检索结果-内蒙古大学图书馆

Local graph cut criterion for supervised dimensionality reduction

Local graph cut criterion for supervised dimensionality redu...

MIPPR 2009 - Pattern Recognition and Computer Vision: 6th International Symposium on Multispectral image processing and Pattern Recognition

作者： Zhang, Xiangrong Zhou, Sisi Jiao, Licheng Key Laboratory of Intelligent Perception and Image Understanding Institute of Intelligent Information Processing Xidian University Xi'an 710071 China

ISBN: (纸本)9780819478078

Graph cut criterion has been proven to be robust and applicable in clustering problems. In this paper the graph cut criterion is applied to construct a supervised dimensionality reduction. A new graph cut, scaling cut, is proposed based on the classical normalized cut. Scaling cut depicts the relationship between samples, which makes it can handle the heteroscedastic and multimodel data in which LDA fails. Meanwhile, the solution to scaling cut is global optimal for it is a generalized eigenvalue problem. To obtain a more reasonable projection matrix and reduce the computational complexity as well, the localized k-nearest neighbor graph is introduced in, which leads to equivalent or better results compared with scaling cut. © 2009 Copyright SPIE - The International Society for Optical Engineering.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

A fast algorithm for color image enhancement with total variation regularization

引用

Science China(Information Sciences) 2010年第9期53卷 1913-1916页

作者： LI Ming1,2 1School of Computer Science and Technology,Huazhong University of Science and Technology,Wuhan 430074,China 2key laboratory of Education Ministry for image processing and intelligent control,Wuhan 430074,China 1. School of Computer Science and Technology Huazhong University of Science and Technology Wuhan 430074 China2. Key Laboratory of Education Ministry for Image Processing and Intelligent Control Wuhan 430074 China

In this paper,a novel algorithm for color image enhancement is *** proposed method,which is based on Retinex theory and total variational framework,improves the original variational method by using a TV penalty term to force spatial smoothness on the reflectance *** split Bregman algorithm is employed to solve the proposed *** practical experiments,it is verified that our method obtains better enhancement performance and much better calculation efficiency.

关键词： color image enhancement Retinex theory total variational model split Bregman algorithm

来源：评论

学校读者我要写书评

暂无评论

Spiking neural P systems for arithmetic operations

Spiking neural P systems for arithmetic operations

引用

6th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2011

作者： Zeng, Xiangxiang Song, Tao Pan, Linqiang Zhang, Xingyi Key Laboratory on Image Processing and Intelligent Control Department of Control Science and Engineering Huazhong University of Science and Technology Wuhan 430074 China Key Lab of Intelligent Computing and Signal Processing School of Computer Science and Technology Anhui University Hefei 230039 China

ISBN: (纸本)9780769545141

Recently, Gutiérrez-Naranjo and Leporati considered performing basic arithmetic operations on a new class of bioinspired computing devices - spiking neural P systems (for short, SN P systems). However, the binary encoding mechanism used in their research looks like the encoding approach in electronic circuits, instead of the style of spiking neurons (in usual SN P systems, information are encoded as the time interval between spikes). In this work, three SN P systems are constructed as adder, subtracter and multiplier, respectively. In these devices, a number is inputted to the system as the interval of time elapsed between two spikes received by input neuron, the result of a computation is the time between the moments when the output neuron spikes. © 2011 IEEE.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Object tracking in infrared image sequence by Monte-Carlo method

Object tracking in infrared image sequence by Monte-Carlo me...

引用

International Congress on image and Signal processing

作者： Ma, Qianli Wang, Min Department of Control Science and Engineering Huazhong University of Science and Technology Wuhan China Image Processing and Intelligent Control Key Laboratory of Education Ministry of China Wuhan China

ISBN: (纸本)9781424465149

This paper presents a robust tracking algorithm for infrared objects in the image sequence, which is based on particle filer. Particle filter is a powerful tool for tracking especially in non-Gaussian condition, but the selection of samples is still a challenging problem. According to the frame-to-frame correlation, two basic assumptions are proposed. Borrowing the idea from Sequence Importance Sampling, Monte-Carlo method will be applied to solve the well-known shortcomings of Particle filter in this paper. Technologically, the proposed algorithm could also track multiple objects successfully. The experimental result has demonstrated its feasibility and validity. ©2010 IEEE.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

Modeling of cortical signals using echo state networks

Modeling of cortical signals using echo state networks

引用

MIPPR 2009 - Pattern Recognition and Computer Vision: 6th International Symposium on Multispectral image processing and Pattern Recognition

作者： Zhou, Hanying Wang, Yongji Huang, Jiangshuai Key Lab. for Image Processing and Intelligent Control Department of Control Science and Engineering Huazhong University of Science and Technology China

ISBN: (纸本)9780819478078

Diverse modeling frameworks have been utilized with the ultimate goal of translating brain cortical signals into prediction of visible behavior. The inputs to these models are usually multidimensional neural recordings collected from relevant regions of a monkey's brain while the outputs are the associated behavior which is typically the 2-D or 3-D hand position of a primate. Here our task is to set up a proper model in order to figure out the move trajectories by input the neural signals which are simultaneously collected in the experiment. In this paper, we propose to use Echo State Networks (ESN) to map the neural firing activities into hand positions. ESN is a newly developed recurrent neural network(RNN) model. Besides its dynamic property and short term memory just as other recurrent neural networks have, it has a special echo state property which endows it with the ability to model nonlinear dynamic systems powerfully. What distinguished it from transitional recurrent neural networks most significantly is its special learning method. In this paper we train this net with a refined version of its typical training method and get a better model. © 2009 Copyright SPIE - The International Society for Optical Engineering.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

Memory Analysis for Memristors and Memristive Recurrent Neural Networks

引用

IEEE/CAA Journal of Automatica Sinica 2020年第1期7卷 96-105页

作者： Gang Bao Yide Zhang Zhigang Zeng Key Laboratory of Cascaded Hydropower Stations Operation and Control Electrical Engineering and New EnergyChina Three Gorges UniversityYichang 443002and Hubei Key Laboratory of Applied Mathematics(Hubei University)Wuhan 430074China Department of Medical Engineering California Institute of TechnologyPasadenaCalifornia 91125 USA School of Artificial Intelligence and Automation Huazhong University of Science and Technologyand also with the Key Laboratory of Image Processing and Intelligent Control of Education Ministry of ChinaWuhan 430074China

Traditional recurrent neural networks are composed of capacitors, inductors, resistors, and operational *** neural networks are constructed by replacing resistors with memristors. This paper focuses on the memory analysis,i.e. the initial value computation, of memristors. Firstly, we present the memory analysis for a single memristor based on memristors’ mathematical models with linear and nonlinear ***, we present the memory analysis for two memristors in series and parallel. Thirdly, we point out the difference between traditional neural networks and those that are memristive. Based on the current and voltage relationship of memristors, we use mathematical analysis and SPICE simulations to demonstrate the validity of our methods.

关键词： Dopant drift memory memristive neural networks memristor

来源：评论

学校读者我要写书评

暂无评论

Sufficient and necessary conditions for Lyapunov stability of Lorenz system and their application

引用

Science China(Information Sciences) 2010年第8期53卷 1574-1583页

作者： LUO Qi 1 , LIAO XiaoXin 2 & ZENG ZhiGang 2 1 College of Information and control, Nanjing University of Information Science and Technology, Nanjing 210044, China 2 Department of control Science and Engineering, Huazhong University of Science and Technology, image processing and intelligent control key laboratory of Education Ministry of China, Wuhan 430074, China 1. College of Information and Control Nanjing University of Information Science and Technology Nanjing 210044 China2. Department of Control Science and Engineering Huazhong University of Science and Technology Image Processing and Intelligent Control Key Laboratory of Education Ministry of China Wuhan 430074 China

The sufficient and necessary conditions for Lyapunov stability of the zero equilibrium point of Lorenz system are discussed, and some brief criteria are presented for globally exponential stability, globally asymptotical stability and instability. Furthermore, the behavior of the non-zero equilibrium point of Lorenz system is also investigated, and several sufficient and necessary conditions are provided for locally exponential stability and instability. The established theorems in this paper develop and extend the existing achievements on Lyapunov stability of Lorenz system. In conclusion, by applying the obtained results, some less conservative feedback-control laws are derived to guarantee the globally exponential stability of the chaos control of Chen system, Lu¨ system, Yang-Chen system and Yu-Xia Li system.

关键词： Lorenz system Lyapunov stability sufficient and necessary condition bifurcation values globally exponential synchronization

来源：评论

学校读者我要写书评

暂无评论

Influence of Si Buffer Layer on the Crystal Quality of SiGe Films in Ge/Si/SiGe Heterostructures: A Molecular Dynamics Investigation

引用

Surface Science 2025年

作者： Jianan Xie Tao Lin Cailin Wang College of Automation and Information Engineering Xi’an University of Technology Xi’an 710048 China Shannxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi’an University of Technology Xi’an 710048 China

SiGe materials have become a research hotspot due to their important applications in semiconductor devices, especially in optoelectronic and high-speed electronic devices. In this study, based on molecular dynamics simulations, the influence of the Si buffer layer on the quality of films in Ge/Si/SiGe heterostructures is investigated. By simulating the growth process of the Ge/Si/SiGe heterostructure, a deposition model based on Ge(100) substrates is established. Inspired by the concept of reverse gradient buffer layers, Si buffer layers are directly grown on Ge substrates, followed by the deposition of SiGe films. This study primarily investigates the effects of the growth temperature and deposition thickness of the Si buffer layer on the quality of SiGe films. Based on the deposition parameters identified as suitable under the current simulation conditions (620 °C, 9.7 nm), the influence of the buffer layer on SiGe films with varying Ge compositions is further analyzed. The results show that the dislocations and stacking faults formed in the Si buffer layer effectively relieve the stress caused by lattice mismatch, thus improving the crystal quality of the subsequent SiGe films. This study provides theoretical insights into the Ge/Si/SiGe heterostructure film growth process, which helps enhance the quality of SiGe films and expands their applications in semiconductor devices.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Redundancy reduction penalty term of loss function in deep neural network

引用

Knowledge-Based Systems 2025年

作者： Xueheng Hu Shuhuan Wen H.K. Lam Engineering Research Center of the Ministry of Education for Intelligent Control System and Intelligent Equipment Yanshan University Qinhuangdao China Key Laboratory of Industrial Computer Control Engineering of Hebei Province Yanshan University Qinhuangdao China Key Laboratory of Intelligent Control and Neural Information Processing Ministry of Education Yanshan University Qinhuangdao 066004 Hebei Province China The Department of Engineering King’s College London London WC2R 2LS United Kingdom

In this paper, we propose a novel regularization algorithm that is introduced as a penalty term to the loss function. Differing from conventional L1 and L2 regularization methods, our approach does not aim to diminish the weights of individual neurons or enforce sparsity by driving certain neurons to zero. Instead, it functions by increasing the differences between neurons and enhancing the diversity of neurons within each layer. Our method incorporates ensemble learning techniques by treating the layer weight matrix as a collective learning model, where each neuron serving as a weak learner within the layer. The proposed algorithm improves the performance of DCNN by simultaneously considering the distance between multiple filters in the same layer. This algorithm reduces the redundancy of the parameter layer filters in DCNN and enhances its robustness. The penalty term proposed by our algorithm dynamically adjusts its value in a cyclical manner, compelling the neural network to navigate away from its current gradient state. In the parameter space, different weights correspond to different locations. The proposed algorithm quantifies the distance between neurons and iteratively increases the distance between neurons during thereby encouraging greater diversity within the network. Experimental evaluations demonstrate the effectiveness of our algorithm in enhancing neural network performance without requiring adjustments to other hyper-parameters.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Immune secondary response and clonal selection inspired optimizers

引用

Progress in Natural Science:Materials International 2009年第2期19卷 237-253页

作者： Maoguo Gong a,Licheng Jiao a,Lining Zhang a,Haifeng Du b a key laboratory of intelligent Perception and image Understanding of Ministry of Education of China,Institute of intelligent Information processing,Xidian University,Xi’an 710071,China b School of Public Policy and Administration,Xi’an Jiaotong University,Xi’an 710049,China [a]Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China Institute of Intelligent Information Processing Xidian University Xi’an 710071 China [b]School of Public Policy and Administration Xi’an Jiaotong University Xi’an 710049 China

The immune system’s ability to adapt its B cells to new types of antigen is powered by processes known as clonal selection and affinity maturation. When the body is exposed to the same antigen,immune system usually calls for a more rapid and larger response to the antigen,where B cells have the function of negative adjustment. Based on the clonal selection theory and the dynamic process of immune response,two novel artificial immune system algorithms,secondary response clonal programming algorithm (SRCPA) and secondary response clonal multi-objective algorithm (SRCMOA),are presented for solving single and multi-objective optimization problems,respectively. Clonal selection operator (CSO) and secondary response operator (SRO) are the main operators of SRCPA and SRCMOA. Inspired by the clonal selection theory,CSO reproduces individuals and selects their improved maturated progenies after the affinity mat-uration process. SRO copies certain antibodies to a secondary pool,whose members do not participate in CSO,but these antibodies could be activated by some external stimulations. The update of the secondary pool pays more attention to maintain the population diversity. On the one hand,decimal-string representation makes SRCPA more suitable for solving high-dimensional function optimiza-tion problems. Special mutation and recombination methods are adopted in SRCPA to simulate the somatic mutation and receptor edit-ing process. Compared with some existing evolutionary algorithms,such as OGA/Q,IEA,IMCPA,BGA and AEA,SRCPA is shown to be able to solve complex optimization problems,such as high-dimensional function optimizations,with better performance. On the other hand,SRCMOA combines the Pareto-strength based fitness assignment strategy,CSO and SRO to solve multi-objective optimization problems. The performance comparison between SRCMOA,NSGA-Ⅱ,SPEA,and PAES based on eight well-known test problems shows that SRCMOA has better performance in converging to approximate Pareto

关键词： Clonal selection Secondary response Artificial immune systems Evolutionary algorithms

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：