Pasupa, Kitsuchart

Preferred name

Pasupa, Kitsuchart

Main Affiliation

School of Information Technology

kitsuchart.pa@kmitl.ac.th

Now showing 1 - 10 of 119

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.
Some of the metrics are blocked by your
consent settings
Combining multiple features for product categorisation by multiple kernel learning
(2019-01-01)
Chavaltada, Chanawee
;
Pasupa, Kitsuchart
;
Hardoon, David R.
E-commerce provides convenience and flexibility for consumers; for example, they can inquire about the availability of a desired product and get immediate response, hence they can seamlessly search for any desired products. Every day, e-commerce sites are updated with thousands of new images and their associated metadata (textual information), causing a problem of big data. Retail product categorisation involves cross-modal retrieval that shows the path of a category. In this study, we leveraged both image vectors of various aspects and textual metadata as features, then constructed a set of kernels. Multiple Kernel Learning (MKL) proposes to combine these kernels in order to achieve the best prediction accuracy. We compared the Support Vector Machine (SVM) prediction results between using an individual feature kernel and an MKL combined feature kernel to demonstrate the prediction improvement gained by MKL.
Some of the metrics are blocked by your
consent settings
Preface
(2020-01-01)
Yang, Haiqin
;
Pasupa, Kitsuchart
Some of the metrics are blocked by your
consent settings
Hybrid Deep Learning Models for Thai Sentiment Analysis
(2022-01-01)
Pasupa, Kitsuchart
;
Seneewong Na Ayutthaya, Thititorn
Many people use social media in their daily life for entertainment, business, personal communication, and catching up with friends. In social media marketing, sentiment analysis is one of the most popular research topics because it can be employed to perform brand or market research monitoring and to keep an eye on the competitors. Machine learning algorithms have been utilized to carry out the task. In addition, sentiment analysis is essential in cognitive computing. Currently, there are still a limited number of Thai sentiment analysis research. This paper proposes a framework for sentiment analysis in Thai along with Thai-SenticNet5 corpus. The framework employs different types of features, namely, word embedding, part-of-speech, sentic features, and all combinations of these features. Furthermore, we fused deep learning algorithms—convolutional neural network (CNN) and bidirectional long short-term memory (BLSTM)—in different ways and compare it to several other fused combinations. Three datasets in Thai were used in this work: ThaiTales, ThaiEconTwitter, and Wisesight datasets. The experimental results show that combining all three features and fusing deep learning algorithms were able to improve overall performance. The best hybrid deep learning was BLSTM-CNN that achieved F<inf>1</inf>-scores of 0.7436, 0.7707, and 0.5521, on ThaiTales, ThaiEconTwitter, and Wisesight datasets, respectively. According to the experimental results, we conclude that feature combination and hybrid deep learning algorithms can improve the overall performances.
Some of the metrics are blocked by your
consent settings
Utilising Kronecker Decomposition and Tensor-based Multi-view Learning to predict where people are looking in images
(2017-07-26)
Pasupa, Kitsuchart
;
Szedmak, Sandor
Eye movement data collection is very expensive and laborious. Moreover, there are usually missing values. Assuming that we are collecting eye movement data from a set of images viewed by different users, there is a possibility that we will not able to collect the data of every user from every image–one or more views may not be represented in the image. We assume that the relationships among the views can be learnt from the whole collection of views (or 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 certain properties of tensor algebra, we showed that this problem can be formulated consistently as a regression type learning task. Furthermore, there is a maximum margin based optimisation framework in which this problem can be solved in a tractable way. This problem is similar to learning to predict where a person is looking in an image. Therefore, we proposed an algorithm called “Tensor-based Multi-View Learning”(TMVL) in this paper. Furthermore, we also proposed a technique for improving prediction by introducing a new feature set obtained from Kronecker decomposition of the image fused with user's eye movement data. Using this new feature can improve prediction performance markedly. The proposed approach was proven to be more effective than two well-known saliency detection techniques.
Some of the metrics are blocked by your
consent settings
A scenario-based analysis of front-facing camera eye tracker for UX-UI survey on mobile banking app
(2020-01-01)
Sunhem, Wisuwat
;
Pasupa, Kitsuchart
Recently, User Experience and User Interface (UX-UI) have become important aspects in designing an effective mobile banking application. Traditionally, developers and designers have relied on explicit feedback derived from questionnaires to gain more insights into UX-UI. With the advancement of new technology, eye-tracking device has been introduced, and the approach has been used to provide a digital footprint indicating exact gazing positions of the users when using an application. So far, many studies have acknowledged the benefits of eye movement tracking and exploited such implicit feedback, alongside the result yielded from a survey. Successful uses of this eye-tracking device would further the development of mobile banking application. In this study, we aimed to build a device-free eye tracking software module that would work efficiently on mobile phones. To achieve this goal, we employed an existing Convolutional Neural Network model in our framework and evaluated the model when it was applied to the specific domain, i.e., UX-UI research design for mobile banking apps. We investigated a GazeCapture dataset, the first large-scale dataset for eye tracking, and conducted a data wrangling technique. The results show that fine-tuning the model with our wrangled data can improve the overall eye-tracking performance. Moreover, enabling user calibration can clearly enhance the predicting performance of the model.
Some of the metrics are blocked by your
consent settings
Using image features and eye tracking device to predict human emotions towards abstract images
(2016-01-01)
Pasupa, Kitsuchart
;
Chatkamjuncharoen, Panawee
;
Wuttilertdeshar, Chotiros
;
Sugimoto, Masanori
Nowadays, emotional semantic image retrieval system enables users to access images that they want in a database according to emotional concept. This leads to affective image classification task which recently attracts researchers’ attention. However, different users may experience different emotions depending on where, in the image, they are gazing on. This paper presents an improved prediction method by taking into account the users eye movement as implicit feedback while they are looking at the image. Our experimental results show that using both eye movement information and image feature together to determine users emotion gave more accurate predictions than using image feature alone.
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
Preface
(2020-01-01)
Yang, Haiqin
;
Pasupa, Kitsuchart
Some of the metrics are blocked by your
consent settings
Prediction of reference evapotranspiration with missing data in Thailand
(2013-01-01)
Pasupa, Kitsuchart
;
Thamwiwatthana, Ek
Artificial Neural Networks (ANNs) has been used in prediction of reference evapotranspiration for a recent decade. Its performance is competitive to a widely used method the so-called 'Penman-Monteith' method. In this study, we aim to estimate the crop evapotranspiration by ANNs from climatic data in Thailand and compare the performance with the Penman-Monteith method. As missing data is inevitable, we also included the missing data situation into the study. This can be solved by expectation-maximization algorithm. The accuracy of the prediction decreases when the amount of missing values increases. Furthermore, we exploit the feature selection in the study. It shows that sunshine duration is the most important feature followed by temperature and wide speed, respectively. © 2013 IEEE.

Pasupa, Kitsuchart

Filters

Settings

Sort By

Results per page