一种稳健的基于VisemicLDA的口形动态特征及听视觉语音识别

视觉特征提取是听视觉语音识别研究的热点问题。文章引入了一种稳健的基于Visemic LDA的口形动态特征,这种特征充分考虑了发音时口形轮廓的变化及视觉Viseme划分。文章同时提出了一利利用语音识别结果进行LDA训练数据自动标注的方法。这种方法免去了繁重的人工标注工作,避免了标注错误。实验表明,将'VisemicLDA视觉特征引入到听视觉语音识别中,可以大大地提高噪声条件下语音识别系统的识别率;将这种视觉特征与多数据流HMM结合之后,在信噪比为10dB的强噪声情况下,识别率仍可以达到80％以上。

Unsupervised Linear Discriminant Analysis

An algorithm for unsupervised linear discriminant analysis was presented. Optimal unsupervised discriminant vectors are obtained through maximizing covariance of all samples and minimizing covariance of local k-nearest neighbor samples. The experimental results show our algorithm is effective.

An Optimization Criterion for Generalized Marginal Fisher Analysis on Undersampled Problems

Marginal Fisher analysis （MFA） not only aims to maintain the original relations of neighboring data points of the same class but also wants to keep away neighboring data points of the different classes.MFA can effectively overcome the limitation of linear discriminant analysis （LDA） due to data distribution assumption and available projection directions.However,MFA confronts the undersampled problems.Generalized marginal Fisher analysis （GMFA） based on a new optimization criterion is presented,which is applicable to the undersampled problems.The solutions to the proposed criterion for GMFA are derived,which can be characterized in a closed form.Among the solutions,two specific algorithms,namely,normal MFA （NMFA） and orthogonal MFA （OMFA）,are studied,and the methods to implement NMFA and OMFA are proposed.A comparative study on the undersampled problem of face recognition is conducted to evaluate NMFA and OMFA in terms of classification accuracy,which demonstrates the effectiveness of the proposed algorithms.

Facial Expression Recognition Model Depending on Optimized Support Vector Machine

In computer vision,emotion recognition using facial expression images is considered an important research issue.Deep learning advances in recent years have aided in attaining improved results in this issue.According to recent studies,multiple facial expressions may be included in facial photographs representing a particular type of emotion.It is feasible and useful to convert face photos into collections of visual words and carry out global expression recognition.The main contribution of this paper is to propose a facial expression recognitionmodel(FERM)depending on an optimized Support Vector Machine(SVM).To test the performance of the proposed model(FERM),AffectNet is used.AffectNet uses 1250 emotion-related keywords in six different languages to search three major search engines and get over 1,000,000 facial photos online.The FERM is composed of three main phases:(i)the Data preparation phase,(ii)Applying grid search for optimization,and(iii)the categorization phase.Linear discriminant analysis(LDA)is used to categorize the data into eight labels(neutral,happy,sad,surprised,fear,disgust,angry,and contempt).Due to using LDA,the performance of categorization via SVM has been obviously enhanced.Grid search is used to find the optimal values for hyperparameters of SVM(C and gamma).The proposed optimized SVM algorithm has achieved an accuracy of 99%and a 98%F1 score.

基于文本挖掘技术校园学生投诉问题分析

本研究主要探索从文本中获得有效信息的问题。本文以投诉学校的文本为处理对象,调用Python对投诉文本分析、词频统计以及主题分析,从而了解投诉文本的集中问题点,为快速有效解决学生投诉问题、合理处理学校与学生的关系提供参考,同时指出对投诉问题分类是值得深入探讨的问题。

近红外光谱结合线性判别分析方法在食醋品牌鉴别中的应用

采用近红外光谱技术结合化学计量学手段,建立不同品牌食醋的快速鉴别方法。用近红外光谱仪对103组食醋样品进行扫描,采用二阶导数对图谱进行预处理、标准化处理、T检验和主成分分析(principal component analysis,PCA),运用留一法构建线性判别分析(linear discriminant analysis,LDA)模型。结果表明,原始近红外谱图经过处理后,显示出同种品牌食醋主成分的聚类趋势;交叉验证结果表明,PCA-LDA模型预测不同品牌食醋的正确率高达85.57%,该模型具有较好的预测效果。该研究结合近红外光谱与PCA-LDA模型,为不同品牌食醋提供一种快速鉴别方法,具有处理近红外光谱数据,研究物质主成分的应用潜力。

Gait Recognition by Cross Wavelet Transform and Graph Model

In this paper, a multi-view gait based human recognition system using the fusion of two kinds of features is proposed.We use cross wavelet transform to extract dynamic feature and bipartite graph model to extract static feature which are coefficients of quadrature mirror filter(QMF)-graph wavelet filter bank. Feature fusion is done after normalization. For normalization of features, min-max rule is used and mean-variance method is used to find weights for normalized features. Euclidean distance between each feature vector and center of the cluster which is obtained by k-means clustering is used as similarity measure in Bayesian framework. Experiments performed on widely used CASIA B gait database show that, the fusion of these two feature sets preserve discriminant information. We report 99.90 % average recognition rate.

Polarimetry feature parameter deriving from Mueller matrix imaging and auto-diagnostic signicance to distinguish HSIL and CSCC

High-grade squamous intraepithelial lesion(HSIL)is regarded as a serious precancerous state of cervix,and it is easy to progress into cervical invasive carcinoma which highlights the importance of earlier diagnosis and treatment of cervical lesions.Pathologists examine the biopsied cervical epithelial tissue through a microscope.The pathological examination will take a long time and sometimes results in high inter-and intra-observer variability in outcomes.Polarization imaging techniques have broad application prospects for biomedical diagnosis such as breast,liver,colon,thyroid and so on.In our team,we have derived polarimetry feature parameters(PFPs)to characterize microstructural features in histological sections of breast tissues,and the accuracy for PFPs ranges from 0.82 to 0.91.Therefore,the aim of this paper is to distinguish automatically microstructural features between HSIL and cervical squamous cell carcinoma(CSCC)by means of polarization imaging techniques,and try to provide quantitative reference index for patho-logical diagnosis which can alleviate the workload of pathologists.Polarization images of the H&E stained histological slices were obtained by Mueller matrix microscope.The typical path-ological structure area was labeled by two experienced pathologists.Calculate the polarimetry basis parameter(PBP)statistics for this region.The PBP statistics(stat PBPs)are screened by mutual information(MI)method.The training method is based on a linear discriminant analysis(LDA)classier whichnds the most simplied linear combination from these stat PBPs and the accuracy remains constant to characterize the specic microstructural feature quantitatively in cervical squamous epithelium.We present results from 37 clinical patients with analysis regions of cervical squamous epithelium.The accuracy of PFP for recognizing HSIL and CSCC was 83.8%and 87.5%,respectively.This work demonstrates the ability of PFP to quantitatively charac-terize the cervical squamous epithelial lesions in the H&E pathological sections.Signicance:Polarization detection technology provides an effcient method for digital pathological diagnosis and points out a new way for automatic screening of pathological sections.

基于小波变换和离散余弦变换的fisher脸识别

本文结合几种现有的人脸识别特征提取算法，先对人脸图像进行小波分解去噪；然后通过离散余弦变换对低频分量作进一步特征提取和压缩，保留人脸图像中对光照、姿态、表情变化不敏感的识别信息；接着利用PCA和LDA相结合得到最终的识别特征；最后采用欧式距离和最近邻分类器识别人脸。实验采用ORL标准人脸库验证了这种组合的有效性。

Monosaccharide analysis and fingerprinting identification of polysaccharides from Poria cocos and Polyporus umbellatus by HPLC combined with chemometrics methods

Objective:Poria cocos and Polyporus umbellatus are similar medicinal fungi in traditional Chinese medicines.A method for fingerprint analysis of monosaccharide composition of polysaccharides by HPLC combined with chemometrics methods has been developed for characterization and discrimination of them in this research.Methods:The polysaccharides were extracted by decocting in water,and then completely hydrolyzed with hydrochloride.Monosaccharides in the hydrolyzates were derivatized with 1-phenyl-3-methyl-5-pyrazolone(PMP)for HPLC analysis.More than 20 batches of P.cocos and P.umbellatus from different regions were analyzed.Results:The fingerprints of P.cocos showed five common characteristic peaks,which were identified by comparing with the reference substances.The five peaks corresponded to the derivatives of mannose,ribose,glucose,galactose,and fucose.At the same time,the fingerprints of P.umbellatus showed eight common characteristic peaks,of which seven were identified as the derivatives of mannose,ribose,rhamnose,glucose,galactose,xylose,and fucose.Moreover,the similarity of their fingerprints was respectively calculated by the Similarity Evaluation System for Chromatographic Fingerprint of TCM published by China Pharmacopoeia Committee(Version 2004 A).And the data were further processed by hierarchical cluster analysis(HCA)and principal component analysis(PCA).The similarity evaluation and HCA indicated that there were no significant difference in P.cocos or P.umbellatus samples from different geographical regions,but PCA was performed to characterize the difference in monosaccharide constituents between P.cocos and P.umbellatus,and linear discriminant analysis(LDA)showed the overall correct classification rate was 100%.Conclusion:The fingerprint analysis method of monosaccharide composition of water-soluble polysaccharides can distinguish P.cocos and P.umbellatus,and can be applied for the authentication or quality control for P.cocos and P.umbellatus.

Identification of Graves’ophthalmology by laser-induced breakdown spectroscopy combined with machine learning method

Diagnosis of the Graves’ophthalmology remains a significant challenge.We identified between Graves’ophthalmology tissues and healthy controls by using laser-induced breakdown spectroscopy(LIBS)combined with machine learning method.In this work,the paraffin-embedded samples of the Graves’ophthalmology were prepared for LIBS spectra acquisition.The metallic elements(Na,K,Al,Ca),non-metallic element(O)and molecular bands((C-N),(C-O))were selected for diagnosing Graves’ophthalmology.The selected spectral lines were inputted into the supervised classification methods including linear discriminant analysis(LDA),support vector machine(SVM),k-nearest neighbor(ANN),and generalized regression neural network(GRNN),respectively.The results showed that the predicted accuracy rates of LDA,SVM,ANN,GRNN were 76.33%,96.28%,96.56%,and 96.33%,respectively.The sensitivity of four models were 75.89%,93.78%,96.78%,and 96.67%,respectively.The specificity of four models were 76.78%,98.78%,96.33%,and 96.00%,respectively.This demonstrated that LIBS assisted with a nonlinear model can be used to identify Graves’ophthalmopathy with a higher rate of accuracy.The ANN had the best performance by comparing the three nonlinear models.Therefore,LIBS combined with machine learning method can be an effective way to discriminate Graves’ophthalmology.

Scores of amino acid 0D-3D information as applied in cleavage site prediction and better specificity elucidation for human immunodeficiency virus type 1 protease

A new set of descriptors,namely score vectors of the zero dimension,one dimension,two dimensions and three dimensions(SZOTT),was derived from principle component analysis of a matrix of 1369 structural variables including 0D,1D,2D and 3D information for the 20 coded amino acids. SZOTT scales were then used in cleavage site prediction of human immunodeficiency virus type 1 protease. Linear discriminant analysis(LDA) and support vector machines(SVM) were applied to developing models to predict the cleavage sites. The results obtained by linear discriminant analysis(LDA) and support vector machines(SVM) are as follows. The Matthews correlation coefficients(MCC) by the resubstitution test,leave-one-out cross validation(LOOCV) and external validation are 0.879 and 0.911,0.849 and 0.901,0.822 and 0.846,respectively. The receiver operating characteristic(ROC) analysis showed that the SVM model possesses better simulative and predictive ability in comparison with the LDA model. Satisfactory results show that SZOTT descriptors can be further used to predict cleavage sites of human immunodeficiency virus type 1 protease.

Adaptive Fault Detection Scheme Using an Optimized Self-healing Ensemble Machine Learning Algorithm

This paper proposes a new cost-efficient,adaptive,and self-healing algorithm in real time that detects faults in a short period with high accuracy,even in the situations when it is difficult to detect.Rather than using traditional machine learning(ML)algorithms or hybrid signal processing techniques,a new framework based on an optimization enabled weighted ensemble method is developed that combines essential ML algorithms.In the proposed method,the system will select and compound appropriate ML algorithms based on Particle Swarm Optimization(PSO)weights.For this purpose,power system failures are simulated by using the PSCA D-Python co-simulation.One of the salient features of this study is that the proposed solution works on real-time raw data without using any pre-computational techniques or pre-stored information.Therefore,the proposed technique will be able to work on different systems,topologies,or data collections.The proposed fault detection technique is validated by using PSCAD-Python co-simulation on a modified and standard IEEE-14 and standard IEEE-39 bus considering network faults which are difficult to detect.

Retrieval of flower videos based on a query with multiple species of flowers

Searching,recognizing and retrieving a video of interest froma large collection of a video data is an instantaneous requirement.This requirement has been recognized as an active area of research in computer vision,machine learning and pattern recognition.Flower video recognition and retrieval is vital in the field of floriculture and horticulture.In this paper we propose a model for the retrieval of videos of flowers.Initially,videos are represented with keyframes and flowers in keyframes are segmented from their background.Then,the model is analysed by features extracted from flower regions of the keyframe.A Linear Discriminant Analysis(LDA)is adapted for the extraction of discriminating features.Multiclass Support VectorMachine(MSVM)classifier is applied to identify the class of the query video.Experiments have been conducted on relatively large dataset of our own,consisting of 7788 videos of 30 different species of flowers captured from three different devices.Generally,retrieval of flower videos is addressed by the use of a query video consisting of a flower of a single species.In this work we made an attempt to develop a system consisting of retrieval of similar videos for a query video consisting of flowers of different species.

Kernel feature extraction methods observed from the viewpoint of generating-kernels

This paper introduces an idea of generating a kernel from an arbitrary function by embedding the training samples into the function.Based on this idea,we present two nonlinear feature extraction methods:generating kernel principal component analysis(GKPCA)and generating kernel Fisher discriminant(GKFD).These two methods are shown to be equivalent to the function-mapping-space PCA(FMS-PCA)and the function-mapping-space linear discriminant analysis(FMS-LDA)methods,respectively.This equivalence reveals that the generating kernel is actually determined by the corresponding function map.From the generating kernel point of view,we can classify the current kernel Fisher discriminant(KFD)algorithms into two categories:KPCA+LDA based algorithms and straightforward KFD(SKFD)algorithms.The KPCA+LDA based algorithms directly work on the given kernel and are not suitable for non-kernel functions,while the SKFD algorithms essentially work on the generating kernel from a given symmetric function and are therefore suitable for non-kernels as well as kernels.Finally,we outline the tensor-based feature extraction methods and discuss ways of extending tensor-based methods to their generating kernel versions.