International Journal of Advanced Science

Application of Data-Driven Prediction and Strategic Optimization in Olympic Medal Distribution

Zhaoyu Zhu, Jiajin Shen, Minghao Yu, Chengtian Liang (Author) — Fri, 28 Feb 2025 00:00:00 +0000

The Olympic medal list is an important indicator to assess the competitive strength of countries, and the prediction and analysis of the distribution of the number of medals provide a scientific basis for countries to formulate sports development strategies. This paper takes the 2024 Paris Olympic Games and the previous Olympic Games as the basic data, combines the historical medal data, the distribution of each Olympic Games and the special characteristics of the host country, constructs a number of mathematical models, explores the law of medal distribution, and proposes a strategy to improve the number of medals.The model in this paper is comprehensive, flexible and practical, which provides a new way of thinking for the analysis of medal distribution in the Olympic Games, and also provides data support for the sports development strategy of each country.

Power Transformer Fault Diagnosis Based on Multi Class SVM and IPSO

Zihan Bai, Ziyu Zhao, Mingshen Xu (Author) — Fri, 28 Feb 2025 00:00:00 +0000

This article focuses on classifying a variety of faults in power transformers with high precision, using an Improved Particle Swarm Optimization-Support Vector Machine (IPSO-SVM) system designed for fault diagnosis. The process begins with the identification of five distinct gases dissolved in oil, serving as diagnostic features. Minimal output encoding is then used to construct multiple binary support vector machine (SVM), facilitating a multi-class classification of transformer faults. While other studies often combine traditional Particle Swarm Optimization (PSO) algorithms with SVMs, our approach employs an enhanced PSO algorithm. This improved algorithm allows for the optimization of inertia and learning factors, values of which adapt based on iteration counts. The PSO is then leveraged on the optimization of the penalty factor and the radial basis function of SVM, thereby improving its classification performance. Simulation results indicate that our IPSO-SVM methodology achieves 90% and 92% accuracy in training and testing sets, respectively. This method significantly enhances the accurateness of
transformer malfunction diagnosis, exhibiting superior diagnostic precision compared to traditional power transformer malfunction diagnosis methods.

The Role of Systematic Taxonomy in Protecting Endangered Animals

Yi HU (Author) — Fri, 28 Feb 2025 00:00:00 +0000

With the escalating biodiversity crisis, systematic taxonomy is essential to the protection of endangered species, as it supports accurate species identification, guides conservation priorities, and informs recovery strategies. This paper highlights the critical role of taxonomy in endangered species conservation and addresses challenges such as taxonomic gaps, technical limitations, insufficient data sharing, and the disconnect between research and conservation efforts. Suggested solutions include integrating taxonomy research into decision-making, improving technical capabilities, fostering international collaboration, enhancing public engagement, and diversifying funding sources. Through case studies of China’s endemic species (giant panda, crested ibis, Chinese giant salamander) and successful global initiatives (EDGE project), the paper illustrates practical strategies for advancing conservation. The discussion also explores future opportunities, including artificial intelligence and environmental DNA technologies, to strengthen taxonomy’s impact on conservation. By combining theoretical insights, practical approaches, and graphical data presentation, this paper provides a foundation for innovative biodiversity protection methods.

Multi-Feature Power Load Forecasting Model Based on Hyperparameter Optimization and Ensemble Learning

Xu Mingshen, Zhang Teng, Xiaotian Li (Author) — Fri, 28 Feb 2025 00:00:00 +0000

Power load forecasting is crucial for the economic dispatch and safe operation of power grids, yet the fluctuating and unstable nature of power load data often limits the accuracy of traditional single-model approaches. This paper presents an integrated learning model designed to improve forecast-ing accuracy and stability by addressing these challenges. The model in-corporates improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN), a vector-weighted average optimization algorithm (INFO), convolutional neural networks (CNN), bidirectional long short-term memory (BiLSTM), and random forest (RF). By thoroughly analyzing and preprocessing the data, the approach effectively handles its non-linear, non-stationary characteristics. The combination of CNN and BiLSTM enhances the model’s ability to capture temporal and spatial features, while RF strengthens generalization. The INFO algorithm dynamically adjusts weights and parameters during training, resulting in significantly improved predictive performance. Experimental results on data from the Australian electricity market confirm that the proposed model outperforms existing approaches in key performance metrics, showcasing its effectiveness and potential for practical applications in power load forecasting.