检索结果-内蒙古大学图书馆

第37届中国控制会议

作者： Yawen Xiao Jun Wu Zongli Lin Xiaodong Zhao Department of Automation Shanghai Jiao Tong Universityand Key Laboratory of System Control and Information Processing of Ministry of Education The Center for Bioinformatics and Computational Biology Shanghai Key Laboratory of Regulatory Biologythe Institute of Biomedical Sciences and School of Life SciencesEast China Normal University Charles L.Brown Department of Electrical and Computer Engineering University of Virginia School of Biomedical Engineering Shanghai Jiao Tong University

Breast cancer is the most often detected cancer in women. At the same time, it is one of the most curable types of cancer if diagnosed early. With the development of the detection technology, a growing amount of clinical data and highdimensional features can be used for breast cancer diagnosis. The high-dimensional data contributes to advances in the diagnostic technology, but also incurs a large amount of computational redundancy. Thus, extracting important information and reducing the feature dimension is critical to effective prediction and an accurate treatment ***, the previous works for breast cancer diagnosis are mainly based on labeled data that is difficult to obtain. To address this issue, in this paper, we demonstrate a new scheme, which integrates a deep learning based unsupervised feature extraction algorithm, the stacked auto-encoders, with a support vector machine model（SAE-SVM）, for breast cancer diagnosis. The stacked auto-encoders with the greedy layerwise pre-training and an improved momentum update algorithm is applied to capture essential information and extract necessary features of the original data. Then, a support vector machine model is employed to classify the samples with new features into malignant or benign tumors. The proposed method was tested on the Wisconsin Diagnostic Breast Cancer data set. The performance is evaluated using various measures and compared with the previously published results. The comparison results show that the proposed SAE-SVM method improves the accuracy to 98.25% and outperforms the other methods. The deep learning based unsupervised feature extraction significantly improves the performance of classification and provides a promising approach to breast cancer diagnosis.

关键词： Deep learning auto-encoder feature extraction breast cancer diagnosis unlabeled data

来源：评论

学校读者我要写书评

暂无评论

Arc-support line segments revisited: An efficient high-quality ellipse detection

arXiv

引用

arXiv 2018年

作者： Lu, Changsheng Xia, Siyu Shao, Ming Fu, Yun Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Jiao Tong University Shanghai200240 China School of Automation Southeast University Nanjing210096 China Department of Computer and Information Science University of Massachusetts DartmouthMA02747 United States Department of ECE Northeastern University BostonMA02115 United States

Over the years many ellipse detection algorithms spring up and are studied broadly, while the critical issue of detecting ellipses accurately and efficiently in real-world images remains a challenge. In this paper, we propose a valuable industry-oriented ellipse detector by arc-support line segments, which simultaneously reaches high detection accuracy and efficiency. To simplify the complicated curves in an image while retaining the general properties including convexity and polarity, the arc-support line segments are extracted, which grounds the successful detection of ellipses. The arc-support groups are formed by iteratively and robustly linking the arc-support line segments that latently belong to a common ellipse. Afterward, two complementary approaches, namely, locally selecting the arc-support group with higher saliency and globally searching all the valid paired groups, are adopted to fit the initial ellipses in a fast way. Then, the ellipse candidate set can be formulated by hierarchical clustering of 5D parameter space of initial ellipses. Finally, the salient ellipse candidates are selected and refined as detections subject to the stringent and effective verification. Extensive experiments on three public datasets are implemented and our method achieves the best F-measure scores compared to the state-of-the-art methods. The source code is available at https://***/AlanLuSun/High-quality-ellipse-detection. Copyright © 2018, The Authors. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Structural Performance Analysis of Wall Climbing Robot

引用

IOP Conference Series: Materials Science and Engineering 2019年第4期569卷

作者： Li Huang Shangchun Liao College of Computer Science and Technology Wuhan University of Science and Technology Hubei Wuhan 430081 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Hubei Wuhan 430081 China Key Laboratory of Metallurgical Equipment and Control Technology Ministry of Education Wuhan University of Science and Technology Hubei Wuhan 430081 China

With the development of artificial intelligence technology, robotics technology has become more and more mature. Ground walking robots not only develop rapidly, but also have been applied in actual production and life. However, the development of wall climbing robot technology is still in the laboratory research and small-scale application. We live in a world where progress is continuing. Large-scale buildings, bridges and ships are becoming more and more common. In these places, it is inevitable to involve the construction, maintenance and clarity of high-rise buildings and ships. In the case of dangerous and inefficient manpower work, the application of wall climbing robots can play a very good role. Therefore, the development of wall climbing robots is of vital importance both now and in the future. Starting from the performance characteristics of wall climbing robot, this paper studies and summarizes the moving mode, control mode, conditions to be satisfied and various adsorption forms of wall climbing robot, and introduces the basic research situation in the field of wall climbing robot.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Synchronized Cell-Balancing Charging of Supercapacitors

引用

IFAC-PapersOnLine 2017年第1期50卷 3338-3343页

作者： Li H. Peng J. He J. Huang Z. Pan J. School of Information Science and Engineering Central South University Changsha 410087 China Department of Computer Science University of Victoria Victoria V8P5C2 Canada Dept. of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Shanghai 200240 China

As a classical cell balancing solution in low-power supercapacitor applications, the switched resistor circuit is vulnerable to resistance deviation effects with existing cell balancing methods. In this paper, we propose a synchronized cell balancing method for switched resistor circuits based on the consensus theory and a cyber-physical approach, with the aim of synchronizing cell voltages before they are fully charged. It is shown that the proposed cell-balancing algorithm is robust to resistance deviation effects. Extensive simulations are provided to show the effectiveness of the proposed method. © 2017

关键词： Cell balancing Charging Consensus Cyber-physical systems Supercapacitors

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to “On Fixed Point Property under Lipschitz and Uniform Embeddings”

引用

Journal of Function Spaces 2019年第1期2019卷

作者： Jichao Zhang Lingxin Bao Lili Su School of Science Hubei University of Technology Wuhan 430068 *** School of Computer and Information Fujian Agriculture and Forestry University Fuzhou 350002 *** Key Laboratory of System and Control Academy of Mathematics and Systems Science Academia Sinica Beijing 100190 *** Engineering University of The Chinese People’s Armed Police Force Xian 710086 China

来源：评论

学校读者我要写书评

暂无评论

Data Stream Online Clustering Based on Fuzzy Expectation-Maximization Approach

Data Stream Online Clustering Based on Fuzzy Expectation-Max...

引用

IEEE International Conference on Data Stream Mining & Processing (DSMP)

作者： Anastasiia O. Deineko Polina Ye. Zhernova Boris Gordon Oleksandr O. Zayika Iryna Pliss Nelya Pabyrivska Artificial Intelligence Department Kharkiv National University of Radio Electronics Kharkiv Ukraine System Engineering Department Kharkiv National University of Radio Electronics Kharkiv Ukraine Computer Systems Department Tallinn University of Technology Tallinn Estonia Control Systems Research Laboratory Kharkiv National University of Radio Electronics Kharkiv Ukraine Department of Mathematics Lviv Polytechnic National University Lviv Ukraine

ISBN: (纸本)9781538628751

In the paper the online fuzzy clustering recurrent procedure has been introduced that allows the forming of hyperellipsoidal clusters with an arbitrary orientation of the axes is proposed. Such clustering system is the generalization of a number of known algorithms, it is intended to solve tasks within the general problems of Data Stream Mining (DSM) and Dynamic Data Mining (DDM), when information is sequentially fed to processing in online mode.

关键词： Data mining Clustering algorithms Task analysis Linear programming Probabilistic logic Minimization Neural networks

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Diagnosis Using an Unsupervised Feature Extraction Algorithm Based on Deep Learning

Breast Cancer Diagnosis Using an Unsupervised Feature Extrac...

引用

Chinese control Conference

作者： Yawen Xiao Jun Wu Zongli Lin Xiaodong Zhao Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Shanghai China The Center for Bioinformatics and Computational Biology East China Normal University Shanghai China Charles L. Brown Department of Electrical and Computer Engineering University of Virginia Charlottesville VA U.S.A School of Biomedical Engineering Shanghai Jiao Tong University Shanghai China

Breast cancer is the most often detected cancer in women. At the same time, it is one of the most curable types of cancer if diagnosed early. With the development of the detection technology, a growing amount of clinical data and high-dimensional features can be used for breast cancer diagnosis. The high-dimensional data contributes to advances in the diagnostic technology, but also incurs a large amount of computational redundancy. Thus, extracting important information and reducing the feature dimension is critical to effective prediction and an accurate treatment decision. However, the previous works for breast cancer diagnosis are mainly based on labeled data that is difficult to obtain. To address this issue, in this paper, we demonstrate a new scheme, which integrates a deep learning based unsupervised feature extraction algorithm, the stacked auto-encoders, with a support vector machine model (SAE-SVM), for breast cancer diagnosis. The stacked auto-encoders with the greedy layer-wise pre-training and an improved momentum update algorithm is applied to capture essential information and extract necessary features of the original data. Then, a support vector machine model is employed to classify the samples with new features into malignant or benign tumors. The proposed method was tested on the Wisconsin Diagnostic Breast Cancer data set. The performance is evaluated using various measures and compared with the previously published results. The comparison results show that the proposed SAE-SVM method improves the accuracy to 98.25% and outperforms the other methods. The deep learning based unsupervised feature extraction significantly improves the performance of classification and provides a promising approach to breast cancer diagnosis.

关键词： Breast cancer Feature extraction Machine learning Support vector machines Electronic mail Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Power optimization control strategy of peak load shifting of energy storage system in business park

Power optimization control strategy of peak load shifting of...

引用

2017 Chinese Automation Congress, CAC 2017

作者： Xiyun, Yang Dehua, Dong Xue, Ma Na, Geng Jianhua, Zhang School of Control and Computer Engineering North China Electric Power University Beijing China EPRI of Jilin Electric Power Co. Ltd. Jilin China State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources North China Electric Power University Beijing China

ISBN: (纸本)9781538635247

With economic and industrial restructuring, the number and size of commercial parks are increasing. The most basic function of energy storage system in commercial parks is to carry out the load side, Which also brings economic benefits and ensures the reliability of power grid. Therefore, it is of practical significance to study the control strategy of energy storage system in business parks. In this paper, a variable parameter power difference control strategy for energy storage system is proposed. Based on the typical daily load of the park, it divides the load interval and the SOC of the energy storage system. Different subspaces are provided with different strategies. Finally, a simulation analysis, taking a Shanghai business park as an actual data sample shows that the proposed method for the energy storage system is effective. © 2017 IEEE.

关键词： Energy storage

来源：评论

学校读者我要写书评

暂无评论

引用

2017 4th International Conference on Engineering Technology and Application (ICETA 2017)

作者： Yue Yan Chongqing Engineering Laboratory for Detection Control and Integrated System Chongqing Technology and Business University College of Computer Science and Information Engineering Chongqing Technology and Business University

Fault localization is a crucial point for the quality of software test. After analyzing the advantages and disadvantages of fault localization method based on trace, we proposed a new computation method to confirm the correlation pattern of statement blocks through relevance of minor defects in the program. We also introduced this method into computation of vector similarity and established a new computation method for execution trace similarity. With realization of details as the basis, the effectiveness of this new method has been verified in combination with NN method. Compared with other commonly-used algorithms, this computation method has higher localization when fault rate is low and can maintain better stability when fault rate is high.

关键词： fault localization execution trace similarity degree suspiciousness ratio test case

来源：评论

学校读者我要写书评

暂无评论

Cascaded PI controller Tuning for Power Plant Superheated Steam Temperature based on Multi-Objective Optimization

引用

IFAC-PapersOnLine 2017年第1期50卷 3227-3231页

作者： Fu H. Pan L. Xue Y.L. Sun L. Li D.H. Lee K.Y. Wu Z.L. He T. Zheng S. Key Laboratory of Energy Thermal Conversion and Control of Ministry of Education Southeast University Nanjing 210096 China State Key Lab of Power System Department of Thermal Engineering Tsinghua University Beijing China Department of Electrical and Computer Engineering Baylor University Waco TX 76798 United States Department of Automation Fuzhou University Fuzhou 350000 China

To improve the superheated steam temperature (SST) control performance, this paper considers the conflicting objectives in SST control, multi-objective optimization (MOO) algorithm is employed in this paper. Firstly, the inner-loop PI controller is optimized by considering the objectives of set-point tracking and disturbance rejection, with and without constraints on robustness level. It is found that robustness constraint is essential in the optimization. Secondly, the regulation performance of the outer-loop PI controller is addressed by optimizing the disturbance rejection and robustness simultaneously. The parameter are determined based on the simulation comparison between the non-dominated solutions. The simulation results demonstrate a promising prospect of promoting the proposed strategy to more industrial practices. © 2017

关键词： Disturbance rejection Pareto optimization Power plant control Robustness Superheated steam temperature

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：