Boosting multiple classifiers by hybrid discriminant analysis for face identification

2005 ◽  
Author(s):  
Jie Yu ◽  
Qi Tian
Keyword(s):  
Discriminant Analysis ◽  
Face Identification ◽  
Multiple Classifiers

INTEGRATION OF MULTIPLE CLASSIFIERS FOR COMPUTERIZED DETECTION OF LUNG NODULES IN CT

2015 ◽  
Vol 27 (04) ◽  
pp. 1550040 ◽  
Author(s):  
Jorge Juan Suárez-Cuenca ◽  
Wei Guo ◽  
Qiang Li
Keyword(s):  
Discriminant Analysis ◽  
Ct Scan ◽  
Majority Voting ◽  
Classifier Combination ◽  
Probability Method ◽  
Multiple Classifiers ◽  
Combination Methods ◽  
Majority Voting Method ◽  
Simple Logistic ◽  
Voting Method

The purpose of this study was to investigate the usefulness of various classifier combination methods for improving the performance of a computer-aided diagnosis (CAD) system for pulmonary nodule detection in computed tomography (CT). We employed 85 CT scans with 110 nodules in the publicly available Lung Image Database Consortium (LIDC) dataset. We first applied our CAD scheme trained previously to the LIDC cases for identifying initial nodule candidates, and extracting 18 features for each nodule candidate. We used eight individual classifiers for false positives (FPs) reduction, including linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), Naïve Bayes, simple logistic, artificial neural network (ANN) and support vector machines (SVMs) with three different kernels. Five classifier combination methods were then employed to integrate the outputs of the eight individual classifiers for improving detection performance. The five combination methods included two supervised (a likelihood ratio (LR) method and a probability method based on the output scores of the eight individual classifiers) and three unsupervised ones (the sum, the product and the majority voting of the output scores from the eight individual classifiers). Leave-one-case-out approach was employed to train and test individual classifiers and supervised combination methods. At a sensitivity of 80%, the numbers of FPs per CT scan for the eight individual classifiers were 6.1 for LDA, 19.9 for QDA, 10.8 for Naïve Bayes, 8.4 for simple logistic, 8.6 for ANN, 23.7 for SVM-dot, 17.0 for SVM-poly, and 23.4 for SVM-anova; the numbers of FPs per CT scan for the five combination methods were 3.3 for the majority voting method, 5.0 for the sum, 4.6 for the product, 65.7 for the LR and 3.9 for the probability method. Compared to the best individual classifier, the majority voting method reduced 45% of FPs at 80% sensitivity. The performance of our CAD can be improved by combining multiple classifiers. The majority voting method achieved higher performance levels than other combination methods and all individual classifiers.

An Introduction to Discriminant Analysis

1989 ◽  
Vol 22 (3) ◽  
pp. 158-168 ◽  
Author(s):  
Carl J Huberty ◽  
Richard M. Barton
Keyword(s):  
Discriminant Analysis

Brief Report. The PCL-R and Gender

2000 ◽  
Vol 16 (3) ◽  
pp. 147-149 ◽  
Author(s):  
Martin Grann
Keyword(s):  
Gender Differences ◽  
Sexual Behavior ◽  
Discriminant Analysis ◽  
Juvenile Delinquency ◽  
Violent Offenders ◽  
Matched Pairs ◽  
Psychopathy Checklist ◽  
Psychopathy Checklist Revised ◽  
And Gender

Summary: Hare's Psychopathy Checklist - Revised (PCL-R; Hare, 1991 ) was originally constructed for use among males in correctional and forensic settings. In this study, the PCL-R protocols of 36 matched pairs of female and male violent offenders were examined with respect to gender differences. The results indicated a few significant differences. By means of discriminant analysis, male Ss were distinguished from their female counterparts through their relatively higher scores on “callous/lack of empathy” (item 8) and “juvenile delinquency” (item 18), whereas the female Ss scored relatively higher on “promiscuous sexual behavior” (item 11). Some sources of bias and possible implications are discussed.

The Assessment of Fear of Flying: Elaboration and Validation of a Videotape as an Analogous Situation of a Flight1

1997 ◽  
Vol 13 (2) ◽  
pp. 118-130 ◽  
Author(s):  
Juan I. Capafóns ◽  
Carmen D. Sosa ◽  
Manuel Herrero ◽  
Conrado Viña
Keyword(s):  
Heart Rate ◽  
Discriminant Analysis ◽  
Post Treatment ◽  
Subjective Measure ◽  
Physiological Measures ◽  
Personal Safety ◽  
Metal Detector ◽  
Fear Of Flying ◽  
Situational Anxiety ◽  
Treatment Measures

The results are presented for the validation of a videotape as an analogous situation for a flight. The video includes the most significant elements of a flight by air: confirmation of the flight, packing, going to the airport, checking-in, going through the metal-detector, departure lounge, boarding the plane, demonstration of the personal safety drills, interiors and exteriors during the flight and landing. Two physiological measures are used for validation (heart rate and temperature) and a subjective measure (situational anxiety, SA). The results (both t-tests and the discriminant analysis) indicate that the videotape is able to discriminate between phobics and non-phobics of flying in the three variables considered. With respect to sensitivity in detecting change produced by various treatments in clients with phobia of flying, the results are also satisfactory. A greater differentiation is produced between the pre-post treatment measures, both in subjective and in the physiological measures.

Sign in / Sign up

Export Citation Format

Share Document