Abstract.With the rapid development of social media, how to accurately gain insights into the public's sentiment tendencies from vast amounts of user text data has become an urgent problem to be solved. To effectively address this challenge, this research proposes an emotion analysis model named ERNIE, which focuses on multi-class sentiment analysis on social media. The construction of this model aims to solve the problem that existing sentiment analysis technologies have difficulty in precisely identifying complex sentiment categories. By manually annotating five-class texts, the ERNIE model retains … Read more →

Abstract.With the rapid development of computer technology, the deep integration of traditional sports and cutting-edge technologies has gradually become a reality, and motion capture technology is increasingly being applied in sports education. This paper designs and implements an intelligent Tai Chi teaching system based on Kinect motion capture devices and the Unity3D platform, aiming to address the lack of interactivity and feedback in traditional teaching methods. The system captures user poses and compares them in real time with standard Tai Chi movements, offering diverse learning and evaluation … Read more →

Abstract.Path planning is widely applied in various fields, including robotic movement and 3D printing. In this paper, we propose a path planning method by combining formal concept analysis and the Q-learning algorithm to study grid map path planning. First, a grid map is represented as a formal context, and based on formal concept analysis theory, the necessary region concepts are defined and introduced into the Q-learning algorithm to obtain the optimal path. Finally, through system experiments, it has been proven that using the necessary region concept can reduce redundant information and the … Read more →

Abstract.Edge computing is a computing paradigm that provides fast and efficient computing services to mobile devices by bringing resources closer to the edge of the network. However, current edge servers lack the computational power to handle the large volume of tasks generated by connected devices. Moreover, some mobile devices may not fully utilize their computational resources. In order to maximize the use of resources, a more sustainable and energy efficient computing paradigm was developed. Minimize the use of Mobile Edge Computing (MEC) servers for applications that run in random environments … Read more →

Abstract.Abstract: The abstract of the study stated that remote sensing images contain abundant details of land objects and terrain, and the denoising process should strive to preserve these critical pieces of information. However, traditional CNN methods performed poorly when dealing with high-resolution, multi-scale, and complex scenes, as they struggled to model the long-range dependencies within images. Methods based on Transformer improved this issue through the self-attention mechanism; however, their high computational cost limited their application in resource-constrained environments. To … Read more →

Abstract.Accurate prediction of battery state of charge (SOC) is vital for extending battery lifespan and ensuring operational safety in electric vehicles. However, traditional approaches exhibit constrained predictive accuracy and robustness under complex environments and variable operating conditions. Therefore, this study proposes the AO-BiGRU-CAM model, integrating Aquila Optimization (AO), a bidirectional Gated Recurrent Units (BiGRU), and a channel attention mechanism (CAM). It refines parameter search while enhancing focus on salient features to improve training efficiency and predictive … Read more →

Abstract.The CMOS high-speed image sensor is a new type of image sensor that has the advantages of high speed, low power consumption, and low noise, and has received widespread attention and research. The CMOS high-speed image sensor has a wide range of applications in medical imaging, industrial inspection, and security monitoring both domestically and internationally. However, this sensor still has some problems in image noise, such as dark current and dark noise. This article proposes strategies such as using new materials and optimizing device structures for optimization. With the continuous … Read more →

Abstract.This study aims to explore the application of AI in English language education in China, especially how it reshapes classroom teaching, online learning, and assessment methods, and to analyze the impact of AI on teachers' roles. First, by analyzing the application of AI in teaching methods and assessment approaches, the study reveals how smart technologies can improve student engagement and learning outcomes, which in turn drive teaching efficiency. Second, the study examines how AI has led to a shift in the role of teachers from traditional knowledge transmitters to learning facilitators and … Read more →

Abstract.In the continuous evolution of intelligent transportation systems, vehicle re-identification technology faces numerous technical challenges, including variations in perspective and equipment resolution. These factors lead to significant intra-class discrepancies in the performance of identical vehicles under varying conditions, as well as inter-class confusion among vehicles with similar appearances. To address these challenges, we integrate vehicle color and type attribute information, enhancing the model’s ability to capture semantic features and improve its discriminative performance. … Read more →

Abstract.Target detection is an important part of radar image interpretation. The use of SAR technology combined with deep learning network models has become an important means of ship target detection. Compared with traditional methods, deep learning has powerful data processing and feature extraction capabilities. Therefore, this paper proposes a multi-scale dynamic fusion (DFS) detection model for target detection based on YOLOv8. The model includes three parts: multi-scale feature extraction and fusion, dynamic alignment, and attention mechanism feature enhancement. Finally, experiments were … Read more →

Abstract.This paper delves into the technological evolution of generative AI and elaborates on its various application forms in the field of image creation, such as image-to-video generation, style transfer, digital human creation, and 3D model generation. On this basis, it further explores effective strategies for guiding AIGC to achieve efficient creation, aiming to provide theoretical and practical references for promoting the deep integration of generative AI and content creation. At the same time, it analyzes the key challenges faced by AIGC in the content creation process, including the lack of … Read more →

Abstract.The material test results show that the chemical composition, size, grain size and hardness test results of the fractured coiled tubing meet the standard requirements, and no abnormal results are found. There are mechanical trauma in the fracture and suspected improper operation on both sides of the fracture position, which causes the tube body damage by the stacking of the clamping blocks, that will cause the deformation of the coiled tubing. The thinning of the wall thickness and the increase of hardness will reduce the strength of the tubing, which is the main reason for the fracture of the … Read more →

Abstract.In recent years, many novel swarm intelligence algorithms have been proposed to apply in various fields. Kernel extreme learning machine (KELM) is combined kernel function with Extreme learning machine (ELM) algorithm. Then, KELM can reach the more robust and better generalization performance than the basic ELM. However, the performance of the method is determined by the crucial parameters in the practical cases. The key parameters of KELM are explored and the selection methods of the KELM-based swarm intelligence optimization are utilized. The FOA and GWO are intelligence computing methods … Read more →