) is a state-of-the-art method that generally dramatically reduces the computational cost. An analysis of the ELM method reveals that there are unsolved key factors, including inefficient hidden node construction, redundant hidden nodes, and unstable results. Therefore, we describe a new learning machine based on analytical incremental learning (AIL) in conjunction with principal component analysis (PCA). This learning machine, PCA-AIL, inherited the advantages from the original one and solved the unsolved key factors of ELM, and also extended AIL capability to serve a multiple-output structure. PCA-AIL was implemented with a single-layer feed-forward neural network architecture, used an adaptive weight determination technique to achieve a compact optimal structure and also used objective relations to support multiple output regression tasks. PCA-AIL has two steps: objective relation estimation and multiple optimal hidden node constructions. In the first step, PCA estimated the objective relations from multiple-output residual errors. In the second step, the multiple optimal nodes were obtained from objective relations and added to the model. PCA-AIL was tested with 16 multiple-objective regression datasets. PCA-AIL mostly outperformed other methods (ELM, EM-ELM, CP-ELM, DP-ELM, PCA-ELM, EI-ELM) in terms of fast testing speed-0.0017 second, a compact model-19.9 nodes, an accurate performance-RMSE 0.11261, and a stable result-S.D. of RMSE 0.00911: reported in averaged.
Some of the metrics are blocked by your
consent settings
Iteration-free Bi-dimensional empirical mode decomposition and its application
(2017-09-01)
Titijaroonroj, Taravichet
;
Woraratpanya, Kuntpong
powerful methods for decomposing non-linear and nonstationary signals without a prior function. It can be applied in many applications such as feature extraction, image compression, and image filtering. Although modified BEMDs are proposed in several approaches, computational cost and quality of their bi-dimensional intrinsic mode function (BIMF) still require an improvement. In this paper, an iteration-free computation method for bi-dimensional empirical mode decomposition, called iBEMD, is proposed. The locally partial correlation for principal component analysis (LPC-PCA) is a novel technique to extract BIMFs from an original signal without using extrema detection. This dramatically reduces the computation time. The LPC-PCA technique also enhances the quality of BIMFs by reducing artifacts. The experimental results, when compared with state-of-The-Art methods, show that the proposed iBEMD method can achieve the faster computation of BIMF extraction and the higher quality of BIMF image. Furthermore, the iBEMD method can clearly remove an illumination component of nature scene images under illumination change, thereby improving the performance of text localization and recognition.
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
Evaluation of deep learning algorithms for semantic segmentation of car parts
(2022-10-01)
Pasupa, Kitsuchart
;
Kittiworapanya, Phongsathorn
;
Hongngern, Napasin
;
Woraratpanya, Kuntpong
Evaluation of car damages from an accident is one of the most important processes in the car insurance business. Currently, it still needs a manual examination of every basic part. It is expected that a smart device will be able to do this evaluation more efficiently in the future. In this study, we evaluated and compared five deep learning algorithms for semantic segmentation of car parts. The baseline reference algorithm was Mask R-CNN, and the other algorithms were HTC, CBNet, PANet, and GCNet. Runs of instance segmentation were conducted with those five algorithms. HTC with ResNet-50 was the best algorithm for instance segmentation on various kinds of cars such as sedans, trucks, and SUVs. It achieved a mean average precision at 55.2 on our original data set, that assigned different labels to the left and right sides and 59.1 when a single label was assigned to both sides. In addition, the models from every algorithm were tested for robustness, by running them on images of parts, in a real environment with various weather conditions, including snow, frost, fog and various lighting conditions. GCNet was the most robust; it achieved a mean performance under corruption, mPC = 35.2, and a relative degradation of performance on corrupted data, compared to clean data (rPC), of 64.4%, when left and right sides were assigned different labels, and mPC = 38.1 and rPC = 69.6 % when left- and right-side parts were considered the same part. The findings from this study may directly benefit developers of automated car damage evaluation system in their quest for the best design.
Some of the metrics are blocked by your
consent settings
Improved triangle box-counting method for fractal dimension estimation
(2015-01-01)
Kaewaramsri, Yothin
;
Woraratpanya, Kuntpong
A fractal dimension (FD) is an effective feature, which characterizes roughness and self-similarity of complex objects. However, the FD in nature scene requires the effective method for estimation. The existing methods focus on the improvement of selecting the suitable height of box-counts. This cannot overcome the overcounting problem, which is a key factor to have an impact on the accuracy of the FD estimation. This paper proposes a more accurate FD estimation, an improved triangle box-counting method, to increase the precision of box-counts associated with box sizes. The triangle-box-partition technique provides the double precision for box-counts, thus it can solve the overcounting issue and enhance the accuracy of the FD estimation. The proposed method is evaluated its performance in terms of fitting error. The experimental results show that the proposed method outperforms the existing methods, including differential box-counting (DBC), improved DBC (IDBC), and box-counting with adaptable box height (ADBC) methods.
Some of the metrics are blocked by your
consent settings
A data generation framework for extremely rare case signals
(2021-08-01)
Chalongvorachai, Thasorn
;
Woraratpanya, Kuntpong
Unlike data augmentation, data generation for extremely rare cases is an approach that can spawn a significant number of high-quality samples based on very few original data. This could be useful in anomaly detection and classification tasks that have the limitation of publicly available datasets for research purposes. Though some other approaches have attempted to solve this problem, such as data augmentation techniques, there was nothing to ensure the characteristics of synthesized samples. Previously, we initiated a framework, called Data Augmentation and Generation for Anomalous Time-series Signals (DAGAT), that was in cooperation with important components: Data Augmentation, Variational Autoencoder (VAE), Data Picker (DP), Signal Fragment Assembler (SFA), and Quality Classifier (QC). And then, an upgraded framework, called An Advanced Data Generation for Anomalous Signals (ADGAS), was introduced to eliminate the limitations of DAGAT; those are uncontrollable outputs and the possibility of bad data included in a training set. By reforming DAGAT architecture, ADGAS achieves a better outcome of generated samples. Nonetheless, ADGAS could be improved through better SFA, DP, and QC. Hence, this paper proposed a Data Generation Framework for Extremely Rare Case Signals. The proposed framework is achievable in generating reliable data for various objectives. We challenged this framework by using the 1D-CNN to serve as the performance evaluator in multi-class anomalous classifications and using the water treatment and water distribution testbed (SWaT and WADI) as the real-world anomaly datasets. The result shows that it surpasses other baseline methods of anomaly data augmentation and data generation techniques.
Some of the metrics are blocked by your
consent settings
Square Wave Quadrature Amplitude Modulation for Visible Light Communication Using Image Sensor
(2019-01-01)
Alfarozi, Syukron Abu Ishaq
;
Pasupa, Kitsuchart
;
Hashizume, Hiromichi
;
Woraratpanya, Kuntpong
;
Sugimoto, Masanori
Most visible light communication (VLC) technologies use a light emitting diode (LED) as a data transmitter and a photodiode as a receiver. In this paper, we alternatively focus on the use of an image sensor or camera as a receiver due to its wide availability. However, the successful use of an image sensor mainly depends on the efficiency of the encoder-decoder and the modulation scheme. Thus, this paper proposes a novel modulation scheme based on a square wave signal called a square wave quadrature amplitude modulation (SW-QAM) method. This method can accommodate different camera settings and overcome the problem of LED flicker that is generally sensed by human eyes when the LED frequency is low. At the transmitter side, multiple LEDs can be used to increase the transmission bit rate, while, at the receiver side, a Wiener filter is used as a complementary technique to SW-QAM for solving the light interference phenomenon due to the closeness of one LED to another. Our experimental results show that the proposed SW-QAM scheme can decode symbols very well either the for close or far communication distances, dark or bright lighting conditions, and single or multiple LED points.
Some of the metrics are blocked by your
consent settings
Local Sigmoid Method: Non-Iterative Deterministic Learning Algorithm for Automatic Model Construction of Neural Network
(2020-01-01)
Alfarozi, Syukron Abu Ishaq
;
Pasupa, Kitsuchart
;
Sugimoto, Masanori
;
Woraratpanya, Kuntpong
A non-iterative learning algorithm for artificial neural networks is an alternative to optimize the neural network parameters with extremely fast convergence time. Extreme learning machine (ELM) is one of the fastest learning algorithms based on a non-iterative method for a single hidden layer feedforward neural network (SLFN) model. ELM uses a randomization technique that requires a large number of hidden nodes to achieve the high accuracy. This leads to a large and complex model, which is slow at the inference time. Previously, we reported analytical incremental learning (AIL) algorithm, which is a compact model and a non-iterative deterministic learning algorithm, to be used as an alternative. However, AIL cannot grow its set of hidden nodes, due to the node saturation problem. Here, we describe a local sigmoid method (LSM) that is also a sufficiently compact model and a non-iterative deterministic learning algorithm to overcome both the ELM randomization and AIL node saturation problems. The LSM algorithm is based on 'divide and conquer' method that divides the dataset into several subsets which are easier to optimize separately. Each subset can be associated with a local segment represented as a hidden node that preserves local information of the subset. This technique helps us to understand the function of each hidden node of the network built. Moreover, we can use such a technique to explain the function of hidden nodes learned by backpropagation, the iterative algorithm. Based on our experimental results, LSM is more accurate than other non-iterative learning algorithms and one of the most compact models.
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
Empirical Monocomponent Image Decomposition
(2017-12-13)
Suttapakti, Ungsumalee
;
Pasupa, Kitsuchart
;
Woraratpanya, Kuntpong
Monocomponent image decomposition plays an important role in image analysis and related areas, such as image denoising, object detection, and texture segmentation. Existing image decomposition methods can extract monocomponents but their performances are insufficiently accurate because of interference and redundancy component problems caused by inaccurate spectrum segmentation. In this paper, an empirical monocomponent image decomposition (EMID) is proposed for fully recoverable monocomponents. The EMID method empirically decomposes an image into monocomponents based on energy concentration in Fourier support. This method is composed of two main processes: 1) energy concentration-based segmentation and 2) empirical image filter bank construction. In the former process, the base of a mountain-shaped energy concentration that can perfectly represent the monocomponent spectrum boundary is detected and identified. This process provides a more accurate spectrum segmentation which helps prevent the serious problems from interference and redundancy components. In the latter process, an empirical image filter bank is constructed in accordance with the actual monocomponent boundaries by means of ellipse and Gaussian functions and used to decompose an image into monocomponent images with fewer ringing artifacts. The experimental results show that the proposed EMID method achieves a better decomposition than the state-of-the-art methods in terms of the quality of monocomponent images that are evaluated by peak signal-to-noise ratio and structural similarity index. Furthermore, in a real world dataset, the EMID method is able to clearly detect text regions, thus significantly improving the efficiency of Thai text character localization in natural scene images.

Woraratpanya, Kuntpong

Filters

Settings

Sort By

Results per page