Support Vector Machine Optimized by Fireworks Algorithm for Handwritten Digit Recognition

Eva Tuba; Romana Capor Hrosik; Adis Alihodzic; Raka Jovanovic; Milan Tuba

doi:10.1007/978-3-030-39237-6_13

Support Vector Machine Optimized by Fireworks Algorithm for Handwritten Digit Recognition

Eva Tuba, Romana Capor Hrosik, Adis Alihodzic, Raka Jovanovic, Milan Tuba^*

^*Corresponding author for this work

QEERI - Energy Center

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

5 Citations (Scopus)

Abstract

Handwritten digit recognition is an important subarea in the object recognition research area. Support vector machines represent a very successful recent binary classifier. Basic support vector machines have to be improved in order to deal with real-world problems. The introduction of soft margin for outliers and misclassified samples as well as kernel function for non linearly separably data leads to the hard optimization problem of selecting parameters for these two modifications. Grid search which is often used is rather inefficient. In this paper we propose the use of one of the latest swarm intelligence algorithms, the fireworks algorithm, for the support vector machine parameters tuning. We tested our approach on standard MNIST base of handwritten images and with selected set of simple features we obtained better results compared to other approaches from literature.

Original language	English
Title of host publication	Modelling and Development of Intelligent Systems - 6th International Conference, MDIS 2019, Revised Selected Papers
Editors	Dana Simian, Laura Florentina Stoica
Publisher	Springer
Pages	187-199
Number of pages	13
ISBN (Print)	9783030392369
DOIs	https://doi.org/10.1007/978-3-030-39237-6_13
Publication status	Published - 2020
Event	6th International Conference on Modelling and Development of Intelligent Systems, MDIS 2019 - Sibiu, Romania Duration: 3 Oct 2019 → 5 Oct 2019

Publication series

Name	Communications in Computer and Information Science
Volume	1126 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	6th International Conference on Modelling and Development of Intelligent Systems, MDIS 2019
Country/Territory	Romania
City	Sibiu
Period	3/10/19 → 5/10/19

Keywords

Fireworks algorithm
Handwritten digit recognition
Machine learning
Optimization
Support vector machine
Swarm intelligence

Access to Document

10.1007/978-3-030-39237-6_13

Cite this

Tuba, E., Capor Hrosik, R., Alihodzic, A., Jovanovic, R., & Tuba, M. (2020). Support Vector Machine Optimized by Fireworks Algorithm for Handwritten Digit Recognition. In D. Simian, & L. F. Stoica (Eds.), Modelling and Development of Intelligent Systems - 6th International Conference, MDIS 2019, Revised Selected Papers (pp. 187-199). (Communications in Computer and Information Science; Vol. 1126 CCIS). Springer. https://doi.org/10.1007/978-3-030-39237-6_13

Tuba, Eva ; Capor Hrosik, Romana ; Alihodzic, Adis et al. / Support Vector Machine Optimized by Fireworks Algorithm for Handwritten Digit Recognition. Modelling and Development of Intelligent Systems - 6th International Conference, MDIS 2019, Revised Selected Papers. editor / Dana Simian ; Laura Florentina Stoica. Springer, 2020. pp. 187-199 (Communications in Computer and Information Science).

@inproceedings{90650e0fa5e9439da32746714140c539,

title = "Support Vector Machine Optimized by Fireworks Algorithm for Handwritten Digit Recognition",

abstract = "Handwritten digit recognition is an important subarea in the object recognition research area. Support vector machines represent a very successful recent binary classifier. Basic support vector machines have to be improved in order to deal with real-world problems. The introduction of soft margin for outliers and misclassified samples as well as kernel function for non linearly separably data leads to the hard optimization problem of selecting parameters for these two modifications. Grid search which is often used is rather inefficient. In this paper we propose the use of one of the latest swarm intelligence algorithms, the fireworks algorithm, for the support vector machine parameters tuning. We tested our approach on standard MNIST base of handwritten images and with selected set of simple features we obtained better results compared to other approaches from literature.",

keywords = "Fireworks algorithm, Handwritten digit recognition, Machine learning, Optimization, Support vector machine, Swarm intelligence",

author = "Eva Tuba and {Capor Hrosik}, Romana and Adis Alihodzic and Raka Jovanovic and Milan Tuba",

note = "Publisher Copyright: {\textcopyright} 2020, Springer Nature Switzerland AG.; 6th International Conference on Modelling and Development of Intelligent Systems, MDIS 2019 ; Conference date: 03-10-2019 Through 05-10-2019",

year = "2020",

doi = "10.1007/978-3-030-39237-6_13",

language = "English",

isbn = "9783030392369",

series = "Communications in Computer and Information Science",

publisher = "Springer",

pages = "187--199",

editor = "Dana Simian and Stoica, {Laura Florentina}",

booktitle = "Modelling and Development of Intelligent Systems - 6th International Conference, MDIS 2019, Revised Selected Papers",

address = "Germany",

}

Tuba, E, Capor Hrosik, R, Alihodzic, A, Jovanovic, R & Tuba, M 2020, Support Vector Machine Optimized by Fireworks Algorithm for Handwritten Digit Recognition. in D Simian & LF Stoica (eds), Modelling and Development of Intelligent Systems - 6th International Conference, MDIS 2019, Revised Selected Papers. Communications in Computer and Information Science, vol. 1126 CCIS, Springer, pp. 187-199, 6th International Conference on Modelling and Development of Intelligent Systems, MDIS 2019, Sibiu, Romania, 3/10/19. https://doi.org/10.1007/978-3-030-39237-6_13

Support Vector Machine Optimized by Fireworks Algorithm for Handwritten Digit Recognition. / Tuba, Eva; Capor Hrosik, Romana; Alihodzic, Adis et al.
Modelling and Development of Intelligent Systems - 6th International Conference, MDIS 2019, Revised Selected Papers. ed. / Dana Simian; Laura Florentina Stoica. Springer, 2020. p. 187-199 (Communications in Computer and Information Science; Vol. 1126 CCIS).

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

TY - GEN

T1 - Support Vector Machine Optimized by Fireworks Algorithm for Handwritten Digit Recognition

AU - Tuba, Eva

AU - Capor Hrosik, Romana

AU - Alihodzic, Adis

AU - Jovanovic, Raka

AU - Tuba, Milan

PY - 2020

Y1 - 2020

N2 - Handwritten digit recognition is an important subarea in the object recognition research area. Support vector machines represent a very successful recent binary classifier. Basic support vector machines have to be improved in order to deal with real-world problems. The introduction of soft margin for outliers and misclassified samples as well as kernel function for non linearly separably data leads to the hard optimization problem of selecting parameters for these two modifications. Grid search which is often used is rather inefficient. In this paper we propose the use of one of the latest swarm intelligence algorithms, the fireworks algorithm, for the support vector machine parameters tuning. We tested our approach on standard MNIST base of handwritten images and with selected set of simple features we obtained better results compared to other approaches from literature.

AB - Handwritten digit recognition is an important subarea in the object recognition research area. Support vector machines represent a very successful recent binary classifier. Basic support vector machines have to be improved in order to deal with real-world problems. The introduction of soft margin for outliers and misclassified samples as well as kernel function for non linearly separably data leads to the hard optimization problem of selecting parameters for these two modifications. Grid search which is often used is rather inefficient. In this paper we propose the use of one of the latest swarm intelligence algorithms, the fireworks algorithm, for the support vector machine parameters tuning. We tested our approach on standard MNIST base of handwritten images and with selected set of simple features we obtained better results compared to other approaches from literature.

KW - Fireworks algorithm

KW - Handwritten digit recognition

KW - Machine learning

KW - Optimization

KW - Support vector machine

KW - Swarm intelligence

UR - http://www.scopus.com/inward/record.url?scp=85079088415&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-39237-6_13

DO - 10.1007/978-3-030-39237-6_13

M3 - Conference contribution

AN - SCOPUS:85079088415

SN - 9783030392369

T3 - Communications in Computer and Information Science

SP - 187

EP - 199

BT - Modelling and Development of Intelligent Systems - 6th International Conference, MDIS 2019, Revised Selected Papers

A2 - Simian, Dana

A2 - Stoica, Laura Florentina

PB - Springer

T2 - 6th International Conference on Modelling and Development of Intelligent Systems, MDIS 2019

Y2 - 3 October 2019 through 5 October 2019

ER -

Tuba E, Capor Hrosik R, Alihodzic A, Jovanovic R, Tuba M. Support Vector Machine Optimized by Fireworks Algorithm for Handwritten Digit Recognition. In Simian D, Stoica LF, editors, Modelling and Development of Intelligent Systems - 6th International Conference, MDIS 2019, Revised Selected Papers. Springer. 2020. p. 187-199. (Communications in Computer and Information Science). doi: 10.1007/978-3-030-39237-6_13

Support Vector Machine Optimized by Fireworks Algorithm for Handwritten Digit Recognition

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this