Current methods in mapping the availability of WiFi networks, such as crowdsourcing platforms (e.g. Project BASS and CoverageMap) and dedicated wardriving, face limitations in terms of data recency, volume, and cost-e...
详细信息
The transmission characteristics of electromagnetic wave signals in farmland soil had been found to be quite complex, making it difficult to identify suitable soil environments where wireless underground sensor networ...
详细信息
In response to the shortcomings of particle swarm optimization (PSO) such as insufficient global search, susceptibility to local optima, and slow convergence speed, this paper proposes an improved adaptive PSO (APSO)....
详细信息
ISBN:
(纸本)9798350386783;9798350386776
In response to the shortcomings of particle swarm optimization (PSO) such as insufficient global search, susceptibility to local optima, and slow convergence speed, this paper proposes an improved adaptive PSO (APSO). Firstly, a superior point set is employed for particle population initialization, achieving a more uniform and extensive particle distribution. Secondly, during the particle velocity update phase, an adaptive Levy flight acceleration coefficient is introduced along with adjustments to the social learning factor, emphasizing global search. Finally, in the particle position update phase, an adaptive scaling factor is introduced to intelligently adjust particle position weights, aiding in obtaining superior solutions. The proposed APSO is applied to the wireless sensor network deployment problem, and experimental results demonstrate its outstanding performance in solving optimization problems.
Data heterogeneity is a major challenge in federated learning. This paper introduces FedKSA, a personalized approach that extends FedKD to handle non-iid data. FedKSA integrates an adaptive local aggregation module in...
详细信息
With the continuous advancement of deep learning technology in medical image processing, precise image segmentation techniques have become increasingly important. Currently, TransUNet, which combines CNN and Transform...
详细信息
Encrypted traffic classification is a key technology for network monitoring and management, and its recent research results are mostly based on deep learning. Due to the difficulty in obtaining sufficient labeled data...
详细信息
ISBN:
(数字)9781665480017
ISBN:
(纸本)9781665480017
Encrypted traffic classification is a key technology for network monitoring and management, and its recent research results are mostly based on deep learning. Due to the difficulty in obtaining sufficient labeled data, few-shot traffic classification has received considerable attention. However, most of the existing results have two defects. First, they are mostly based on the assumption of a labeled base dataset for pre-training. Second, they neglect the problem of unknown traffic discovery under open-set conditions. In this paper, aiming at the problem of few-shot open-set encrypted traffic classification, a corresponding framework FSOSTC is constructed under the condition of unsupervised pretraining. Two data augmentation methods for packet feature map are proposed to assist the pre-training through self-supervised learning, which is combined with parameter fine-tuning, unknown discovery and class extension strategies. Experiments on public datasets verify the effectiveness of FSOSTC. For the few-shot open-set malicious traffic classification task, the CSA reaches 95.41 % and the AUROC reaches 0.8664.
Schizophrenia (SCH) and depression (DEP) may be misdiagnosed, mainly because their symptoms have certain similarities and are susceptible to emotional changes. In this study, a deep learning model (CEEGA-Net) based on...
详细信息
In this paper, we propose a novel decentralized learning algorithm over networks, termed as DLAGD, which combines the consensus mechanism with an auto-switchable local optimizer. Specifically, each node updates its lo...
详细信息
The proceedings contain 116 papers. The topics discussed include: LFEMSFF: a basketball posture detection model combining local feature enhancement and multi-camera spatio-temporal feature fusion;video action recognit...
ISBN:
(纸本)9798350366143
The proceedings contain 116 papers. The topics discussed include: LFEMSFF: a basketball posture detection model combining local feature enhancement and multi-camera spatio-temporal feature fusion;video action recognition model based on local and global spatial-temporal feature;design of a spring boot-based safety grading evaluation system for industrial robots;twin-t network oscillator based on Knowm memristors;design and implementation of frequency hopping signal detection system based on FPGA+DSP;detail-enhanced video-based super-resolution networks;research on template discovery technology for multi-source heterogeneous log fusion;and improving high-voltage line obstacle detection with multi-scale feature fusion in YOLO algorithm.
This study proposes a deep learning-based SSVEP classification model, ConvFormer, aiming to enhance the performance of brain-computer interface (BCI) systems. The model combines a global Fourier transform encoder and ...
详细信息
暂无评论