奇异类内离差矩阵条件下的Fisher最优判据

特征提取是模式分类与识别的重要环节，Fisher最优判据是特征提取的基本方法之一．本文提出了一种计算奇异类内离差矩阵条件下Fisher最优判据的新方法，并给出了计算步骤．     

A multi-target approach for isolated word recognition using artificial neural network

I.TntroductionStatisticalandneuralnetworkmcthodsforpatternclassiflcationusesignificantlydifTerentapproachesintrainingaclassificr.Inthestatistica1approach,thcformationofaclassifier1arge1ydependsonthestatisticsofthetrainingpatternsand,insomecases,theassumptionsaboutthedistributionofthepopulation.Theneuralnetworkmethodisnon-parametricandcanbeadaptivcinthetrainingprocessl'l.Becauseofitssimplicityandflexibility,theneuralnetworkhasbecnincreasing1yusedforpatternclassiflcation.Itisnowwe11knownthatan…     

Spectral pattern recognition of improved voice quality

The self-organizing map (a neural network) was applied to the spectral pattern recognition of voice quality in 34 subjects: 15 patients operated on because of insufficient glottal closure and 19 subjects not treated for voice disorders. The voice samples, segments of sustained /a/, were perceptually rated by six experts. A self-organized acoustic feature map was first computed from tokens of /a/ and then used for the analysis of the samples. The locations of the samples on the map were determined and the distances from a normal reference were compared with the perceptual ratings. The map locations corresponded to the degree of audible disorder: the samples judged as normal were overlapping or close to the normal reference, whereas the samples judged as dysphonie were located further away from it. The comparison of pre- and postoperative samples of the patients showed that the perceived improvement of voice quality was also detected by the map.     

On a new stochastic global optimization algorithm based on censored observations

In this paper a new algorithm is proposed for global optimization problems. The main idea is that of modifying a standard clustering approach by sequentially sampling the objective function while adaptively deciding an appropriate sample size. Theoretical as well as computational results are presented.     

Spectroscopic study on the complex formation of chromogenic bridged calixarenes with aliphatic amines

The complex formation between chromogenic capped calix 4 arene derivatives comprising indophenol indicator group(s), and aliphatic amines has been studied by UV/Vis spectroscopy. The equilibrium constants have been determined in ethanol, and—for one ligand—also in dimethylsulfoxide. The results have been interpreted in terms of various types of host–guest interactions and of steric effects.     

Theoretical study of peptide model dimers. Homo versus heterochiral complexes

The study of possible chiral recognition of a series of peptide models (For-Gly-NH₂, For-Ala-NH₂ and four of their fluoro substituted derivatives) has been carried out by means of DFT calculations. Homo (L,L) and heterochiral (L,D) dimers formed by hydrogen bond (HB) complexation have been considered. Initially, the conformational preferences of the monomers have been calculated and used to generate all the possible homo and heterochiral dimers. The energetic results show that in most cases, the β monomers are the most stable while in the dimers, the γ–γ complexes show the strongest interaction energies. In three of the four chiral cases studied, a heterochiral dimer is the most stable one. In addition, the electron density and nuclear shielding of the complexes have been studied.     

基于Delaunay三角法的电压门控钾离子通道的分类和拓扑结构识别

本文构建了一个Delaunay模型对电压门控钾离子(Kv)通道进行预测。该方法通过建立一系列带有隐含变量的单纯形来分类电压门控钾离子通道,然后通过未知序列在主成分空间里面的投影来预测结构。结果表明该模型无论是在分类和结构预测上均可以得到很好的结果。     

汉字识别的加工模型

通过文献分析,概述了认知心理学关于汉字识别过程及其加工机制研究的几种主要的加工模型,即经成分识别模型、多层次交互激活模型、连接主义模型、合体汉字字形识别模型和汉字识别的多层次格式塔双向加工模型.     

Design and synthesis of novel imidazolium-based ionic liquids with a pseudo crown-ether moiety: diastereomeric interaction of a racemic ionic liquid with enantiopure europium complexes

A planar-chiral imidazolium salt with a tris(oxoethylene) bridge was synthesized, and its potential application as a room temperature ionic liquid with a molecular-recognition ability was demonstrated.     

Security Applications of Optical Face Recognition System: Access Control in E-Learning

The educational system has gradually shifted from a face-to-face to an e-learning system, which has become prevalent in advanced countries with the advance of information technology, and connection of global networks. Accordingly, a growing demand is emerging for more reliable individual certification with technical precision in order to measure and record learning achievements and credentials of participants. The present system has a limit in terms of registration capacity, therefore, its accuracy has often been questioned. Against this background, an individual certification system is proposed particularly for access control in e-learning. Under our proposed system, a compact optical correlator for facial recognition is employed. This correlator was previously tested for of biometrics authentication accuracy and proved highly reliable, having recorded remarkably low error rates (below 1%). The recorded error rate is sufficiently robust that the system itself can be regarded as a valid and practical viable attestation system.