This paper addresses the limitations of standard chips in processing large-scale datasets by leveraging neuromorphic architectures, particularly spiking neural networks (SNNs), to simulate the pulsed signals of biolog...
详细信息
With the increase of electric vehicles, the demand of electric vehicles for charging piles is increasing, but the number of charging piles is far less than that of electric vehicles, especially in rural areas and unde...
详细信息
The flexibility and mobility of Unmanned Aerial Vehicle (UAV) swarms enable them to integrate with federated learning (FL), an emerging distributed machine learning framework. UAV-FL creates an edge intelligence syste...
详细信息
As medical insurance continues to grow in size, the losses caused by medical insurance fraud cannot be underestimated. Current data mining and predictive techniques have been applied to analyze and explore the health ...
详细信息
A lightweight object detection algorithm based on YOLOv7 is proposed, optimized for deployment on resource-constrained drone platforms. key improvements include optimizing the network structure, adjusting depth and ch...
详细信息
ISBN:
(数字)9798331513054
ISBN:
(纸本)9798331513061
A lightweight object detection algorithm based on YOLOv7 is proposed, optimized for deployment on resource-constrained drone platforms. key improvements include optimizing the network structure, adjusting depth and channel dimensions, and integrating the Bi-directional Feature Pyramid Network (BiFPN) to enhance multi-scale feature fusion for improved detection accuracy and robustness. A 2-Level Haar Wavelet Transform (2-level HWT) replaces traditional strided convolutions, efficiently preserving spatial information for better feature extraction. Additionally, a novel Dual Cross Stage Partial Fusion (DCSPF) module is introduced to improve feature reuse and representation capacity by facilitating information flow across stages. The detection head is further enhanced with the Group Batch Normalization Reweighting Unit (GNRU) and the Adaptive Grouped Convolution Unit (AGCU) to dynamically adjust feature importance. Experimental results on the Vis-Drone2019 dataset show a 2.6% increase in mAP@50 and a 6.1% reduction in GFLOPs, validating the proposed approach's balance between accuracy and computational efficiency, suitable for drones with limited resources.
Preventing network attacks and protecting user privacy are consistently hot research topics in the Internet of Things (IoT) and edge computing fields. Recent advancements in Federated Learning (FL) have shown promise ...
详细信息
ISBN:
(数字)9798331520861
ISBN:
(纸本)9798331520878
Preventing network attacks and protecting user privacy are consistently hot research topics in the Internet of Things (IoT) and edge computing fields. Recent advancements in Federated Learning (FL) have shown promise in addressing these challenges. FL allows various clients to collaboratively build an intrusion detection system (IDS) without sharing their private data. However, most existing methods train a single intrusion detection model for all clients and assume that the training and test data distribution are identical, leading to unsatisfactory detection accuracy and generalization abilities in practice. To overcome these challenges, this paper introduces a prototype-guided personalized FL approach named PG-FedIDS. We propose two novel mechanisms within this method. Firstly, we utilize class prototypes as auxiliary information carriers to generate personalized models for each client, rather than generating a single global model as in previous works. Secondly, we propose a prototype-guided ensemble learning strategy, which can leverage the global knowledge in prototypes to enhance detection accuracy and generalization abilities for each client. We conduct extensive experiments on two benchmark datasets with different evaluation test settings. The results demonstrate that our PG-FedIDS achieves promising detection accuracy and consistently outperforms other FL baselines.
Semi-supervised techniques for medical image segmentation have demonstrated potential, effectively training models using scarce labeled data alongside a wealth of unlabeled data. Therefore, semi-supervised medical ima...
详细信息
Network softwarization is a breakthrough in designing modern networks and providing numerous new network operations and services. This change is exemplified by Software Defined Networks (SDN) and Network Function Virt...
详细信息
Uncertainty in LiDAR measurements, stemming from factors such as range sensing, is crucial for LIO (LiDAR-Inertial Odometry) systems as it affects the accurate weighting in the loss function. While recent LIO systems ...
详细信息
Deep learning has been widely used in source code classification tasks, such as code classification according to their functionalities, code authorship attribution, and vulnerability detection. Unfortunately, the blac...
详细信息
暂无评论