检索结果-内蒙古大学图书馆

Initial Offset-Boosted Coexisting Hidden Chaos and Firing Multistability in Memristive Ring Neural Network With Hardware Implementation

引用

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS 2025年第2期72卷 2024-2033页

作者： Zhang, Sen Li, Yongxin Wang, Xiaoping Zeng, Zhigang Nanjing Univ Informat Sci & Technol Sch Artificial Intelligence Nanjing 210044 Jiangsu Peoples R China Nanjing Univ Informat Sci & Technol Sch Elect & Informat Engn Nanjing 210044 Jiangsu Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Educ Minist China Wuhan 430074 Peoples R China

Memristors can be introduced into neural networks for convenient chaos generation even combined with regulating firing activities. This article presents a no-equilibrium memristive ring neural network with dual memristors, one of which is used to mimic neural synapses and the other to describe the effects of external electromagnetic radiation. Initial conditions of different variables bring the chance to arise bistability and tristability. Initial offset-boosted coexisting hidden attractors are arranged by offset boosting, where homogeneous and heterogeneous multistabilities are captured simultaneously. When homogeneous attractors break barriers and connect together, the growth of attractors becomes apparent, allowing for flexible regulation over time and effective self-reproduction through varying initial values. Interestingly, abundant hidden firing patterns are well regulated by memristor-related parameters or the external current. Bursting and spiking firings are switched flexibly by proper knobs. In addition, infinitely many coexisting bursting and spiking firing patterns are also triggered by the initial values of the memristor acting as the coupled synapse or considered as an external electromagnetic radiation. Finally, a digital circuit based on CH32 is constructed to verify the characteristics of various coexisting hidden attractors and abundant firing patterns, thus confirming these new findings.

关键词： Firing multistability hardware implementation initial offset boosting memristive ring neural network memristor

来源：评论

学校读者我要写书评

暂无评论

Adaptive Drive-Response Synchronization of Timescale-Type Neural Networks With Unbounded Time-Varying Delays

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2025年第1期36卷 1056-1068页

作者： Wan, Peng Zhou, Yufeng Zeng, Zhigang Wuhan Univ Sci & Technol Sch Informat Sci & Engn Wuhan 430081 Peoples R China Wuhan Univ Sci & Technol Engn Res Ctr Met Automat & Measurement Technol Wuhan 430081 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Educ Minist China Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China

In recent years, adaptive drive-response synchronization (DRS) of two continuous-time delayed neural networks (NNs) has been investigated extensively. For two timescale-type NNs (TNNs), how to develop adaptive synchronization control schemes and demonstrate rigorously is still an open problem. This article concentrates on adaptive control design for synchronization of TNNs with unbounded time-varying delays. First, timescale-type Barbalat lemma and novel timescale-type inequality techniques are first proposed, which provides us practical methods to investigate timescale-type nonlinear systems. Second, using timescale-type calculus, novel timescale-type inequality, and timescale-type Barbalat lemma, we demonstrate that global asymptotic synchronization can be achieved via adaptive control under algebraic and matrix inequality criteria even if the time-varying delays are unbounded and nondifferentiable. Adaptive DRS is discussed for TNNs, which implies our control schemes are suitable for continuous-time NNs, their discrete-time counterparts, and any combination of them. Finally, numerical examples on TNNs and timescale-type chaotic Ikeda-like oscillator with unbounded time-varying delays are carried out to verify the adaptive control schemes.

关键词： Artificial neural networks Delays Adaptive control Synchronization Time-varying systems Mathematical models Behavioral sciences Adaptive control asymptotic stability synchronization timescale-type neural networks (TNNs) unbounded time-varying delays

来源：评论

学校读者我要写书评

暂无评论

CSFuser: A Cascade Siamese Fusion Architecture for RGB-Infrared Object Detection 18th

CSFuser: A Cascade Siamese Fusion Architecture for RGB-Infra...

引用

18th International Conference on Neural Networks (ISNN)

作者： Li, Ziyi Zhang, Gang Zeng, Zhigang Hu, Xiaolin Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Tsinghua Univ THU Bosch JCML Ctr BNRist Dept Comp Sci & Technol Beijing 100084 Peoples R China Educ Minist China Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China

ISBN: (纸本)9789819743988;9789819743995

RGB-Infrared multi-modal object detection harnesses diverse and complementary information from RGB and infrared images, offering significant advantages in intelligent transportation. The primary challenge lies in the effective fusion of RGB and infrared images. Presently, the fusion process is hindered by two aspects: firstly, the misalignment between RGB and infrared images complicates the fusion process;secondly, the substantial differences in features between the two modalities impede the learning of complementary features. Existing fusion architectures often overlook these challenges or prioritize the RGB data, thereby neglecting the full potential of infrared data. To address these challenges, we introduce Multi-scale Attention-based Complementary Fusion (MACF) module, a straightforward yet effective feature fusion module embedded within the cascade siamese architecture. A lightweight alignment module is designed to align the two modalities before feature extraction. Through progressive fusion of RGB and infrared features, CSFuser addresses challenges directly. Extensive experiments on the DENSE dataset under adverse conditions like heavy snow, rain, and fog demonstrates CSFuser's superiority over the leading method, HRFuser, while being 2x faster. The excellent performance underscores our method's ability to effectively fuse RGB and infrared images. The codes will be made publicly available.

关键词： Object detection Siamese network Multi-modal fusion

来源：评论

学校读者我要写书评

暂无评论

Double Low-rank Based Matrix Decomposition for Surface Defect Segmentation of Steel Sheet

引用

ISIJ INTERNATIONAL 2021年第7期61卷 2111-2121页

作者： Zhou, Shiyang Wu, Shiqian Cui, Ketao Liu, Huaiguang Wuhan Univ Sci & Technol Sch Machinery & Automat Minist Educ Key Lab Met Equipment & Control Technol Wuhan 430081 Peoples R China Huazhong Univ Sci & Technol Minist Educ Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China

Despite advances in surface defect segmentation of steel sheet, it is still far from meeting the needs of real-world applications due to some method usually lack of adaptiveness to different shape, size, location and texture of defect object. Based on the assumption that each defect image is composed of defect-free background components that reflect the similarities of different regions and defect foreground components that reflect unique object information, we formulate the segmentation task as an image decomposition problem. To this end, we develop a double low-rank based matrix factorization framework for decomposing the surface defect image into defect foreground image and defect-free background image. Furthermore, considering the similarity of the defect-free background sub-regions and the defective sub-regions, Laplacian and sparse regularization terms are introduced into the matrix decomposition framework to improve their representation ability and discriminative ability. Importantly, the proposed method is unsupervised and training-free, so it does not requiring a large number of training samples with time-consuming manual labels. Experimental results on synthetic and real-world surface defect images show that the proposed method outperforms some state-of-the-art approaches in terms of both subjective and objective experiments.

关键词： surface defect of steel sheet image segmentation low-rank matrix decomposition

来源：评论

学校读者我要写书评

暂无评论

Jointly Class-specific and Shared Discriminative Dictionary Learning for Classifying Surface Defects of Steel Sheet

引用

ISIJ INTERNATIONAL 2021年第11期61卷 2773-2784页

作者： Zhou, Shiyang Liu, Huaiguang Cui, Ketao Ha, Zhiqiang Wuhan Univ Sci & Technol Sch Machinery & Automat Minist Educ Key Lab Met Equipment & Control Technol Wuhan 430081 Peoples R China Huazhong Univ Sci & Technol Minist Educ Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China

For surface defect images that captured from a practical steel production line, feature extraction for classification is a challenging task due to inter-class similarity and intra-class difference of defect images. In this paper, we propose a class-specific and shared discriminative dictionary learning (CASDDL) method for extracting discriminative class-specific features to classify surface defects of steel sheet. Specifically, we learn a shared sub-dictionary as well as several class-specific sub-dictionaries to explicitly capture common information shared by all classes and class-specific information belonging to corresponding class. We adopt a mutual incoherence constrain for each sub-dictionary to encourage learned sub-dictionaries to be as independent as possible. A Fisher-like discriminative criterion is also introduced to coding vectors over all the class-specific sub-dictionaries, which can indirectly improve the discriminative ability of learned dictionary. In addition, we further impose a low-rank constrain on coding vector over shared sub-dictionary to guarantee learned dictionary has the abilities of same class of samples itself reconstruction and different class of samples reconstruction. Finally, classification can be efficiently performed by discriminative coding vector that obtained from a reconstructive and discriminative dictionary. Experimental results demonstrate that our proposed CASDDL method achieves a comparable or better performance than the state-of-the-art dictionary learning methods in classifying surface defects of steel sheet.

关键词： class-specific and shared dictionary discriminative dictionary learning image classification surface defects of steel sheet

来源：评论

学校读者我要写书评

暂无评论

A novel adaptive event-triggered controller for exponential quasi-synchronization and synchronization problems to coupled inertial memristive neural networks with time delays☆

引用

JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS 2025年 460卷

作者： Jiang, Ping Chen, Jiejie Chen, Boshan Zeng, Zhigang Hubei PolyTech Univ Comp Sch Huangshi 435002 Peoples R China Hubei Normal Univ Coll Comp Sci & Informat Engn Huangshi 435002 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Educ Minist China Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China Hubei Normal Univ Coll Math & Stat Huangshi 435002 Peoples R China

In this paper, we study the quasi-synchronization and synchronization problems for a coupled inertial delayed memristive neural networks (CIDMNNs) via adaptive event-triggered control. An adaptive event-triggered controller is designed, and a new Lyapunov function method is used to prove that the quasi-synchronization of CIDMNN is realized under this controller. As a corollary, some sufficient conditions to ensure the exponential synchronization of CIDMNNs are obtained. Finally, Numerical results validate the theoretical analysis, showing significant improvements in synchronization performance, including reduced control input and enhanced system stability.

关键词： Inertial delayed memristive neural networks Adaptive technique Event-triggered strategy Exponential quasi-synchronization

来源：评论

学校读者我要写书评

暂无评论

Spiking neural P systems with cooperative synapses

引用

NEUROCOMPUTING 2022年 501卷 222-230页

作者： Zhang, Luping Xu, Fei Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Informat Proc Wuhan 430074 Hubei Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Intelligent Control Educ Minist China Wuhan 430074 Hubei Peoples R China

Spiking neural P systems (SN P systems) are a class of neuron-inspired computation models, where each synapse independently passes a spike produced by the pre-synaptic neuron to the post-synaptic neuron. Motivated by the mechanism of cooperative synapses in biological systems, we propose a variant of SN P systems called spiking neural P systems with cooperative synapses (SNPCS systems). Specifically, for a set of cooperative synapses in an SNPCS system, if all the synapses in the set have spikes passing through, then each post-synaptic neuron of these synapses receives a unit positive potential;if some synapses in the set, instead of all, have spikes passing through, then each post-synaptic neuron of the synapses passing spikes through receives a unit negative potential. The computation power of SNPCS systems is investigated. It is proved that SNPCS systems are Turing universal as function computing devices. Moreover, SNPCS systems are constructed to solve the NP-hard problem, the Subset Sum problem, in a uniform way.(c) 2022 Elsevier B.V. All rights reserved.

关键词： Bio-inspired computing Membrane computing Spiking neural P system Subset Sum problem Cooperative synapse

来源：评论

学校读者我要写书评

暂无评论

Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity

arXiv

引用

arXiv 2024年

作者： Zhang, Huaxin Xu, Xiaohao Wang, Xiang Zuo, Jialong Huang, Xiaonan Gao, Changxin Zhang, Shanjun Yu, Li Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China University of Michigan Ann Arbor United States Kanagawa University Japan

How can we enable models to comprehend video anomalies occurring over varying temporal scales and contexts? Traditional Video Anomaly Understanding (VAU) methods focus on frame-level anomaly prediction, often missing the interpretability of complex and diverse real-world anomalies. Recent multimodal approaches leverage visual and textual data but lack hierarchical annotations that capture both short-term and long-term anomalies. To address this challenge, we introduce HIVAU-70k, a large-scale benchmark for hierarchical video anomaly understanding across any granularity. We develop a semi-automated annotation engine that efficiently scales high-quality annotations by combining manual video segmentation with recursive free-text annotation using large language models (LLMs). This results in over 70,000 multi-granular annotations organized at clip-level, event-level, and video-level segments. For efficient anomaly detection in long videos, we propose the Anomaly-focused Temporal Sampler (ATS). ATS integrates an anomaly scorer with a density-aware sampler to adaptively select frames based on anomaly scores, ensuring that the multimodal LLM concentrates on anomaly-rich regions, which significantly enhances both efficiency and accuracy. Extensive experiments demonstrate that our hierarchical instruction data markedly improves anomaly comprehension. The integrated ATS and visual-language model outperform traditional methods in processing long videos. Our benchmark and model are publicly available at https: //***/pipixin321/HolmesVAU. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Mixture-of-Experts for Open Set Domain Adaptation: A Dual-Space Detection Approach

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年

作者： Du, Zhenbang An, Jiayu Tu, Yunlu Hong, Jiahao Wu, Dongrui Key Laboratory of the Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

Open Set Domain Adaptation (OSDA) copes with the distribution and label shifts between the source and target domains simultaneously, performing accurate classification for known classes while identifying unknown class samples in the target domain. Most existing OSDA approaches, depending on the final image feature space of deep models, require manually-tuned thresholds, and may easily misclassify unknown samples as known classes. Mixture-of-Experts (MoE) could be a remedy. Within an MoE, different experts handle distinct input features, producing unique expert routing patterns for various classes in a routing feature space. As a result, unknown class samples may display different expert routing patterns to known classes. This paper proposes Dual-Space Detection, which exploits the inconsistencies between the image feature space and the routing feature space to detect unknown class samples without any threshold. A Graph Router is further introduced to better make use of the spatial information among the image patches. Experiments on three datasets validated the effectiveness and superiority of our approach. © 2020 IEEE.

关键词： Mixture-of-Experts Open Set Domain Adaptation Routing Feature

来源：评论

学校读者我要写书评

暂无评论

Phenotyping multiple maize ear traits from a single image: Kernels per ear, rows per ear, and kernels per row*

引用

COMPUTERS AND ELECTRONICS IN AGRICULTURE 2022年 193卷 106681-106681页

作者： Shi, Min Zhang, Shuaisong Lu, Hao Zhao, Xiaoming Wang, Xiqing Cao, Zhiguo Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Minist Educ Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China China Agr Univ Coll Biol Sci Ctr Crop Funct Genom & Mol Breeding Beijing 100193 Peoples R China

Certain traits of maize ears, such as kernels per ear, kernels per row, and rows per ear, are highly related with the grain yield and stress resistance. They can be used as quantitative indices for selecting superior varieties and analyzing experimental results in maize breeding. However, these traits are often manually obtained, which is laborious and prone to error. image-based object counting methods can replace the manual counting procedure safely, which is fast and accurate. Although a constellation of methods have been proposed, problems remain: i) classic image processing-based methods are not robust to variations of illuminations and resolutions;ii) deep learning-based object counting methods can only predict the total kernels per ear. To address this, we propose a high-throughput maize ear phenotyping pipeline. From a single image, our pipeline estimates kernels per ear, rows per ear, and kernels per row in an interpretable way. The image is first input into a Maize Kernel Counting Network (MKNet), which outputs the estimated kernel density map. Then, receiving the density map as input, a Row Mask Generator (RMG) generates a series of masks;each covers a ear row. Naturally, rows per ear and kernels per row can be recovered from the masks. Extensive experiments show that our method can predict kernels per ear, rows per ear, and kernels per row precisely, with a mean absolute error of 7.48, 0.32 and 1.07, respectively. The results show that, compared with existing object counting methods, MKNet can not only reduce the counting error on kernels per ear, but also produce more accurate localization of maize kernels. The visualizations also demonstrate that RMG is robust to the irregular shapes of ear rows.

关键词： Maize kernel counting Convolutional neural network Kernels per row Rows per ear Deep learning

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：