检索结果-内蒙古大学图书馆

data Driven Control and Learning Systems (DDCLS)

作者： Hao Wu YingHao Zhao Xu Yang Jian Huang Jiarui Cui Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing China

Driven by the increasing needs for production safety, a fault detection method based on multi-sensor fusion with adaptive weight coefficients is proposed in this paper to make full use of multi-measuring points information. To this end, considering the different information among multi-measuring points, the variance contribution rate (VCR) of vibration signals are used to design adaptive weight coefficients for data fusion to fully utilize the information contained in each vibration signal. On this basis, the least atoms contain time domain and frequency domain are extracted based on dictionary sparse representation (DSR) algorithm to represent the feature information of the original signal to weaken the influence of the curse of dimensionality. Finally, K-nearest neighbor distance is used in sparse residual space (SRS) for fault detection (K-SRS). The effectiveness of the proposed method is demonstrated by the rolling bearings data, and results show the advantage of our proposed approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A fuzzy relational clustering algorithm with q-weighted medoids

引用

Journal of Computational Information Systems 2014年第6期10卷 2389-2396页

作者： Gao, Ying Qi, Hong Liu, Dayou Li, Jiafei Li, Lina College of Computer Science and Technology Jilin University Changchun 130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun 130012 China

Medoids-based fuzzy relational clustering generates clusters of objects based on relational data, which records pairwise similarity or dissimilarities among objects. Compared with single-medoid based approaches, multiple-weighted medoids has shown superior performance in clustering. In this paper, we present a new version of fuzzy relational clustering in this family called fuzzy clustering with q weighted medoids (FQMdd). Based on the objective function of FQMdd, the update of memberships, prototypes of each cluster and weights are given. Compared with two existing fuzzy relational clustering approaches fuzzy c-medoids (FCMdd) and fuzzy clustering with multi-medoids (FMMdd), FQMdd can represent rich cluster-based information by multiple-weighted objects and strengthen contribution of core objects in clusters as well. Experiments on synthetic and real-world datasets show that FQMdd mostly has higher clustering accuracy than FCMdd and FMMdd. Copyright © 2014 Binary Information Press.

关键词： Fuzzy clustering

来源：评论

学校读者我要写书评

暂无评论

key Value Ordering Heuristic for Solving Algorithm Based on the AC-4 Algorithm

Key Value Ordering Heuristic for Solving Algorithm Based on ...

引用

2010 International Conference on Computer,Mechatronics,Control and Electronic engineering(2010计算机、机电、控制与电子工程国际会议 CMCE 2010)

作者： Zhan-shan Li Hai-jiao Shen Hui-ying Du Zi-wen Wang School of Computer Science and Technology Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University ChangchunChina

ISBN: (纸本)9781424479573

We have studied the AC-4 algorithm and then present key value ordering heuristic forming the new solving algorithm BT-KVV, which is based on the AC-4 algorithm. This algorithm takes full advantage of the state information of the data structure used in the AC-4 algorithm after the process of arc consistency. The algorithm sorts the values of the variables' domain according to the key importance of the values. So this order forces the solving algorithm to give priority to extend the key values of variables. In this way, the efficiency of the solving algorithm can be improved a lot. The result of our experiments shows that our algorithm has much more advantage over other solving algorithms.

关键词： arc consistency AC-4 value ordering heuristic solving algorithm key value

来源：评论

学校读者我要写书评

暂无评论

Load balance and time delay efficient algorithm for VNF service chain deployment based on DQN 18

Load balance and time delay efficient algorithm for VNF serv...

引用

18th International Conference on Computational Intelligence and Security, CIS 2022

作者： Xuan, Hejun Lin, Lidan Liu, Zhenghui Zhao, Xuelin Xinyang Normal University Department of Computer and Information Technology China Big Data Xinyang Normal University Henan Key Laboratory of Analysis and Applications of Education Xinyang Henan China Luo He Vocational Technology College Department of Information Engineering Luohe Henan China

ISBN: (纸本)9798350346275

In mobile edge computing, computing and storage resources are close to the network of the user device, which can effectively reduce network access and computing service delay. However, network function virtualization for mobile edge computing networks is more challenging due to the strong coupling of CPU resources, storage resources, and wireless resources. In order to solve the problems of load balance and long response time of user-oriented service function chain deployment algorithm in mobile edge computing networks, this paper proposed a load balance and time delay efficient algorithm (denoted as LBDQN) for virtual network function service chain deployment problem based Deep Q-LearningFirst, a global optimization model, which minimizes time delay and maximizes the load balance, is established. Then, a new real-time algorithm for VNF service chain deployment based on DQN is proposed. In this algorithm, an adaptive ϵ-greedy method is designed. In addition, a particle swarm optimization is used to optimize the neural network parameters. To demonstrate the efficiency of the proposed algorithm, some simulation experiments are conducted and the experimental results show that the algorithm can effectively reduce the time delay and improve the load balance than the compared algorithms. © 2022 IEEE.

关键词： Time delay

来源：评论

学校读者我要写书评

暂无评论

A real time multi-focus image fusion framework

引用

Journal of Information and Computational Science 2014年第4期11卷 1295-1302页

作者： Liu, Zhaojun Li, Xiongfei Zhang, Xiaoli Key Laboratory of Symbolic Computation and Knowledge Engineering for Ministry of Education Jilin University Changchun 130012 China College of Computer Science and Technology Jilin University Changchun 130012 China

In this paper, we proposed a new image fusion scheme on spatial domain. The interest of the scheme is its real time. The framework contains two steps: saliency detection and coefficient selection based on the principle of maximum saliency preservation. Mean Square Error, Average Gradient and Spectral Residual Approach are adopted to detect the saliency of original images. Two group of experimental data are shown, and results shown that the image fusion framework works well, and Spectral Residual Approach base fusion scheme performs best among the three schemes. 1548-7741/Copyright © 2014 Binary Information Press.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Multi-objective evolutionary optimization for hardware-aware neural network pruning

引用

Fundamental Research 2024年第4期4卷 941-950页

作者： Wenjing Hong Guiying Li Shengcai Liu Peng Yang Ke Tang Guangdong Provincial Key Laboratory of Brain-Inspired Inteligent Computation Department of Computer Science and EngineeringSouthern University of Science and TechnologyShenzhen 518055China Research Institute of Trustworthy Autonomous Systems Southern University of Science and TechnologyShenzhen 518055China Department of Statistics and Data Science Southern University of Science and TechnologyShenzhen 518055China

Neural network pruning is a popular approach to reducing the computational complexity of deep neural *** recent years,as growing evidence shows that conventional network pruning methods employ inappropriate proxy metrics,and as new types of hardware become increasingly available,hardware-aware network pruning that incorporates hardware characteristics in the loop of network pruning has gained growing attention,Both network accuracy and hardware efficiency(latency,memory consumption,etc.)are critical objectives to the success of network pruning,but the conflict between the multiple objectives makes it impossible to find a single optimal *** studies mostly convert the hardware-aware network pruning to optimization problems with a single *** this paper,we propose to solve the hardware-aware network pruning problem with Multi-Objective Evolutionary Algorithms(MOEAs).Specifically,we formulate the problem as a multi-objective optimization problem,and propose a novel memetic MOEA,namely HAMP,that combines an efficient portfoliobased selection and a surrogate-assisted local search,to solve *** studies demonstrate the potential of MOEAs in providing simultaneously a set of alternative solutions and the superiority of HAMP compared to the state-of-the-art hardware-aware network pruning method.

关键词： Multi-objective optimization Evolutionary algorithm Neural network pruning Hardware-awaremachine learning Hardware efficiency

来源：评论

学校读者我要写书评

暂无评论

A Low-Area Overhead Secure Scan Architecture Resisting Scan-Based Attacks for Crypto Chips

A Low-Area Overhead Secure Scan Architecture Resisting Scan-...

引用

2017 International MultiConference of Engineers and Computer Scientists, IMECS 2017

作者： Weizheng, Wang Jincheng, Wang Shuo, Cai Peng, Liu Tieqiao, Liu College of Computer and Communication Engineering Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science and Technology Changsha Hunan410114 China College of Computer and Communication Engineering Changsha University of Science and Technology Changsha410114 China College of Computer and Communication Engineering Changsha University of Science and Technology Changsha410114 China Information Science and Engineering Department Hunan University Changsha410082 China Management School Hangzhou Dianzi University Hangzhou310018 China

ISBN: (纸本)9789881404732

Scan design is a widely used design-for-testability (DFT) technique that improves the controllability and observability of integrated circuits (ICs) resulting in the facilitation of the testing. However, it can also be used to access secret information of crypto chips, and thus threaten dramatically the security of the cipher keys. In this paper, we propose a secure scan DFT architecture to thwart scan-based side-channel attacks. This architecture provides the scan chain reset mechanism, and thus can prevent these attacks based on mode switching. Meanwhile, the secret key is isolated from scan chains of an advanced encryption standard (AES) design in the test mode. Therefore, it can also halt the test-mode-only scan attacks. The proposed secure scan DFT technique ensures the security without compromising the testability of original chip. Most important of all, the secure scan test is implemented with extremely low hardware overhead.

关键词： Design for testability

来源：评论

学校读者我要写书评

暂无评论

High-precision FMCW ranging with a hybrid-integrated external cavity laser

High-precision FMCW ranging with a hybrid-integrated externa...

引用

2023 Opto-Electronics and Communications Conference, OECC 2023

作者： Liu, Chuxin Xu, Ruiyang Xu, Weihan Lu, Liangjun Guo, Yuyao Li, Yu Chen, Jianping Zhou, Linjie Shanghai Jiao Tong University State Key Laboratory of Advanced Optical Communication Systems and Networks Shanghai Key Lab of Navigation and Location Services Shanghai Institute for Advanced Communication and Data Science Department of Electronic Engineering Shanghai China SJTU-Pinghu Institute of Intelligent Optoelectronics Pinghu China Shanghai314200 China

We implement an analog EO-PLL for a III/V-Si3N4 hybrid integrated ECL to generate a highly-linear FMCW signal over multiple wavelengths. A high range precision of 4.2 cm is achieved for a 200-m distance. © 2023 I... 详细信息

ISBN: (纸本)9781665462136

关键词： Continuous wave lasers

来源：评论

学校读者我要写书评

暂无评论

Extreme Large Margin Distribution Machine and its applications for biomedical datasets

Extreme Large Margin Distribution Machine and its applicatio...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Zhiyong Yang Jingcheng Lu Taohong Zhang Department of Computer University of Science and Technology Beijing (USTB) Beijing China Beijing Key Laboratory of Knowledge Engineering for Materials Science Beijing China

ISBN: (纸本)9781509016129

Classification methods has become increasingly popular for biomedical and bioinformatical data analysis. However, due to the difficulty of data acquisition, sometimes we could only obtain small-scale datasets which may leads to unreasonable generalization performances. For SVM-like algorithms, we could resort to Large Margin theory to find out solutions for such dilemma. Recent studies on large margin theory show that, besides maximizing the minimum margin of a given training dataset, it is also necessary to optimization the margin distribution to boost the overall generalization ability. Correspondingly, a novel SVM-like algorithm called Large Margin Distribution Machine (LDM) realizes this idea by maximizing the average of margin and minimizing the variance of margin simultaneously. And a series of applications has been reported thereafter. There is another well-known machine learning algorithm called Extreme Learning Machine (ELM) which shares similar framework with SVM. It is believed in this paper ELM could also benefit from the virtues of margin distribution optimization. Bearing this in mind, a novel algorithm called Extreme Large Margin Distribution Machine(ELDM) is proposed in this paper by bridging the advantages of ELM and LDM. And an efficient extension of ELDM for multi-class classifications under One vs. All Scheme is proposed subsequently. Finally, the experiment results on both benchmark datasets and biomedical classification datasets show the effectiveness of our proposed algorithm.

关键词： Heart Glass Training Support vector machines Algorithm design and analysis Diabetes Kernel

来源：评论

学校读者我要写书评

暂无评论

Linear(hull) cryptanalysis of round-reduced versions of KATAN 2

Linear(hull) cryptanalysis of round-reduced versions of KATA...

引用

2nd International Conference on Information Systems Security and Privacy, ICISSP 2016

作者： Shi, Danping Hu, Lei Sun, Siwei Song, Ling State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China Data Aburance and Communication Security Research Center Chinese Academy of Sciences Beijing100093 China University of Chinese Academy of Sciences Beijing100093 China

ISBN: (纸本)9789897581670

KATAN is a family of block ciphers published at CHES 2009. Based on the Mixed-integer linear programming(MILP) technique, we propose the first third-party linear cryptanalysis on KATAN. Furthermore, we evaluate the security of KATAN against the linear attack without ignoring the dependence of the input bits of the 2×1 S-box(the AND operation). Note that in previous analysis, the dependence is not considered, and therefore the previous results are not accurate. Furthermore, the mounted 131/120-round attack on KATAN32/48 respectively by our 84/90-round linear hull is the best single-key known-plaintext attack. In addition, a best 94-round linear hull attack is mounted on KATAN64 by our 76-round linear hull. Copyright © 2016 by SCITEPRESS - Science and Technology Publications, Lda.

关键词： Integer programming

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：