检索结果-内蒙古大学图书馆

A Robot Pick and Place Skill Learning Method Based on Maximum Entropy and DDQN Algorithm

Journal of Physics: Conference Series 2022年第1期2203卷

作者： Peiliang Wu Yan Zhang Yao Li Bingyi Mao Wenbai Chen Guowei Gao School of Information Science and Engineering Yanshan University Qinhuangdao Hebei 066004 China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao Hebei 066004 China School of Automation Beijing Information Science & Technology University Beijing 100192 China

Pick and place (PAP) skill learning is a fundamental ability of intelligent robots, such as home service robot. Due to the NP-hard nature of the PAP problem, it takes a long time for an intelligent robot to learn the PAP skill based on current methods. In order to improve the learning efficiency of robot PAP skills, this paper proposes a Soft-DDQN-based PAP skill learning method. Firstly, the Soft-DDQN is proposed by introducing maximum entropy into robot DDQN framework, and the learning goal of Soft-DDQN is to maximize reward and information entropy. Secondly, PAP problem is modelled as a discrete form and Soft-DDQN is applied to solve the PAP problem. Finally, in order to verify the efficiency of Soft-DDQN-based PAP skill learning, comparisons have been given from two standard perspectives and shown that Soft-DDQN improves efficiency of PAP skill learning evidently.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design of Irregular QC-LDPC Code Based Multi-Level Coded Modulation Scheme for High Speed Optical Communication Systems

引用

China Communications 2019年第5期16卷 106-120页

作者： Liqian Wang Dongdong Wang Yongjing Ni Xue Chen Midou Cui Fu Yang Beijing University of Posts and Telecommunications Beijing 100876China The 54th Research Institute of China Electronics Technology Group Corporation Shijiazhuang 050081China Science and Technology on Communication Networks Laboratory Shijiazhuang 050081China College of Information Science and Engineering Yanshan UniversityQinhuangdao 066000China College of Information Science and Engineering Hebei University of Science and TechnologyShijiazhuang 050000China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Yanshan University Qinhuangdao 066000China

In this paper, we focus on the design of irregular QC-LDPC code based multi-level coded modulation(MLCM) scheme by jointly optimizing the component code rate and the degree distribution of the irregular QC-LDPC component code. Firstly, the sub-channel capacities of MLCM systems is analyzed and discussed, based on which the optimal component code rate can be obtained. Secondly, an extrinsic information transfer chart based two-stage searching algorithm is proposed to find the good irregular QC-LDPC code ensembles with optimal component code rates for their corresponding sub-channels. Finally, by constructing the irregular QC-LDPC component codes from the designed ensembles with the aim of possibly enlarging the girth and reducing the number of the shortest cycles, the designed irregular QC-LDPC code based 16QAM and 64QAM MLCM systems can achieve 0.4 dB and 1.2 dB net coding gain, respectively, compared with the recently proposed regular QC-LDPC code based 16QAM and 64QAM MLCM systems.

关键词： quasi-cyclic low-density parity check (QC-LDPC) code irregular, extrinsic information transfer(EXIT) chart generalized mutual information(GMI) multi-level coded modulation(MLCM)

来源：评论

学校读者我要写书评

暂无评论

Outlier detection based on cluster outlier factor and mutual density

引用

International Journal of Intelligent Information and Database Systems 2019年第1-2期12卷 91-108页

作者： Zhang, Zhongping Zhu, Mengfan Qiu, Jingyang Liu, Cong Zhang, Debin Qi, Jie School of Information Science and Engineering Yanshan University Qinghuangdao Hebei066004 China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province 438 West Section of Hebei Street Haigang District Qinhuangdao City Hebei Province066004 China Hebei Education Examinations Authority 231 Hongqi Street Shijiazhuang City Hebei Province050000 China First Middle School of Qian An Country 347 Wutong Road Qianan Jilin131400 China

Outlier detection is an important task in data mining with numerous applications. Recent years, the study on outlier detection is very active, many algorithms were proposed including based on clustering. However, most outlier detection algorithms based on clustering often need parameters and it is very difficult to select a suitable parameter for different data set. In order to solve this problem, an outlier detection algorithm called outlier detection based on cluster outlier factor and mutual density is proposed in this paper. The mutual density and γ density is used to construct decision graph. The data points with γ density anomalously large in decision graph are treated as cluster centres. This algorithm detect the boundary of outlier cluster using cluster outlier factor called cluster outlier factor (COF), it can automatic find the parameter. This method can achieve good performance in clustering and outlier detection which be shown in the experiments. Copyright © 2019 Inderscience Enterprises Ltd.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

BAF-detector: An efficient CNN-based detector for photovoltaic cell defect detection

arXiv

引用

arXiv 2020年

作者： Su, Binyi Chen, Haiyong Zhou, Zhong State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China School of Artificial Intelligence and Data Science Hebei University of Technology Tianjin300130 China

The multi-scale defect detection for photovoltaic (PV) cell electroluminescence (EL) images is a challenging task, due to the feature vanishing as network deepens. To address this problem, an attention-based top-down and bottom-up architecture is developed to accomplish multi-scale feature fusion. This architecture, called Bidirectional Attention Feature Pyramid Network (BAFPN), can make all layers of the pyramid share similar semantic features. In BAFPN, cosine similarity is employed to measure the importance of each pixel in the fused features. Furthermore, a novel object detector is proposed, called BAF-Detector, which embeds BAFPN into Region Proposal Network (RPN) in Faster RCNN+FPN. BAFPN improves the robustness of the network to scales, thus the proposed detector achieves a good performance in multi-scale defects detection task. Finally, the experimental results on a large-scale EL dataset including 3629 images, 2129 of which are defective, show that the proposed method achieves 98.70% (F-measure), 88.07% (mAP), and 73.29% (IoU) in terms of multi-scale defects classification and detection results in raw PV cell EL images. Copyright © 2020, The Authors. All rights reserved.

关键词： Photoelectrochemical cells

来源：评论

学校读者我要写书评

暂无评论

Outlier detection based on cluster outlier factor and mutual density 10th

Outlier detection based on cluster outlier factor and mutual...

引用

10th International Symposium on Intelligence Computation and Applications, ISICA 2018

作者： Zhang, Zhongping Zhu, Mengfan Qiu, Jingyang Liu, Cong Zhang, Debin Qi, Jie School of Information Science and Engineering Yanshan University QinhuangdaoHebei066004 China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province QinhuangdaoHebei066004 China Hebei Education Examinations Authority ShijiazhuangHebei050000 China The First Middle School of Qian An Country Qian’anJilin131400 China

ISBN: (纸本)9789811364723

Outlier detection is an important task in data mining with numerous applications. Recent years, the study on outlier detection is very active, many algorithms were proposed including that based on clustering. However, most outlier detection algorithms based on clustering often need parameters, and it is very difficult to select a suitable parameter for different data set. In order to solve this problem, an outlier detection algorithm called outlier detection based on cluster outlier factor and mutual density is proposed in this paper which combining the natural neighbor search algorithm of the Natural Outlier Factor (NOF) algorithm and based on the Density and Distance Cluster (DDC) algorithm. The mutual density and γ density is used to construct decision graph. The data points with γ density anomalously large in decision graph are treated as cluster centers. This algorithm detect the boundary of outlier cluster using cluster outlier factor called Cluster Outlier Factor (COF), it can automatic find the parameter. This method can achieve good performance in clustering and outlier detection which be shown in the experiments. © Springer Nature Singapore Pte Ltd. 2019.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Improved BP classifier via distance for sample reduction

引用

Journal of computers (Taiwan) 2019年第2期30卷 1-13页

作者： Wen, Jia Deng, Jia Liu, Peng-Fei Wang, Hong-Jun Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Yanshan University Qinhuangdao China School of Information Science and Engineering Yanshan University Qinhuangdao China State Key Laboratory of Software Engineering of Hebei Province Yanshan University Qinhuangdao China

The BP neural network algorithm is a commonly used technique in the classification field of pattern recognition, which iterates training samples continuously to obtain the decision boundary, until the error reaches the convergence precision. However, due to the extensive redundancy of training samples, this carpet-like training method can easily lead to slow network convergence and low classification performance. In this paper, from the view of sample, a novel BP training method called improved BP Classifier algorithm using Distance for Sample Reduction (DRBP) is proposed. Through the sample weight to get the new training sample, which are the near of the classification interface like support vector, and then iterative training BP classifier to solve the classification issue. The main function of this method is to keep the original sample information, realize the sample reduction, and improve the generalization ability of the BP neural network. First, point sets is used to visualize the training process. And then use 10 sets of the University of California Irvine (UCI) to verify the effectiveness and superiority of our experiments. Finally through Cross-validation, the classification error rate of 10 sets of UCI datasets tested by DRBP training method is lower than that of standard BP neural network (STBP). So the result of the experiment showed that the method of the combined distance sample reduce with BP network can significantly enhance the generalization ability of BP network. © 2019 computer Society of the Republic of China. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Detecting shilling profiles in collaborative recommender systems via multidimensional profile temporal features

Detecting shilling profiles in collaborative recommender sys...

引用

作者： Hao, Yaojun Zhang, Fuzhi School of Information Science and Engineering Yanshan University Qinhuangdao Hebei Province China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao Hebei Province China Department of Computer Science and Technology Xinzhou Teachers University Xinzhou Shanxi Province China

To defend recommender systems, various methods have been proposed to detect shilling profiles, which can be categorised as user- and item-based detection methods. Most of the user-based methods identify shilling profiles via statistical signatures of rating values and suffer from low precision when detecting different types of attacks. Most of the item-based methods use temporal information to detect the anomaly items, but they assume that the fake ratings were injected in short periods. So they are invalid for the long duration and decentralised injection attacks. To address these limitations, the authors extract the multidimensional profile temporal features and present a shilling detection method. First, from the user profile view, user rating behaviours are characterised by corrected conditional entropy and the dissimilarity with the rest-rating model. Second, from the item profile view, the user features are extracted according to item temporal popularity. Third, the features based on weighted deviation from dynamic mean are extracted according to the fact that the items mean changes with time. Finally, support vector machine is exploited to detect shilling profiles based on the proposed features. Experimental results on the Netflix dataset indicate that the performance of the proposed method is better than that of the benchmark methods. © The Institution of Engineering and technology 2018.

关键词： User profile

来源：评论

学校读者我要写书评

暂无评论

Robust visual tracking via combinative deep learning

Robust visual tracking via combinative deep learning

引用

International Conference on Mechanical, Electric and Industrial Engineering, MEIE 2018

作者： Wen, Jia Zhao, Jiwei Liu, Pengfei Wang, Hongjun Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Yanshan University Qinhuangdao China Information Science and Engineering College Yanshan University Qinhuangdao China State Key Laboratory of Software Engineering of Hebei Province Yanshan University Qinhuangdao China

Object tracking is a hot topic in computer vision. In recent years, a large number of trackers has been proposed, in which the deep learning tracker has achieved excellent performance. The real-time capability of the deep learning tracker is not good enough due to the high-complexity of the network structures. This paper proposed an innovative tracking method to solve this problem. There are three important differences between this tracker and the other deep learning trackers. Firstly, the overcomplete basis in the deep learning tracker results in heavy computational cost. In order to reduce the complexity of the network, fewer units are used in the first hidden layer to replace the overcomplete basis. Secondly, a training method combining two observation models is used in the tracking process. The denoising automatic encoder is used in the first layer and the backpropagation is used in the other layers. This can avoid the diffusion of gradients which is caused by BP and adapt to the change of the targets easier. Thirdly, this tracker using adaptive particle filter to track targets. The number of particles is dynamic changes in tracking process. In this paper, we use different kinds of unlabelled datum to train network and initialize observation model. The observation model uses the samples collected in the tracking to adjust dynamically so as to adapt to the target appearance and complex environment. Compared with the existing methods, the results of experiments in different video sequences show that this tracker has a higher speed and the similar accuracy compared. © Published under licence by IOP Publishing Ltd.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Dynamic community mining based on behavior prediction

引用

International Journal of Performability Engineering 2018年第7期14卷 1590-1599页

作者： Chen, Xiao Hu, Xinzhuan Pan, Xiao Guo, Jingfeng Network Technology Center Hebei Normal University of Science and Technology Qinhuangdao066004 China College of Economics and Management YanShan University Qinhuangdao066004 China College of Economic and Management Shijiazhuang Tiedao University Shijiazhuang050043 China College of Information Science and Engineering YanShan University Qinhuangdao066004 China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao066004 China

Dynamic network research has been a new trend in recent years. Based on the influence of vertex behavior on community structure, this paper studies signed network dynamic community mining. Firstly, the set pair connection degree is introduced to describe the relation between vertices, and the edge prediction model of signed network is proposed by taking into account the variability of the relation between vertices. Secondly, based on the prediction model, a set pair signed networks dynamic model is proposed by adding time axis T to the signed network. Then, based on the dynamic model, the evolution of signed networks and community discovering are studied. Finally, network evolution law and community stability are analyzed by using the connection trend and connection entropy in set pair theory, and the accuracy and validity of the dynamic community mining algorithm are verified by experiments. © 2018 Totem Publishers Ltd. All rights reserved.

关键词： Dynamic models

来源：评论

学校读者我要写书评

暂无评论

Mining Important Functions in Software Network by Node Vulnerability

引用

Journal of Physics: Conference Series 2020年第1期1453卷

作者： Bing Zhang Shengting Sun Xiaobing Hao School of Information Science and Engineering Yanshan University Qinhuangdao Hebei P.R.China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao City China 066004

Given that analysis on the vulnerability of functions is helpful to the detection and improvement of software security, this paper aims to propose an efficient methods to identify the vulnerable nodes (ITVN) in different software by the interdependence of functions. First, the dynamic software execution process was constructed as Software Execution Dependency Network (SEDN) based on Complex network theory. Second, by analyzing the dependency relationship among functions, the algorithm calVulAndScoOfNodes (CVSN) was designed to compute the vulnerability and the affected scope of each node for further analysis. Third, in order to measure the functions vulnerability in the whole software network, the algorithm calVulDegreeOfNodes (CVDN) was put forward to calculate the vulnerable degree of each node. Finally, the Vulnerable Nodes in different software were obtained by ITVN. Experimental results show that the vulnerable nodes selected as important nodes are well-reasoned in software network by testing different software, and the measures are effective for evaluating nodes vulnerability.

关键词：

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：