This study applies machine learning methods such as Decision Tree (CART) and Random Forest to classify drought intensity based on meteorological data. The goal of the study was to evaluate the effectiveness of these methods for drought classification and their use in water resource management and agriculture. The methodology involved using two machine learning models that analyzed temperature and humidity indicators, as well as wind speed indicators. The models were trained and tested on real meteorological data to assess their accuracy and identify key factors affecting predictions. Results showed that the Random Forest model achieved the highest accuracy of 94.4% when analyzing temperature and humidity indicators, while the Decision Tree (CART) achieved an accuracy of 93.2%. When analyzing wind speed indicators, the models’ accuracies were 91.3% and 93.0%, respectively. Feature importance revealed that atmospheric pressure, temperature at 2 m, and wind speed are key factors influencing drought intensity. One of the study’s limitations was the insufficient amount of data for high drought levels (classes 4 and 5), indicating the need for further data collection. The innovation of this study lies in the integration of various meteorological parameters to build drought classification models, achieving high prediction accuracy. Unlike previous studies, our approach demonstrates that using a wide range of meteorological data can significantly improve drought classification accuracy. Significant findings include the necessity to expand the dataset and integrate additional climatic parameters to improve models and enhance their reliability.

This research presents a novel approach utilizing a self-enhanced chimp optimization algorithm (COA) for feature selection in crowdfunding success prediction models, which offers significant improvements over existing methods. By focusing on reducing feature redundancy and improving prediction accuracy, this study introduces an innovative technique that enhances the efficiency of machine learning models used in crowdfunding. The results from this study could have a meaningful impact on how crowdfunding campaigns are designed and evaluated, offering new strategies for creators and investors to increase the likelihood of campaign success in a rapidly evolving digital funding landscape.

This paper investigates the evolving clustering and historical progression of “Asian regionalisms” concerning their involvement in multilateral treaties deposited in the United Nations system. We employ criteria such as geographic proximity, historical connections, cultural affinities, and economic interdependencies to identify twenty-eight candidate countries from East Asia, Southeast Asia, South Asia, and Central Asia for this empirical testing. Using a social network analysis approach, we model the network of these twenty-eight Asian state actors alongside 600 major treaties from the United Nations system, identifying clusters among Asian states by assessing similarities in their treaty participation behavior. Specifically, we observe dynamic changes in these clusters across three key historical eras: Post-war reconstruction and transformation (1945–1968), Cold War tensions and global transformations (1969–1989), and post-Cold War era and globalization (1990–present). Employing the Louvain cluster detection algorithm, the results reveal the evolution in cluster numbers and changes in membership status throughout the world timeline. The results also identify the current situation of six distinct Asian clusters based on states’ inclinations to engage or abstain from multilateral treaties across six policy domains. These findings provide a foundation for further research on the trajectories of Asian regionalisms amidst evolving global dynamics and offer insights into potential alliances, cooperation, or conflicts within the region.

The proposed research work encompasses implications for infrastructure particularly the cybersecurity as an essential in soft infrastructure, and policy making particularly on secure access management of infrastructure governance. In this study, we introduce a novel parameter focusing on the timestamp duration of password entry, enhancing the algorithm titled EPSBalgorithmv01 with seven parameters. The proposed parameter incorporates an analysis of the historical time spent by users entering their passwords, employing ARIMA for processing. To assess the efficacy of the updated algorithm, we developed a simulator and employed a multi-experimental approach. The evaluation utilized a test dataset comprising 617 authentic records from 111 individuals within a selected company spanning from 2017 to 2022. Our findings reveal significant advancements in EPSBalgorithmv01 compared to its predecessor namely EPSBalgorithmv00. While EPSBalgorithmv00 struggled with a recognition rate of 28.00% and a precision of 71.171, EPSBalgorithmv01 exhibited a recognition rate of 17% with a precision of 82.882%. Despite a decrease in recognition rate, EPSBalgorithmv01 demonstrates a notable improvement of approximately 14% over EPSBalgorithmv00.