检索结果-内蒙古大学图书馆

Synchronization in Multiple Neural Networks With Delay and Disconnected Switching Topology via Event-Triggered Impulsive control Strategy

引用

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS 2021年第3期68卷 2491-2500页

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

In this article, an event-triggering impulsive control strategy is proposed, in which the impulsive time sequence can be different from the event-triggered time sequence. The synchronization problems of a multiple neural network with delay (MDNN) and the directed disconnected switching topology are discussed by using this strategy. The considered switching topology is assumed to be directed and sequentially or jointly connected. The combined measurement method is adopted in the event-triggering strategy, so that each delayed neural network only updates the control rules at the moment of its event triggering. First, we prove that the designed event-triggering rules can avoid Zeno behavior. Then, the sufficient conditions of event-based quasi-synchronization (synchronization) for the MDNN can be obtained by using the iterative method. In addition, as an extension, the case of a jointly connected topology and the case of a pure impulsive control protocol are considered, too. Finally, a numerical example is provided to test the results in theory analysis.

关键词： Synchronization Switches Topology Network topology Delays Artificial neural networks Event triggered impulsive control multiple neural networks (MNNs) switching topology synchronization

来源：评论

学校读者我要写书评

暂无评论

OadTR: Online action detection with transformers

arXiv

引用

arXiv 2021年

作者： Wang, Xiang Zhang, Shiwei Qing, Zhiwu Shao, Yuanjie Zuo, Zhengrong Gao, Changxin Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China DAMO Academy Alibaba Group China

Most recent approaches for online action detection tend to apply Recurrent Neural Network (RNN) to capture long-range temporal structure. However, RNN suffers from non-parallelism and gradient vanishing, hence it is hard to be optimized. In this paper, we propose a new encoder-decoder framework based on Transformers, named OadTR, to tackle these problems. The encoder attached with a task token aims to capture the relationships and global interactions between historical observations. The decoder extracts auxiliary information by aggregating anticipated future clip representations. Therefore, OadTR can recognize current actions by encoding historical information and predicting future context simultaneously. We extensively evaluate the proposed OadTR on three challenging datasets: HDD, TVSeries, and THUMOS14. The experimental results show that OadTR achieves higher training and inference speeds than current RNN based approaches, and significantly outperforms the state-of-the-art methods in terms of both mAP and mcAP. Code is available at https://***/wangxiang1230/OadTR. Copyright © 2021, The Authors. All rights reserved.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

An imbalance aware lithography hotspot detection method based on HDAM and pre-trained GoogLeNet

引用

MEASUREMENT SCIENCE AND TECHNOLOGY 2021年第12期32卷 125008-125008页

作者： Zhou, Kaibo Zhang, Kaifeng Liu, Jie Liu, Yanan Liu, Shiyuan Cao, Guannan Zhu, Jinlong Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Minist China Key Lab Image Informat Proc & Intelligent Control Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Civil & Hydraul Engn Wuhan 430074 Peoples R China Univ Illinois Dept Elect & Comp Engn Ctr Computat Electromagnet Urbana IL 61801 USA Huazhong Univ Sci & Technol State Key Lab Digital Mfg Equipment & Technol Wuhan 430074 Peoples R China

Due to the continuous shrinkage of transistor size and the ever-increasing complexity of integrated circuit design layout, great challenges arise in optical lithography-any defect on the mask will be transferred to the silicon wafer, which may lead to severe defects such as open circuit and short circuit. These defects on masks are called hotspots. Before transferring the circuit layout on the mask to the silicon wafer, the entire mask must be inspected to accurately find out the hotspots before optical lithography. Although traditional lithography hotspot detection approaches, such as pattern matching and machine learning, have gained satisfactory results the performance of the model degrades when encountering problems such as complex layout and data imbalance. In this paper, a hotspot detection method based on hybrid data enhancement, data compression and pre-trained GoogLeNet is proposed to solve the aforementioned problems. Our study shows that the average recall rate can be up to 98.3%. Meanwhile, the false alarm is reduced and the F1-score is 63.5%. Experimental results show that the proposed method achieves better performance on the ICCAD 2012 contest benchmark compared to hotspot detection methods based on deep or representative machine learning.

关键词： very large scale integration (VLSI) hotspot detection hybrid data augment method data compression deep learning

来源：评论

学校读者我要写书评

暂无评论

Fault prognosis control of solid oxide fuel cell system based on health evaluation

引用

INTERNATIONAL JOURNAL OF HYDROGEN ENERGY 2021年第77期46卷 38425-38450页

作者： Cheng, Tianliang Qin, Hongchuan Cheng, Zhe Yan, Dong Jia, Lichao Jiang, Jianhua Li, Jian Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Educ Minist Image Proc & Intelligent Control Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Mat Sci & Engn State Key Lab Mat Proc & Dye & Mold Technol Wuhan 430074 Peoples R China Forschungszentrum Julich GmbH Electrochem Proc Engn IEK 14 Inst Energy & Climate Res Julich Germany Rhein Westfal TH Aachen Fac Mech Engn Aachen Germany

High cost and short life-span hinder the large-scale commercial application of solid oxide fuel cell technology. System performance inevitably degrades and gradually evolves into faults in the long run, leading to the change of system input-output characteristics. The control system designed based on initial conditions faces with problems such as parameter mismatch, inaccurate control and even wrong control laws. This paper proposes an adaptive control strategy to enable the system controller to cope with degradation and fault phenomena in real systems. The system characteristics under different degradation and fault conditions are investigated. A novel health evaluation system is developed, where an early fault identification and pretreatment approach based on optimal operation point optimization model and fuzzy neural network are adopted for control optimization. Simulation results show that the enhanced system controller can improve system efficiency by about 2% and prolong life-span significantly with the reality of degradation and fault mechanisms. (c) 2021 Hydrogen Energy Publications LLC. Published by Elsevier Ltd. All rights reserved.

关键词： SOFC system Performance degradation principle Fault evolution mechanism Multi-mode model Health evaluation system control optimization

来源：评论

学校读者我要写书评

暂无评论

Dual robust regression for pattern classification

引用

INFORMATION SCIENCES 2021年 546卷 1014-1029页

作者： Qian, Jianjun Zhu, Shumin Wong, Wai Keung Zhang, Hengmin Lai, Zhihui Yang, Jian Nanjing Univ Sci & Technol Sch Comp Sci & Engn Key Lab Intelligent Percept & Syst High Dimens In Minist EducPCA Lab Nanjing Peoples R China Nanjing Univ Sci & Technol Jiangsu Key Lab Image & Video Understanding Socia Sch Comp Sci & Engn Nanjing Peoples R China Hong Kong Polytech Univ Inst Text & Clothing Hong Kong Peoples R China East China Univ Sci & Technol Key Lab Adv Control & Optimizat Chem Proc Minist Educ Shanghai Peoples R China Shenzhen Univ Coll Comp Sci & Software Engn Shenzhen Peoples R China

Linear regression-based and extended methods have been widely used in pattern classification. These methods can be roughly divided into two categories: reconstruction error based methods and discriminative methods. The reconstruction error-based methods search the target label by learning the representation coefficients to compute the minimal reconstruction error. The goal of the discriminative methods is to learn the projection matrix to predict the target label of the image. To combine the advantages of these two kinds of regression-based methods, this paper presents a dual robust regression framework (DualRR) for pattern classification. In the training stage, a double low-rank robust regression model (DLR) is proposed to learn the projection matrix. In DLR, low-rank robust regression motivates us to model the data as the sum of a low-rank clean data and sparse noise matrix. The low-rank is further used to constrain the projection matrix to enhance the discriminative performance. In the testing stage, the proposed framework employs a robust regression representation model to learn the optimal representation coefficients and obtain the reconstruction sample to approximate the test sample. We thus apply the reconstruction sample to search the classification label by using the projection matrix learned in the training stage. Extensive experiments are conducted on six public available databases, namely, LFW, FRGC, CUHK Sketch, PolyU Palm, NUST-RF and Caltech 101, demonstrating the merits of the proposed model over state-of-the-art regression-based classification methods. (c) 2020 Elsevier Inc. All rights reserved.

关键词： Robust regression Pattern classification Low-rank Sparse representation

来源：评论

学校读者我要写书评

暂无评论

Self-supervised learning for semi-supervised temporal action proposal

arXiv

引用

arXiv 2021年

作者： Wang, Xiang Zhang, Shiwei Qing, Zhiwu Shao, Yuanjie Gao, Changxin Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China DAMO Academy Alibaba Group China

Self-supervised learning presents a remarkable performance to utilize unlabeled data for various video tasks. In this paper, we focus on applying the power of self-supervised methods to improve semi-supervised action proposal generation. Particularly, we design an effective Self-supervised Semi-supervised Temporal Action Proposal (SSTAP) framework. The SSTAP contains two crucial branches, i.e., temporal-aware semi-supervised branch and relation-aware self-supervised branch. The semi-supervised branch improves the proposal model by introducing two temporal perturbations, i.e., temporal feature shift and temporal feature flip, in the mean teacher framework. The self-supervised branch defines two pretext tasks, including masked feature reconstruction and clip-order prediction, to learn the relation of temporal clues. By this means, SSTAP can better explore unlabeled videos, and improve the discriminative abilities of learned action features. We extensively evaluate the proposed SSTAP on THUMOS14 and ActivityNet v1.3 datasets. The experimental results demonstrate that SSTAP significantly outperforms state-of-the-art semi-supervised methods and even matches fully-supervised methods. Code is available at https://***/wangxiang1230/SSTAP. © 2021, CC BY.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Memristive Quantized Neural Networks: A Novel Approach to Accelerate Deep Learning On-Chip

引用

IEEE TRANSACTIONS ON CYBERNETICS 2021年第4期51卷 1875-1887页

作者： Zhang, Yang Cui, Menglin Shen, Linlin Zeng, Zhigang Shenzhen Univ Natl Engn Lab Big Data Syst Comp Technol Guangdong Key Lab Intelligent Informat Proc Comp Vis InstSch Comp Sci & Software Engn Shenzhen 518060 Peoples R China Univ Massachusetts Dept Elect & Comp Engn Amherst MA 01003 USA Univ Nottingham Sch Comp Sci Ningbo 315100 Peoples R China Shenzhen Univ Sch Comp Sci & Software Engn Comp Vis Inst Natl Engn Lab Big Data Syst Comp Technol Shenzhen 518060 Peoples R China Shenzhen Univ Guangdong Key Lab Intelligent Informat Proc Shenzhen 518060 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

Existing deep neural networks (DNNs) are computationally expensive and memory intensive, which hinder their further deployment in novel nanoscale devices and applications with lower memory resources or strict latency requirements. In this paper, a novel approach to accelerate on-chip learning systems using memristive quantized neural networks (M-QNNs) is presented. A real problem of multilevel memristive synaptic weights due to device-to-device (D2D) and cycle-to-cycle (C2C) variations is considered. Different levels of Gaussian noise are added to the memristive model during each adjustment. Another method of using memristors with binary states to build M-QNNs is presented, which suffers from fewer D2D and C2C variations compared with using multilevel memristors. Furthermore, methods of solving the sneak path issues in the memristive crossbar arrays are proposed. The M-QNN approach is evaluated on two image classification datasets, that is, ten-digit number and handwritten images of mixed National Institute of Standards and Technology (MNIST). In addition, input images with different levels of zero-mean Gaussian noise are tested to verify the robustness of the proposed method. Another highlight of the proposed method is that it can significantly reduce computational time and memory during the process of image recognition.

关键词： Memristors Neural networks Acceleration System-on-chip Training Memory management Device-to-device communication Acceleration crossbar array image processing image recognition memristor quantized convolutional neural networks (CNNs)

来源：评论

学校读者我要写书评

暂无评论

Weakly supervised person search with region siamese networks

arXiv

引用

arXiv 2021年

作者： Han, Chuchu Su, Kai Yu, Dongdong Yuan, Zehuan Gao, Changxin Sang, Nong Yang, Yi Wang, Changhu Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology ByteDance University of Technology Sydney

Supervised learning is dominant in person search, but it requires elaborate labeling of bounding boxes and identities. Large-scale labeled training data is often difficult to collect, especially for person identities. A natural question is whether a good person search model can be trained without the need of identity supervision. In this paper, we present a weakly supervised setting where only bounding box annotations are available. Based on this new setting, we provide an effective baseline model termed Region Siamese Networks (R-SiamNets). Towards learning useful representations for recognition in the absence of identity labels, we supervise the R-SiamNet with instance-level consistency loss and cluster-level contrastive loss. For instance-level consistency learning, the R-SiamNet is constrained to extract consistent features from each person region with or without out-of-region context. For cluster-level contrastive learning, we enforce the aggregation of closest instances and the separation of dissimilar ones in feature space. Extensive experiments validate the utility of our weakly supervised method. Our model achieves the rank-1 of 87.1% and mAP of 86.0% on CUHK-SYSU benchmark, which surpasses several fully supervised methods, such as OIM [36] and MGTS [4], by a clear margin. More promising performance can be reached by incorporating extra training data. We hope this work could encourage the future research in this field. Copyright © 2021, The Authors. All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Transition in collective motion decision making

引用

Physical Review E 2022年第1期106卷 014611-014611页

作者： Biao Wang Yue Wu Guangwei Wang Lan Liu Guanrong Chen Hai-Tao Zhang School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control State Key Laboratory of Digital Manufacturing Equipment and Technology Huazhong University of Science and Technology Wuhan 430074 China National Engineering Laboratory for Educational Big Data Central China Normal University Wuhan 430079 China Department of Electrical Engineering City University of Hong Kong Hong Kong SAR China

Collective decision making in a biological motion group requires fast and robust transmission of information. Typically, directional switching information propagation across the whole group obeys a linear dispersion law. However, conventional dynamic collective motion models, such as the Vicsek model and the Couzin model did not take into account ultrafast directional synchronous motions. In the present paper, a multiparticle model is proposed based on inertial spin self-propel action, which can provide adequate description of such group motion. By considering both spin mechanism and collision avoidance, the proposed self-propelled particle spin model can nicely describe collective motion with fast directional switching. By analyzing the order parameter of the group-velocity synchronization, a mechanism of group decision making is revealed, which is based on the difference between two clusters of divergent leaders, showing a transition from the compromising phase (i.e., following the group average) to the preferred phase (i.e., aligning to a leader cluster). The finding provides new insight to the decision-making process of followers when they face with divergent leaders in group motion.

关键词： Collective behavior in networks Network phase transitions Pattern formation Self-organized systems

来源：评论

学校读者我要写书评

暂无评论

Cooperative Stabilization control of the Linear Time-invariant System Based on Distributed Observers

Cooperative Stabilization Control of the Linear Time-invaria...

引用

Chinese Automation Congress (CAC)

作者： Li, Min Liu, Zhi-Wei Chi, Ming Zhang, Jia-Hao Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Minist Educ Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China

ISBN: (纸本)9781728176871

In this paper, the cooperative stabilization problem of linear time-invariant (LTI) systems is studied based on a class of distributed Luenberger observers. A given LTI system is estimated by a network of observers. In case of observability configuration or external attack, each observer has to possess different measurement output of the LTI system. Classical distributed control strategies cannot be directly used because they are assumed to obtain identical information. In view of this problem, a class of distributed observers are designed under an undirected graph, which can recover the state of the LTI system by limited local information. By using any single channel of the estimated state, a control input is proposed to stabilize the LTI system. By analysing the stability of an augmented system which involves the LTI system and the estimation error system, some necessary and sufficient conditions arc derived for the existence of control gains that guarantee the stabilization of the LTI system. In addition, some algorithms are proposed to specify the control gains. Lastly, some simulation examples are given to verify the effectiveness of the theoretical result.

关键词： distributed observers stabilization state omniscience global observability

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：