检索结果-内蒙古大学图书馆

Decentralized Voting-Based Federated Learning Framework for Lightweight Node Selection in Edge Collaborative IoT

IEEE Internet of Things Journal 2025年第12期12卷 20272-20287页

作者： Chen, Yishan Wang, Zhiqiang Min, Yuan Liu, Zhiquan Jiangxi University of Science and Technology Jiangxi Provincial Key Laboratory of Multidimensional Intelligent Perception and Control Ganzhou341000 China Jinan University College of Cyber Security Guangzhou510632 China

Federated Learning (FL) is an emerging distributed machine learning paradigm that has privacy-preserving properties, but still poses privacy leakage risks in traditional centralized FL (CFL) caused by the frequent transmission of model parameters during training. Due to the resource differences among nodes, the training process is constrained by the slowest node, while frequent data transmissions result in significant communication overhead, leading to the reduced overall efficiency. What's more, resource-rich nodes cannot fully utilize their potentials, and large models cannot be deployed on resource-constrained end devices. Therefore, selecting participating nodes and their local training strategies efficiently is a key issue in FL. To address the aforementioned issues, this paper proposes an edge-cooperative decentralized lightweight FL framework (Dec-LWFL), which introduces a multi-agent reinforcement learning (MARL) method, and designs a scoring voting mechanism for selecting participating FL nodes, determining their local training strategies, and allocating the model aggregation tasks. During agent interactions, Gaussian noise is added to the state information to safeguard the privacy of edge nodes and users, and Rényi differential privacy (RDP) is utilized to quantify the effectiveness of the privacy protection mechanism. To adapt to the resource-constrained IoT environment, Huffman coding is employed during FL training phase to compress the transmitted models and reduce the communication overhead;then, knowledge distillation is selected during the deployment phase to achieve the goal of lightweight deployment. Experimental results demonstrate that Dec-LWFL can effectively balance the privacy and performance. The framework can significantly optimize the training latency and energy consumption, while satisfying the requirements for lightweight deployment. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Non-Line-of-Sight Identification and Localization Using UWB Based on Deep Learning 24

Non-Line-of-Sight Identification and Localization Using UWB ...

引用

4th Asia-Pacific Artificial Intelligence and Big Data Forum, AIBDF 2024

作者： Huang, Kangni Yu, Meng Song, Penghui Long, Keliu Jiangxi Provincial Key Laboratory of Multidimensional Intelligent Perception and Control Jiangxi University of Science and Technology Jiangxi Ganzhou China

ISBN: (纸本)9798400710865

Due to its characteristics of high precision, high reliability, and low power consumption, UWB technology is widely used in indoor positioning. However, the performance of UWB positioning systems can be affected by issues such as multipath effects and signal attenuation in both non-line-of-sight (NLOS) and line-of-sight (LOS) environments. This paper proposes an algorithm for NLOS and LOS state identification and localization using UWB, based on deep learning. First, a recognition model suitable for NLOS and LOS environments is established by analyzing UWB channel models and signal characteristics. Then, a method for identifying NLOS and LOS states is designed using deep learning techniques, with classification accuracy metrics introduced to evaluate model performance. To validate the proposed positioning algorithm, a UWB node positioning system is designed and tested in real environments. Experiments were conducted in two different environments-a basement and a lounge-to verify the positioning performance. Subsequently, the deep learning-based NLOS error identification and mitigation algorithm proposed in this paper was tested. The experiments compared the effects of different deep learning algorithms on NLOS error identification and mitigation. Results show that the positioning algorithm using the Convolutional Neural Network Long Short-Term Memory (CNN-LSTM) model performs best in identifying and mitigating NLOS errors, achieving the highest positioning accuracy. The study results demonstrate that the proposed algorithm not only has theoretical value but also shows great potential for practical applications. © 2024 Copyright held by the owner/author(s).

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Kolmogorov-Arnold Networks for Enhancing Gravitational Wave Glitch Classification Performance 24

Kolmogorov-Arnold Networks for Enhancing Gravitational Wave ...

引用

4th Asia-Pacific Artificial Intelligence and Big Data Forum, AIBDF 2024

作者： Cai, Yiting Ma, Cunliang Xiao, Wanhai Jiangxi Provincial Key Laboratory of Multidimensional Intelligent Perception and Control Jiangxi University of Science and Technology Jiangxi Ganzhou China

ISBN: (纸本)9798400710865

Detecting gravitational waves is essential for the success of the LIGO and Virgo experiments, requiring thorough comprehension of how these instruments are affected by environmental and instrumental noise. In particular, the data recorded by the LIGO/Virgo detectors frequently include transient noise events, referred to as"glitches". These glitches can interfere with real gravitational wave signals and, in some cases, their characteristics may resemble those of actual gravitational wave signals, leading to misidentification. Identifying and differentiating these glitches plays a vital role in improving the precision and dependability of gravitational wave observations. LIGO’s initial observation of gravitational waves marked a transformative achievement in expanding our comprehension of the universe. However, because of the detectors’ exceptional sensitivity, they also pick up many other noise sources that can interfere with the observation of gravitational waves. To address this challenge, numerous classification methods have been proposed;however, as model complexity increases, so does the risk of overfitting, requiring more computational resources and resulting in significantly longer training and inference times. The Kolmogorov-Arnold Network (KAN), with its unique high-dimensional mapping and powerful feature extraction capabilities, demonstrates greater robustness and accuracy than traditional methods, thus improving classification performance. In this paper, we explore multi-view classification of gravitational wave glitches using KAN networks, where the linear and convolutional layers of conventional neural networks are replaced with KAN-based structures, and residual connections are incorporated within the KAN modules. © 2024 Copyright held by the owner/author(s).

关键词： Gravitational effects

来源：评论

学校读者我要写书评

暂无评论

Edge Gradient Exploration Attack based on Graph Neural Networks 24

Edge Gradient Exploration Attack based on Graph Neural Netwo...

引用

4th Asia-Pacific Artificial Intelligence and Big Data Forum, AIBDF 2024

作者： Yang, Shuxin Ge, Ran Jiangxi Province Key Laboratory of Multidimensional Intelligent Perception and Control Jiangxi University of Science and Technology Jiangxi Ganzhou China

ISBN: (纸本)9798400710865

Graph Neural Networks (GNNs) have achieved remarkable success in various graph-structured tasks due to their powerful graph representation learning capabilities. By aggregating and transforming information from the neighboring nodes, GNNs explore the structure of the graph and the features of the nodes. However, recent theoretical and empirical analyses have revealed that GNNs are particularly vulnerable to adversarial attacks. Among these, gradient-based attacks have been widely studied for their inherent efficiency and effectiveness. Nevertheless, due to the discrete nature of graph data, gradient-based attacks often result in suboptimal outcomes. Furthermore, the portability of some previously proposed attack algorithms requires further improvement. To address these two issues, we propose a novel Multi-Network Exploratory Attack (MNEA) aimed at enhancing gradient-based graph perturbations and improving their transferability. MNEA consists of two phases: the generation phase and the reconstruction phase. In the generation phase, multiple networks are utilized to generate a variety of candidate edges, preventing the generated perturbed edges from being too targeted toward a single model, which could lead to decreased transferability. The reconstruction phase introduces multiple edges for recombination, with the objective of avoiding misleading information potentially provided by the maximum gradient. Experimental results that are conducted on three publicly available benchmark datasets demonstrate that MNEA significantly outperforms baseline methods in terms of performance. © 2024 Copyright held by the owner/author(s).

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Temporal Dynamic Frequency Autoencoder: Enhancing the Performance of Unsupervised Dimensionality Reduction for Gravitational Wave Glitch Clustering 24

Temporal Dynamic Frequency Autoencoder: Enhancing the Perfor...

引用

4th Asia-Pacific Artificial Intelligence and Big Data Forum, AIBDF 2024

作者： Xiao, Wanhai Ma, Cunliang Cai, Yiting Jiangxi Provincial Key Laboratory of Multidimensional Intelligent Perception and Control Jiangxi University of Science and Technology Jiangxi Ganzhou China

ISBN: (纸本)9798400710865

With the ongoing advancements in gravitational wave detection technology, the results are becoming increasingly precise. However, it is precisely this high precision that has led to the detection of noise signals that should not have been recorded, which are then mixed with real gravitational wave signals. As a result, efficient and accurate algorithms are needed to distinguish between these signals and noise. Past research has mostly relied on fully supervised or semi-supervised learning methods to classify and cluster these glitches, thereby improving the accuracy and reliability of glitch detection. However, neural networks typically require a large amount of training data to perform well, and in future work, it is impractical to manually label a vast number of experimental samples. Additionally, as time progresses, new unlabeled glitches may emerge. To address this issue, we adopted a Temporal Dynamic Frequency Autoencoder (TDFAE) based on a Kolmogorov-Arnold Network (KAN) that integrates Vision Transformers (ViT) and a four-branch encoder. To enhance feature extraction accuracy, we utilized a multi-branch fusion approach with the CLS (Class) token. This innovative unsupervised learning technique focuses on dimensionality reduction and clustering of gravitational wave glitches. Our approach, tested on the GravitySpy O3 dataset, outperforms current semi-supervised learning methods in clustering tasks. Additionally, our work on unsupervised clustering methods for traditional LIGO datasets offers significant potential, representing a key advancement in gravitational wave research. © 2024 Copyright held by the owner/author(s).

关键词： Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

Monocular Depth Estimation Algorithm Guided by Global Structure and Local Details 24

Monocular Depth Estimation Algorithm Guided by Global Struct...

引用

4th Asia-Pacific Artificial Intelligence and Big Data Forum, AIBDF 2024

作者： Wang, Wenhao Ma, Cunliang Jiangxi Provincial Key Laboratory of Multidimensional Intelligent Perception and Control Jiangxi University of Science and Technology Jiangxi Ganzhou China

ISBN: (纸本)9798400710865

In the current encoder-decoder architecture for monocular depth estimation, there are issues with unclear structural details of depth scene objects during the decoder’s upsampling process, as well as insufficient capability to extract contextual information from the scene. To address these problems, this paper proposes a monocular depth estimation algorithm guided by global structure and local details. The algorithm utilizes a pre-trained Swin-Transformer as the encoder to downsample the monocular image and extract multi-scale features from different levels of encoder representations. During the decoder phase, high-level features are fused with low-level features to create feature guidance maps enriched with structural semantic and positional information. These maps are then refined layer by layer with local detail feature maps output from a context aggregation module. This process ensures the model retains more global and local information during the multi-scale feature fusion. Finally, global structure guidance maps and local detail guidance maps from all layers are combined to predict the final depth map. Extensive experimental results on both indoor and outdoor datasets demonstrate the superiority of the proposed model. Compared to the AdaBins algorithm, our approach reduces RMSE by 10.46% and 7.41% on the KITTI and NYU Depth v2 datasets, respectively. © 2024 Copyright held by the owner/author(s).

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

A binary logical operation algorithm for solving the 0-1 programming problem 24

A binary logical operation algorithm for solving the 0-1 pro...

引用

4th Asia-Pacific Artificial Intelligence and Big Data Forum, AIBDF 2024

作者： Zhou, Zhehao Yang, Huogen Zhong, Yuanming Hu, Yiwen College of Science Jiangxi University of Science and Technology Jiangxi Ganzhou China Jiangxi Provincial Key Laboratory of Multidimensional Intelligent Perception and Control Jiangxi Ganzhou China

ISBN: (纸本)9798400710865

Based on population and logical operation, a binary logical operation algorithm is proposed to solve the 0-1 programming problem. Introduce the uniform initialization operator to improve the survival rate and diversity of the population and avoid premature death;Introduce logical operations and construct the model of retention probability and decay coefficient, and intro-duce dynamic update operators to adaptively balance the ability of exploration and exploitation. In order to verify the effectiveness of the algorithm, the convergence of the algorithm is analyzed based on the martingale method, and the classical 0-1 knapsack problem public data set is selected and divided into two groups of experimental data sets of different sizes. The BLOA algorithm is compared with genetic algorithm, particle swarm optimization algorithm, binary flying eagle algorithm and other algorithms. The experimental results show that the time cost of the BLOA algorithm is reduced by 90.36%, and the average accuracy of the solution is improved by 15.59%. Finally, through the ablation experiment, the effectiveness of the uniform initialization operator generation algorithm and the dynamic adjustment update operator strategy designed by BLOA is verified. © 2024 Copyright held by the owner/author(s).

关键词： Consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

Energy-Aware Task Offloading for Rotatable STAR-RIS-Enhanced Mobile Edge Computing Systems

引用

IEEE Internet of Things Journal 2025年第12期12卷 20239-20250页

作者： Yang, Dongdong Li, Bin Niyato, Dusit Nanjing University of Information Science and Technology School of Computer Science Nanjing210044 China Huzhou Key Laboratory of Urban Multidimensional Perception and Intelligent Computing Huzhou313000 China Nanyang Technological University College of Computing and Data Science Singapore Singapore

Simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) can expand the coverage of mobile edge computing (MEC) services by reflecting and transmitting signals simultaneously, enabling full-space coverage. The orientation of the STAR-RIS plays a crucial role in optimizing the gain of received and transmitted signals, and a rotatable STAR-RIS offers potential enhancement for MEC systems. This paper investigates a rotatable STAR-RIS-assisted MEC system, operated under three protocols, namely energy splitting, mode switching, and time switching. The goal is to minimize energy consumption for multiple moving user devices through the joint optimization of STAR-RIS configurations, orientation, computation resource allocation, transmission power, and task offloading strategies. Considering the mobility of user devices, we model the original optimization problem as a sequential decision-making process across multiple time slots. The high-dimensional, highly coupled, and nonlinear nature makes it a challenging non-convex decision-making problem for traditional optimization algorithms. Therefore, a deep reinforcement learning (DRL) approach is employed, specifically utilizing soft actor-critic algorithm to train the DRL model. Simulation results demonstrate that the proposed algorithm outperforms the benchmarks in both convergence speed and energy efficiency, while reducing energy consumption by up to 52.7% compared to the fixed STAR-RIS scheme. Among three operating protocols, the energy splitting yields the best performance. © 2014 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Multi-Class Token Attention Learning for Weakly Supervised Semantic Segmentation 23

Multi-Class Token Attention Learning for Weakly Supervised S...

引用

23rd International Conference on Machine Learning and Cybernetics, ICMLC 2024

作者： Zeng, Zhen Luo, Huilan School of Information Engineering Jiangxi University of Science and Technology Ganzhou341000 China Jiangxi Provincial Key Laboratory of Multidimensional Intelligent Perception and Control Ganzhou341000 China

ISBN: (纸本)9798331528041

Weakly supervised semantic segmentation (WSSS) using only image-level class labels is a challenging task. Due to the local receptive fields of convolutional neural networks (CNNs), CAMs applied to CNNs often suffer from partial activation-highlighting the most discriminative parts of the image. To capture both local features and global representations, we propose an approach called MCTRM, which is a WSSS solution based on an improved Conformer as backbone. To ensure each class token's discriminative ability for the respective target class, we design a class-aware training strategy (CAT) to establish a one-to-one correspondence between the output class tokens and the ground-truth class labels. To enhance the class discrimination ability between each class token, we propose a class token regularization module (CTRM) to enhance the learning of discriminative class tokens so that the model can better capture the unique features and attributes of each class. To obtain a fine-grained CAM, we propose the refinement module (RM) to combine the class-specific attention and inherent patch-level pairwise affinity between image patches learned by the Transformer branch with the CAM of the CNN branch. Despite its simplicity, MCTRM achieves the state-of-the-art performance of 69.0% and 68.4% on the PASCAL VOC 2012 validation and test sets, respectively. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Combine deep learning and Bayesian analysis to separate overlapping gravitational wave signals

引用

Science China(Physics,Mechanics & Astronomy) 2025年第5期68卷 205-219页

作者： Cunliang Ma Weiguang Zhou Zhoujian Cao Mingzhen Jia Jiangxi Provincial Key Laboratory of Multidimensional Intelligent Perception and Control Jiangxi University of Science and TechnologyGanzhou 341000China Institute of Applied Mathematics Academy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China School of Fundamental Physics and Mathematical Sciences Hangzhou Institute for Advanced StudyUCASHangzhou 310024China

Future gravitational wave(GW)observatories,such as the Einstein Telescope,are anticipated to encounter overlapping GW signals,presenting considerable obstacles to GW data processing techniques,including signal identification and parameter *** this letter,we propose a scheme of combining deep learning and Bayesian analysis to disentangle overlapping GW *** deep learning part takes a data-driven approach that employs an encoder-separation-decoder framework which is powerful enough to extract the shape of the signal even when the GW signals completely *** Bayesian analysis part takes the matched filtering technique to extract the amplitude of the GW *** scheme can facilitate the utilization of existing GW detection and parameter estimation methods for future instances of overlapping *** methodology effectively reduces biases in parameter estimation when handling multiple intertwined ***,this marks the first known instance where deep learning has been successfully utilized to disentangle overlapping GW signals.

关键词： gravitational wave separation machine learning Einstein Telescope parameter estimation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：