Linear discriminant analysis

About: Linear discriminant analysis is a research topic. Over the lifetime, 18361 publications have been published within this topic receiving 603195 citations. The topic is also known as: Linear discriminant analysis & LDA.

The SAGE Dictionary of Quantitative Management Research

Abstract: Introduction A/B Split Testing Analytic Hierarchy Process Association and Causation in Quantitative Research Association Rule Mining Bass Model Canonical Correlation Chaos Theory Classification and Ranking Belief Simplex Clustering Algorithms Cluster Analysis Coding Conventions for Representing Information Conceptual Equivalence Confidence Intervals Conjoint Analysis Construct Operationalization Review (CORE) Correlation Analysis Correspondence Analysis Cross-National/Cultural Comparisons Cross-Sectional Designs Data Envelopment Analysis in Management Data Mining Data Set Structure Data Transformation Dempster-Shafer Theory Designing Experiments Discriminant Analysis Dominance Analysis DS/AHP Dummy Variable Coding Event Studies Methodology Evaluation Research Experimental Design Exploratory or Confirmatory Factor Analysis Factor Analysis Fuzzy Decision Trees Fuzzy Sets Fuzzy Time Series Models Generalized Linear Mixed Models Generalized Linear Models Geodemographics Geographical Information Systems Growth Models Intraclass Correlation Coefficient Internal and External Validity Item Response Theory Item Response Theory for Management Latent Segments Analysis Latent Variable Models Logical Discriminant Models Logistic Growth Model Logistic Regression Logistic Spline Model Measurement Reliability Measurement Invariance in Multigroup Research Measurement Scales Moderator-Mediator Variable Distinction Mixture Models Multi-Attribute Utility/Value Theory Multidimensional Scaling Multilevel Models Multi-Logistic Growth Model Multinomial Logistic Regression Multi-State Modelling Non-Parametric Measures of Association Optimal Control Models in Management Ordinary Least-Squares Regression Panel Design Paper Versus Electronic Surveys Parametric Tests Partial Correlation Principal Components Analysis Programme Evaluation PROMETHEE Method of Ranking Alternatives Proportional Odds Model Quantile Estimators Quantile Estimators - Bootstrap Confidence Intervals Rasch Model for Measurement Receiver Operating Characteristic Response Styles in Cross-National Research Retail Site Selection Sampling Equivalence in Cross-National Research Sample Size for Proportions Sample Sizes Versus Usable Observations Self-Organizing Maps Single-Case Research Designs Single-Case Single-Baseline Designs Sngle-Case Multiple-Baseline Designs Simulation - Discrete Event Simulation - Methodology Structural Equation Modelling in Business Management Structural Equation Modelling in Marketing - Part 1: Introduction and Basic Concepts Structural Equation Modelling in Marketing - Part 2: Model Calibration Structural Equation Modelling in Marketing - Part 3: An Example Study Design Survey Design Tabu Search Testing a Simple Hypothesis Validity Variable Precision Rough Sets Voronoi Diagrams Web Surveys Index

Approaching automatic recognition of emotion from voice: a rough benchmark

Abstract: Automatic recognition of a speaker’s emotions is a natural objective for research, but is difficult to gauge the level of performance that is currently attainable We describe a study that offers a rough benchmark Speech data came from five passages of about 100 syllables each They had been selected following pilot studies because they were effective at evoking specific emotion fear, anger, happiness, sadness, and neutrality 40 subjects were recorded reading them A battery of 32 potentially relevant features was extracted using our ASSESS system They were broadly speaking prosodic, derived from contours tracing the movement of intensity and pitch They were input to statistical decision mechanisms, of two types Discriminant analysis uses linear combinations of variables to separate samples that belong to different categories There are reasons to suspect that linear combination will not be appropriate, so neural net classifiers were also considered An automatic relevance determination procedure was used to identify the most relevant parameters Discriminant analysis outperformed the neural networks Using 90% of the data for training, and testing on the remaining 10%, a classification rate of 55 % (+/008%) was achieved The most useful predictors covered a variety of properties – intensity (relative to the start of the passage) and its spread; pitch spread; durations of silences, rises in intensity, and syllables; and a property related to the shape of ‘tunes’, the number of inflections in the F0 contour per tune Many more variables were less important, but nevertheless contributed

Gabor-Based Kernel Partial-Least-Squares Discrimination Features for Face Recognition

Abstract: The paper presents a novel method for the extraction of facial features based on the Gabor-wavelet representation of face images and the kernel partial-least-squares discrimination (KPLSD) algorithm. The proposed feature-extraction method, called the Gabor-based kernel partial-least-squares discrimination (GKPLSD), is performed in two consecutive steps. In the first step a set of forty Gabor wavelets is used to extract discriminative and robust facial features, while in the second step the kernel partial-least-squares discrimination technique is used to reduce the dimensionality of the Gabor feature vector and to further enhance its discriminatory power. For optimal performance, the KPLSD-based transformation is implemented using the recently proposed fractional-power-polynomial models. The experimental results based on the XM2VTS and ORL databases show that the GKPLSD approach outperforms feature-extraction methods such as principal component analysis (PCA), linear discriminant analysis (LDA), kernel principal component analysis (KPCA) or generalized discriminant analysis (GDA) as well as combinations of these methods with Gabor representations of the face images. Furthermore, as the KPLSD algorithm is derived from the kernel partial-least-squares regression (KPLSR) model it does not suffer from the small-sample-size problem, which is regularly encountered in the field of face recognition.