Genetic algorithms, neural networks, fuzzy inference system, support vector machines for call performance classification

Pretesh B. Patel; Tshilidzi Marwala

doi:10.1109/ICMLA.2009.43

Genetic algorithms, neural networks, fuzzy inference system, support vector machines for call performance classification

Pretesh B. Patel, Tshilidzi Marwala

Faculty of Engineering and the Built Environment

University of Johannesburg

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

6 Citations (Scopus)

Abstract

Accurate classification of caller interactions within Interactive Voice Response systems would assist corporations to determine caller behavior within these telephony applications. This paper details the development of such a classification system for a pay beneficiary application. Fuzzy Inference Systems, Multi-Layer Perceptron, Support Vector Machine and ensemble of classifiers were developed. Accuracy, sensitivity and specificity performance metrics were computed as well as compared for these classification solutions. Ideally, a classifier should have high sensitivity and high specificity. Exceptional results were achieved. The ensemble of classifiers is the preferred solution, yielding an accuracy of 99.17%.

Original language	English
Title of host publication	8th International Conference on Machine Learning and Applications, ICMLA 2009
Pages	415-420
Number of pages	6
DOIs	https://doi.org/10.1109/ICMLA.2009.43
Publication status	Published - 2009
Event	8th International Conference on Machine Learning and Applications, ICMLA 2009 - Miami Beach, FL, United States Duration: 13 Dec 2009 → 15 Dec 2009

Publication series

Name	8th International Conference on Machine Learning and Applications, ICMLA 2009

Conference

Conference	8th International Conference on Machine Learning and Applications, ICMLA 2009
Country/Territory	United States
City	Miami Beach, FL
Period	13/12/09 → 15/12/09

Keywords

Artificial neural networks
Caller experience performance classification
Ensemble of classifiers
Fuzzy inference systems
Genetic algorithms
Interactive voice response
Support vector machines

ASJC Scopus subject areas

Computer Science Applications
Human-Computer Interaction
Software

Access to Document

10.1109/ICMLA.2009.43

Cite this

Patel, P. B., & Marwala, T. (2009). Genetic algorithms, neural networks, fuzzy inference system, support vector machines for call performance classification. In 8th International Conference on Machine Learning and Applications, ICMLA 2009 (pp. 415-420). Article 5381487 (8th International Conference on Machine Learning and Applications, ICMLA 2009). https://doi.org/10.1109/ICMLA.2009.43

@inproceedings{9c346a064ffc425cb1dec64edc7ae46a,

title = "Genetic algorithms, neural networks, fuzzy inference system, support vector machines for call performance classification",

abstract = "Accurate classification of caller interactions within Interactive Voice Response systems would assist corporations to determine caller behavior within these telephony applications. This paper details the development of such a classification system for a pay beneficiary application. Fuzzy Inference Systems, Multi-Layer Perceptron, Support Vector Machine and ensemble of classifiers were developed. Accuracy, sensitivity and specificity performance metrics were computed as well as compared for these classification solutions. Ideally, a classifier should have high sensitivity and high specificity. Exceptional results were achieved. The ensemble of classifiers is the preferred solution, yielding an accuracy of 99.17%.",

keywords = "Artificial neural networks, Caller experience performance classification, Ensemble of classifiers, Fuzzy inference systems, Genetic algorithms, Interactive voice response, Support vector machines",

author = "Patel, {Pretesh B.} and Tshilidzi Marwala",

year = "2009",

doi = "10.1109/ICMLA.2009.43",

language = "English",

isbn = "9780769539263",

series = "8th International Conference on Machine Learning and Applications, ICMLA 2009",

pages = "415--420",

booktitle = "8th International Conference on Machine Learning and Applications, ICMLA 2009",

note = "8th International Conference on Machine Learning and Applications, ICMLA 2009 ; Conference date: 13-12-2009 Through 15-12-2009",

}

Patel, PB & Marwala, T 2009, Genetic algorithms, neural networks, fuzzy inference system, support vector machines for call performance classification. in 8th International Conference on Machine Learning and Applications, ICMLA 2009., 5381487, 8th International Conference on Machine Learning and Applications, ICMLA 2009, pp. 415-420, 8th International Conference on Machine Learning and Applications, ICMLA 2009, Miami Beach, FL, United States, 13/12/09. https://doi.org/10.1109/ICMLA.2009.43

Genetic algorithms, neural networks, fuzzy inference system, support vector machines for call performance classification. / Patel, Pretesh B.; Marwala, Tshilidzi.
8th International Conference on Machine Learning and Applications, ICMLA 2009. 2009. p. 415-420 5381487 (8th International Conference on Machine Learning and Applications, ICMLA 2009).

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

TY - GEN

T1 - Genetic algorithms, neural networks, fuzzy inference system, support vector machines for call performance classification

AU - Patel, Pretesh B.

AU - Marwala, Tshilidzi

PY - 2009

Y1 - 2009

N2 - Accurate classification of caller interactions within Interactive Voice Response systems would assist corporations to determine caller behavior within these telephony applications. This paper details the development of such a classification system for a pay beneficiary application. Fuzzy Inference Systems, Multi-Layer Perceptron, Support Vector Machine and ensemble of classifiers were developed. Accuracy, sensitivity and specificity performance metrics were computed as well as compared for these classification solutions. Ideally, a classifier should have high sensitivity and high specificity. Exceptional results were achieved. The ensemble of classifiers is the preferred solution, yielding an accuracy of 99.17%.

AB - Accurate classification of caller interactions within Interactive Voice Response systems would assist corporations to determine caller behavior within these telephony applications. This paper details the development of such a classification system for a pay beneficiary application. Fuzzy Inference Systems, Multi-Layer Perceptron, Support Vector Machine and ensemble of classifiers were developed. Accuracy, sensitivity and specificity performance metrics were computed as well as compared for these classification solutions. Ideally, a classifier should have high sensitivity and high specificity. Exceptional results were achieved. The ensemble of classifiers is the preferred solution, yielding an accuracy of 99.17%.

KW - Artificial neural networks

KW - Caller experience performance classification

KW - Ensemble of classifiers

KW - Fuzzy inference systems

KW - Genetic algorithms

KW - Interactive voice response

KW - Support vector machines

UR - http://www.scopus.com/inward/record.url?scp=77950843199&partnerID=8YFLogxK

U2 - 10.1109/ICMLA.2009.43

DO - 10.1109/ICMLA.2009.43

M3 - Conference contribution

AN - SCOPUS:77950843199

SN - 9780769539263

T3 - 8th International Conference on Machine Learning and Applications, ICMLA 2009

SP - 415

EP - 420

BT - 8th International Conference on Machine Learning and Applications, ICMLA 2009

T2 - 8th International Conference on Machine Learning and Applications, ICMLA 2009

Y2 - 13 December 2009 through 15 December 2009

ER -

Genetic algorithms, neural networks, fuzzy inference system, support vector machines for call performance classification

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this