检索结果-内蒙古大学图书馆

Software and hardware synergy for accelerated plant disease identification

APPLIED SOFT COMPUTING 2025年 174卷

作者： Wen, Hongxing Li, Chuandong Wang, Xinpei Chen, Ling Southwest Univ Coll Elect Informat & Engn Chongqing Key Lab Nonlinear Circuits & Intelligent Chongqing 400715 Peoples R China

Plant diseases are one of the main causes of reduced crop yields. Therefore, it is necessary to adopt timely and effective identification methods and take corresponding measures. Some physical and biological detection methods have been proposed by researchers, but these methods require specialized techniques and expensive detection costs. Furthermore, the limited number of skilled technicians means that disease identification is not always timely or effective. To achieve real-time identification of plant diseases in remote areas where network and circuit are not well connected, We adopted a hardware and software co-acceleration approach to implement the design. First, we designed a lightweight convolutional neural network (CNN) and trained this network using a knowledge distillation approach. Then, we quantified the model parameters into int8 type using a method of model quantization to further compress the model size. After compression, the model size of the network is 0.035 MB and the recognition accuracy is 94.06% on the test set of the experiment. In order to deploy the proposed network on resource constrained Field-programmable Gate Array (FPGA) devices, we used time-division multiplexing and feature map segmentation to deploy the network. Finally, our design is implemented on ZYNQ7020 with an inference speed of 35.73ms/frame and a power consumption of 1.97 W. The experimental results show that our design has the advantages of consuming less FPGA resources, low power consumption, high speed and portability. It can be used for disease recognition in multiple plant classes.

关键词： Convolutional neural network Field-programmable gate array Acceleration Plant disease

来源：评论

学校读者我要写书评

暂无评论

Asynchronous Distributed Nonsmooth Composite Optimization via Computation-Efficient Primal-Dual proximal Algorithms

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2025年第2期9卷 1595-1609页

作者： Ran, Liang Li, Huaqing Zheng, Lifeng Li, Jun Southwest Univ Coll Elect & Informat Engn Chongqing Key Lab Nonlinear Circuits & Intelligent Chongqing 400715 Peoples R China

This paper focuses on a distributed nonsmooth composite optimization problem over a multiagent networked system, in which each agent is equipped with a local Lipschitz-differentiable function and two possibly nonsmooth functions, one of which incorporates a linear mapping. To address this problem, we introduce a synchronous distributed algorithm featuring uncoordinated relaxed factors. It serves as a generalized relaxed version of the recent method TriPD-Dist. Notably, the considered problem in the presence of asynchrony and delays remains relatively unexplored. In response, a new asynchronous distributed primal-dual proximal algorithm is first proposed, rooted in a comprehensive asynchronous model. It is operated under the assumption that agents utilize possibly outdated information from their neighbors, while considering arbitrary, time-varying, yet bounded delays. With some special adjustments, new asynchronous distributed extensions of existing centralized methods are obtained via the proposed asynchronous algorithm. Theoretically, a new convergence analysis technique of the proposed algorithms is provided. Specifically, a sublinear convergence rate is explicitly derived by showcasing that the iteration behaves as a nonexpansive operator. In addition, the proposed asynchronous algorithm converges the optimal solution in expectation under the same step-size conditions as its synchronous counterpart. Finally, numerical studies substantiate the efficacy of the proposed algorithms and validate their performance in practical scenarios.

关键词： Delays Optimization Distributed algorithms Convergence Vectors Convex functions Computational intelligence Asynchrony delayed communication nonsmooth convex functions distributed optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Adaptive Fixed-Time Control for Full State-Constrained nonlinear Systems: Switched-Self-Triggered Case

引用

IEEE TRANSACTIONS ON circuits AND SYSTEMS II-EXPRESS BRIEFS 2024年第2期71卷 752-756页

作者： Wang, Ziming Wang, Xin Pang, Ning Southwest Univ Coll Westa Chongqing Key Lab Nonlinear Circuits & Intelligent Chongqing 400715 Peoples R China Southwest Univ Coll Elect & Informat Engn Chongqing Key Lab Nonlinear Circuits & Intelligent Chongqing 400715 Peoples R China

In this brief, an one-to-one asymmetric NM based auxiliary system is put forward to deal with the state transformation problem for nonstrict full state-constrained systems under the adaptive fixed-time control. Then one proposed a novel switched-self-triggered mechanism (SSTM) in the controller update, which is helpful to obtain a better system performance. In addition, one can show that under the condition of state-constraints, semiglobal practical fixed-time stability (SPFTS) standard can also preserved both the tracking performance and the stability of the closed-loop system in a specified time. Finally, the effectiveness of the controller design is thoroughly shown via an illustrative simulation example.

关键词： Control systems Switches nonlinear systems Lyapunov methods Convergence Stability criteria nonlinear circuits Fixed-time control full-state constraints RBF NN switched-self-triggered mechanism (SSTM)

来源：评论

学校读者我要写书评

暂无评论

Edge-based distributed primal-dual algorithms for seeking generalized Nash equilibria

引用

EUROPEAN JOURNAL OF CONTROL 2024年 77卷

作者： Li, Huaqing Fan, Luming Ran, Liang Wang, Zheng Zheng, Zuqing Li, Zhe Li, Songyang Zheng, Lifeng Li, Jun Southwest Univ Coll Elect & Informat Engn Chongqing Key Lab Nonlinear Circuits & Intelligent Chongqing 400715 Peoples R China

This paper introduces two novel distributed algorithms aimed at finding the generalized Nash equilibria (GNE) in noncooperative games. To tackle this, we utilize the variational inequality framework, transforming the noncooperative game into the challenge of identifying the zeros of a sum of monotone operators. Within noncooperative games, the decisions made by individual players are interlinked via shared affine constraints. Our proposed approach involves two edge -based distributed algorithms, differentiated by their access to players' actions, whether it is full -decision information or partial -decision information. We establish the parameter range and demonstrate the convergence of both algorithms, showcasing their efficacy under local constant step -sizes. Additionally, we validate the effectiveness and advantages of these algorithms through two numerical experiments.

关键词： Primal-dual method Distributed algorithm Non-cooperative game Generalized Nash equilibria (GNE)

来源：评论

学校读者我要写书评

暂无评论

Stabilization of nonlinear delayed systems subject to impulsive disturbance via aperiodic intermittent control

引用

JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS 2024年第6期361卷

作者： Wang, Yinuo Li, Chuandong Wu, Hongjuan Deng, Hao Southwest Univ Coll Elect & Informat Engn Chongqing Key Lab Nonlinear Circuits & Intelligent Chongqing 400715 Peoples R China

In this paper, the finite -time stabilization (FS) of nonlinear delayed systems subject to impulsive disturbance is addressed via designing an aperiodic intermittent control (APIC), which can be segmented into time -triggered intermittent control (TAPIC) and event -triggered intermittent control (EAPIC). On account of Lyapunov method, sufficient conditions are exhibited to render FS can be achieved. Under TAPIC, the relationship between impulsive disturbance and control parameters is set up, from which the impulsive instants and the width of each control period can be resolved. In the framework of finite -time stabilization, the relationship among impulsive disturbance, intermittent control parameters, threshold value of event -triggered mechanism (ETM) under EAPIC is built up to ensure FS, and the sequence of impulsive disturbance instants is generated by the pre -designed ETM. Besides, the Zeno phenomenon can be ruled out. Based on the Chua's oscillator with time delay, two examples are depicted to demonstrate the validity of the acquired results under TAPIC and EAPIC, respectively.

关键词： Stabilization analysis nonlinear delayed systems Impulsive disturbance Aperiodic intermittent control Event-triggered control

来源：评论

学校读者我要写书评

暂无评论

Recyclable solid waste detection based on image fusion and convolutional neural network

引用

JOURNAL OF MATERIAL CYCLES AND WASTE MANAGEMENT 2024年第4期26卷 2043-2057页

作者： Xiao, Yao Chen, Bin Feng, Changhao Qin, Jiongming Wang, Cong Southwest Univ Coll Elect & Informat Engn Chongqing Key Lab Nonlinear Circuits & Intelligent Chongqing 400715 Peoples R China

The most solid waste image datasets usually contain only a single object with a plain background, which is quite different from the real environment. In addition, the waste images labeling process takes a long time and is labor cost. To address these problems, we proposed an effective method to extend the dataset based on image fusion. Herein, we use image fusion technology to make a recyclable solid waste dataset Trash-Fusion automatically, where the images contain different categories of objects with complex background, and all classification and location labels are collected in the process of image fusion. Moreover, an actual scene dataset Trash-Collect is constructed, images of which are downloaded from the Internet or collected by ourselves. A mixed dataset of Trash-Fusion and Trash-Collect is sent to several convolutional neural networks for training, and YOLO v5 achieves the highest detection precision with 60 FPS.

关键词： Recyclable solid waste Image fusion Convolutional neural network Mixed training Waste detection

来源：评论

学校读者我要写书评

暂无评论

Global μ-synchronization for coupling delayed complex dynamical networks via event-triggered delayed impulsive control

引用

ISA TRANSACTIONS 2024年 145卷 124-131页

作者： Zhang, Wei Xiao, Jun Gong, Bingyan Southwest Univ Dept Elect & Informat Engn Chongqing Key Lab Nonlinear Circuits & Intelligent Chongqing 400715 Peoples R China

This paper mainly focuses on solving the global mu-synchronization issue of complex dynamical networks (CDNs) by a novel event-triggered impulsive control (ETIC) method with time delays. This method combines the advantages of impulsive control and event-triggered control and gets rid of the limitation that the Lyapunov function decreases strictly monotonically with the sequence of event triggers. An event-triggered mechanism is specifically designed to realize mu-synchronization for CDNs in this paper, which means that event-triggered control has been applied to mu-synchronization field for the first time. Compared with periodic impulsive control, ETIC only produces control effects when the event-triggered mechanism are met, which is more in line with the actual situation. By Lyapunov-Razumikhin, recursion, etc, some valid global mu-synchronization criteria of CDNs are obtained and also Zeno behavior is avoided. Additionally, coupled delays and uncertainties are considered in CDNs. Finally, two numerical examples are shown to demonstrate the correctness of the designed ETIC strategy.

关键词： Parametric uncertainty nonlinear complex dynamical networks Time delay mu-synchronization Event-triggered control

来源：评论

学校读者我要写书评

暂无评论

Impulsive projection Neural Networks for Variational Inequalities and Sparse Signal Reconstruction Application

引用

COGNITIVE COMPUTATION 2024年第3期16卷 877-887页

作者： Xu, Jing Li, Chuandong He, Xing Wen, Hongsong Southwest Univ Coll Elect & Informat Engn Chongqing Key Lab Nonlinear Circuits & Intelligent Chongqing 400715 Peoples R China

Variational inequalities (VIs) have become a general framework for efficient problems in various fields such as optimal control and nonlinear programming. Some real problems in application areas such as signal processing and network resource allocation can be transformed into VIs. VIs have been frequently solved using neurodynamic approaches, which have good performance and low computational cost. In this paper, two novel projection neural networks (PNNs) with impulsive effects are presented to deal with VIs. Based on the impulsive system theory and PNN, an impulsive projection neural network (IPNN) and its modified version are proposed. Then the stability properties of the presented IPNN and modified impulsive projection neural network (MIPNN) are analyzed by Lyapunov functions and impulsive system theory. VIs can be addressed with the proposed IPNN and MIPNN. Furthermore, two PNNs are applied to sparse signal reconstruction. It is also shown that the solutions of the proposed IPNN and MIPNN converge to the solution of the corresponding VIs. Meanwhile, sparse signals can also be accurately reconstructed by IPNN and MIPNN. Compared with the classical neural network, the newly designed IPNN and MIPNN have an improvement in the convergence rates because of the introduction of impulsive effects. Theoretical results and simulations show the effectiveness and feasibility of the IPNN and MIPNN.

关键词： projection Neural Networks (PNNs) Impulsive effect Variational Inequalities (VIs) Sparse signal reconstruction

来源：评论

学校读者我要写书评

暂无评论

Mean square exponential stabilization analysis of stochastic neural networks with saturated impulsive input

引用

NEURAL NETWORKS 2024年 170卷 127-135页

作者： Deng, Hao Li, Chuandong Chang, Fei Wang, Yinuo Southwest Univ Coll Elect & Informat Engn Chongqing Key Lab Nonlinear Circuits & Intelligent Chongqing 400715 Peoples R China

The exponential stabilization of stochastic neural networks in mean square sense with saturated impulsive input is investigated in this paper. Firstly, the saturated term is handled by polyhedral representation method. When the impulsive sequence is determined by average impulsive interval, impulsive density and mode-dependent impulsive density, the sufficient conditions for stability are proposed, respectively. Then, the ellipsoid and the polyhedron are used to estimate the attractive domain, respectively. By transforming the estimation of the attractive domain into a convex optimization problem, a relatively optimum domain of attraction is obtained. Finally, a three-dimensional continuous time Hopfield neural network example is provided to illustrate the effectiveness and rationality of our proposed theoretical results.

关键词： Saturated impulsive input Stochastic neural networks Average impulsive interval Impulsive density Attractive domain

来源：评论

学校读者我要写书评

暂无评论

Error-robust multi-view subspace clustering with nonconvex low-rank tensor approximation and hyper-Laplacian graph embedding

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2024年第PartC期133卷

作者： Pan, Baicheng Li, Chuandong Che, Hangjun Southwest Univ Coll Elect & Informat Engn Chongqing 400715 Peoples R China Chongqing Key Lab Nonlinear Circuits & Intelligent Chongqing 400715 Peoples R China

Tensor based subspace clustering, a method aimed at partitioning multi-view data into distinct clusters through the tensor low-rank representation, has gained widespread popularity. Despite the effectiveness of tensor singular value decomposition (t-SVD) based nuclear norm in extracting high-dimensional information from multiple views, certain limitations persist. Firstly, while the commonly used l(2,1) norm enhances clustering robustness, it remains susceptible to the impact of high-intensity noises. Secondly, the t-SVD based nuclear norm provides a biased estimation of tensor rank. Thirdly, existing methods either fail to preserve manifold structures from the original space or only extract binary relationships between data points. To address these challenges and enhance clustering performance in both high-intensity noisy and real-world conditions, an error-robust multi-view subspace clustering with nonconvex low-rank tensor approximation and hyperLaplacian graph embedding (EMSC-NLTHG) method is proposed. Specifically, Cauchy loss function which reduces sensitivity to larger noises and outliers is introduced. Based on the Cauchy loss function, we develop the Cauchy pseudo norm to represent the reconstruction error in clustering to enhance the robustness. Moreover, rather than uniformly weighting all singular values in the t-SVD nuclear norm, a nonconvex tensor nuclear norm is adopted to add weights adaptively and approximate the true tensor rank. Additionally, hypergraph is embedded in the representation matrices to preserve local manifold structures and extract the complex multivariate relationships between data points. Extensive experiments demonstrate that the proposed EMSCNLTHG method consistently outperforms state-of-the-art techniques by approximately 18% to 40% on datasets corrupted by high-intensity noises and around 1% to 27% on eight real-world datasets across six popular evaluation metrics.

关键词： Multi-view clustering Low-rank tensor approximation Subspace clustering Error-robust clustering

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：