Feature Selection

Tony Bellotti; Ilia Nouretdinov; Meng Yang; Alexander Gammerman

doi:10.1016/B978-0-12-398537-8.00006-7

Feature Selection

Tony Bellotti, Ilia Nouretdinov, Meng Yang, Alexander Gammerman

Research output: Chapter in Book/Conference proceeding › Book Chapter › peer-review

5 Citations (Scopus)

Abstract

In this chapter we consider the implementation of feature selection approaches within the Conformal Predictor framework. We begin with a review of feature selection, then consider several approaches to implementation. First, we use existing feature selection methods within conformal predictors, which raises some computational issues. Second, we use techniques specifically designed for conformal predictors: (1) the strangeness minimization feature selection (SMFS) method and (2) the average confidence maximization (ACM) method. SMFS minimizes the overall nonconformity values of a sequence of examples, whereas ACM maximizes the average confidence output by the conformal predictor using a subset of features. We also give some results and illustrations based on a medical dataset for abdominal pain diagnosis collected in a Scottish hospital.

Original language	English
Title of host publication	Conformal Prediction for Reliable Machine Learning
Subtitle of host publication	Theory, Adaptations and Applications
Publisher	Elsevier Inc.
Pages	115-130
Number of pages	16
ISBN (Print)	9780123985378
DOIs	https://doi.org/10.1016/B978-0-12-398537-8.00006-7
Publication status	Published - Apr 2014
Externally published	Yes

Keywords

Confidence Maximization
Feature Selection
Microarray Classification
Nearest Centroid Classifier
Strangeness Minimization
Support Vector Machine

ASJC Scopus subject areas

General Computer Science

Access to Document

10.1016/B978-0-12-398537-8.00006-7

Cite this

@inbook{d2c9f85bb31946f093716d6fa9393f28,

title = "Feature Selection",

abstract = "In this chapter we consider the implementation of feature selection approaches within the Conformal Predictor framework. We begin with a review of feature selection, then consider several approaches to implementation. First, we use existing feature selection methods within conformal predictors, which raises some computational issues. Second, we use techniques specifically designed for conformal predictors: (1) the strangeness minimization feature selection (SMFS) method and (2) the average confidence maximization (ACM) method. SMFS minimizes the overall nonconformity values of a sequence of examples, whereas ACM maximizes the average confidence output by the conformal predictor using a subset of features. We also give some results and illustrations based on a medical dataset for abdominal pain diagnosis collected in a Scottish hospital.",

keywords = "Confidence Maximization, Feature Selection, Microarray Classification, Nearest Centroid Classifier, Strangeness Minimization, Support Vector Machine",

author = "Tony Bellotti and Ilia Nouretdinov and Meng Yang and Alexander Gammerman",

year = "2014",

month = apr,

doi = "10.1016/B978-0-12-398537-8.00006-7",

language = "English",

isbn = "9780123985378",

pages = "115--130",

booktitle = "Conformal Prediction for Reliable Machine Learning",

publisher = "Elsevier Inc.",

address = "United States",

}

TY - CHAP

T1 - Feature Selection

AU - Bellotti, Tony

AU - Nouretdinov, Ilia

AU - Yang, Meng

AU - Gammerman, Alexander

PY - 2014/4

Y1 - 2014/4

N2 - In this chapter we consider the implementation of feature selection approaches within the Conformal Predictor framework. We begin with a review of feature selection, then consider several approaches to implementation. First, we use existing feature selection methods within conformal predictors, which raises some computational issues. Second, we use techniques specifically designed for conformal predictors: (1) the strangeness minimization feature selection (SMFS) method and (2) the average confidence maximization (ACM) method. SMFS minimizes the overall nonconformity values of a sequence of examples, whereas ACM maximizes the average confidence output by the conformal predictor using a subset of features. We also give some results and illustrations based on a medical dataset for abdominal pain diagnosis collected in a Scottish hospital.

AB - In this chapter we consider the implementation of feature selection approaches within the Conformal Predictor framework. We begin with a review of feature selection, then consider several approaches to implementation. First, we use existing feature selection methods within conformal predictors, which raises some computational issues. Second, we use techniques specifically designed for conformal predictors: (1) the strangeness minimization feature selection (SMFS) method and (2) the average confidence maximization (ACM) method. SMFS minimizes the overall nonconformity values of a sequence of examples, whereas ACM maximizes the average confidence output by the conformal predictor using a subset of features. We also give some results and illustrations based on a medical dataset for abdominal pain diagnosis collected in a Scottish hospital.

KW - Confidence Maximization

KW - Feature Selection

KW - Microarray Classification

KW - Nearest Centroid Classifier

KW - Strangeness Minimization

KW - Support Vector Machine

UR - http://www.scopus.com/inward/record.url?scp=84902232904&partnerID=8YFLogxK

U2 - 10.1016/B978-0-12-398537-8.00006-7

DO - 10.1016/B978-0-12-398537-8.00006-7

M3 - Book Chapter

AN - SCOPUS:84902232904

SN - 9780123985378

SP - 115

EP - 130

BT - Conformal Prediction for Reliable Machine Learning

PB - Elsevier Inc.

ER -

Feature Selection

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this