检索结果-南通市图书馆

结合改进型主动外观模型与马尔科夫随机场的椎间盘核磁共振图像分析

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

生物医学工程学杂志 2010年第1期27卷 6-9,15页

作者：郝世杰詹曙蒋建国李鸿 Ian Ross 合肥工业大学计算机与信息学院合肥230009 安徽医科大学第一附属医院骨科合肥230022 London Health Science Center London Ontario Canada N6A 5A5

针对目前腰部医学图像处理较少涉及分割并量化分析软组织的现状,提出一种腰部核磁共振图像(magnet-ic resonance imaging,MRI)中椎间盘分割及定量分析的算法:首先用改进的基于独立分量分析的主动外观模型(in-dependent component analys... 详细信息

针对目前腰部医学图像处理较少涉及分割并量化分析软组织的现状,提出一种腰部核磁共振图像(magnet-ic resonance imaging,MRI)中椎间盘分割及定量分析的算法:首先用改进的基于独立分量分析的主动外观模型(in-dependent component analysis based active appearance model,ICA-AAM)分割椎体,并基于最小描述长度(minimumdescription length,MDL)准则获得腰部弯曲曲线;利用上述分割结果,结合椎间盘成像特点和局部图像灰度投影,进一步实现基于马尔科夫随机场(Markov random field,MRF)的椎间盘快速无监督分割;通过分割结果判断并定量计算椎间盘突出程度。实验表明该算法快速有效,可以辅助医生诊断、治疗腰椎间盘突出等疾病。

关键词：医学图像处理与分析腰部核磁共振图像基于独立分量分析的主动外观模型马尔科夫随机场

The upper bound of the minimal number of hidden neurons for the parity problem in binary neural networks

在线全文

学校读者我要写书评

暂无评论

Science china(information Sciences) 2012年第7期55卷 1579-1587页

作者： LU Yang ,YANG Juan,WANG Qiang & HUANG ZhenJin school of computer and information,hefei university of technology,hefei 230009,china school of computer and information Hefei University of Technology Hefei China

Binary neural networks (BNNs) have important value in many application *** adopt linearly separable structures,which are simple and easy to implement by *** a BNN with single hidden layer,the problem of how to determine the upper bound of the number of hidden neurons has not been solved well and *** paper defines a special structure called most isolated samples (MIS) in the Boolean *** prove that at least 2 n 1 hidden neurons are needed to express the MIS logical relationship in the Boolean space if the hidden neurons of a BNN and its output neuron form a structure of AND/OR *** the paper points out that the n -bit parity problem is just equivalent to the MIS ***,by proposing a new concept of restraining neuron and using it in the hidden layer,we can reduce the number of hidden neurons to n .This result explains the important role of restraining neurons in some ***,on the basis of Hamming sphere and SP function,both the restraining neuron and the n -bit parity problem are given a clear logical meaning,and can be described by a series of logical expressions.

关键词： binary neural network restraining neuron n -bit parity problem Hamming sphere SP function

THE LIMITING CASE OF THIELE'S INTERPOLATING CONTINUED FRACTION EXPANSION

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Computational Mathematics 2001年第4期19卷 433-444页

作者： Jie-qing Tan (Institute of Applied Mathematics, College of Science and CAD/CG Division College of computer & information hefei, university of technology, hefei 230009, china) 中国科学技术大学安徽合肥 230009

By means of the determinantal formulae for inverse and reciprocal differences with coincident data points, the limiting case of Thiele's interpolating continued fraction expansion is studied in this paper and given numerical example shows that the limiting Thiele's continued fraction expansion can be determined once for all instead of carrying out computations for each step to obtain each convergent as done in [3].

关键词： Continued fraction Inverse difference Reciprocal difference Expansion.

在线全文

学校读者我要写书评

暂无评论

基于邻域粗糙集的偏标记特征选择

山东大学学报（理学版） 2024年第5期59卷 100-113页

作者：高贺飞李艳王硕河北大学数学与信息科学学院河北保定071002 北京师范大学珠海分校应用数学学院广东珠海519000

基于邻域粗糙集框架提出一种针对偏标记数据的特征选择方法,构建偏标记邻域决策系统,定义偏标记学习问题中邻域粗糙集的下近似和依赖度,建立适用于偏标记分类问题的特征选择算法。该算法能够在对特征空间进行邻域粒化的同时度量候选标... 详细信息

基于邻域粗糙集框架提出一种针对偏标记数据的特征选择方法,构建偏标记邻域决策系统,定义偏标记学习问题中邻域粗糙集的下近似和依赖度,建立适用于偏标记分类问题的特征选择算法。该算法能够在对特征空间进行邻域粒化的同时度量候选标记集合中标记间的相似程度,选出与标记信息相关性较强的特征子集。使用了2种不同于最常用随机方法的假阳性候选标记生成机制,在实验部分对不同偏标记生成机制进行分析和对比。最后给出了在6个真实偏标记数据集和6个受控单标记数据集上的大量实验对比结果,验证了所提特征选择方法的有效性。

关键词：偏标记学习特征选择偏标记邻域决策系统领域粗糙集

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

在线全文

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 school of computer Science and technology Anhui University Hefei China Department of Electronic information and Electrical Engineering Hefei University Hefei 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

FUZZY MODEL FOR TWO-DIMENSIONAL RIVER WATER QUALITY SIMULATION UNDER SUDDEN POLLUTANTS DISCHARGED

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Hydrodynamics 2007年第4期19卷 434-441页

作者： LI Ru-zhong SHIGEKI Masunaga HONG Tian-qiu QIAN Jia-zhong school of Resources and Environmental Engineering Hefei University of Technology Hefei 230009 China Graduate school of Environment and information Sciences Yokohama National University Yokohama 240-8501 Japan

Based on the fuzziness and impreciseness of water environmental system, the fuzzy arithmetic was used to simulate the fuzzy and imprecise relations in modeling river water quality. By defining the parameters of water quality model as symmetrical triangular fuzzy numbers, a two-dimensional fuzzy water quality model for sudden pollutant discharge is established. From the fuzzy model, the pollutant concentrations, corresponding to the specified confidence level of a, can be obtained by means of the a-cut technique and arithmetic operations of triangular fuzzy numbers. Study results reveal that it is feasible in theory and reliable on calculation applying triangular fuzzy numbers to the simulation of river water quality.

关键词： fuzzy water quality simulation model triangular fuzzy number membership function a-cut technique

Discriminative Latent Model Based Chinese Multiword Expression Extraction

在线全文

学校读者我要写书评

暂无评论

china Communications 2012年第3期9卷 124-133页

作者： Xiao, Sun hefei Univ Technol AnHui Prov Key Lab Affect Comp & Adv Intelligent Hefei 230009 Peoples R China Dalian Univ Technol Sch Comp Sci & Technol Dalian 116024 Peoples R China

Discriminative Latent Model(DLM) is proposed for Multiword Expressions(MWEs) extraction in Chinese text to improve the performance of Machine Translation(MT) system such as Template Based MT(TBMT).For MT systems to become of further practical use,they need to be enhanced with MWEs processing *** our study towards this goal,we propose DLM,which is developed for sequence labeling task including hidden structures,to extract MWEs for MT *** combines the advantages of existing discriminative models,which can learn hidden structures in sequence labeling *** our evaluations,DLM achieves precisions ranging up to 90.73% for some type of MWEs,which is higher than state-of-the-art discriminative *** results demonstrate that it is feasible to automatically identify many Chinese MWEs using our DLM *** MWEs processing model,BLEU score of MT system has also been increased by up to 0.3 in close test.

关键词：模型基提取中国机器翻译系统 DLM 中文文本判别模型自动识别

Hybrid of comprehensive learning particle swarm optimization and SQP algorithm for large scale economic load dispatch optimization of power system

在线全文

学校读者我要写书评

暂无评论

Science china(information Sciences) 2010年第8期53卷 1566-1573页

作者： WANG Yu , LI Bin & YUAN Bo Department of Electronic Science and technology, school of information Science and technology, university of Science and technology of china, hefei 230027, china Department of Electronic Science and technology School of Information Science and Technology University of Science and Technology of China Hefei China

Economic load dispatch (ELD) is an important optimization task in power systems. In the previous works, various researchers attempted to address this problem by both mathmatical and heuristic optimization algorithms. However, there are still two practically important issues that have not attracted sufficient attention: 1) the stability of these algorithms cannot be effectively ensured; 2) the performance of these algorithms on large scale ELD optimization tasks remains to be unsatisfactory. CLPSO is an effective global optimization algorithm. To strengthen the convergence ability of CLPSO, the sequential quadratic programming (SQP) is introduced into it. This results in a new algorithm hybrid of comprehensive learning particle swarm optimization and sequential quadratic programming (SQP-CLPSO). To assess the performance of SQP-CLPSO, it is compared with several state-of-the-art evolutionary algorithms (EAs) on the classical ELD optimization problems. Experimental results show that SQP-CLPSO has very good abilities of convergence, diversity maintainence and scalability, which make it suitable for complex ELD problems.

关键词： particle swarm optimization comprehensive learning particle swarm optimization sequential quadratic programming local search power systems economic load dispatch

THE DISTRIBUTION FUNCTIONS FOR THE LINEAR COMPLEXITY OF PERIODIC SEQUENCES

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Electronics(china) 2012年第Z2期 211-214页

作者： Yang Minghui* Zhu Shixin* ** *(school of computer & information, hefei university of technology, hefei 230009, china) **(school of Mathematics, hefei university of technology, hefei 230009, china)

Linear complexity is an important standard to scale the randomicity of stream ciphers. The distribution function of a sequence complexity measure gives the function expression for the number of sequences with a given complexity measure value. In this paper, we mainly determine the distribution function of sequences with period over using Discrete Fourier Transform (DFT), where and the characteristics of are odd primes, gcd and is a primitive root modulo The results presented can be used to study the randomness of periodic sequences and the analysis and design of stream cipher.

关键词： Linear complexity Periodic sequences Discrete Fourier Transform (DFT)