This study focuses on optimizing multimodal robot route planning in intelligent logistics management by integrating Transformer models, Graph Neural Networks (GNNs), and Generative Adversarial Networks (GANs). Using a graph structure representing map information, cargo distribution, and robot states, spatial and resource constraints are considered to optimize paths. Extensive simulations based on real logistics datasets demonstrate significant improvements over traditional methods, with an average 15\% reduction in path length, 20% improvement in time efficiency, and 10% reduction in energy consumption. These results underscore the effectiveness and superiority of the proposed multimodal pat... More >

This study introduces a method for efficiently detecting objects within 3D point clouds using convolutional neural networks (CNNs). Our approach adopts a unique feature-centric voting mechanism to construct convolutional layers that capitalize on the typical sparsity observed in input data. We explore the trade-off between accuracy and speed across diverse network architectures and advocate for integrating an L1 penalty on filter activations to augment sparsity within intermediate layers. This research pioneers the proposal of sparse convolutional layers combined with L1 regularization to effectively handle large-scale 3D data processing. Our method’s efficacy is demonstrated on the MVTec... More >

This paper reviews advancements in assistive technology for deaf and hard of hearing individuals, highlighting the Internet of Things' (IoTs) pivotal role in enhancing their daily lives. Despite progress in sign language technologies, communication barriers persist. To address these gaps, we developed a video-based American Sign Language (ASL) identification system. Our approach utilizes MediaPipe for hand tracking, OpenCV for image normalization, and Gesture Control Convolutional Neural Network (CNN) for gesture localization. Implemented in Python, the system records video streams, filters hand regions, and recognizes ASL letter gestures with high accuracy. Leveraging computer vision and ma... More >

With the rapid development of the new energy vehicle (NEV) industry, supply chain finance (SCF) has become one of the key factors promoting the prosperity of this industry. Based on in total 884 samples, this study investigates the impact of SCF on the integrated business performance of NEV enterprises. Through empirical analysis, it is confirmed that SCF significantly and positively affects the integrated business performance. In addition, the results of the mediation effect test indicate that by alleviating financing constraints of small and medium-sized enterprises, SCF enables the improvement of firms' overall business performance. These findings provide new insights to NEV enterprises'... More >

Monitoring the health condition of wind turbines is crucial to ensure the safety and efficient operation of wind farms. Wireless sensor networks (WSNs) provide an economical and effective solution for such monitoring. However, when sensors detect faults in wind turbines, traditional WSN routing protocols often lead to redundant data transmission, resulting in energy waste. To address this issue, an event-triggered energy-efficient wireless routing protocol (EEWRP) is proposed specifically in this paper for wind turbine fault monitoring. The protocol improves the distributed energy-efficient clustering algorithm (DEEC) by first identifying the type of event and then using an adaptive dynamic... More >

With the rapid development of artificial intelligence, extracting latent information from medical data has become increasingly critical. Cardiovascular disease is now a major threat to human health, being one of the leading causes of mortality. Therefore, developing effective prediction methods for cardiovascular diseases is urgently needed. Current medical approaches primarily focus on disease detection rather than prediction, which limits early intervention. By leveraging computational methods, it is possible to predict cardiovascular disease in advance, enabling timely treatment and potentially reducing the disease’s impact. This study employs machine learning techniques, including Supp... More >

This paper aims to design a rehabilitation medical product system tailored to the needs of future intelligent elderly care environments, with the goal of enhancing the efficiency of rehabilitation training for older adults. Through an in-depth analysis of the anticipated medical needs in elderly care apartments, we propose a comprehensive design concept for a rehabilitation medical product system. The design is approached from three key perspectives: products, services, and systems, ensuring that it aligns with the healthcare requirements specific to elderly care settings. The proposed solutions focus on optimizing rehabilitation training by integrating intelligent technologies and user-cent... More >

Sea ice is a crucial component of the cryosphere, and extensive research has been conducted on sea ice using microwave remote sensing due to its robustness against cloud cover and illumination variations. This paper focuses on classifying Arctic sea ice based on microwave remote sensing data. Leveraging the high stability of microwave radiometers, we analyze the characteristics of different sea ice types across the Arctic region in January 2017 using high-resolution AMSR-E/AMSR2 data at the 89 GHz frequency band. Data at this frequency are less susceptible to cloud and water vapor interference, while lower frequency bands have traditionally been more commonly used in similar studies. However... More >

To enhance the LOMAX algorithm for sea ice concentration analysis in the polar regions, SSM/I 91.6GHz data was utilized, addressing the underuse of higher frequency data. The refinement process involved redefining PCT values for one-year and multi-year ice regions through both interpolation and least squares methods. Moreover, band operations were conducted to facilitate Arctic multi-year ice concentration retrieval. Comparative analyses with the NT algorithm indicated that the Arctic sea ice extents determined by both algorithms were similar, affirming the credibility of the modified LOMAX algorithm. When examining the results for March and September, the updated LOMAX algorithm demonstrate... More >

The volume and complexity of data in various fields, particularly in biology, are increasing exponentially, posing a challenge to existing analytical methods, which often struggle with high-dimensional data such as single-cell Hi-C data. To address this issue, we employ unsupervised methods, specifically Principal Component Analysis (PCA) and t-Distributed Stochastic Neighbor Embedding (t-SNE), to reduce data dimensions for visualization. Furthermore, we assess the information retention of the decomposed components using a Linear Discriminant Analysis (LDA) classifier model. Our findings indicate that these dimensionality reduction techniques effectively capture and present information not r... More >

In light of the rapid advancements in big data and artificial intelligence technologies, the trend of uploading local files to cloud servers to mitigate local storage limitations is growing. However, the surge of duplicate files, especially images and videos, results in significant network bandwidth wastage and complicates server management. To tackle these issues, we have developed a multi-parameter video quality assessment model utilizing a 3D convolutional neural network within a video deduplication framework. Our method, inspired by the analytic hierarchy process, thoroughly evaluates the effects of packet loss rate, codec, frame rate, bit rate, and resolution on video quality. The model... More >

This study investigates the application of Internet of Things (IoT) technology in agriculture, focusing on the cultivation of patchouli, a medicinal plant known for its therapeutic properties. The research highlights the specific growth requirements and medicinal benefits of patchouli, and proposes a monitoring system based on ZigBee technology. The system's hardware design incorporates cc2530 and esp8266 chips for wireless data transmission, while communication between the OneNET cloud server and the MySQL database is managed through MQTT, TCP/IP, and HTTP protocols. This integration showcases the potential of IoT to significantly enhance agricultural efficiency by providing real-time data... More >

This system, combining with recruitment service characteristics of private college, adopts B/S pattern design for private colleges enrollment management system. The system includes PC terminal and mobile terminal access, realizing the display of SVG-based map, fully considering the convenience and friendly interactive interface of the system mobile terminal access, providing online consultation, registration, enrollment, payment, data statistical analysis and other functions, improving the efficiency and accuracy of enrollment data processing, so as to realize the information management of school enrollment. After the test, it meets the needs of enrollment management. More >

As more and more traditional application systems begin to integrate 3D technology, building a 3D library application system with the advantages of 3D technology is conducive to improving the user's borrowing experience, improving the efficiency of users' querying books and reserving seats, and combining monitoring equipment can effectively improve the accuracy of seat occupancy monitoring, and through the statistics and analysis of reservation data, borrowing data and other data, it can provide decision support for library managers, thereby improving the quality of library services. This paper takes the library of Henan University of Technology as an example, based on the SuperMap iClient3D... More >

Because of the special geographical location, dry weather, high temperature and dense vegetation in Liangshan, Sichuan, it is easy to cause forest fires, so it is of great significance to use remote sensing data to evaluate forest fires in Liangshan, Sichuan. In this paper, the forest fire in Muli County, Liangshan, Sichuan Province on March 28th, 2020 was evaluated by using Landsat-8 remote sensing data which can be obtained free of charge. The NDVI of the pre-processed remote sensing images before and after the fire was calculated respectively. After the difference was made, the threshold of the classification of fire and non-fire areas was determined according to the maximum inter-class d... More >

The identification of immature apples is a key technical link to realize automatic real-time monitoring of orchards, expert decision-making, and realization of orchard output prediction. In the orchard scene, the reflection caused by light and the color of immature apples are highly similar to the leaves, especially the obscuration and overlap of fruits by leaves and branches, which brings great challenges to the detection of immature apples. This paper proposes an improved YOLOv3 detection method for immature apples in the orchard scene. Use CSPDarknet53 as the backbone network of the model, introduce the CIOU target frame regression mechanism, and combine with the Mosaic algorithm to impro... More >

In order to optimize the deployment of wireless sensor network nodes, and avoid network energy consumption increase due to node redundancy and uneven coverage, the multi-objective mathematical optimization problem of area coverage is transformed into a function problem. Aiming at network coverage rate, node dormancy rate and network coverage uniformity, the idea of genetic algorithm mutation is introduced based on the discrete binary particle swarm optimization and the global optimal speed is mutated to avoid the algorithm falling into the local optimal solution. In order to further improve the optimization ability of the algorithm, the adaptive learning factor and inertia weight are introdu... More >