Performance comparison of machine learning classification algorithms

K. M. Veena, K. Manjula Shenoy, K. B. Ajitha Shenoy

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Classification of binary and multi-class datasets to draw meaningful decisions is the key in today’s scientific world. Machine learning algorithms are known to effectively classify complex datasets. This paper attempts to study and compare the classification performance if four supervised machine learning classification algorithms, viz., “Classification And Regression Trees, k-Nearest Neighbor, Support Vector Machines and Naive Bayes” to five different types of data sets, viz., mushrooms, page-block, satimage, thyroid and wine. The classification accuracy of each algorithm is evaluated using the 10-fold cross-validation technique. “The Classification And Regression Tree” algorithm is found to give the best classification accuracy.

Original languageEnglish
Title of host publicationAdvances in Computing and Data Science - Second International Conference, ICACDS 2018, Revised Selected Papers
EditorsTuncer Ören, P. K. Gupta, Jan Flusser, Vipin Tyagi, Mayank Singh
PublisherSpringer Verlag
Pages489-497
Number of pages9
ISBN (Print)9789811318122
DOIs
Publication statusPublished - 01-01-2018
Event2nd International Conference on Advances in Computing and Data Sciences, ICACDS 2018 - Dehradun, India
Duration: 20-04-201821-04-2018

Publication series

NameCommunications in Computer and Information Science
Volume906
ISSN (Print)1865-0929

Conference

Conference2nd International Conference on Advances in Computing and Data Sciences, ICACDS 2018
CountryIndia
CityDehradun
Period20-04-1821-04-18

Fingerprint

Performance Comparison
Classification Algorithm
Learning systems
Learning Algorithm
Machine Learning
Classification and Regression Trees
Naive Bayes
Tree Algorithms
Supervised Learning
Multi-class
Cross-validation
Nearest Neighbor
Support Vector Machine
Fold
Classify
Binary
Wine
Learning algorithms
Support vector machines

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Mathematics(all)

Cite this

Veena, K. M., Manjula Shenoy, K., & Ajitha Shenoy, K. B. (2018). Performance comparison of machine learning classification algorithms. In T. Ören, P. K. Gupta, J. Flusser, V. Tyagi, & M. Singh (Eds.), Advances in Computing and Data Science - Second International Conference, ICACDS 2018, Revised Selected Papers (pp. 489-497). (Communications in Computer and Information Science; Vol. 906). Springer Verlag. https://doi.org/10.1007/978-981-13-1813-9_49
Veena, K. M. ; Manjula Shenoy, K. ; Ajitha Shenoy, K. B. / Performance comparison of machine learning classification algorithms. Advances in Computing and Data Science - Second International Conference, ICACDS 2018, Revised Selected Papers. editor / Tuncer Ören ; P. K. Gupta ; Jan Flusser ; Vipin Tyagi ; Mayank Singh. Springer Verlag, 2018. pp. 489-497 (Communications in Computer and Information Science).
@inproceedings{942cb37873354756b94f1e84e65fe2e2,
title = "Performance comparison of machine learning classification algorithms",
abstract = "Classification of binary and multi-class datasets to draw meaningful decisions is the key in today’s scientific world. Machine learning algorithms are known to effectively classify complex datasets. This paper attempts to study and compare the classification performance if four supervised machine learning classification algorithms, viz., “Classification And Regression Trees, k-Nearest Neighbor, Support Vector Machines and Naive Bayes” to five different types of data sets, viz., mushrooms, page-block, satimage, thyroid and wine. The classification accuracy of each algorithm is evaluated using the 10-fold cross-validation technique. “The Classification And Regression Tree” algorithm is found to give the best classification accuracy.",
author = "Veena, {K. M.} and {Manjula Shenoy}, K. and {Ajitha Shenoy}, {K. B.}",
year = "2018",
month = "1",
day = "1",
doi = "10.1007/978-981-13-1813-9_49",
language = "English",
isbn = "9789811318122",
series = "Communications in Computer and Information Science",
publisher = "Springer Verlag",
pages = "489--497",
editor = "Tuncer {\"O}ren and Gupta, {P. K.} and Jan Flusser and Vipin Tyagi and Mayank Singh",
booktitle = "Advances in Computing and Data Science - Second International Conference, ICACDS 2018, Revised Selected Papers",
address = "Germany",

}

Veena, KM, Manjula Shenoy, K & Ajitha Shenoy, KB 2018, Performance comparison of machine learning classification algorithms. in T Ören, PK Gupta, J Flusser, V Tyagi & M Singh (eds), Advances in Computing and Data Science - Second International Conference, ICACDS 2018, Revised Selected Papers. Communications in Computer and Information Science, vol. 906, Springer Verlag, pp. 489-497, 2nd International Conference on Advances in Computing and Data Sciences, ICACDS 2018, Dehradun, India, 20-04-18. https://doi.org/10.1007/978-981-13-1813-9_49

Performance comparison of machine learning classification algorithms. / Veena, K. M.; Manjula Shenoy, K.; Ajitha Shenoy, K. B.

Advances in Computing and Data Science - Second International Conference, ICACDS 2018, Revised Selected Papers. ed. / Tuncer Ören; P. K. Gupta; Jan Flusser; Vipin Tyagi; Mayank Singh. Springer Verlag, 2018. p. 489-497 (Communications in Computer and Information Science; Vol. 906).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Performance comparison of machine learning classification algorithms

AU - Veena, K. M.

AU - Manjula Shenoy, K.

AU - Ajitha Shenoy, K. B.

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Classification of binary and multi-class datasets to draw meaningful decisions is the key in today’s scientific world. Machine learning algorithms are known to effectively classify complex datasets. This paper attempts to study and compare the classification performance if four supervised machine learning classification algorithms, viz., “Classification And Regression Trees, k-Nearest Neighbor, Support Vector Machines and Naive Bayes” to five different types of data sets, viz., mushrooms, page-block, satimage, thyroid and wine. The classification accuracy of each algorithm is evaluated using the 10-fold cross-validation technique. “The Classification And Regression Tree” algorithm is found to give the best classification accuracy.

AB - Classification of binary and multi-class datasets to draw meaningful decisions is the key in today’s scientific world. Machine learning algorithms are known to effectively classify complex datasets. This paper attempts to study and compare the classification performance if four supervised machine learning classification algorithms, viz., “Classification And Regression Trees, k-Nearest Neighbor, Support Vector Machines and Naive Bayes” to five different types of data sets, viz., mushrooms, page-block, satimage, thyroid and wine. The classification accuracy of each algorithm is evaluated using the 10-fold cross-validation technique. “The Classification And Regression Tree” algorithm is found to give the best classification accuracy.

UR - http://www.scopus.com/inward/record.url?scp=85056464156&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056464156&partnerID=8YFLogxK

U2 - 10.1007/978-981-13-1813-9_49

DO - 10.1007/978-981-13-1813-9_49

M3 - Conference contribution

AN - SCOPUS:85056464156

SN - 9789811318122

T3 - Communications in Computer and Information Science

SP - 489

EP - 497

BT - Advances in Computing and Data Science - Second International Conference, ICACDS 2018, Revised Selected Papers

A2 - Ören, Tuncer

A2 - Gupta, P. K.

A2 - Flusser, Jan

A2 - Tyagi, Vipin

A2 - Singh, Mayank

PB - Springer Verlag

ER -

Veena KM, Manjula Shenoy K, Ajitha Shenoy KB. Performance comparison of machine learning classification algorithms. In Ören T, Gupta PK, Flusser J, Tyagi V, Singh M, editors, Advances in Computing and Data Science - Second International Conference, ICACDS 2018, Revised Selected Papers. Springer Verlag. 2018. p. 489-497. (Communications in Computer and Information Science). https://doi.org/10.1007/978-981-13-1813-9_49