Abstract.This study proposes a novel interactive visualization system that addresses the growing complexity of big data in educational contexts by integrating multimodal knowledge graphs (KGs) with adaptive user interfaces. The system unifies structured and unstructured data from diverse sources, including course ontologies, lecture transcripts, and code repositories, into a cohesive KG framework. Entity extraction, summarization, and cross-modal embedding techniques are employed to construct the KG, which is then visualized through a combination of 2D and 3D rendering engines. The visualization … Read more →

Abstract.As an emerging product, electronic products have a large market demand, but related enterprises are also faced with the problem of high prices of raw materials and easy loss in the production process. This paper establishes a multi-index evaluation system model for quantitative analysis, which aims to help enterprises improve production steps, formulate reasonable product production process detection and exchange strategies, and improve enterprise revenue. The core idea of this paper is to establish a multi-index evaluation system by selecting appropriate evaluation indicators, calculate the … Read more →

Abstract.With the booming development of digital game market, Steam platform, as the world's largest digital game distribution and sales platform, covers a huge amount and multi-dimensional game data. In this paper, based on Python crawler technology, we collect and organize the information of thousands of games on Steam platform, such as price, ratings, reviews, genres and tags, as well as release time. By visualizing and analyzing the game price distribution, the correlation of ratings and reviews, the characteristics of genres and popular tags, and the trend of release time and other dimensions, we … Read more →

Abstract.Lung cancer is one of the leading causes of morbidity and mortality worldwide, and early detection is crucial for improving patient survival rates. Medical imaging, particularly chest CT scans, plays a vital role in early lung cancer screening and pulmonary nodule detection. However, the detection of pulmonary nodules is challenging due to the variability in size, shape, density, and location of nodules, as well as their complex background, which often includes normal or benign structures such as blood vessels and bronchial walls. To address these challenges, this paper presents a novel … Read more →

Abstract.Large-scale dynamic scene reconstruction methods based on spatiotemporal field models demonstrate significant potential in autonomous driving applications. However, existing neural radiance field (NeRF) and 3D Gaussian splatting (3DGS) techniques remain constrained by their dynamic element modeling capabilities and computational efficiency, failing to effectively address complex reconstruction tasks involving intertwined static and dynamic regions in driving scenarios. To address these challenges, this study proposes a novel framework integrating spatiotemporal attention mechanisms with sparse … Read more →

Abstract.Facing the high-dimensionality, heterogeneity and temporal complexity of anomaly detection in big data environment, an intelligent detection model integrating graph neural network, self-encoder and attention mechanism is designed. The model structure is equipped with multimodal feature encoding capability and online adaptive mechanism, which improves the recognition performance of rare anomalies and structural mutations. Experiments based on the KDDCup99 and NSL-KDD datasets demonstrate that the model outperforms multiple comparative methods in terms of accuracy and robustness, and shows good … Read more →

Abstract.In this paper, a local path planning algorithm based on improved artificial potential field (APF) method and model predictive control (MPC) is proposed for the safe driving of autonomous vehicles under complex working conditions. An adjustment factor is introduced to establish a novel obstacle repulsive potential field and an enhanced gravitational potential field, which are then integrated with the MPC algorithm. Secondly, introduce the potential field at the road boundary to ensure that vehicles travel within the safe area of the road. Finally, simulation results demonstrate the … Read more →

Abstract.With the rapid development of 3D Geographic Information Systems (3D GIS) and smart city construction, oblique photogrammetry has been widely adopted for 3D reality modeling due to its efficiency and high precision. However, the triangular irregular network (TIN) models generated from oblique imagery typically form continuous surface models, making direct individualization and independent management challenging. This paper systematically examines the strengths and limitations of existing individualization methods and proposes a structured workflow for model individualization. By employing … Read more →

Abstract.Aiming at the cooperative path planning problem of AUV cluster in underwater complex environment, this paper proposes a deep distributed optimization algorithm (DNPFS-OA) based on the intelligent behavior of Tanzhou Pseudosciaena crocea. This algorithm is different from the traditional leader-follower architecture. By establishing the deep coupling between the bio-pressure sensing model and the hydrodynamic equation, and combining with the communication-control collaborative optimization framework, the autonomous collaboration of AUV clusters in the three-dimensional strong disturbance … Read more →

Abstract.With the rapid growth of international trade and shipping, ships are the main mode of transportation connecting various parts of the world. Therefore, the reliability and effectiveness of communication systems on ships are very important. As an important means of modern communication, computer networks have been increasingly applied in ship communication. This article introduces the current situation, advantages, and existing problems of the application of computer networks in ship communication, and proposes corresponding solutions. Introduced the basic concepts of network and communication, … Read more →

Abstract.To improve the insufficient identification rate of remote garbage targets by water surface cleaning equipment, a model based on RT-DETR for remote garbage target detection called FRT-DETR was developed. First, CSPCAA-ADown was proposed as a modified backbone network, which better captures feature information of garbage targets beyond 30 meters at different scales while reducing computational burden, thus minimizing the impact of insufficient feature information caused by distance. Second, a CCGAF module was introduced to dynamically adjust the importance of features from different layers. … Read more →