检索结果-内蒙古大学图书馆

2019 IEEE International Conference on Unmanned Systems, ICUS 2019

作者： Wang, Kang Zhao, Jiajia Wang, Yang Zhou, Shuigeng Fudan University Shanghai Key Lab of Intelligent Information Processing School of Computer Science Shanghai200433 China Beijing Electro-Mechanical Engineer Institute Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China Nanchang University School of Information Engineering 330031 China

ISBN: (纸本)9781728137926

Recent object detection models have achieved satisfactory performance by deep learning with large-scale annotated datasets. However, these models often perform poorly when the training examples are not sufficient enough, especially for one-shot object detection where there is only one training example of each target class. In this paper, we propose a network parameter generation framework for effective one-shot object detection. By leveraging the semantic relationship between the source-domain and the target-domain (new classes), our framework can generate network parameters for the new classes directly. Furthermore, we develop two implementation schemes for this framework: weighting-based parameter generation and regression-based parameter generation. These two schemes use different information to construct the relationship and transfer knowledge from the source-domain to the target-domain. Experiments on the PASCAL-OSCD benchmark show that our methods can significantly boost the performance of one-shot object detection. © 2019 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Research method of identifying transformer inrush current and fault current based on VMD-HHT

Research method of identifying transformer inrush current an...

引用

第三十八届中国控制会议

作者： Shangbin Jiao Yuan Chang Qing Zhang Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing(Xi'an University of Technology)

To settle the problem that identifying inrush current and fault current of large transformer is difficult,a new identification method which is a combination of variational mode decomposition(VMD)and Hilbert-Huang transform(HHT)is come up ***,the inrush current and fault current signals are decomposed into multi-band intrinsic mode function(IMF)by using ***,the instantaneous frequencies of each intrinsic mode function(IMF)of inrush current and fault current are calculated respectively by Hilbert-Huang transform,so that the corresponding Hilbert spectrum is ***,the Hilbert spectra of inrush current and fault current are filtered by band-pass filter to remove the similar main lobes and some *** is concluded that the Hilbert spectra of inrush current and fault current are significantly different from each *** order to facilitate engineering application,the energy values of the first 16 sites in the Hilbert spectra of the two are taken to identify the inrush current and fault current,and the protection criteria are obtained.

关键词： inrush current fault current variational mode decomposition Hilbert-Huang transform

来源：评论

学校读者我要写书评

暂无评论

Temperature prediction of generator carbon brush based on LSTM neural network

Temperature prediction of generator carbon brush based on LS...

引用

Chinese Automation Congress (CAC)

作者： Qing Zhang Tingyang Jiao Yinxing Ma Youmin Zhang Xiaohui Wu Pengyue Wu Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi’an University of Technology Xi’an China The Faculty of Computing Science The University of Alberta Edmonton Alberta Canada Concordia University Montreal Canada Huaneng Weihai Power Generation Co. Ltd Wei’hai China Xi’an Thermal Power Research Institute Co. Ltd Xi’an China

ISBN: (纸本)9781665426480

In order to improve the prediction accuracy of the carbon brush temperature trend of the generator, analyzing the operating state of the generator more accurately, and reduce other accidents like the unplanned outage caused by carbon brush failure of the generator in the power plant. A multi-step temperature prediction model based on the LSTM (Long Short-Term Memory) neural network is proposed. The data comes from real operating carbon brush temperature of Weihai Power Plant in ten days. Then the temperature prediction model is established to achieve an accurate prediction of the carbon brush temperature in the future day. The prediction error is stable within 0.4 °C. By comparing the predicted results of the BP model and Elman model, the error between the predicted results of each model and the actual temperature data is analyzed. By comparing the indicators and analyzing the actual curves, the results show that LSTM neural network has higher accuracy in predicting the temperature of generator carbon brush. This method is of reference significance for the accurate analysis of the operation state of the generator and the load analysis of the excitation system.

关键词： Analytical models Temperature distribution Brushes Neural networks Predictive models Market research Generators

来源：评论

学校读者我要写书评

暂无评论

A Spectral Radius Based Evaluation Function for Automatic Focusing

A Spectral Radius Based Evaluation Function for Automatic Fo...

引用

IEEE International Symposium on Parallel and Distributed processing with Applications and IEEE International Conference on Ubiquitous Computing and Communications (ISPA/IUCC)

作者： Guojin Peng Meini Lv Kuikui Wang Guangxi Colleges and Universities Key Laboratory of Image Processing and Intelligent Information System Wuzhou University WuZhou china

ISBN: (纸本)9781728152103

Curves generated by traditional evaluating functions contain large amount of local extremums, easily leading to focal-plane misjudgments. We propose a new clarity evaluation method based on spectral radius. The spatial information is converted into frequency domain by Discrete Cosine Transformation, then a sector that contains more than 99 percent of the total spectrum energy is extracted, and the radius of this sector is employed to estimate the degree of clarity of current image. Since the scope of spectral radius is steady and limited to image size, it provides effective reference for selection of lower limit of spectral radius which is utilized to avoid local fluctuation and maintain the unimodality of evaluation curves. The experimental results demonstrate that the spectral radius based evaluation method forms curves with fewer local extremums and better robustness.

关键词： discrete cosine transforms gradient methods image recognition spectral radius discrete cosine transforms gradient methods image recognition Curves Clarity Current Pick image SIZE Sectoring SPECTRAL ENERGY evaluation method

来源：评论

学校读者我要写书评

暂无评论

Distributed Nonconvex Optimization: Gradient-free Iterations and ϵ-Globally Optimal Solution

arXiv

引用

arXiv 2020年

作者： He, Zhiyu He, Jianping Chen, Cailian Guan, Xinping Department of Automation Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China Automatic Control Laboratory ETH Zurich Zurich8092 Switzerland

Distributed optimization utilizes local computation and communication to realize a global aim of optimizing the sum of local objective functions. This article addresses a class of constrained distributed nonconvex optimization problems involving univariate objectives, aiming to achieve global optimization without requiring local evaluations of gradients at every iteration. We propose a novel algorithm named CPCA, exploiting the notion of combining Chebyshev polynomial approximation, average consensus, and polynomial optimization. The proposed algorithm is i) able to obtain ϵ-globally optimal solutions for any arbitrarily small given accuracy ϵ, ii) efficient in both zeroth-order queries (i.e., evaluations of function values) and inter-agent communication, and iii) distributed terminable when the specified precision requirement is met. The key insight is to use polynomial approximations to substitute for general local objectives, distribute these approximations via average consensus, and solve an easier approximate version of the original problem. Due to the nice analytic properties of polynomials, this approximation not only facilitates efficient global optimization, but also allows the design of gradient-free iterations to reduce cumulative costs of queries and achieve geometric convergence for solving nonconvex problems. We provide a comprehensive analysis of the accuracy and complexities of the proposed algorithm. © 2020, CC BY-NC-SA.

关键词： Polynomial approximation

来源：评论

学校读者我要写书评

暂无评论

A novel single-phase-to-earth fault line method in small current grounding systems

A novel single-phase-to-earth fault line method in small cur...

引用

第三十八届中国控制会议

作者： Jiao Shangbin Guo Jingwen Li Yunjun Xiao Ting Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing(Xi'an University of Technology)

Aiming at the problem that the fault characteristics of single-phase-to-ground fault in small current grounding system are not obvious,the fault situation is complex,and the single fault criterion is difficult to accurately select the *** this paper,a new method for small current single-phase ground fault line selection is proposed based on improved Empirical Wavelet Transform(EWT)and D-S evidence *** method firstly smoothes the transient zero-sequence current spectrum of each feeder,and then performs EWT decomposition to extract the natural modal function that best characterizes the original signal,and obtains the energy peak and the intrinsic modal energy value to determine the probability of each line fault,***,the results of the two methods are fused by D-S evidence theory,and the final line selection results are obtained.

关键词： Small current Single-phase grounding Fault line selection EWT D-S evidence theory

来源：评论

学校读者我要写书评

暂无评论

A Clustering Routing Algorithm for Extending the Lifecycle in WSN

A Clustering Routing Algorithm for Extending the Lifecycle i...

引用

International Conference on information Science and control Engineering (ICISCE)

作者： Hongbing Li Xiaolong Liu Yang Luo Hua Luo Meng Huang Kunlin Xie Juan Wu Key Laboratory of Intelligent Information Processing and Control of Chongqing Municipal Institutions of Higher Education Chongqing China Chongqing Engineering Research Center of Internet of Things and Intelligent Control Technology Chongqing Three Gorges University Chongqing China Chongqing Key Laboratory of Geological Environment Monitoring and Disaster Early-warning in Three Gorges Reservoir Area Chongqing Three Gorges University Chongqing China

In order to extend the life of wireless sensor networks and improve the stability of wireless sensor networks, a cluster head election mechanism based on energy center of gravity and regional segmentation is proposed. The sensor network monitoring area was divided into finite subregions, and the common nodes of each subregion competed for cluster heads in their own regions, which made the distribution of cluster heads in the whole network more uniform. Each sub-region node is selected for the cluster head based on two factors: energy center and communication distance. The cluster head is responsible for receiving the data perceived by ordinary nodes in the region, and the received information is fused and compressed and transmitted to the base station, thus solving the problems of uneven cluster head distribution and unbalanced node energy loss in the clustering algorithm. The simulation results show that compared with the traditional LEACH clustering algorithm and the improved LEACH-M algorithm, the new algorithm can achieve the purpose of balancing the energy loss of each node, effectively reduce the overall energy loss of the sensor network, and thus extend the network life cycle.

关键词： Wireless communication Wireless sensor networks Energy loss Voting Simulation Clustering algorithms Routing

来源：评论

学校读者我要写书评

暂无评论

Universal enzymatic numerical P systems with small number of enzymatic variables

引用

Science China(information Sciences) 2018年第9期61卷 38-49页

作者： Zhiqiang ZHANG Tingfang WU ANDrei P■UN Linqiang PAN Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China School of Automation Huazhong University of Science and Technology Department of Computer Science Faculty of Mathematics and Computer ScienceUniversity of Bucharest Bioinformatics Department National Institute of Research and Development for Biological Sciences School of Electric and Information Engineering Zhengzhou University of Light Industry

Numerical P systems(for short, NP systems) are distributed and parallel computing models inspired from the structure of living cells and economics. Enzymatic numerical P systems(for short, ENP systems) are a variant of NP systems, which have been successfully applied in designing and implementing controllers for mobile robots. Since ENP systems were proved to be Turing universal, there has been much work to simplify the universal systems, where the complexity parameters considered are the number of membranes, the degrees of polynomial production functions or the number of variables used in the *** the number of enzymatic variables, which is essential for ENP systems to reach universality, has not been investigated. Here we consider the problem of searching for the smallest number of enzymatic variables needed for universal ENP systems. We prove that for ENP systems as number acceptors working in the all-parallel or one-parallel mode, one enzymatic variable is sufficient to reach universality; while for the one-parallel ENP systems as number generators, two enzymatic variables are sufficient to reach *** results improve the best known results that the numbers of enzymatic variables are 13 and 52 for the all-parallel and one-parallel systems, respectively.

关键词： bio-inspired computing numerical P system mobile robot membrane controller universality

来源：评论

学校读者我要写书评

暂无评论

VRAS: A virtual rehearsal assistant system for live performance 2nd

VRAS: A virtual rehearsal assistant system for live performa...

引用

2nd International Conference on Smart Vehicular Technology, Transportation, Communication and Applications, VTCA 2018

作者： Wu, Yufeng Ding, Gangyi Li, Hongsong Xue, Tong Jiao, Di Huang, Tianyu Zhang, Longfei Zhang, Fuquan Xu, Lin Digital Performance and Simulation Key Laboratory School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350121 China Key Laboratory of Nondestructive Testing Fuqing Branch of Fujian Normal University Fuzhou350300 China

ISBN: (纸本)9783030045845

The VR technologies are widely adopted for training purposes by providing the users with educational virtual experience. In this work, we propose an immersive VR system that help the choreographers and the dancers to facilitate their dance rehearsal experience. The system integrates motion capture devices and head-mounted displays (HMDs). The motions of the dancers, their partners, and the choreographers are captured and projected into a virtual dancing scene in an interactive frame rate. The dancers who are wearing the HMDs, are allowed to observe the synthesized virtual performances within a virtual stage space from several selected third-person views. These are the audience’s view, the dancing partner’s view, and the choreographer’s view. Such synthesized external self-images augment dancer’s perception of their dance performance and their understanding of the choreography. Feedbacks from the participants indicate the proposed system is effective and the preliminary experimental results agree with our observations. © Springer Nature Switzerland AG 2019.

关键词： Helmet mounted displays

来源：评论

学校读者我要写书评

暂无评论

Fruit detection using faster R-CNN based on deep network 2nd

Fruit detection using faster R-CNN based on deep network

引用

2nd International Conference on Smart Vehicular Technology, Transportation, Communication and Applications, VTCA 2018

作者： Ma, Linjuan Zhang, Fuquan Xu, Lin School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350121 China Key Laboratory of Nondestructive Testing Fuqing Branch of Fujian Normal University Fuzhou350300 China

ISBN: (纸本)9783030045845

Fruit detection is of great significance in the agriculture. Recently, deep neural network has been widely studied in fruit detection. In our paper, we present a new approach of fruit detection, which uses Faster R-CNN based on deep network AlexNet. Our aim is to develop a fast, accurate and convenient model to detect and classify the fruit. Data augmentation is also used to increase the fruit dataset and avoid the overfitting in some degree. We use the fruits-360 dataset to perform the experiments. © Springer Nature Switzerland AG 2019.

关键词： Deep neural networks

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：