Pasupa, Kitsuchart

Preferred name

Pasupa, Kitsuchart

Main Affiliation

School of Information Technology

kitsuchart.pa@kmitl.ac.th

Now showing 1 - 10 of 74

Some of the metrics are blocked by your
consent settings
Text-background decomposition for thai text localization and recognition in natural scenes
(2014-01-12)
Woraratpanya, Kuntpong
;
Pasupa, Kitsuchart
;
Suttapakti, Ungsumalee
;
Boonchukusol, Pimlak
;
Titijaroonroj, Taravichet
Thai text localization and recognition in natural scenes is still a grand challenge in current applications. However, the efficiency of recognition rates depends on text localization, i.e., the higher purity of text-background decomposition leads to the higher accuracy rate of character recognition. In order to achieve this purpose, the text-background decomposition methods, namely adaptive boundary clustering (ABC) and n-point boundary clustering (n-PBC), are proposed to improve a precision of text localization. These methods are evaluated by self-en-tropy for purity measure. Based on 300 test images, the experimental results demonstrate that the ABC method achieves the very low self-entropy, i.e., the low self-entropy implies the good decomposition of text and background. Furthermore, based on 8,077 characters in natural scene test images, the ABC method helps increase the precision of text localization and improves the accuracy rate of character recognition, when compared to the conventional methods.
Some of the metrics are blocked by your
consent settings
Towards Sentic-Aware Multimodal Models for Cyberbullying Detection in Thai Memes
(2026-01-01)
Weradechtaweewon, Nattawat
;
Boondamnoen, Mongkol
;
Pasupa, Kitsuchart
Cyberbullying has become an increasingly urgent issue in online communities. Memes, a popular form of online expression, often blend text and imagery in emotionally charged, sarcastic, or offensive ways–posing unique challenges for automatic harmful content detection. This work explores sentic-aware multimodal models for cyberbullying detection in Thai memes, with a focus on integrating affective commonsense knowledge through SenticNet-based features that emphasize conceptual reasoning and structured emotion representation. To enable this, we propose ThaiSenticNet 7, a resource adapted for the Thai language by translating from SenticNet 7, which supports the generation of sentic features. We investigate three representations–sentic vectors, sentic spectrograms, and sentic mel-spectrograms–and their integration with various sequential models to form sentic embeddings. These embeddings are fused with textual and visual information, extracted via a fine-tuned WangchanBERTa and a Swin Transformer, respectively, forming a unified multimodal pipeline. Experiments on a curated Thai meme dataset show that incorporating sentic features significantly enhances classification performance, with the best configuration–combining all three modalities–achieving an F<inf>1</inf>-score of 0.8044. Notably, the mel-spectrogram transformation proves particularly effective, suggesting that frequency-domain encoding helps capture subtle affective transitions in text-derived emotional signals. Our findings highlight the value of affective knowledge and multimodal modeling in tackling harmful content in memes.
Some of the metrics are blocked by your
consent settings
An approach to face shape classification for hairstyle recommendation
(2016-04-07)
Sunhem, Wisuwat
;
Pasupa, Kitsuchart
It is important to choose a good hairstyle for women because it can enhance their beauty, personality, and confidence. One of the most important factors to consider for choosing the right hairstyle is the individuals face shape. An effective face shape classification can be used for constructing a hairstyle recommendation system. This paper presents a classification approach that divides face shapes into 5 different shapes: round, oval, oblong, square, and heart. This approach, which is based on an Active Appearance Model (AAM) and a face segmentation technique, produces a set of features that can be evaluated by several popular machine learning methods, namely, Linear Discriminant Analysis (LDA), Artificial Neural Networks (ANN), and Support Vector Machine (SVM). Our results show that the Support Vector Machine with Radial Basis function kernel was the best algorithm that predicted accurately up to 72%.
Some of the metrics are blocked by your
consent settings
Analytical incremental learning: Fast constructive learning method for neural network
(2016-01-01)
Alfarozi, Syukron Abu Ishaq
;
Setiawan, Noor Akhmad
;
Adji, Teguh Bharata
;
Woraratpanya, Kuntpong
;
Pasupa, Kitsuchart
Extreme learning machine (ELM) is a fast learning algorithm for single hidden layer feed-forward neural network (SLFN) based on random input weights which usually requires large number of hidden nodes. Recently, novel constructive and destructive parsimonious (CP and DP)-ELM which provide the effectiveness generalization and compact hidden nodes have been proposed. However, the performance might be unstable due to the randomization either in ordinary ELM or CP and DP-ELM. In this study, analytical incremental learning (AIL) algorithm is proposed in which all weights of neural network are calculated analytically without any randomization. The hidden nodes of AIL are incrementally generated based on residual error using least square (LS) method. The results show the effectiveness of AIL which has not only smallest number of hidden nodes and more stable but also good generalization than those of ELM, CP and DP-ELM based on seven benchmark data sets evaluation.
Some of the metrics are blocked by your
consent settings
Sparse Fisher discriminant analysis with Jeffrey's hyperprior
(2012-12-01)
Pasupa, Kitsuchart
The penalty function requires a choice of regularization parameter which controls the degree of parsimony in sparse kernel classifier. This involves an extra parameter apart from kernel parameter in the optimization which must be found via, e.g. cross-validation. This paper introduces a new parsimonious binary kernel Fisher discriminant analysis which does not require a regularization parameter. This can be done by using a Jeffrey's noninformative hyperprior. A Jeffrey's noninformative hyperprior is parameter-free and is adopted through a hierarchical-Bayes interpretation of the Laplacian prior distribution. This leads to a non-requirement of the regularization parameter. The proposed algorithm is compared with other machine learning methods on substantial benchmarks. Moreover, it is also compared with the leading machine learning in virtual screening application. It is found to be less accurate but it is still comparable in a number of cases. © 2012 IEEE.
Some of the metrics are blocked by your
consent settings
Learning to predict where people look with tensor-based multi-view learning
(2015-01-01)
Pasupa, Kitsuchart
;
Szedmak, Sandor
Eye movements data collection is very expensive and laborious. Moreover, there are usually missing values. Assuming that we are collecting eye movements data on a set of images from different users (views). There is a possibility that we are not able to collect eye movements of all users on all images. One or more views are not represented in the image. We assume that the relationships among the views can be learnt from the complete items. The task is then to reproduce the missing part of the incomplete items from the relationships derived from the complete items and the known part of these items. Using the properties of tensor algebra we show that this problem can be formulated consistently as a regression type learning task. Furthermore, there is a maximum margin based optimisation framework where this problem can be solved in a tractable way. This problem is similar to learning to predict where human look. The proposed algorithm is proved to be more effective than well-known saliency detection techniques.
Some of the metrics are blocked by your
consent settings
Efficient distributed SNP selection by a Modified Binary Flower Pollination Algorithm
(2020-07-01)
Rathasamuth, Wanthanee
;
Pasupa, Kitsuchart
Porcine Single Nucleotide Polymorphisms (SNPs-certain pieces of nucleotide in a DNA sequence) can be indirectly associated with traits of an individual pig, like its meat quality or resistance to common diseases. It is most desirable to obtain a smallest number of most significant SNPs in genomics research, and several computer classification algorithms have been used to do so. For instance, for breed classification, one needs to obtain a set of a much smaller number of significant SNPs than that of the entire SNP data set. This study attempted to find such significant porcine SNPs by using computational feature selection and classification methods. In a preliminary trial, a binary flower pollination algorithm (BFPA) was used and shown not to able to reduce the number of selected SNPs to a sufficiently low number. Therefore, to achieve our objective, we developed a vertically distributed feature selection method incorporating a modified BFPA and a support vector machine classifier for selecting significant porcine SNPs. The developed method was evaluated and compared against four baseline methods. It provided the smallest average number of significant SNPs (128.40) that resulted in 94.57% classification accuracy. This and other findings in this study may directly benefit researchers in the bioinformatics field in their effort to map SNPs.
Some of the metrics are blocked by your
consent settings
Analysis of Dust Exposure Impact on Cardiovascular Diseases Risk Prediction in Bangkok, Thailand
(2021-01-21)
Sonsanit, Jakkrit
;
Sirigate, Watcharin
;
Pasupa, Kitsuchart
;
Wiseschinda, Varut
;
Kunanusont, Chaiyos
Cardiovascular disease (CVD) is a leading cause of death for people around the world. Prediction of CVD risk in advance is one of the most useful and effective tools to prevent and control your risk of developing CVD. Air pollution is a threat to health problems worldwide due to the development of the economy and society. The past studies found that air pollution was one factor that can cause CVD. Additionally, for the Thai population, pollution was one of the factors contributing to premature death. In this work, we aim to predict CVD risk using the patient data set from Bangkok Hospital in Bangkok alone with several algorithms and increase the accuracy using a combination of health and pollution. The prediction based on health data alone with the average AUC scores 0.89\pm 0.03, while the prediction with added air pollution data with the average AUC scores 0.91\pm 0.03 an average 0.02 increase than based on health data results alone. We found that considering pollution data can improve the overall performance of the model to predict CVD risk.
Some of the metrics are blocked by your
consent settings
Correlated Online k-Nearest Neighbors Regressor Chain for Online Multi-output Regression
(2024-01-01)
Wu, Zipeng
;
Loo, Chu Kiong
;
Pasupa, Kitsuchart
Online multi-output regression is a crucial task in machine learning with applications in various domains such as environmental monitoring, energy efficiency prediction, and water quality prediction. This paper introduces CONNRC, a novel algorithm designed to address online multi-output regression challenges and provide accurate real-time predictions. CONNRC builds upon the k-nearest neighbor algorithm in an online manner and incorporates a relevant chain structure to effectively capture and utilize correlations among structured multi-outputs. The main contribution of this work lies in the potential of CONNRC to enhance the accuracy and efficiency of real-time predictions across diverse application domains. Through a comprehensive experimental evaluation on six real-world datasets, CONNRC is compared against five existing online regression algorithms. The consistent results highlight that CONNRC consistently outperforms the other algorithms in terms of average Mean Absolute Error, demonstrating its superior accuracy in multi-output regression tasks. However, the time performance of CONNRC requires further improvement, indicating an area for future research and optimization.
Some of the metrics are blocked by your
consent settings
MS-PatchTST: Leveraging Multi-Scale Temporal Features for Water Level Forecasting
(2025-01-01)
Zhang, Dong
;
Pasupa, Kitsuchart
;
Liu, Zongying
;
Pan, Mingyang
Accurate water level forecasting is essential for navigation, enabling safe sailing, effective drought management, optimized route planning, and efficient port operations. However, traditional statistical approaches and conventional machine learning models often struggle to capture adaptive, multi-scale temporal features, thereby limiting forecasting accuracy. In recent years, patch-based forecasting methods have demonstrated strong capabilities in modeling consecutive temporal features. Building on this foundation, we propose Multi-Scale PatchTST (MS-PatchTST), a framework designed to enhance the perception of multi-scale information. The model incorporates a newly developed multi-scale parallel convolutional network (Multi-Scale ConvNet) to extract interaction features across different time scales. These features are then fused through a Transformer Encoder with relative positional encoding to capture temporal dependencies more effectively. Finally, the kernel mean squared error loss function is employed in place of the conventional mean squared error loss, improving the optimization process and enhancing overall training performance. Experiments on four real-world water level datasets demonstrate that MS-PatchTST consistently outperforms state-of-the-art baselines, achieving an average reduction of approximately 13% in both MAE and SMAPE compared with PatchTST.

Pasupa, Kitsuchart

Filters

Settings

Sort By

Results per page