Thannob Aribarg

Dr. Thannob Aribarg


Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
15 December 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
KYKarn Yongsiriwit
Karn Yongsiriwit
PCParkpoom Chaisiriprasert
Parkpoom Chaisiriprasert
TAThannob Aribarg
Thannob Aribarg
SKSokliv Kork
Sokliv Kork
Visual emotion recognition in unconstrained environments remains challenging, as single-stream deep learning models often fail to capture the localized facial cues and contextual information necessary for accurate classification. This study introduces a hierarchical multi-level feature fusion framework that systematically combines low-level micro-textural features (Local Binary Patterns), mid-level facial cues (Facial Action Units), and high-level scene semantics (Places365) with ResNet-50 global embeddings. Evaluated on the large-scale EmoSet-3.3M dataset, which contains 3.3 million images across eight emotion categories, the framework demonstrates marked performance gains with the best configuration (LBP-FAUs-Places365-ResNet). The proposed framework achieves 74% accuracy and a macro-averaged F1-score of 0.75 under its best configuration (LBP-FAUs-Places365-ResNet), representing a five-percentage-point improvement over the ResNet-50 baseline. The approach excels at distinguishing high-intensity emotions, maintaining efficient inference (2.2 ms per image, 29 M parameters), and analysis confirms that integrating facial muscle activations with scene context enables nuanced emotional differentiation. These results validate that hierarchical feature integration significantly advances robust, human-aligned visual emotion recognition, making it suitable for real-world Human–Computer Interaction (HCI) and affective computing applications.

12 November 2025 in Sustainability
Verified
Journal Article
Open access
PDF file
TAThannob Aribarg
Thannob Aribarg
KYKarn Yongsiriwit
Karn Yongsiriwit
PCParkpoom Chaisiriprasert
Parkpoom Chaisiriprasert
Nattapat PatchsuwanNattapat Patchsuwan
Nattapat Patchsuwan
SSSeree Supharatid
Seree Supharatid
The 2011 Great Flood in Thailand exposed critical deficiencies in water management across the Chao Phraya River Basin, particularly in controlling inflows and discharges from major reservoirs such as Sirikit and Bhumibol. Inadequate rainfall monitoring at the Nakhon Sawan station further intensified the disaster’s impact. As climate change continues to amplify extreme weather events, this study aims to improve flood forecasting accuracy and promote sustainable water resource management aligned with the Sustainable Development Goals (SDGs 6, 11, and 13). Advanced climate data from the Coupled Model Intercomparison Project Phase 5 (CMIP5) were spatially refined and integrated with hydrological models to enhance regional accuracy. The Discrete Wavelet Transform (DWT) was applied for feature extraction to capture hydrological variability, while the Nonlinear Autoregressive Model with Exogenous Factors (NARX) was employed to model complex temporal relationships. A multi-model ensemble framework was developed to merge climate forecasts with real-time hydrological data. Results demonstrate significant model performance improvements, with DWT-NARX achieving 55–98% lower prediction errors (RMSE) compared to baseline methods and correlation coefficients exceeding 0.91 across all forecasting scenarios. Marked seasonal variations emerge, with higher inflows during wet periods and reduced inflows during dry seasons. Under RCP8.5 climate scenarios, wet-season inflows are projected to increase by 15.8–17.4% by 2099, while dry-season flows may decline by up to 33.5%, potentially challenging future water availability and flood control operations. These findings highlight the need for adaptive and sustainable water management strategies to enhance climate resilience and advance SDG targets on water security, disaster risk reduction, and climate adaptation.

PYPongjan Yoopat
Pongjan Yoopat
NJNisakorn Julraksa
Nisakorn Julraksa
WLWeerawat Liemmanee
Weerawat Liemmanee
KYKarn Yongsiriwit
Karn Yongsiriwit
TAThannob Aribarg
Thannob Aribarg
Retail service workers face complex occupational demands across psychosocial, environmental, and physical domains; however, integrated multidomain workload assessments remain limited. A cross-sectional study among 253 retail workers used the Find My Stress Progressive Web Application (PWA)—a digital tool assessing subjective workload (Subjective Workload Index; SWI), psychosocial factors, environmental discomfort, musculoskeletal symptoms, and handgrip strength. Hierarchical multiple regression identified four significant SWI predictors: postural difficulty (β = 0.176, p = 0.012), workplace bullying (β = 0.175, p = 0.008), task duration (β = −0.179, p = 0.004), and air quality (β = 0.171, p = 0.011; Adjusted R2 = 0.199, ΔR2 = 0.227, p < 0.001; VIF: 1.03–1.57). Grip strength was retained as a functional capacity indicator. Sex-stratified analyses revealed distinct risk profiles: postural difficulty and task duration predicted SWI in men (Adjusted R2 = 0.224); workplace bullying was the sole predictor in women (Adjusted R2 = 0.170). The PWA demonstrated excellent reliability (α = 0.97) and usability (87%; n = 359). The Find My Stress PWA provides a scalable platform for multidomain stress screening. Integrated ergonomic, organisational, and environmental interventions guided by digital screening offer targeted strategies for reducing occupational workload burden in retail settings.


9 April 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
PYPongjan Yoopat
Pongjan Yoopat
NJNisakorn Julraksa
Nisakorn Julraksa
WLWeerawat Liemmanee
Weerawat Liemmanee
KYKarn Yongsiriwit
Karn Yongsiriwit
TAThannob Aribarg
Thannob Aribarg
Retail service workers face complex occupational demands across psychosocial, environmental, and physical domains; however, integrated multidomain assessments of psychological workload remain limited. A cross-sectional study was conducted among 253 full-time retail workers using the Find My Stress Progressive Web Application (PWA)—a field-deployable digital screening tool. The PWA assessed subjective workload (Subjective Workload Index; SWI), psychosocial factors (workplace bullying, postural difficulty), environmental discomfort (thermal conditions, air quality, noise), musculoskeletal symptoms, and bilateral handgrip strength. Spearman correlations and multiple regression identified significant predictors. Postural difficulty (β = 0.21, p = .003), workplace bullying (β = 0.17, p = .008), thermal discomfort (β = 0.16, p = .021), air quality concerns (β = 0.14, p = .043), task duration (β = −0.16, p = .010), and grip strength (suppressor effect; β = 0.13, p = .030) independently predicted SWI (Adjusted R² = .22, F(6, 214) = 11.45, p < .001). The PWA demonstrated excellent reliability (Cronbach’s α = 0.97) and high usability (87% positive ratings; n = 359). A multidomain digital assessment successfully identified interacting psychosocial, environmental, and functional determinants of psychological workload. The Find My Stress PWA offers a scalable, low-burden platform for occupational stress screening applicable in workplace health surveillance.