Teerawat Simmachan

Dr. Teerawat Simmachan

Department of Mathematics and Statistics, Faculty of Science and Technology, Thammasat University, Pathum Thani, Thailand
orcid

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 November 2022 in PLOS ONE
Verified
Journal Article
Open access
PDF file
Teerawat SimmachanTeerawat Simmachan
Teerawat Simmachan
Noppachai WongsaiNoppachai Wongsai
Noppachai Wongsai
SWSangdao Wongsai
Sangdao Wongsai
RLRattana Lerdsuwansri
Rattana Lerdsuwansri
In 2013, Thailand was ranked second in the world in road accident fatalities (RAFs), with 36.2 per 100,000 people. During the Songkran festival, which takes place during the traditional Thai New Year in April, the number of road traffic accidents (RTAs) and RAFs are markedly higher than on regular days, but few studies have investigated this issue as an effect of festivity. This study investigated the factors that contribute to RAFs using various count regression models. Data on 20,229 accidents in 2015 were collected from the Department of Disaster Prevention and Mitigation in Thailand. The Poisson and Conway–Maxwell–Poisson (CMP) distributions, and their zero-Inflated (ZI) versions were applied to fit the data. The results showed that RAFs in Thailand follow a count distribution with underdispersion and excessive zeros, which is rare. The ZICMP model marginally outperformed the CMP model, suggesting that having many zeros does not necessarily mean that the ZI model is required. The model choice depends on the question of interest, and a separate set of predictors highlights the distinct aspects of the data. Using ZICMP, road, weather, and environmental factors affected the differences in RAFs among all accidents, whereas month distinguished actual non-fatal accidents and crashes with or without deaths. As expected, actual non-fatal accidents were 2.37 times higher in April than in January. Using CMP, these variables were significant predictors of zeros and frequent deaths in each accident. The RAF average was surprisingly higher in other months than in January, except for April, which was unexpectedly lower. Thai authorities have invested considerable effort and resources to improve road safety during festival weeks to no avail. However, our study results indicate that people’s risk perceptions and public awareness of RAFs are misleading. Therefore, nationwide road safety should instead be advocated by the authorities to raise society’s awareness of everyday personal safety and the safety of others.

25 March 2025 in Journal of Current Science and Technology
Verified
Journal Article
Open access
PDF file
Teerawat SimmachanTeerawat Simmachan
Teerawat Simmachan
Pichit BoonkrongPichit Boonkrong
Pichit Boonkrong
Road traffic accidents (RTAs) pose a significant global challenge, particularly in Thailand. This study investigates the impact of resampling techniques on machine learning (ML) models for classifying road accident severity in Thailand, utilizing data from 31,817 road traffic accidents collected between January 1, 2021, and December 31, 2022. The primary challenge addressed is class imbalance, where fatal accidents represent a small fraction of the dataset. Three popular ML models, including Random Forest (RF), K-Nearest Neighbors (KNN), and Extreme Gradient Boosting (XGB), were evaluated with four resampling techniques: Imbalanced (IB), Under-sampling (US), Over-sampling (OS), and Combined Sampling (CS). These resampling approaches generated 12 ML models, whose performance was evaluated under three different train/test split ratios: 70/30, 80/20, and 90/10. Compared to the IB approach, the results demonstrate that all US, OS and CS techniques significantly improved model performance, particularly in terms of F1 score, G-mean, and balanced accuracy. Among the models, RF-CS, KNN-OS, and XGB-CS exhibited the best classification performance. Although these evaluation metrics improved over the imbalanced scheme, KNN’s overall performance in detecting fatal accidents was weaker compared to RF and XGB. Specifically, KNN struggled more with the imbalanced dataset, even after applying resampling techniques. These findings suggest that choosing the appropriate resampling techniques is crucial for enhancing model performance in classifying accident severity.

1 May 2023 in Mathematics and Statistics
Verified
Journal Article
Open access
PDF file
WPWikanda Phaphan
Wikanda Phaphan
Teerawat SimmachanTeerawat Simmachan
Teerawat Simmachan
IAIbrahim Abdullahi
Ibrahim Abdullahi
The three-parameter weighted mixture generalized gamma (WMGG) distribution was developed from the four-parameter mixture generalized gamma (MGG) distribution since the parameter estimation of MGG distribution faced with the problem. The estimate of the weighted parameter p was out of the interval [0, 1]. The previous study proposed the maximum likelihood estimators (MLEs) of the WMGG distribution. However, their MLEs were written in nonlinear equations, and certain iterative methods were necessarily needed to solve numerically. The three parameters λ, β, and α were estimated by the quasi-Newton method. Nevertheless, this method performed well only the parameter λ. This motivated the main objective of this work. Consequently, the parameter estimation of the WMGG was further improved. This article developed two maximum likelihood estimation methods: expectation-maximization (EM) algorithm and simulated annealing algorithm of the three parameters of the WMGG distribution. These two methods were compared to the previous study's quasi-Newton method. Monte Carlo simulation technique was employed to assess the algorithm's performance. Sample sizes ranged from small to large as 10, 30, 50, and 100. The simulation was repeated 10,000 rounds in each scenario. Assessment criteria were the mean square error (MSE) and bias. The results revealed that the EM algorithm outperformed the other methods. Furthermore, the quasi-Newton method had the lowest efficiency.

13 September 2025 in Healthcare Analytics
Verified
Journal Article
Open access
Teerawat SimmachanTeerawat Simmachan
Teerawat Simmachan
NLNapatsawan Lerdpraserdpakorn
Napatsawan Lerdpraserdpakorn
JDJarupa Deesrisuk
Jarupa Deesrisuk
CSChanadda Sriwipat
Chanadda Sriwipat
SSSubij Shakya
Subij Shakya
Pichit BoonkrongPichit Boonkrong
Pichit Boonkrong

26 September 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
Pichit BoonkrongPichit Boonkrong
Pichit Boonkrong
SSSubij Shakya
Subij Shakya
WKWantika Kraunamkam
Wantika Kraunamkam
Teerawat SimmachanTeerawat Simmachan
Teerawat Simmachan
This study investigates the relationship between dietary patterns and psoriasis severity using advanced machine learning (ML) techniques. The dataset, comprising 37 features including demographic, clinical and dietary features from 142 Thai psoriasis patients, exhibits moderately high dimensionality typical of clinical studies. To address limitations posed by the small sample size, a hybrid resampling strategy integrating bootstrapping with K-fold Cross-Validation (CV) was implemented. Using Random Forest (RF) and eXtreme Gradient Boosting (XGB), a total of 60 classification models were evaluated by varying train/test splits and applying multiple feature selection methods, including Least Absolute Shrinkage and Selection Operator (LASSO), Mean Decrease Accuracy (MDA), and Mean Decrease Impurity (MDI). Although bootstrapping alone sometimes resulted in overfitting, its combination with K-fold CV improved generalizability. In optimal configurations, both RF and XGB achieved sensitivity, specificity, and F1-scores exceeding 90%, alongside area under the curve (AUC) values above 95%. SHapley Additive exPlanations (SHAP) analysis revealed key dietary factors associated with increased psoriasis severity, including high-sodium foods, processed meats, alcohol, red meats, fermented products, and dark-colored vegetables. Clinically, prioritizing weight management is essential, as Body Mass Index (BMI) arose as the strongest feature of psoriasis severity. Dietary triggers identified in this study should inform comprehensive care plans. Popular Thai cuisines, especially Tom Yum Kung emerged as a potentially suitable option, while Som Tum, Pad Thai, Moo Kratha, and Khao Niao Mamuang were identified as potential triggers when consumed excessively. These findings highlight the importance of dietary moderation and personalized guidance, supporting health literacy, patient management, and smart healthcare innovations in Thailand.

1 December 2024 in Lobachevskii Journal of Mathematics
Verified
Journal Article
Closed access
PDF file
Teerawat SimmachanTeerawat Simmachan
Teerawat Simmachan
Pichit BoonkrongPichit Boonkrong
Pichit Boonkrong
This study investigates the estimation of claim frequencies in voluntary automobile insurance, a critical component of actuarial risk assessment and premium rating. As automobile usage in Thailand continues to rise, accurately predicting claim occurrences becomes increasingly vital for insurers to maintain financial stability and appropriate reserve allocation. The research employs a dataset of 4,986 automobile insurance policies from 2017 to compare the efficacy of six regression models including Poisson, Negative Binomial (NB), Conway–Maxwell–Poisson (CMP), and their Zero-Inflated (ZI) versions; ZIP, ZINB, and ZICMP. Then, the model performance was evaluated using likelihood based methods including Akaike’s Information Criterion (AIC), Bayesian Information Criterion (BIC), Likelihood Ratio test (LRT), and Vuong test. The numerical results indicate that the ZICMP model demonstrates superior performance in predicting claim frequencies, yielding the lowest AIC and BIC of 3,923.10 and 3,968.70, respectively. The LRT and Vuong test also support our conclusion. The crucial factors influencing claim occurrence were identified as premium, no-claim bonus, and incurred loss. These findings contribute to the actuarial literature by providing insights into optimal modeling techniques for claim frequency prediction in the Thai voluntary automobile insurance market. The results have practical implications for insurers in premium calculation, reserve setting, and risk factor identification, potentially enhancing overall risk management strategies.