Numerous metrics, such as visitor numbers, tourism net profit, and hotel occupancy rates, are included in the dataset presented in this study, which covers 77 provinces. A baseline-based concept of shock recovery is introduced to measure impact and recovery paths in different regions. Recurrent neural networks incorporate engineered elements that capture seasonality, trend dynamics, shock strength, volatility, and recovery timing. Importantly, latent spatial heterogeneity and cross-regional dependencies are learned within a single architecture by integrating province-level spatiotemporal embeddings. To jointly forecast tourism demand and net profit, Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) models are created. Using a time-preserving evaluation technique, model performance is assessed against statistical time-series baselines and XGBoost. In early 2020, the results show a structural break that exceeded the 95% decline, along with significantly unequal recovery patterns. The suggested deep learning models surpass baselines by roughly 22-28% in RMSE and 14-16% in MAPE, exhibiting superior ability in capturing spatial heterogeneity and nonlinear recovery dynamics.
Radiographic imaging remains a cornerstone of diagnostic practice. However, accurate interpretation faces challenges from subtle visual signatures, anatomical variability, and inter-observer inconsistency. Conventional deep learning approaches, such as convolutional neural networks and vision transformers, deliver strong predictive performance but often lack anatomical grounding and interpretability, limiting their trustworthiness in imaging applications. To address these challenges, we present SpineNeuroSym, a neuro-geometric imaging framework that unifies geometry-aware learning and symbolic reasoning for explainable medical image analysis. The framework integrates weakly supervised keypoint and region-of-interest discovery, a dual-stream graph-transformer backbone, and a Differentiable Radiographic Geometry Module (dRGM) that computes clinically relevant indices (e.g., slip ratio, disc asymmetry, sacroiliac spacing, and curvature measures). A Neuro-Symbolic Constraint Layer (NSCL) enforces monotonic logic in image-derived predictions, while a Counterfactual Geometry Diffusion (CGD) module generates rare imaging phenotypes and provides diagnostic auditing through counterfactual validation. Evaluated on a comprehensive dataset of 1613 spinal radiographs from Sunpasitthiprasong Hospital encompassing six diagnostic categories-spondylolisthesis (n = 496), infection (n = 322), spondyloarthropathy (n = 275), normal cervical (n = 192), normal thoracic (n = 70), and normal lumbar spine (n = 258)-SpineNeuroSym achieved 89.4% classification accuracy, a macro-F1 of 0.872, and an AUROC of 0.941, outperforming eight state-of-the-art imaging baselines. These results highlight how integrating neuro-geometric modeling, symbolic constraints, and counterfactual validation advances explainable, trustworthy, and reproducible medical imaging AI, establishing a pathway toward transparent image analysis systems.
OBJECTIVE:Consumption of fermented freshwater fish is common in Northeast Thailand but increases the risk of Opisthorchis viverrini (OV) infection, nitrosamine exposure, and cholangiocarcinoma (CCA). This study evaluated a 3Es-based safety program designed to enhance knowledge, attitudes, behaviors, and to reduce ergonomic risks among informal fish processors. METHODS:A quasi-experimental study was conducted with 100 participants from two fishing communities in Ubon Ratchathani Province. The experimental group (n = 50) received a 13-week safety program based on engineering, education, and enforcement (3Es), while the comparison group (n = 50) received routine health services. Data were collected through a structured questionnaire and an ergonomic assessment using the Rapid Upper Limb Assessment (RULA). Statistical analyses included t-tests and effect size estimation with Cohen's d. RESULTS:Post-intervention, the experimental group demonstrated significantly greater improvements than the comparison group in knowledge (mean difference = 2.09, p < 0.001, d = 2.69, very large effect), attitudes (mean difference = 0.39, p < 0.001, d = 3.88, very large effect), and behaviors (mean difference = 0.25, p < 0.001, d = 1.06, large effect). RULA scores also improved markedly, with fish sorting, drying, and packaging risk levels reduced from high to low, and cleaning and gutting reduced from very high to medium risk. CONCLUSION:The 3Es-based program significantly improved safety-related knowledge, attitudes, behaviors, and reduced ergonomic risks. Large effect sizes confirm that these gains are both statistically and practically meaningful, supporting integration into community health services and local policies for sustainable OV and CCA prevention.
Sok Chan Forest, located in Lao Suea Kok District, Ubon Ratchathani Province, Thailand, is frequently affected by wildfires during the dry season, resulting in significant environmental degradation and adverse impacts on the livelihoods of local communities. In this study, we outline the development of a prototype wildfire early warning system utilizing LoRa technology to address the long-distance data transmission limitations that are commonly encountered when using conventional Internet of Things (IoT) solutions. The proposed system comprises sensor nodes that communicate from peer to peer with a central node, which subsequently relays the collected data to a remote database server via the internet. Real-time alerts are disseminated through both a smartphone application and a web-based platform, thereby facilitating timely notification of authorities and community members. Field experiments in Sok Chan Forest demonstrated reliable single-hop communication with a 100% packet delivery ratio at distances up to 1500 m, positive SNR, and RSSI levels above receiver sensitivity, as well as sub-second end-to-end detection latency in both single- and two-hop configurations. A controlled alarm accuracy evaluation yielded an overall classification accuracy of 91.7%, with perfect precision for the Fire class, while a user study involving five software development experts and fifteen firefighters yielded an average effectiveness score of 3.84, reflecting a high level of operational efficacy.
Objective: This cross-sectional study aimed to determine the factors related to sleep quality among older adults aged 60 years and above in a northeastern province of Thailand. Material and Methods: A total of 355 participants were randomly selected by multistage sampling between October and December 2024. Data collection tools included general characteristics, physical environment, family relationships, stress assessment, the Thai Geriatric Depression Scale (TGDS-15), and the Pittsburgh Sleep Quality Index (PSQI). The instrument’s content validity was ≥0.67 for each item, and the reliability was 0.77. Descriptive statistics and multiple logistic regression analysis were performed using a statistical software package. A p-value set at <0.05.Results: Average age of participants was 68.59±8.741 years old; 45.7% had no underlying medical conditions and 23.1% lived in a rural area. Factors associated with sleep quality were being female (aOR, 0.58; 95%CI, 0.352 to 0.954), living in a rural area (aOR, 1.97; 95%CI, 1.104 to 3.493), having severe problems related to their physical environment (aOR, 3.60; 95%CI, 1.362 to 9.510), having moderate stress (aOR, 2.11; 95%CI, 1.219 to 3.635), and having signs of depression (aOR, 2.12; 95%CI, 1.270 to 3.553). Conclusion: People in both urban and rural areas should be supported by intervention programs in order to increase good sleep quality. Furthermore, encouraging family bonding can promote a supportive home environment, strengthen relationships, and enhance overall family well-being. Activities that promote mental health, such as exercise, recreational activities, and meditation, are suggested to help reduce stress and depression in this population.
