检索结果-内蒙古大学图书馆

Belief-Selective Propagation Detection for MIMO Systems

IEEE TRANSACTIONS ON COMMUNICATIONS 2023年第12期71卷 7244-7257页

作者： Zhou, Wenyue Shen, Yifei Li, Liping Huang, Yongming Zhang, Chuan You, Xiaohu Southeast Univ Natl Mobile Commun Res Lab LEADS LEADS Nanjing 211189 Peoples R China Southeast Univ Frontiers Sci Ctr Mobile Informat Commun & Secur Nanjing 211189 Peoples R China Purple Mt Labs Nanjing 211100 Peoples R China Ecole Polytech Fed Lausanne EPFL Telecommun Circuits Lab TCL CH-1015 Lausanne Switzerland Anhui Univ Key Lab Intelligent Comp & Signal Proc Minist Educ Hefei 230039 Peoples R China

Compared to the linear MIMO detectors, the Belief Propagation (BP) detector has shown greater capabilities in achieving near-optimal performance and better nature to iteratively cooperate with channel decoders. Aiming at real applications, recent works mainly fall into the category of reducing the complexity by simplified calculations, at the expense of performance sacrifice. However, the complexity is still unsatisfactory with exponentially increasing complexity or required exponentiation operations. Furthermore, the state-of-the-art (SOA) BP detectors persistently encounter error floor in high signal-to-noise ratio (SNR) region, which becomes even worse with calculation approximation. This work aims at a revised BP detector, named Belief-selective Propagation (BsP) detector by selectively utilizing the trusted incoming messages with sufficiently large a priori probabilities for updates. Two proposed strategies: symbol-based truncation (ST) and edge-based simplification (ES) squeeze the complexity (orders lower than the BP detector), while greatly relieving the error floor issue over a wide range of antenna and modulation combinations. For the 256-QAM 128 chi 64 uplink massive multiuser MIMO (MU-MIMO) system, the B(1,1) BsP detector achieves more than 1dB performance gain (@BER=10(-4)) with lower complexity than the state-of-the-art (SOA) BP detector. Trade-off between performance and complexity towards different application requirements can be conveniently obtained by tuning the parameters of the ST and ES strategies.

关键词： Multiple-input multiple-output (MIMO) belief-selective propagation (BsP) error floor complexity

来源：评论

学校读者我要写书评

暂无评论

Hybrid manifold-deep convolutional neural network for sleep staging

引用

METHODS 2022年 202卷 164-172页

作者： Zhang, Chuanhao Liu, Sen Han, Fang Nie, Zedong Lo, Benny Zhang, Yuan Southwest Univ Coll Elect & Informat Engn Chongqing Key Lab Nonlinear Circuits & Intelligent Chongqing Peoples R China Shandong First Med Univ Dept Oncol Cent Hosp Jinan Peoples R China Peking Univ Peoples Hosp Beijing Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol Shenzhen Peoples R China Imperial Coll London Dept Surg & Canc London England

Analysis of electroencephalogram (EEG) is a crucial diagnostic criterion for many sleep disorders, of which sleep staging is an important component. Manual stage classification is a labor-intensive process and usually suffered from many subjective factors. Recently, more and more computer-aided techniques have been applied to this task, among which deep convolutional neural network has been performing well as an effective automatic classification model. Despite some comprehensive models have been developed to improve classification results, the accuracy for clinical applications has not been reached due to the lack of sufficient labeled data and the limitation of extracting latent discriminative EEG features. Therefore, we propose a novel hybrid manifold-deep convolutional neural network with hyperbolic attention. To overcome the shortage of labeled data, we update the semi-supervised training scheme as an optimal solution. In order to extract the latent feature representation, we introduce the manifold learning module and the hyperbolic module to extract more discriminative information. Eight subjects from the public dataset are utilized to evaluate our pipeline, and the model achieved 89% accuracy, 70% precision, 80% sensitivity, 72% f1-score and kappa coefficient of 78%, respectively. The proposed model demonstrates powerful ability in extracting feature representation and achieves promising results by using semi-supervised training scheme. Therefore, our approach shows strong potential for future clinical development.

关键词： Sleep staging Convolutional neural network Manifold learning Hyperbolic attention

来源：评论

学校读者我要写书评

暂无评论

Multi-cluster nonlinear unsupervised feature selection via joint manifold learning and generalized Lasso

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年第PartA期255卷

作者： Wang, Yadi Huang, Mengyao Zhou, Liming Che, Hangjun Jiang, Bingbing Henan Univ Henan Key Lab Big Data Anal & Proc Kaifeng 475004 Peoples R China Henan Univ Inst Data & Knowledge Engn Sch Comp & Informat Engn Kaifeng 475004 Peoples R China Southwest Univ Coll Elect & Informat Engn Chongqing 400715 Peoples R China Southwest Univ Chongqing Key Lab Nonlinear Circuits & Intelligent Chongqing 400715 Peoples R China Hangzhou Normal Univ Sch Informat Sci & Engn Hangzhou 311121 Peoples R China

Due to the scarcity of data labels, unsupervised feature selection has received a lot of attention in recent years. While many unsupervised feature selection methods are capable of selecting relevant features, they often fail to comprehensively consider the impact of both local and global information of the data on feature selection, nor can they effectively handle the complex nonlinear relationships commonly found in real-world data. As a result, suboptimal feature subsets are often selected. In this paper, inspired by the Uniform Manifold Approximation and Projection (UMAP) manifold learning technique and the nonlinear sparse learning method based on Feature-Wise Kernelized Lasso, we propose a novel unsupervised feature selection method called Multi-Cluster Unsupervised nonlinear Feature Selection based on UMAP and block HSIC Lasso (MUNFS). MUNFS greatly improves the representation of high-dimensional data during dimensionality reduction and effectively handles complex nonlinear relationships in such data. Specifically, by capturing the intrinsic topology of the data, MUNFS accurately preserves the local structure of the data while keeping as much of the global structure as possible. Furthermore, the kernel-based Hilbert-Schmidt Independence Criterion (HSIC) may measure the nonlinear dependency between the features and the target variables, while applying the l(1) regularization term in feature selection to achieve sparsity. This allows for a more precise assessment of the significance of each feature. Extensive experimental results on five benchmark datasets and eight hyperspectral datasets demonstrate that the MUNFS method performs much better than several other feature selection methods.

关键词： Unsupervised feature selection Manifold learning Non-linear Sparse learning Hilbert-Schmidt independence criterion

来源：评论

学校读者我要写书评

暂无评论

Exponential Lag Synchronization of Memristive Neural Networks with Reaction Diffusion Terms via Neural Activation Function Control and Fuzzy Model

引用

ASIAN JOURNAL OF CONTROL 2020年第1期22卷 346-361页

作者： Liu, Yicheng Liao, Xiaofeng Li, Chuandong Southwest Univ Coll Elect & Informat Engn Chongqing Key Lab Nonlinear Circuits & Intelligen Chongqing 400715 Peoples R China

This paper is concerned with the problem of exponential lag synchronization of memristive neural networks with reaction diffusion terms via neural activation function control and fuzzy model. An memristor-based circuit which exhibits the feature of pinched hysteresis is introduced and further, the memristive neural networks with reaction diffusion terms and such system containing fuzzy model are described at length, respectively. By utilizing the Lyapunov functional method and the neural activation function controller depending on the output of the system in the case of packed circuits, some concise conditions are acquired to guarantee the slave systems exponential lag synchronized with the master systems. Finally, several simulated examples are also presented to demonstrate the correctness of the theoretical results.

关键词： Memristive neural networks reaction diffusion terms lag synchronization neural activation function fuzzy model

来源：评论

学校读者我要写书评

暂无评论

Impulsive Consensus of nonlinear Multi-Agent Systems via Edge Event-Triggered Control

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2020年第6期31卷 1995-2004页

作者： Xu, Ziqiang Li, Chuandong Han, Yiyan Southwest Univ Chongqing Key Lab Nonlinear Circuits & Intelligen Coll Elect & Informat Engn Chongqing 400715 Peoples R China

In this paper, we mainly investigate two kinds of consensuses of multi-agent systems (MASs) with nonlinear dynamics based on impulsive control, event-triggered control, and sampled-data control. The two types of impulsive protocols are proposed for the case without and with leader agent. Edge event-triggered technique is presented, where for each communication link, occurrence of edge event can activate the mutual state sampling and controller update of the corresponding agents. The control approach combines the characteristics of impulsive control and edge event-triggered control and is defined as "impulsive edge event-triggered control." It has good performance in robustness against disturbance and reduces the communication cost. The results with the aid of the Lyapunov function approach and stability theory of impulsive control show that if some sufficient conditions are satisfied, the consensus of MASs can be guaranteed and the rate of convergence can be exponentially estimated. Additionally, Zeno-behavior can be eliminated by using impulsive edge event-triggered control, which reduces the burden of event detectors. Finally, two simulations are provided to illustrate the effectiveness and performance of our theoretical analysis.

关键词： Protocols Multi-agent systems Topology nonlinear dynamical systems Convergence Graph theory Eigenvalues and eigenfunctions Edge event-triggered control impulsive consensus multi-agent systems (MASs) nonlinear dynamics

来源：评论

学校读者我要写书评

暂无评论

Stability and Oscillation Analysis of a Gene Regulatory Network With Multiple Time Delays and Diffusion Rate

IEEE TRANSACTIONS ON NANOBIOSCIENCE

引用

IEEE TRANSACTIONS ON NANOBIOSCIENCE 2020年第2期19卷 285-298页

作者： Dong, Tao Zhang, Qinqin Southwest Univ Coll Elect & Informat Engn Chongqing Key Lab Nonlinear Circuits & Intelligen Chongqing 400715 Peoples R China

In genetic regulatory networks (GRNs), the diffusion rate of mRNA and protein play a key role in regulatory mechanisms of gene expression, especially in translation and transcription. However, the influence of diffusion rate on oscillatory gene expression is not well understood. In this paper, by considering the diffusion rate of mRNA and protein, a novel GRN is proposed. Then, two basic problems of such network, i.e. stability and oscillation, are solved in detail. Moreover, the properties of oscillation are also investigated. it is found that the total biochemistry reaction time can affect the stability of the positive equilibrium and give rise to the oscillation. The diffusion rate of mRNA and proteins have a major impact on the oscillation properties. Finally, two examples not only verify the theoretical results, but also show that a slight diffusion rate increasing may lead to huge change in oscillatory gene expressions.

关键词： Reaction-diffuison genetic regulatory networks time delays oscillation

来源：评论

学校读者我要写书评

暂无评论

Consensus of nonlinear multi-agent systems with fuzzy modelling uncertainties via state-constraint hybrid impulsive protocols

引用

INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS 2020年第12期11卷 2653-2664页

作者： You, Le Li, Chuandong Han, Yiyan Southwest Univ Coll Elect & Informat Engn Chongqing Key Lab Nonlinear Circuits & Intelligen Chongqing 400715 Peoples R China

In this paper, the nonlinear multi-agent system which contains uncertainty and is controlled by state-constraint impulsive protocol is taken into consideration. For the uncertainty of the multi-agent system, it is replaced by fuzzy logic system approximately and a judgement strategy which only contains the relative information with neighbors is proposed in this paper. In order to do research in state-constraint impulsive protocol, three kinds of impulsive control protocols which conclude partial input saturation, double actuator saturation and single actuator saturation are discussed. Then, some sufficient conditions of the system are obtained to reach consensus. Finally, some numerical simulation examples are provided to prove the effectiveness of the theoretical analysis.

关键词： Multi-agent system Fuzzy logic system Impulsive protocol Partial input saturation Actuator saturation

来源：评论

学校读者我要写书评

暂无评论

Finite-time stability of nonlinear systems with state-dependent delayed impulses

引用

nonlinear DYNAMICS 2020年第1期102卷 197-210页

作者： Zhang, Xiaoyu Li, Chuandong Southwest Univ Chongqing Key Lab Nonlinear Circuits & Intelligen Coll Elect & Informat Engn Chongqing 400715 Peoples R China

This paper addresses the issue of finite-time stability (FTS) and finite-time contractive stability (FTCS) of nonlinear systems involving state-dependent delayed impulsive perturbation. Several sufficient conditions are obtained by using theories of impulsive control and Lyapunov stability. The relation between impulsive perturbation and state-dependent delay is established to achieve FTS and FTCS. For time-varying nonlinear system and nonlinear system with fixed parameters, we derive some sufficient conditions based on the main thought of this paper, respectively. Finally, three numerical examples are provided to illustrate the effectiveness and validity of achieved results.

关键词： Finite-time stability Finite-time contractive stability State-dependent delay Delayed impulses Impulsive theory

来源：评论

学校读者我要写书评

暂无评论

Edge-Based Stochastic Gradient Algorithm for Distributed Optimization

引用

IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING 2020年第3期7卷 1421-1430页

作者： Wang, Zheng Li, Huaqing Southwest Univ Coll Elect & Informat Engn Chongqing Key Lab Nonlinear Circuits & Intelligen Chongqing 400715 Peoples R China

This paper investigates distributed optimization problems where a group of networked nodes collaboratively minimizes the sum of all local objective functions. The local objective function of each node is further set as an average of a finite set of subfunctions. This adjustment is motivated by machine learning problems with large training samples distributed and known privately to individual computational nodes. An augmented Lagrange (AL) stochastic gradient algorithm is presented to address the distributed optimization problem, which is integrated with the factorization of weighted Laplacian and local unbiased stochastic averaging gradient methods. At each iteration, only one randomly selected gradient of a subfunction is evaluated at a node, and a variance-reduced stochastic averaging gradient technique is applied to approximate the gradient of local objective function. Strong convexity of the local subfunction and Lipschitz continuity of its gradient are shown to ensure a linear convergence rate of the proposed algorithm in expectation. Numerical experiments on a logistic regression problem demonstrate the correctness of theoretical results.

关键词： Convergence Optimization Linear programming Convex functions Laplace equations Machine learning Training Distributed convex optimization machine learning augmented Lagrange stochastic averaging gradient

来源：评论

学校读者我要写书评

暂无评论

Miniaturized Wideband Self-Oscillating Active Integrated Antenna With Power Enhancement

引用

IEEE ANTENNAS AND WIRELESS PROPAGATION LETTERS 2024年第10期23卷 2964-2968页

作者： Du, Zhi-Xia Cui, Manman Zhang, Yao Guo, Chunbing Guangdong Univ Technol Sch Integrated Circuits Guangzhou 510006 Peoples R China Guangxi Key Lab Wireless Wideband Commun & Signal Guilin 541004 Peoples R China Guangzhou Univ Chinese Med Sch Med Informat Engn Guangzhou 510006 Peoples R China Guangzhou Univ Chinese Med Intelligent Chinese Med Res Inst Guangzhou 510006 Peoples R China Xiamen Univ Inst Electromagnet & Acoust Xiamen 361005 Peoples R China

This letter proposes a compact and wideband self-oscillating active integrated antenna (AIA) with power enhancement. It consists of a dc-charged wideband antenna with large equivalent capacitance and a pulse-triggered network controlling its working states. In the design, a capacitively coupled region is created in the antenna, which not only improves the frequency bandwidth but also enhances the energy storage capacity. Consequently, the proposed design enables greater energy storage within the antenna in the charging state, thereby significantly increasing the radiated power in the radiation state. Measured results show that the effective isotropic radiated power (EIRP) of the proposed AIA is approximately 8 dB greater than the EIRP of the self-oscillating AIA employing a conventional dipole antenna, while the system size is only 0.1 lambda x 0.1 lambda at the frequency that corresponds to the maximum output power.

关键词： oscillator radiated power enhancement Active integrated antenna (AIA) wideband antenna wideband antenna radiated power enhancement wideband antenna

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：