Abstract.This paper focuses on cybercrime characteristics and cybersecurity assessment, with the aim of understanding the global distribution of cybercrime and conducting modeling analysis. In terms of research methodology, data on cybercrime rates, frustration rates, success rates, reporting rates and prosecution rates of many countries and regions such as the U.S., China and the U.K. are collected; entropy weighting method (EWM) is used to calculate social coefficients and analyze the relationship between socio-economic factors and crime rates; and fuzzy comprehensive evaluation model is used to … Read more →

Abstract.This paper constructs a multi-objective optimization model and focuses on its application in optimizing tourism resource allocation based on genetic algorithm. Firstly, the study determines the weights by establishing a multi-objective function system containing multiple indices, combining the hierarchical analysis method (AHP) and entropy weighting method, and solves the optimal solution by genetic algorithm. Among them, the genetic algorithm adopts Latin hypercubic sampling to generate the initial population and balances the global search and local convergence by dynamically adjusting the … Read more →

Abstract.Accurate prediction of the rate of penetration (ROP) is one of the important factors to improve the drilling efficiency of oil fields. At present, most of the established ROP prediction models have low accuracy, because the traditional noise reduction methods are generally used to process the drilling data. At the same time, the influence of wellbore friction and well deviation on WOB is not considered, and only the ground WOB is qualitatively used as the input parameter of the ROP prediction model. In this paper, seven deep directional wells in the central part of Bohai Bay, China are … Read more →

Abstract.This study focuses on research related to the Olympic Games, employing a combination of Analytical Hierarchy Process (AHP), Random Forest Regression, and K-means Clustering techniques to analyze athletes' abilities, medal outcomes of various countries, and their sporting specializations. First, an AHP-based athlete performance evaluation model is constructed, where athletes are scored based on total medal count, gold medal count, number of events participated in, and event diversity. Second, a Random Forest Regression prediction model is developed, which, using historical medal data of … Read more →

Abstract.Brain tumor refers to a cluster of abnormally proliferating cells in the brain, usually formed by uncontrolled division of malignant cancer cells, and belongs to high-risk neurological disorders. At present, the specific pathogenic mechanism of brain tumors has not been fully elucidated in the medical community. But research has shown that early screening can effectively prevent tumor malignancy and significantly improve clinical cure rates. In recent years, breakthroughs in deep learning technology have driven the development of intelligent assisted diagnostic systems, providing medical … Read more →

Abstract.For the fault region identification of transformer heat sink, in order to accurately segment the abnormal region in the heat sink, this paper studies a new abnormal region segmentation method for transformer heat sink. Firstly, Gaussian filtering and 4-direction Laplace operator are used to preprocess the infrared image of the heat sink to get a cleaner image, which provides the basis for the subsequent fault region segmentation; then the FCM segmentation algorithm is used to pre-segment the image of the heat sink to remove the interference of the background, and to get the target region of … Read more →

Abstract.This paper presents a highly efficient and accurate model for identifying road conditions, specifically distinguishing between normal roads and potholes in images. Given the challenges posed by potholes, such as their prevalence in shaded areas, cluttered backgrounds, difficulty in annotation, and diverse shapes, we initiate the process by normalizing the dataset. We select the VanillaNet neural network as our foundational training architecture due to its elegant and simplistic design, which maintains exceptional performance in computer vision tasks. VanillaNet commences with several layers … Read more →

Abstract.In recent years, the rapid development of Large language models (LLMs) provides a new idea for supply chain risk assessment. In this paper, a global supply chain risk assessment method based on LLMs is proposed. By using named entity identification, relationship extraction, text classification and sentiment analysis, a knowledge map of supply chain risk is constructed, and a risk assessment model is constructed by combining machine learning or deep learning algorithm to achieve accurate assessment and early warning of global supply chain risks. Taking the "Ever Given" Suez Canal stranded in … Read more →

Abstract.With the rapid development of the Internet of Things, big data, artificial intelligence and other technologies, the Internet of vehicles industry is booming. The massive big data generated by the Internet of vehicles has brought new opportunities and changes to the intelligent marketing of the automobile industry. This paper deeply studies the intelligent marketing method based on the big data of the Internet of vehicles, elaborates the characteristics and sources of the big data of the Internet of vehicles, and constructs the accurate user portrait through in-depth analysis using the Apriori … Read more →

Abstract.With the rapid development of information technology, the Internet of vehicles has produced massive data, which has brought new opportunities for the intelligent marketing of the automobile industry. However, there is ambiguity and uncertainty in these data, which brings challenges to effective use. This paper introduces the theory of fuzzy mathematics into the processing of car networking data, aiming to construct an innovative intelligent marketing program. Through the collection of Telematics data, analysis and processing based on fuzzy mathematics, it can realize accurate market … Read more →

Abstract.This study presents an exploration of the implementation of intelligent coupling SNCR/SCR denitrification technology for thermal power station boilers, addressing the global imperatives of carbon peaking and carbon neutrality. By leveraging artificial intelligence (AI) techniques and advanced control strategies, the project has developed an innovative technical solution that integrates multi-objective optimization algorithms, data-driven predictive models, and fuzzy control algorithms. This solution not only tackles the complexities inherent in the denitrification process but also optimizes … Read more →

Abstract.Intrusion detection in construction scenes can effectively reduce the occurrence of hazardous incidents. Current detection methods, while effective, are often too complex. This paper proposes a lightweight monitoring model based on convolutional neural networks (CNNs). First, the model is trained using a dataset to achieve high accuracy. Then, the model is lightweighted using CNNs. Simulation results show that the model can maintain accuracy while occupying a smaller volume. Read more →

Abstract.With the rapid development of information technology, network security has increasingly become a key focus across various industries. In particular, in multi-domain network environments, network security not only involves traditional firewalls and intrusion detection systems, but also faces challenges in data privacy protection. Especially when data is shared and collaborated across multiple domains, the risk of privacy leakage increases. Therefore, how to enhance network security while ensuring data privacy protection has become a pressing issue to address. This paper proposes a … Read more →

Abstract.This comparative study evaluates real-time production platforms across three core metrics: visual quality, team collaboration efficiency, and hardware compatibility. Tested through nine professional implementations—including major film productions using LED wall technology—the research highlights distinct strengths among solutions. Epic's Unreal Engine 5.2 delivers superior 4K output (43 fps) when handling intricate 3D models via its Nanite architecture, surpassing Unity's 28 fps in comparable scenarios. Conversely, Unity accelerates mixed reality development cycles, enabling 70% faster … Read more →