检索结果-南通市图书馆

An Improved Learning with Local and Global Consistency

在线全文

cnki会议

学校读者我要写书评

暂无评论

An Improved Learning with Local and Global Consistency

2010 Chinese Control and Decision Conference

作者： Ming Li,Xiaoli Zhang,Xuesong Wang school of information and electrical engineering,china university of mining and technology,xuzhou,Jiangsu 221116 china

Learning with local and global consistency(LLGC) algorithm can effectively label a data,but it is helpless for noise *** reason is that the LLGC algorithm will predict a label for each unlabelled data without taking into account whether a data has noise or *** at the deficiency of the LLGC algorithm,an improved version for semi-supervised learning algorithm with local and global consistency is proposed in this *** first,we compute the similarity of each data to all *** then the data can be ascribed to one class according to its *** improved LLGC algorithm not only can label data as the conventional LLGC,but also can identify noise existed in data set *** results show that the improved LLGC algorithm can effectively avoid noise data being viewed as normal data.

关键词： Semi-supervised learning Learning with local and global consistency Graph Similarity Noise data

Model Selection for SVM Based on Similarity Margin of Inner Product

在线全文

cnki会议

学校读者我要写书评

暂无评论

Model Selection for SVM Based on Similarity Margin of Inner ...

2010 Chinese Control and Decision Conference

作者： Zhu Jin,Ying Chen,Xiaoping Ma The school of information and electrical engineering,china university of mining & technology,xuzhou,Jiangsu 221116,china

＜正＞By investigating the relationships among generalization performance,VC dimension and margin in SVM,this paper proposes a novel similarity margin of inner ***,the richness or flexibility of corresponding function class,along with estimative upper bound of relevant dimensionality,is analyzed in *** at the demerit of difficult selection of optimal kernel function and its parameters in SVM,we discuss the improvement of generalization performance in terms of similarity margin of inner product and construct a model selection approach based on similarity margin of inner product,by which we could effectively avert such shortcomings as high computational costs and formulation complexity in traditional model selection *** results on both artificial dataset and practical dataset show that our algorithm can find out preferable kernel parameter model,as well as maintain better classification accuracy,so it is more applicable.

关键词： Support Vector Machine Margin Model Selection Kernel Function

Spatial continuity incorporated multi-attribute fuzzy clustering algorithm for blood vessels segmentation

在线全文

cnki会议

学校读者我要写书评

暂无评论

Science china(information Sciences) 2010年第4期53卷 752-759页

作者： HAO JuTao1*, ZHAO JingJing2 & LI MingLu3 1school of Optical-electrical and Computer engineering, university of Shanghai for Science and technology, Shanghai 200093, china 2Department of electrical engineering, Shanghai university of Electric Power, Shanghai 200090, china 3Department of Computer Science and engineering, Shanghai Jiaotong university, Shanghai 200240, china 1. school of Optical-electrical and Computer engineering University of Shanghai for Science and Technology Shanghai 200093 China2. Department of Electrical Engineering Shanghai University of Electric Power Shanghai 200090 China3. Department of Computer Science and Engineering Shanghai Jiaotong University Shanghai 200240 China

A three-dimensional representation of vasculature can be extremely important in image-guided neurosurgery, pre-surgical planning. In this paper, a spatial continuity incorporated multi-attribute fuzzy clustering algorithm (MAFCM S) is proposed to segment entire blood vessels from TOF MRA images. This clustering method takes both the intensity information and the geometrical information into account, while most of the cur- rent clustering methods only deal with the former. In this method, a new dissimilarity measure, which integrates the intensity and the geometry shape dissimilarity, is introduced. Because of the presence of the geometrical information, the new measure is able to differentiate the pixels with similar intensity values within different geometrical shape structures. Experimental results show that the new algorithm can get better segmentation.

关键词： fuzzy c-means clustering scale space analysis spatial continuity blood vessel segmentation multi-attribute fuzzy clustering

Intelligent Tribological Forecasting Model and System for Disc Brake

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Intelligent Tribological Forecasting Model and System for Di...

第24届中国控制与决策会议

作者： Jiusheng Bao 1,2 , Minming Tong 3 , Zhencai Zhu 1 , Yan Yin 1 1. school of Mechanical and electrical engineering, china university of mining and technology, xuzhou, 221116, china 2. Mobile Postdoctoral Station for Control Science and engineering, china university of mining and technology, xuzhou, 221116, china 3. school of information and electrical engineering, china university of mining and technology, xuzhou, 221116, china

This paper aims at improving the braking ability and reliability of disc brakes. Based on some braking tests of the disc brake, an intelligent forecasting model for its tribological properties was established firstly by the artificial neural network （ANN） technology. Its input layer contains three braking cells: braking pressure, sliding velocity and surface temperature. And its output layer contains three tribological cells: friction coefficient and its stability coefficient, and wear rate. Secondly, an intelligent forecasting system was developed based on the model. It is mainly composed of three parts: sensing system, data collecting system, and data computing system. Finally, the disc brake used in mine hoists was tested on the system as an example. It is shown that the experimental data which contain nonlinear relationships between the braking conditions and tribological properties of disc brake are theoretical foundations of the tribological forecasting. The ANN is especially suitable for establishing the tribological forecasting model. And the optimized BP network is proved as a simple and effective computing model. The intelligent model and system established in this paper has quite favorable forecasting ability and practicability. By the contrast, it has higher precision for forecasting of the friction coefficient and its stability coefficient than the wear rate. The difference was attributed to man-made testing errors of data samples during tribological experiments.

关键词： Intelligent Forecasting Tribological Properties Disc Brake Braking Condition ANN

Modeling of human colonic blood flow for a novel artificial anal sphincter system

在线全文

cnki会议

学校读者我要写书评

暂无评论

Journal of Zhejiang university-Science B(Biomedicine & Biotechnology) 2008年第9期9卷 734-738页

作者： Peng ZAN, Guo-zheng YAN, Hua LIU (school of Electronics, information and electrical engineering, Shanghai Jiao Tong university, Shanghai 200240, china) school of Electronics Information and Electrical Engineering Shanghai Jiao Tong University Shanghai 200240 China zanpeng@***.

A novel artificial anal sphincter system has been developed to simulate the normal physiology of the human anorectum. With the goal of engineering a safe and reliable device, the model of human colonic blood flow has been built and the relationship between the colonic blood flow rate and the operating occlusion pressure of the anorectum is achieved. The tissue ischemia is analyzed based on constitutive relations for human anorectum. The results suggest that at the planned operating occlusion pressure of less than 4 kPa the artificial anal sphincter should not risk the vascularity of the human colon.

关键词： Incontinence Artificial anal sphincter Colonic blood flow Tissue ischemia

Fast parallel algorithms for discrete Gabor expansion and transform based on multirate filtering

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science china(information Sciences) 2012年第2期55卷 293-300页

作者： TAO Liang1 & GU JuanJuan2 1school of Computer Science and technology,Anhui university,Hefei 230039,china 2Department of Electronic information and electrical engineering,Hefei university,Hefei 230022,china 1. school of Computer Science and technology Anhui University Hefei 230039 China2. Department of Electronic Information and Electrical Engineering Hefei University Hefei 230022 China

The Gabor transform has long been recognized as a very useful tool for the joint time and frequency analysis in signal *** real time applications,however,were limited due to the high computational complexity of the Gabor transform *** this paper,some novel and fast parallel algorithms for the finite discrete Gabor expansion and transform are presented based on multirate *** analysis filter bank is designed for the finite discrete Gabor transform(DGT)and a synthesis filter bank is designed for the finite discrete Gabor expansion(DGE).Each of the parallel channels in the two filter banks has a unified structure and can apply the FFT and the IFFT to reduce its computational *** computational complexity of each parallel channel does not change as the oversampling rate *** fact,it is very low and depends only on the length of the input discrete signal and the number of the Gabor frequency sampling *** computational complexity of the proposed parallel algorithms is analyzed and compared with that of the major existing parallel algorithms for the finite DGT and *** results indicate that the proposed parallel algorithms for the finite DGT and DGE based on multirate filtering are very attractive for real time signal processing.

关键词： discrete Gabor expansion discrete Gabor transform critical sampling and oversampling multirate filtering analysis and synthesis filter banks

Reinforcement Learning Method Based on Semi-parametric Regression Model

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Reinforcement Learning Method Based on Semi-parametric Regre...

2010 Chinese Control and Decision Conference

作者： Yuhu Cheng,Xuesong Wang,Xilan Tian school of information and electrical engineering,china university of mining and technology,xuzhou,Jiangsu 221116 china

＜正＞In order to make full use of the advantages of both parametric and non-parametric models simultaneously,a kind of semi-parametric support vector machine（SVM） was proposed by combining a non-parametric SVM model and a parametric linear basis function *** semi-parametric SVM was used to estimate the Q values of continuous-state-discontinuous-action pairs in an on-line manner so as to generalize a standard Q learning method to continuous state *** results concerning the balancing control problem of an inverted pendulum show that the proposed Q learning method has good adaptability for changes of system parameters and initial states,which provides a new approach to solve the generalization problem of continuous space of reinforcement learning.

关键词： Semi-parametric Regression model Reinforcement learning Support vector machine

Observer-Based Robust Control for Measure Differential Systems with Parameter Uncertainty and Time Delay

在线全文

cnki会议

学校读者我要写书评

暂无评论

Systems Science and Systems engineering 2000年第3期10卷 257-263页

作者： YUE Dong\+1,\ Tso S K 2,\ Won Sangchul 3 1.College of information & electrical engineering, china university of mining & technology, xuzhou Jiangsu, 221008, china 2.City university of Hong Kong, Hong Kong 3.Deptartment of electrical engineering, Po

In this paper, we propose a robust control based on the observer for a class of measure differential systems with time delay. To implement the control, we only need the output signal of the systems. In the finial sect... 详细信息

关键词： observer measure differential systems stability

维普期刊数据库

Decentralized H-infinity state feedback control for discrete-time singular large-scale systems

在线全文

学校读者我要写书评

暂无评论

控制理论与应用（英文版） 2010年第2期8卷 200-204页

作者： Songlin WO 1 , Yun ZOU 2 , Shengyuan XU 2 (1.school of electrical and information engineering, Jiangsu Teachers university of technology, Changzhou Jiangsu 213001, china 2.school of Automation, Nanjing university of Science and technology, Nanjing Jiangsu 210094, china) school of electrical and information engineering Jiangsu Teachers University of Technology Changzhou Jiangsu China school of Automation Nanjing University of Science and Technology Nanjing Jiangsu China

The decentralized H-infinity control problem for discrete-time singular large-scale systems is considered. Based on the bounded real lemma of discrete-time singular systems, a sufficient condition for the existence of decentralized H-infinity controller for discrete-time singular large-scale systems is presented in terms of the solvability to a certain system of linear matrix inequalities by linear matrix inequality (LMI) approach, and the feasible solutions to the system of LMIs provide a parameterized representation of a set of decentralized H-infinity controller. The given example shows the application of the method.

关键词： Discrete-time singular large-scale system Linear matrix inequality (LMI) Decentralized H-infinity control

维普期刊数据库