Pasupa, Kitsuchart

Preferred name

Pasupa, Kitsuchart

Main Affiliation

School of Information Technology

kitsuchart.pa@kmitl.ac.th

Now showing 1 - 10 of 23

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
CowXNet: An automated cow estrus detection system
(2023-01-01)
Lodkaew, Thanawat
;
Pasupa, Kitsuchart
;
Loo, Chu Kiong
Estrus detection is essential for dairy farms to take cows for artificial insemination promptly. Conventional approaches for detecting estrus cows use electronic devices attached to cows to gather data for software analysis. However, electronic devices can be costly and make a cow moody and uncomfortable while moving. In a common approach, observers detect estrus cows by observing their behaviors. However, continuous observation can easily lead to errors due to the observer's fatigue. Therefore, we designed CowXNet, an automatic estrus detection system for cows, to assist farmers to detect estrus cows. CowXNet requires only a camera attached in a pen and a computer to analyze recorded videos. CowXNet analyzes the estrus behaviors of each cow in a pen and helps farmers to identify estrus cows. To develop and evaluate CowXNet efficiently and effectively, we collected data from Chokchai Farm, the biggest dairy farm in Asia (14.65483<sup>∘</sup>N, 101.34853<sup>∘</sup>E). CowXNet has four modules: (i) cow detection uses YOLOv4 to detect cows in recorded videos; (ii) body part detection uses a convolutional neural network to estimate locations of body parts of detected cows; (iii) estrus behavior detection uses body part coordinates to extract a set of discriminative features, and a classification algorithm to detect estrus behaviors, and (iv) behavior analysis module displays estrus behavior for analysis purposes. We evaluated CowXNet for two instances: module-independent evaluation and end-to-end framework evaluation. Overall, CowXNet was promising; it correctly detected estrus behavior interval of cows 83% of cases.
Some of the metrics are blocked by your
consent settings
Weighted error-output recurrent Xavier echo state network for concept drift handling in water level prediction
(2024-11-01)
Liu, Zongying
;
Zhang, Wenru
;
Pan, Mingyang
;
Loo, Chu Kiong
;
Pasupa, Kitsuchart
Water level holds utmost significance in maritime domains. Precise water level predictions furnish indispensable insights for safe maritime navigation, guiding ships and vessels through passages, harbors, and waterways. This paper introduces a novel approach: the Weighted Error-Output Recurrent Xavier Echo State Network with Adaptive Forgetting Factor (WER-XESN-AFF). One of the contributions of this study is the introduction of the Xavier weights selection method, which replaces random weight selection from the Echo State Network (ESN). This method not only enhances forecasting performance but also reduces uncertainty in predictions. Additionally, two modified concept drift detectors, the Early Drift Detection Method and the Adaptive Forgetting Factor, are employed to address concept drift challenges. Another notable contribution is the introduction of a novel weighted error-output recurrent multi-step algorithm. This algorithm successfully overcomes the error accumulation problem by using past forecast errors to update current output weights. This study performs extensive experiments to evaluate the effectiveness of our approach in multi-step prediction in synthetic and real datasets. It compares the performance between the conventional randomization-based models and the ESN with the new weights selection approach and also tests the ability of concept drift detectors and the weighted error-output multi-step algorithm. Empirical findings and statistical analyses demonstrate that our proposed methods achieve expected effects, and the proposed model has better prediction ability than baselines. A significant improvement rate of 75.39% in Mean Squared Error is evident within the Jiujiang water level dataset when contrasting the performance of WER-XESN-AFF against the baseline model R-ESN across the 1–5 period.
Some of the metrics are blocked by your
consent settings
Diagnosing metabolic syndrome using genetically optimised Bayesian ARTMAP
(2019-01-01)
Kakudi, Habeebah Adamu
;
Loo, Chu Kiong
;
Moy, Foong Ming
;
Masuyama, Naoki
;
Pasupa, Kitsuchart
Metabolic Syndrome (MetS) constitutes of metabolic abnormalities that lead to non-communicable diseases, such as type II diabetes, cardiovascular diseases, and cancer. Early and accurate diagnosis of this abnormality is required to prevent its further progression to these diseases. This paper aims to diagnose the risk of MetS using a new non-clinical approach called 'genetically optimized Bayesian adaptive resonance theory mapping' (GOBAM). We evolve the Bayesian adaptive resonance theory mapping (BAM) by using genetic algorithm to optimize the parameters of BAM and its training input sequence. We use the GOBAM algorithm to classify individuals as either being at risk of MetS or not at risk of MetS with a related posterior probability, which ranges between 0 and 1. A data set of 11 237 Malaysians from the CLUSTer study stratified by age and gender into four subcategories was used to evaluate the proposed GOBAM algorithm. The comparative evaluation of our results suggested that the GOBAM performs significantly better than other classical adaptive resonance theory mapping models on the area under the receiver operating characteristic curves (AUC) and others criteria. Our algorithm gives an AUC of 86.42 %, 87.04 %, 91.08 %, and 89.24 % for the young female, middle aged female, young male, and middle-aged male subcategories, respectively. The proposed model can be used to support medical practitioners in accurate and early diagnosis of MetS.
Some of the metrics are blocked by your
consent settings
Highlight Detection in Podcasts: A Multimodal Deep Learning Approach
(2025-01-01)
Phuengpanyaloet, Wongsapat
;
Boonruengkhao, Nonpipat
;
Anchutin, Viktor
;
Pasupa, Kitsuchart
;
Loo, Chu Kiong
Podcasts have become a pervasive form of digital media, offering diverse content that often spans long hours. However, the vast volume of podcast episodes can make it challenging for listeners to locate the most engaging segments. Speech Emotion Recognition (SER) has witnessed remarkable advancements with the integration of deep learning techniques. This work proposes utilizing deep learning techniques employed in SER to discern emotional cues within podcasts, thereby enabling the detection of highlights. The task is framed as a binary classification problem, where the positive class contains examples of speech segments with high emotional activation. Transfer learning techniques from computer vision and speech recognition domains are applied, utilizing pre-trained models such as ConvNeXt, Vision Transformer, and wav2vec 2.0, which are compared with a baseline Convolutional Neural Network-Transformer hybrid. Additionally, multimodal models are introduced that learn from two distinct modalities: log mel-spectrograms and high-dimensional vector embeddings, both extracted from the raw audio data. The two modalities are combined using (i) a Simple Concatenated and (ii) CentralNet models. Experimental results demonstrate the effectiveness of combining two modalities over a single modality, achieving F<inf>1</inf>-scores of 0.6111 and 0.6270 for the Simple Concatenated and CentralNet models, respectively.
Some of the metrics are blocked by your
consent settings
Revisiting Echo State Networks for Continuous Gesture Recognition
(2022-01-01)
Yadav, Alok
;
Pasupa, Kitsuchart
;
Loo, Chu Kiong
Smartphones are equipped with Inertial Measurement Units (IMUs) that can capture user gesture data. Continuous gesture recognition is essential as it can be utilized and enhance human-computer interaction. Echo State Networks (ESNs) and Long Short-Term Memory (LSTM) models are well suited to performing this task. They have been successfully applied to the task in previous research, with LSTMs outperforming ESNs while having a considerably longer training time. However, the application of ESNs to continuous gesture recognition has not been fully explored as only the leaky integrator ESN has been used without hyperparameter optimization. In this study, we attempt to improve the ESN performance on the continuous gesture recognition task by experimenting with different model architectures and hyperparameter tuning. The performance of ESN models is significantly enhanced in terms of F1-score to 0.88, which is higher than the previously best performance of 0.87 using an LSTM model on continuous gesture recognition. The significant improvement is in training time, which is approximately 13 seconds for the ESN model compared to 89 seconds for the LSTM model in past research.
Some of the metrics are blocked by your
consent settings
Multiple steps time series prediction by a novel Recurrent Kernel Extreme Learning Machine approach
(2017-07-01)
Liu, Zongying
;
Loo, Chu Kiong
;
Masuyama, Naoki
;
Pasupa, Kitsuchart
This paper proposes a novel recurrent multi-steps- prediction model called Recurrent Kernel Extreme Learning Machine (RKELM). This model combines the strengths of recurrent multi-steps-prediction and Extreme Learning Machine (ELM) to unleash the limitation of prediction horizon. The kernel matrix is applied to replace the hidden layer mapping of ELM in order to solve the lack of predicting deterministic and parameter dependency. In the experiment, we apply two synthetic benchmark datasets and two real-world time series datasets including Malaysia palm oil price, ozone concentration of Toronto to evaluate RKELM and compare its performance against Recurrent Support Vector Regression (RSVR) and Recurrent Extreme Learning Machine (RELM). The experimental results show that RKELM has superior abilities in the different predicting horizons and stronger predicting deterministic than others.
Some of the metrics are blocked by your
consent settings
Recurrent kernel online sequential extreme learning machine with kernel adaptive filter for time series prediction
(2017-07-01)
Liu, Zongying
;
Loo, Chu Kiong
;
Pasupa, Kitsuchart
This paper proposes a novel recurrent multi-steps-prediction model call Recurrent Kernel Online Sequential Extreme Learning Machine with Surprise Criterion (SC-RKOS-ELM). This model combines the strengths of Kernel Online Sequential Extreme Learning Machine (KOS-ELM), the characteristics of surprise criterion and advantages of recurrent multi-steps-prediction algorithm to unleash the restriction of prediction horizon and reduce the computation complexation of the learning part. In the experiment, we employ two synthetic and two real-world data sets, including Mackey-Glass, Lorenz, palm oil price and water level in Thailand, to evaluate Recurrent Online Sequential Extreme Learning Machine (ROS-ELM) and Recurrent Kernel Online Sequential Extreme Learning Machine with Fixed-budget Criterion (FB-RKOS-ELM). The results of experiments indicate that SC-RKOS-ELM has the superior predicting ability in all data sets than others.
Some of the metrics are blocked by your
consent settings
DIAGNOSIS OF METABOLIC SYNDROME USING MACHINE LEARNING, STATISTICAL AND RISK QUANTIFICATION TECHNIQUES: A SYSTEMATIC LITERATURE REVIEW
(2021-01-01)
Kakudi, Habeebah Adamu
;
Loo, Chu Kiong
;
Moy, Foong Ming
;
Kau, Lim Chee
;
Pasupa, Kitsuchart
Metabolic syndrome (MetS), known to substantially lower the quality of life is associated with the increased incidence of non-communicable diseases (NCDs) such as type II diabetes mellitus, cardiovascular diseases and cancer. Evidence suggests that MetS accounts for the highest global mortality rate. For the early and accurate diagnosis of MetS, various statistical and ML techniques have been developed to support its clinical diagnosis. We performed a systematic review to investigate the various statistical and machine learning techniques (ML) that have been used to support the clinical diagnoses of MetS from the earliest studies to December 2020. Published literature relating to statistical and ML techniques for the diagnosis of MetS were identified by searching five major scientific databases: PubMed, Science Direct, IEEE Xplore, ACM digital library, and SpringerLink. Fifty-seven primary studies that met the inclusion criteria were obtained after screening titles, abstracts and full text. Three main types of techniques were identified: statistical (n=10), ML (n=44), and risk quantification (n=3). Standardized Z-score is the only statistical technique identified while the ML techniques include principal component analysis, confirmatory factory analysis, artificial neural networks, multiple logistics regression, decision trees, support vector machines, random forests, and Bayesian networks. The areal similarity degree risk quantification, framingham risk score and simScore were the three risk quantification techniques identified. Evidence suggests that evaluated ML techniques, with accuracy ranging from 75.5% to 98.9%, can more accurately diagnose MetS than both statistical and risk quantification techniques. The standardised Z-score is the most frequent statistical technique identified. However, highlighted proof based on performance measures indicate that the decision tree and artificial neural network ML techniques have the highest predictive performance for the prediction of MetS. Evidence suggests that more accurate diagnosis of MetS is required to evaluate the predictive performance of the statistical and ML techniques.
Some of the metrics are blocked by your
consent settings
Optimizing echo state networks for continuous gesture recognition in mobile devices: A comparative study
(2024-03-15)
Yadav, Alok
;
Pasupa, Kitsuchart
;
Loo, Chu Kiong
;
Liu, Xiaofeng
Continuous gesture recognition can be used to enhance human-computer interaction. This can be accomplished by capturing human movement with the use of the Inertial Measurement Units in smartphones and using machine learning algorithms to predict the intended gestures. Echo State Networks (ESNs) consist of a fixed internal reservoir that is able to generate rich and diverse nonlinear dynamics in response to input signals that capture temporal dependencies within the signal. This makes ESNs well-suited for time series prediction tasks, such as continuous gesture recognition. However, their application has not been rigorously explored, with regard to gesture recognition. In this study, we sought to enhance the efficacy of ESN models in continuous gesture recognition by exploring diverse model structures, fine-tuning hyperparameters, and experimenting with various training approaches. We used three different training schemes that used the Leave-one-out Cross-validation (LOOCV) protocol to investigate the performance in real-world scenarios with different levels of data availability: Leaving out data from one user to use for testing (F<inf>1</inf>-score: 0.89), leaving out a fraction of data from all users to use in testing (F<inf>1</inf>-score: 0.96), and training and testing using LOOCV on a single user (F<inf>1</inf>-score: 0.99). The obtained results outperformed the Long Short-Term Memory (LSTM) performance from past research (F<inf>1</inf>-score: 0.87) while maintaining a low training time of approximately 13 seconds compared to 63 seconds for the LSTM model. Additionally, we further explored the performance of the ESN models through behaviour space analysis using memory capacity, Kernel Rank, and Generalization Rank. Our results demonstrate that ESNs can be optimized to achieve high performance on gesture recognition in mobile devices on multiple levels of data availability. These findings highlight the practical ability of ESNs to enhance human-computer interaction.

Pasupa, Kitsuchart

Filters

Settings

Sort By

Results per page