Chidchanok Choksuchat
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Chidchanok Choksuchat has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
Chantana Chantrapornchai
Kasetsart University, Bangkok, Thailand
9 shared publications- Chantana Chantrapornchai
Department of Computer Engineering, Faculty of Engineering, Kasetsart University, Bangkok 10900, Thailand
6 shared publications - Korakot Wichitsa-Nguan Jetwanna
Prince of Songkla University
3 shared publications - Anny Mardjo
College of Digital Science, Prince of Songkla University, Hat Yai, Thailand
2 shared publications - Kochakorn Sukjan Inthanuchit
Prince of Songkla University
2 shared publications - Numtip Trakulmaykee
Prince of Songkla University
2 shared publications
Latest Publications
- 29 March 2025
- Published by Elsevier in Journal of Vascular Nursing
- Vol. 43 (2) , 80-85
Effects of an electronic foot massage device on venous blood flow velocity in healthy adults
- 29 March 2025
- Published by Elsevier in Journal of Vascular Nursing
- Vol. 43 (2) , 80-85
Effects of an electronic foot massage device on venous blood flow velocity in healthy adults
- Open Access
- 1 December 2024
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 14 (6) , 6807-6816
Moderating roles of user’s intention to use LINE official account in healthcare context: body mass index
This study aimed to investigate the extended factors based on the technology acceptance model, and the moderating roles of customer behavioral intention factors to use information technology. This research is a questionnaire-based survey with convenience sampling approach where 386 cases were collected from healthcare customers. For statistical analysis, the study used SmartPLS as a tool for regression analysis and descriptive statistics. The findings revealed the influence of social norm on customer behavioral intention to use information technology in the healthcare context as significant factors at 0.001. In addition, the results indicated the small effect of two moderating variables in the proposed model. First, the problematic body mass index (BMI) can be a moderator on the relationship between social norm and customer behavioral intention to use technology at a significant level of 0.05. Second, the technology experience can moderate the relationship between perceived ease of use and customer behavioral intention to use technology at a significant level of 0.05. The proposed model may guide for future exploration, especially information services in healthcare businesses and developers.
- 1 December 2024
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 14 (6) , 6807-6816
Open AccessModerating roles of user’s intention to use LINE official account in healthcare context: body mass index
This study aimed to investigate the extended factors based on the technology acceptance model, and the moderating roles of customer behavioral intention factors to use information technology. This research is a questionnaire-based survey with convenience sampling approach where 386 cases were collected from healthcare customers. For statistical analysis, the study used SmartPLS as a tool for regression analysis and descriptive statistics. The findings revealed the influence of social norm on customer behavioral intention to use information technology in the healthcare context as significant factors at 0.001. In addition, the results indicated the small effect of two moderating variables in the proposed model. First, the problematic body mass index (BMI) can be a moderator on the relationship between social norm and customer behavioral intention to use technology at a significant level of 0.05. Second, the technology experience can moderate the relationship between perceived ease of use and customer behavioral intention to use technology at a significant level of 0.05. The proposed model may guide for future exploration, especially information services in healthcare businesses and developers.
- Open Access
- 8 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 50792-50808
HyBiLSTM: Multivariate Bitcoin Price Forecasting Using Hybrid Time-Series Models With Bidirectional LSTM
Despite their growing popularity in recent research, most hybrid models that harness the strengths of both classical time-series analysis and deep learning models have been explored within the univariate forecasting context. In the econometric domain, where exogenous factors play a crucial role; there is a pressing need for more studies focusing on multivariate forecasting. This paper introduces a novel hybrid model, HyBiLSTM. It integrates an ARIMAX GARCHX model for initial forecasting, followed by a second forecasting phase that addresses the residuals using a bidirectional long short-term memory model optimized through grey wolf optimization algorithm. The final forecast is a composite derived from both models. Three quantitative metrics (mean absolute error, root mean square error, and mean absolute percentage error) assessed the model performance using data that spanned social and economic variables from July 1, 2019, to December 31, 2022. The results revealed several key findings: 1) The addition of exogenous factors improved the performance of the ARIMA and GARCH models. 2) The BiLSTM variant outperformed other LSTM variants when combined with the ARIMAX GARCHX model. 3) An analysis using Shapley additive explanations indicated that bitcoin price was influenced by stock prices, Twitter volume, gold prices, and the Twitter sentiment index. 4) The presence of a structural break had a significant effect on the model’s forecasting accuracy. Beyond expanding the academic literature on hybrid models within a multivariate context, this offers valuable practical insights for investors. Specifically, it analyzes various factors that could serve as early indicators of bitcoin price fluctuations.
- 8 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 50792-50808
Open AccessHyBiLSTM: Multivariate Bitcoin Price Forecasting Using Hybrid Time-Series Models With Bidirectional LSTM
Despite their growing popularity in recent research, most hybrid models that harness the strengths of both classical time-series analysis and deep learning models have been explored within the univariate forecasting context. In the econometric domain, where exogenous factors play a crucial role; there is a pressing need for more studies focusing on multivariate forecasting. This paper introduces a novel hybrid model, HyBiLSTM. It integrates an ARIMAX GARCHX model for initial forecasting, followed by a second forecasting phase that addresses the residuals using a bidirectional long short-term memory model optimized through grey wolf optimization algorithm. The final forecast is a composite derived from both models. Three quantitative metrics (mean absolute error, root mean square error, and mean absolute percentage error) assessed the model performance using data that spanned social and economic variables from July 1, 2019, to December 31, 2022. The results revealed several key findings: 1) The addition of exogenous factors improved the performance of the ARIMA and GARCH models. 2) The BiLSTM variant outperformed other LSTM variants when combined with the ARIMAX GARCHX model. 3) An analysis using Shapley additive explanations indicated that bitcoin price was influenced by stock prices, Twitter volume, gold prices, and the Twitter sentiment index. 4) The presence of a structural break had a significant effect on the model’s forecasting accuracy. Beyond expanding the academic literature on hybrid models within a multivariate context, this offers valuable practical insights for investors. Specifically, it analyzes various factors that could serve as early indicators of bitcoin price fluctuations.
- Open Access
- 27 December 2023
- Published by Silpakorn University in Science, Engineering and Health Studies
- p. 23020007
Utilization of various time series models forecasting gold prices in Thailand
This work develops an interactive dashboard integrating various time series models to forecast gold prices in Thailand, enabling investors to make better decisions more efficiently and effectively manage their investments. The study used monthly data from 2009 to 2021, separated the data series into in- and out-samples, and found that the gold price dataset did not have an autoregressive conditional heteroskedasticity (ARCH) effect. The process consumed the autoregressive integrated moving average (ARIMA) best model without passing through the generalized autoregressive conditionally heteroskedastic (GARCH)/ARIMA best model. The highest-performance model for forecasting was the ARIMA (1,1,1) model. This research extends the implementation scope of previous research on gold price forecasting with developer fulfillment in Thailand by developing a business intelligence dashboard for users to utilize the predictions. The dashboard is interactive, allowing users to filter the data and predictions based on their needs. Integrating various time series models for forecasting gold prices in Thailand on a single dashboard will enable investors to make better decisions and manage their investments efficiently and effectively. The authors are also developing an automatic utilization script to further improve the dashboard usability.
- 27 December 2023
- Published by Silpakorn University in Science, Engineering and Health Studies
- p. 23020007
Open AccessUtilization of various time series models forecasting gold prices in Thailand
This work develops an interactive dashboard integrating various time series models to forecast gold prices in Thailand, enabling investors to make better decisions more efficiently and effectively manage their investments. The study used monthly data from 2009 to 2021, separated the data series into in- and out-samples, and found that the gold price dataset did not have an autoregressive conditional heteroskedasticity (ARCH) effect. The process consumed the autoregressive integrated moving average (ARIMA) best model without passing through the generalized autoregressive conditionally heteroskedastic (GARCH)/ARIMA best model. The highest-performance model for forecasting was the ARIMA (1,1,1) model. This research extends the implementation scope of previous research on gold price forecasting with developer fulfillment in Thailand by developing a business intelligence dashboard for users to utilize the predictions. The dashboard is interactive, allowing users to filter the data and predictions based on their needs. Integrating various time series models for forecasting gold prices in Thailand on a single dashboard will enable investors to make better decisions and manage their investments efficiently and effectively. The authors are also developing an automatic utilization script to further improve the dashboard usability.
- 2 November 2023
- Published by Springer Nature in Universal Access in the Information Society
- Vol. 24 (1) , 99-125
IoT-based systems and applications for elderly healthcare: a systematic review
- 2 November 2023
- Published by Springer Nature in Universal Access in the Information Society
- Vol. 24 (1) , 99-125
IoT-based systems and applications for elderly healthcare: a systematic review
- 12 September 2023
- Published by Springer Nature
- p. 61-70
Results of Using Business Intelligence Forecasting Customer Insight of World Integrated Suvarnabhumi Education Platform
- 12 September 2023
- Published by Springer Nature
- p. 61-70
Results of Using Business Intelligence Forecasting Customer Insight of World Integrated Suvarnabhumi Education Platform
- Open Access
- 26 September 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 101889-101897
HyVADRF: Hybrid VADER–Random Forest and GWO for Bitcoin Tweet Sentiment Analysis
In recent years, Bitcoin and other cryptocurrencies have been increasingly considered investment options for emerging markets. However, Bitcoin’s erratic behavior has discouraged some potential investors. To get insights into its behavior and price fluctuation, past studies have discovered the correlation between Twitter sentiments and Bitcoin behavior. Most of them have exclusively focused on their relationships, instead of the Twitter sentiment analysis itself. Finding the most suitable classification algorithms for sentiment analysis for this kind of data is challenging. For the enormous data in Twitter, the supervised sentiment analysis approach of unlabeled data can be time-consuming and expensive, which has been studied to be superior to unsupervised ones. As such, we propose the HyVADRF (hybrid valence aware dictionary and sentiment reasoner (VADER)–random forest) and gray wolf optimizer (GWO) model. A semantic and rule-based VADER was used to calculate polarity scores and classify sentiments, which overcame the weakness of manual labeling, while a random forest was utilized as its supervised classifier. Furthermore, considering Twitter’s massive size, we collected over 3.6 million tweets and analyzed various dataset sizes as these are related to the model’s learning process. Lastly, GWO parameter tuning was conducted to optimize the classifier’s performance. The results show that 1) the HyVADRF model had an accuracy of 75.29%, precision of 70.22%, recall of 87.70%, and F1-score of 78%. 2) The most ideal dataset size percentage is 90% of the total collected tweets ( $n =1$ ,249,060). 3) The standard deviations are 0.0008 for accuracy and F1-score and 0.0011 for precision and recall. Hence, the HyVADRF model consistently delivers stable results.
- 26 September 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 101889-101897
Open AccessHyVADRF: Hybrid VADER–Random Forest and GWO for Bitcoin Tweet Sentiment Analysis
In recent years, Bitcoin and other cryptocurrencies have been increasingly considered investment options for emerging markets. However, Bitcoin’s erratic behavior has discouraged some potential investors. To get insights into its behavior and price fluctuation, past studies have discovered the correlation between Twitter sentiments and Bitcoin behavior. Most of them have exclusively focused on their relationships, instead of the Twitter sentiment analysis itself. Finding the most suitable classification algorithms for sentiment analysis for this kind of data is challenging. For the enormous data in Twitter, the supervised sentiment analysis approach of unlabeled data can be time-consuming and expensive, which has been studied to be superior to unsupervised ones. As such, we propose the HyVADRF (hybrid valence aware dictionary and sentiment reasoner (VADER)–random forest) and gray wolf optimizer (GWO) model. A semantic and rule-based VADER was used to calculate polarity scores and classify sentiments, which overcame the weakness of manual labeling, while a random forest was utilized as its supervised classifier. Furthermore, considering Twitter’s massive size, we collected over 3.6 million tweets and analyzed various dataset sizes as these are related to the model’s learning process. Lastly, GWO parameter tuning was conducted to optimize the classifier’s performance. The results show that 1) the HyVADRF model had an accuracy of 75.29%, precision of 70.22%, recall of 87.70%, and F1-score of 78%. 2) The most ideal dataset size percentage is 90% of the total collected tweets ( $n =1$ ,249,060). 3) The standard deviations are 0.0008 for accuracy and F1-score and 0.0011 for precision and recall. Hence, the HyVADRF model consistently delivers stable results.
- 9 March 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 333-336
On the Design and Evaluation of Decision Support Platform for Prostate Cancer Disease
The study aims to design and evaluate the Decision Support Platform (DSP) for prostate cancer disease. The system was developed based on COX regression model for predicting survival analysis by training data of the patients' profiles with factors that are relevant to prostate cancer, which includes age and laboratory examination results using R script. The results are the mathematics component analysis. First, they uploaded various file types of input to decision support system for prostate cancer disease which converted those formulas to a matrix. Second, a new profile from patients is retrieved to DSP for patient decision aids. Third, the reports from the second step can support the treatment decision making process to physicians. They can empower patients to take a proactive role in their treatment pathway and to make participatory medicine possible. Finally, web service engine and endpoints were used to design the system and publish to the co-research developers, the medical statistician staff and other patients. In evaluation, the developed decision support platform for prostate cancer disease was measured in terms of system performance of “uploading 6 types of input” and user satisfaction with 60% of excellent to see how the system can support the users. The results show that system usage assessment category satisfaction level is 48% of excellent “content”, 45% excellent on “design”, and 66.67% excellent on “utilization”.
- 9 March 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 333-336
On the Design and Evaluation of Decision Support Platform for Prostate Cancer Disease
The study aims to design and evaluate the Decision Support Platform (DSP) for prostate cancer disease. The system was developed based on COX regression model for predicting survival analysis by training data of the patients' profiles with factors that are relevant to prostate cancer, which includes age and laboratory examination results using R script. The results are the mathematics component analysis. First, they uploaded various file types of input to decision support system for prostate cancer disease which converted those formulas to a matrix. Second, a new profile from patients is retrieved to DSP for patient decision aids. Third, the reports from the second step can support the treatment decision making process to physicians. They can empower patients to take a proactive role in their treatment pathway and to make participatory medicine possible. Finally, web service engine and endpoints were used to design the system and publish to the co-research developers, the medical statistician staff and other patients. In evaluation, the developed decision support platform for prostate cancer disease was measured in terms of system performance of “uploading 6 types of input” and user satisfaction with 60% of excellent to see how the system can support the users. The results show that system usage assessment category satisfaction level is 48% of excellent “content”, 45% excellent on “design”, and 66.67% excellent on “utilization”.
- 28 August 2020
- Published by IGI Global Scientific Publishing
- p. 247-269
A Proposed Conceptual Framework of Factors Influencing Consumer E- Wallet Adoption in Malaysia and Thailand
The proposed conceptual framework in this research was developed by Venkatesh. The framework will extend the Unified Theory of Acceptance and Useful Technology (UTAUT) model by incorporating with other variables in order to determine the factors that influence the intention of e-wallet adoption among the consumers from the respective countries: Malaysia and Thailand. By integrating with other variables which are based on the usage of e-wallet, the research outcome will be able to provide more comprehensive and better explanations on the consumer behaviour instead of just focusing on the technology characteristics. Furthermore, this research will also compare the results between Malaysian consumers and Thai consumers in order to explain the factors of e-wallet adoption and consumer behaviour between the two countries.
- 28 August 2020
- Published by IGI Global Scientific Publishing
- p. 247-269
A Proposed Conceptual Framework of Factors Influencing Consumer E- Wallet Adoption in Malaysia and Thailand
The proposed conceptual framework in this research was developed by Venkatesh. The framework will extend the Unified Theory of Acceptance and Useful Technology (UTAUT) model by incorporating with other variables in order to determine the factors that influence the intention of e-wallet adoption among the consumers from the respective countries: Malaysia and Thailand. By integrating with other variables which are based on the usage of e-wallet, the research outcome will be able to provide more comprehensive and better explanations on the consumer behaviour instead of just focusing on the technology characteristics. Furthermore, this research will also compare the results between Malaysian consumers and Thai consumers in order to explain the factors of e-wallet adoption and consumer behaviour between the two countries.