This study deals with two approaches—viz. via Box-Jenkins and artificial neuron network to forecast the unemployment rate in Thailand. The Box-Jenkins approach proves more efficient to estimate the unemployment rate in Thailand, with less MAPE compared to the second model. The forecast values are consistent with the actual values and tend to decrease.

The purpose of this study is to address two major issues: (1) the spread of epidemics such as COVID-19 due to long waiting times caused by a large number of waiting for customers, and (2) excessive energy consumption resulting from the elevator patterns used by various customers. The first issue is addressed through the development of a mobile application, while the second issue is tackled by implementing two strategies: (1) determining optimal stopping strategies for elevators based on registered passengers and (2) assigning passengers to elevators in a way that minimizes the number of floors the elevators need to stop at. The mobile application serves as an input parameter for the optimization toolbox, which employs the exact method and multi-objective variable neighborhood strategy adaptive search (M-VaNSAS) to find the optimal plan for passenger assignment and elevator scheduling. The proposed method, which adopts an even-odd floor strategy, outperforms the currently practiced procedure and leads to a 42.44% reduction in waiting time and a 29.61% reduction in energy consumption. Computational results confirmed the effectiveness of the proposed approach.

The log-normal distribution is a commonly used parametric distribution applied in reliability and survival analysis. For two or more populations, various techniques have been developed to derive confidence intervals for functions of the population parameters under the assumptions of independence and linear dependence between the samples. We extend the existing log-normal confidence interval methodologies by utilizing a jackknifing procedure based on the inference for margins methodology under parametrically defined copula dependence structures. We assess the performance of the procedure on simulated data and apply the methodology to calculate confidence intervals for the mean maximal damage area caused by ground based tornadoes in Canada.

This study presents a Graph-Based Adaptive Fusion Network (GAFN) for forecasting the closing prices of Bitcoin, Ethereum, Litecoin, and XRP at 7-, 14-, and 30-day horizons. GAFN combines a BiLSTM encoder, a graph attention network constructed from training-period return correlations, and target-conditioned adaptive fusion. It predicts standardized future log returns as intermediate outputs, which are converted to closing-price forecasts for evaluation. The experiments used 3131 aligned daily observations from Yahoo Finance covering 9 November 2017 to 5 June 2026. The data were divided chronologically into training, validation, and confirmatory test partitions. The final 156 observations, covering 1 January to 5 June 2026, yielded 97 forecast origins after sequence generation. Feature and target standardization and graph construction used the training partition only; model selection and residual scaling used the validation partition. GAFN was compared with Persistence, recurrent, fusion, attention-based, and graph-based models using asset-level NRMSE and an unweighted macro-average across the four assets. Each trainable model was evaluated over five random seeds. Several simpler models achieved lower macro-averaged NRMSE than GAFN at 7 days. At 14 days, GAFN tied with LSTM at the reported precision. At the 30-day horizon, GAFN achieved a macro-averaged test NRMSE of 0.03997 ± 0.00019, compared with 0.03979 for Persistence and 0.04062 for Concatenation Fusion. GAFN had the lowest mean NRMSE among the trainable models at this horizon, but the observed differences were not statistically significant after adjustment for multiple comparisons. The ablation results also showed no consistent improvement from any individual component across all three horizons. GAFN was therefore competitive in this experiment, but the results do not establish superiority beyond the tested assets and period.

The climate change plays an important role in influencing the growth and yield of rice. The objective of this research was to find the vague relationship between the climatic variation and rice production in northeastern part of Thailand. Five variables viz.—rainfall, temperature, GMI, humidity and ENSO show the most effect to rice production, high direct effects to rice production were rainfall and temperature, and indirect effects were temperature and GMI. In the case of drought or dry spell occurred, the suggestions for the farmers were set.

Flood occasionally occurs in Northeast of Thailand especially in Mun river basin and cause of damage for socioeconomic loss and losses to humans and poses a potential danger in urban areas located downstream of large river basins. The research focuses on discharge and comparing of Artificial Neural Network, Long Short-Term Memory, and the Physics-Guided Long Short-Term Memory models to developed prediction models. Evaluation of the models’ performance shows that the Artificial Neural Network model outperforms Long Short-Term Memory and the Physics-Guided Long Short-Term Memory models in predicting daily discharge, achieving lower Root Mean Square Error, Percentage Bias, and higher Nash–Sutcliffe Efficiency. The findings suggest that Artificial Neural Network based models offer good performance in river discharge prediction for flood warring system, with potential for further enhancement through model architecture adjustments.