检索结果-内蒙古大学图书馆

EEG-Based Epilepsy Recognition via Federated Learning With Differential Privacy

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE 2025年第9-11期37卷

作者： Luo, Yuling Jiang, Bingxiong Qin, Sheng Fu, Qiang Zhang, Shunsheng Guangxi Normal Univ Sch Elect & Informat Engn Guangxi Key Lab Brain Inspired Comp & Intelligent Guilin Peoples R China Guangxi Normal Univ Educ Dept Guangxi Zhuang Autonomous Reg Key Lab Nonlinear Circuits & Opt Commun Guilin Peoples R China

Epilepsy is a complex chronic brain disorder that can be identified by observing brain signals. In general, the electroencephalogram (EEG) can be used to detect these brain signals. In order to produce a high-quality model, data from numerous patients can be gathered on a central server. However, sending the patient's raw data to the central computer may lead to privacy leakage. To address this problem, this work uses federated learning and differential privacy to train the model jointly. Furthermore, the epilepsy data is unbalanced as seizure only happens for a minority of time in one day, which influences the performance of the model. Thus, this work also uses label-distribution-aware-margin (LDAM) loss to solve this issue. This work is evaluated in intracranial EEG datasets, which consist of two dogs' EEG records. The global model trained jointly with LDAM loss can achieve an accuracy of 96.95%, a sensitivity of 78.9%, a specificity of 96.145%, an F1 score of 70.435%, and a geometric mean of 87.785%. Compared with the other works, the accuracy has improved by about 9.31%, while the specificity and the geometric mean have also improved by about 10.75% and 1.8%, respectively.

关键词： differential privacy epilepsy recognition federated learning LDAM

来源：评论

学校读者我要写书评

暂无评论

Data-driven bipartite synchronization control of multi-agent systems with asymmetric input saturation over switching networks

引用

APPLIED MATHEMATICS AND COMPUTATION 2025年 494卷

作者： Shen, Ziwen Dong, Tao Huang, Tingwen Southwest Univ Coll Elect & Informat Engn Chongqing Key Lab Nonlinear Circuits & Intelligent Chongqing 400715 Peoples R China Shenzhen Univ Adv Technol Fac Comp Sci & Control Engn Shenzhen 518055 Peoples R China

This paper addresses the bipartite synchronization (BS) issue of nonlinear discrete-time multi- agent systems (NDTMASs) with asymmetric input saturation in switching cooperative-competitive networks. First, a local neighborhood error system (LNES) is constructed based on the switching cooperative-competitive networks. By utilizing a hyperbolic function, we design a novel local cost function and derive an optimal control policy. Based on this control policy, we construct a novel saturation-input policy iteration (SIPI) technique. Furthermore, we establish the convergence of the SIPI algorithm. It is demonstrated that the LNES can converge to zero, and thus the BS problem for MASs can be solved. To implement the SIPI algorithm, a control framework based on an actor-critic architecture is constructed. To achieve asymmetric input saturation, we select an asymmetric constrained function as the activation function for the actor network. Finally, an example is presented to illustrate the reliability of our approach.

关键词： Multi-agent systems Input saturation Cooperative-competitive networks Bipartite synchronization Switching topologies

来源：评论

学校读者我要写书评

暂无评论

Predicting chaos in permanent magnet synchronous motor using dual reservoir interaction with high-order state reservoir computing

引用

PHYSICA SCRIPTA 2025年第3期100卷 036010-036010页

作者： Ye, Zuo Wei Wei, Du Qu Guangxi Normal Univ Coll Elect & Informat Engn Guangxi Key Lab Brain Inspired Comp & Intelligent Guilin 541004 Peoples R China Guangxi Normal Univ Educ Dept Guangxi Zhuang Autonomous Reg Key Lab Nonlinear Circuits & Opt Commun Guilin Peoples R China

Permanent Magnet Synchronous Motor (PMSM), as core driving components of new energy vehicles, face significant challenges in performance and stability due to their complex chaotic behavior. Accurate prediction of chaotic behavior is crucial for the modeling and control of PMSM. This paper proposes a novel approach based on Reservoir Computing-the Dual Reservoir Interacting with High-Order State Reservoir Computing (DRI-HOSRC)-for predicting chaos in PMSM. By introducing high-order state expansion and the dual reservoir interaction mechanism, this method significantly enhances the ability to capture the nonlinear dynamic characteristics of PMSM. Experimental results show that the proposed DRI-HOSRC model outperforms traditional methods in terms of both prediction accuracy and time range, enabling a more precise capture of the system's complex chaotic features. These results validate the model's potential for application in PMSM, providing an innovative solution for accurate forecasting. The research also demonstrates the advantages of the dual reservoir interacting with high-order state reservoir model in nonlinear dynamics modeling and offers an effective pathway for long-term predictions of complex systems.

关键词： Permanent Magnet Synchronous Motor (PMSM) dual reservoir interaction high-order state expansion chaos prediction nonlinear dynamics

来源：评论

学校读者我要写书评

暂无评论

Chaotic time series prediction of motor system based on WOA-MFRFNN

引用

PHYSICA SCRIPTA 2025年第1期100卷

作者： Ma, Qianran Wei, Duqu Guangxi Normal Univ Coll Elect & Informat Engn Guangxi Key Lab Brain inspired Comp & Intelligent Guilin 541004 Peoples R China Guangxi Normal Univ Educ Dept Guangxi Zhuang Autonomous Reg Key Lab Nonlinear Circuits & Opt Commun Guilin Peoples R China

The complexity of the operation of permanent magnet synchronous motor (PMSM) has heightened interest in its stability and reliability. Evidence suggests that chaotic oscillatory behavior can occur during PMSM operation, making the prediction of such chaotic motion crucial for maintaining stable motor performance. In this paper, a WOA-MFRFNN (Whale Optimization Algorithm-Multi Functional Recurrent Fuzzy Neural Network) model is proposed to predict chaotic time series of PMSM, where WOA is used to train the network weights and the MFRFNN contains two TSK fuzzy rules for fuzzy neural networks, which are used for the output and the state of network, respectively. The experimental results of WOA-MFRFNN are compared with those of SSA-BP, ROA-RF and iTransformer. The results imply that the WOA-MFRFNN outperforms other methods and the RMSE can reach 5.45 x 10-4. It is also shown that the WOA-MFRFNN model exhibits good predictive effect on the real-world PMSM dataset.

关键词： chaotic time series motors WOA MFRFNN

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Random Delayed Impulsive Consensus of Multi-Agent Systems With Time-Varying Delay

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2025年第2期9卷 2059-2064页

作者： Zhang, Wei Chen, Junjie Wen, Shiping Huang, Tingwen Southwest Univ Dept Elect & Informat Engn Chongqing Key Lab Nonlinear Circuits & Intelligent Chongqing 400715 Peoples R China Univ Technol Sydney Sydney NSW 2007 Australia Texas A&M Univ Qatar Doha 23874 Qatar

In this study, the issue of consensus of multi-agent systems (MASs) with time-varying delays is studied using the event-triggered delayed impulsive control strategy. An impulsive controller protocol with random impulsive delay is designed for packet loss that sometimes occurs in multi-agent systems, and a Bernoulli sequence is used to indicate whether an impulse has a delay or not. Based on Lyapunov function and delayed impulsive control, sufficient conditions are given to achieve multi-agent systems consensus under continuous and periodic event triggered mechanism (ETM), respectively. For the continuous ETM, Zeno behavior is excluded and an upper bound on the impulsive control delay is derived. For periodic ETM, an upper bound on the sampling period is additionally given. In addition, useful propositions in Lemma form are given. Finally, numerical examples are used to demonstrate the strategy's success.

关键词： Delays Time-varying systems Multi-agent systems Control systems Computational intelligence Protocols Mathematical models consensus event-triggered impulsive control random delay

来源：评论

学校读者我要写书评

暂无评论

Optimized backstepping tracking control using reinforcement learning for strict-feedback nonlinear systems with monotone tube performance boundaries

引用

INTERNATIONAL JOURNAL OF CONTROL 2025年

作者： Zhang, Gengning Wang, Xin Wang, Ziming Pang, Ning Southwest Univ Coll Westa Chongqing Key Lab Nonlinear Circuits & Intelligent Chongqing Peoples R China Southwest Univ Coll Elect & Informat Engn Chongqing Key Lab Nonlinear Circuits & Intelligent Chongqing Peoples R China Hong Kong Univ Sci & Technol Guangzhou Syst Hub Robot & Autonomous Syst Thrust Guangzhou Peoples R China Shanghai Jiao Tong Univ Dept Automat Shanghai 200240 Peoples R China

Recently proposed monotone tube boundaries enhance performance but exacerbate the challenge of the entry capture problem (ECP). This article addresses the ECP under monotone tube boundaries and employs optimal control strategies combined with reinforcement learning (RL) to enhance performance in unknown state situations. By utilising error scaling functions (ESF), the proposed method effectively confines the error to a predefined neighbourhood in a specified time, without knowing the specific value of the initial error. Furthermore, this article innovatively incorporates the actor-critic structure into the monotone tube boundaries, significantly enhancing system performance. Due to the condition of state immeasurability, a neural network (NN)-based state observer is designed to estimate the states of the system. Additionally, command filters are used to simplify the multiple derivative calculations in traditional backstepping methods, addressing the 'explosion of complexity' problem. Mathematical derivations and simulation confirm its ability to meet predefined performance criteria.

关键词： Entry capture problem (ECP) error scaling functions (ESF) prescribed performance control (PPC) reinforcement learning (RL) nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

DPO-Face: Differential privacy obfuscation for facial sensitive regions

引用

COMPUTERS & SECURITY 2025年 154卷

作者： Luo, Yuling Hu, Tinghua Ouyang, Xue Liu, Junxiu Fu, Qiang Qin, Sheng Min, Zhen Lin, Xiaoguang Guangxi Normal Univ Sch Elect & Informat Engn Guangxi Key Lab Brain inspired Comp & Intelligent Guilin 541004 Peoples R China Guangxi Normal Univ Educ Dept Guangxi Zhuang Autonomous Reg Key Lab Nonlinear Circuits & Opt Commun Guilin 541004 Peoples R China

User-sensitive face images captured by widely used image-collection devices are frequently shared on social media. If these images are misused, they may pose a serious threat to users' privacy. To ensure both privacy-preserving and image usability, this work introduces a Differential Privacy Obfuscation method of Face images (DPO-Face), which addresses the current limitations in balancing privacy and recognition accuracy. DPO-Face effectively balances privacy preservation and recognition accuracy to meet practical application demands. First, sensitive and non-sensitive regions of the image are accurately identified and located using an improved hybrid convolutional neural network by DPO-Face. Subsequently, face parsing technology is employed to precisely segment the input face image into multiple internal and external facial components. Moreover, precisely adjusted noise is introduced to the internal facial component regions using a differential privacy mechanism to disturb them, effectively protecting the privacy information of these regions while leaving the non-sensitive external components unchanged. Finally, the privacy-protected image is transmitted to the face detection and recognition module to evaluate the effectiveness of the privacy protection, such as maintaining high face detection and recognition accuracy. Experimental results demonstrate that DPO-Face meets epsilon-local differential privacy requirements, achieving recognition rates of 91%-96% and a maximum privacy protection success rate of 0.9720. This method allows the privacy level to be precisely adjusted, preventing privacy leaks to honest but curious third-party servers, thus achieving a balance between privacy-preserving and usability.

关键词： Differential privacy Privacy-preserving Neural network

来源：评论

学校读者我要写书评

暂无评论

Neuron Segmentation via a Frequency and Spatial Domain-Integrated Encoder-Decoder Network

引用

INTERNATIONAL JOURNAL OF intelligent SYSTEMS 2025年第1期2025卷

作者： Song, Haixing Zeng, Xuqing Li, Guanglian Wu, Rongqing Liu, Simin He, Fuyun Guangxi Normal Univ Sch Elect & Informat Engn Dept Artificial Intelligence Guangxi Key Lab Brain Inspired Comp & Intelligent Guilin Peoples R China Guangxi Normal Univ Educ Dept Guangxi Zhuang Autonomous Reg Key Lab Nonlinear Circuits & Opt Commun Guilin Peoples R China

Three-dimensional (3D) segmentation of neurons is a crucial step in the digital reconstruction of neurons and serves as an important foundation for brain science research. In neuron segmentation, the U-Net and its variants have showed promising results. However, due to their primary focus on learning spatial domain features, these methods overlook the abundant global information in the frequency domain. Furthermore, issues such as insufficient processing of contextual features by skip connections and redundant features resulting from simple channel concatenation in the decoder lead to limitations in accurately segmenting neuronal fiber structures. To address these problems, we propose an encoder-decoder segmentation network integrating frequency domain and spatial domain to enhance neuron reconstruction. To simplify the segmentation task, we first divide the neuron images into neuronal cubes. Then, we design 3D FregSNet, which leverages both frequency and spatial domain features to segment the target neurons within these cubes. Then, we introduce a multiscale attention fusion module (MAFM) that utilizes spatial and channel position information to enhance contextual feature representation. In addition, a feature selection module (FSM) is incorporated to adaptively select discriminative features from both the encoder and decoder, increasing the weight on critical neuron locations and significantly improving segmentation performance. Finally, the segmented nerve fiber cubes were assembled into complete neurons and digitally reconstructed using available neuron tracking algorithms. In experiments, we evaluated 3D FregSNet on two challenging 3D neuron image datasets (the BigNeuron dataset and the CWMBS dataset). Compared to other advanced segmentation methods, 3D FregSNet demonstrates more accurate extraction of target neurons in noisy and weakly visible neuronal fiber images, effectively improving the performance of 3D neuron segmentation and reconstruction.

关键词： 3D image segmentation deep residual network frequency-space domain multi-scale feature neuron reconstruction

来源：评论

学校读者我要写书评

暂无评论

Unsupervised feature selection based on generalized regression model with linear discriminant constraints

引用

COMPLEX & intelligent SYSTEMS 2025年第6期11卷 1-11页

作者： Dai, Xiangguang Guan, Mingyu Dai, Facheng Zhang, Wei Zhang, Tingji Che, Hangjun Dai, Xiangqin Chongqing Three Gorges Univ Chongqing Engn Res Ctr Internet Things & Intellige Wanzhou 404100 Peoples R China Coll Elect & Informat Chongqing Key Lab Nonlinear Circuits & Intelligent Chongqing 400715 Peoples R China

Unsupervised feature selection (UFS) methods play a crucial role in improving the efficiency of extracting relevant information and reducing computational complexity in the context of big data analysis. Despite notable advancements in the field of unsupervised feature selection for large-scale datasets, many UFS methods still remain redundant and irrelevant features during the feature selection process. To tackle these challenges, we present a novel unsupervised feature selection method that leverages the generalized regression model with linear discriminant constraints to learn discriminant and effective features from the data. Benefited from this, the relationships and patterns within the high-dimensional data are retained in the reduced-dimensional feature space. We reformulate our proposed method as a multi-variable optimization problem that incorporates equality constraints. To efficiently solve this problem, we develop an algorithm that updates each variable alternately. Extensive experiments on six datasets among nine state-of-the-art methods on the clustering task are conducted to demonstrate the effectiveness of the proposed method.

关键词： Unsupervised feature selection Generalized regression model Linear discriminant constraints

来源：评论

学校读者我要写书评

暂无评论

Weight consistency and cluster diversity based concept factorization for multi-view clustering

引用

DIGITAL SIGNAL PROCESSING 2025年 157卷

作者： Tao, Youyang Che, Hangjun Li, Chenglu Pan, Baicheng Leung, Man-Fai Southwest Univ Coll Elect & Informat Engn Chongqing Peoples R China Sichuan Univ Sch Elect & Informat Engn Chengdu Peoples R China Chongqing Key Lab Nonlinear Circuits & Intelligent Chongqing Peoples R China Anglia Ruskin Univ Fac Sci & Engn Sch Comp & Informat Sci Cambridge England

In the era of information explosion, clustering analysis of multi-view data plays a crucial role in revealing the intrinsic structures of data. Despite the advancements in existing multi-view clustering methods for processing complex data, they often overlook the weight differences among various views and the diversity between clusters. To address the issues, the paper introduces a novel multi-view clustering approach termed weight consistency and cluster diversity based concept factorization for multi-view clustering (MVCF-WD). Specifically, the proposed method automatically learns the weights of the views, and incorporates a cluster diversity term to enhance the discriminability of clusters. Furthermore, to solve the formulated optimization model, an iterative optimization algorithm based on multiplication rules is developed and the convergence is analyzed. Extensive experiments conducted across seven datasets compared with ten state-of-the-art clustering algorithms demonstrate the superior clustering performance of the proposed method.

关键词： Concept factorization Multi-view clustering Cluster diversity Weight consistency

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：