An Iterative Algorithm of Key Feature Selection for Multi-class Classification

Daeun Jung; Hyunggon Park

doi:10.1109/ICUFN.2019.8806074

An Iterative Algorithm of Key Feature Selection for Multi-class Classification

Daeun Jung, Hyunggon Park

Electronic and Electrical Engineering

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

1 Scopus citations

Abstract

In this paper, we propose an iterative algorithm of key feature selection for multi-class classification problems, where the data includes a large number of features but the amount of data is limited. For efficient classification, the proposed algorithm first extracts a set of key feature candidates based on Boruta algorithm and then iteratively adopts conventional machine learning based classification algorithms to determine key features. Simulation results show that the proposed algorithm can effectively determine key features, leading to improved classification accuracy compared to direct adoption of multi-class classification algorithms.

Original language	English
Title of host publication	ICUFN 2019 - 11th International Conference on Ubiquitous and Future Networks
Publisher	IEEE Computer Society
Pages	523-525
Number of pages	3
ISBN (Electronic)	9781728113395
DOIs	https://doi.org/10.1109/ICUFN.2019.8806074
State	Published - Jul 2019
Event	11th International Conference on Ubiquitous and Future Networks, ICUFN 2019 - Zagreb, Croatia Duration: 2 Jul 2019 → 5 Jul 2019

Publication series

Name	International Conference on Ubiquitous and Future Networks, ICUFN
Volume	2019-July
ISSN (Print)	2165-8528
ISSN (Electronic)	2165-8536

Conference

Conference	11th International Conference on Ubiquitous and Future Networks, ICUFN 2019
Country/Territory	Croatia
City	Zagreb
Period	2/07/19 → 5/07/19

Bibliographical note

Funding Information:
00024, Supervised Agile Machine Learning Techniques for Network Automation based on Network Data Analytics Function) and supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT)(No. NRF-2017R1A2B4005041).

Funding Information:
This work was partly supported by Institute of Information AND communications Technology Planning AND Evaluation (IITP) grant funded by the Korea government(MSIT) (No. 2019-0-00024

Funding Information:
This work was partly supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government(MSIT) (No. 2019-0-

Publisher Copyright:
© 2019 IEEE.

Keywords

feature extraction
feature selection
machine learning
multi-class classification
omics data

Access to Document

10.1109/ICUFN.2019.8806074

Cite this

Jung, D., & Park, H. (2019). An Iterative Algorithm of Key Feature Selection for Multi-class Classification. In ICUFN 2019 - 11th International Conference on Ubiquitous and Future Networks (pp. 523-525). Article 8806074 (International Conference on Ubiquitous and Future Networks, ICUFN; Vol. 2019-July). IEEE Computer Society. https://doi.org/10.1109/ICUFN.2019.8806074

@inproceedings{f473b0071cba41cdad3a7dc71fe6a558,

title = "An Iterative Algorithm of Key Feature Selection for Multi-class Classification",

abstract = "In this paper, we propose an iterative algorithm of key feature selection for multi-class classification problems, where the data includes a large number of features but the amount of data is limited. For efficient classification, the proposed algorithm first extracts a set of key feature candidates based on Boruta algorithm and then iteratively adopts conventional machine learning based classification algorithms to determine key features. Simulation results show that the proposed algorithm can effectively determine key features, leading to improved classification accuracy compared to direct adoption of multi-class classification algorithms.",

keywords = "feature extraction, feature selection, machine learning, multi-class classification, omics data",

author = "Daeun Jung and Hyunggon Park",

note = "Funding Information: 00024, Supervised Agile Machine Learning Techniques for Network Automation based on Network Data Analytics Function) and supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT)(No. NRF-2017R1A2B4005041). Funding Information: This work was partly supported by Institute of Information AND communications Technology Planning AND Evaluation (IITP) grant funded by the Korea government(MSIT) (No. 2019-0-00024 Funding Information: This work was partly supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government(MSIT) (No. 2019-0- Publisher Copyright: {\textcopyright} 2019 IEEE.; 11th International Conference on Ubiquitous and Future Networks, ICUFN 2019 ; Conference date: 02-07-2019 Through 05-07-2019",

year = "2019",

month = jul,

doi = "10.1109/ICUFN.2019.8806074",

language = "English",

series = "International Conference on Ubiquitous and Future Networks, ICUFN",

publisher = "IEEE Computer Society",

pages = "523--525",

booktitle = "ICUFN 2019 - 11th International Conference on Ubiquitous and Future Networks",

}

Jung, D & Park, H 2019, An Iterative Algorithm of Key Feature Selection for Multi-class Classification. in ICUFN 2019 - 11th International Conference on Ubiquitous and Future Networks., 8806074, International Conference on Ubiquitous and Future Networks, ICUFN, vol. 2019-July, IEEE Computer Society, pp. 523-525, 11th International Conference on Ubiquitous and Future Networks, ICUFN 2019, Zagreb, Croatia, 2/07/19. https://doi.org/10.1109/ICUFN.2019.8806074

An Iterative Algorithm of Key Feature Selection for Multi-class Classification. / Jung, Daeun; Park, Hyunggon.
ICUFN 2019 - 11th International Conference on Ubiquitous and Future Networks. IEEE Computer Society, 2019. p. 523-525 8806074 (International Conference on Ubiquitous and Future Networks, ICUFN; Vol. 2019-July).

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

TY - GEN

T1 - An Iterative Algorithm of Key Feature Selection for Multi-class Classification

AU - Jung, Daeun

AU - Park, Hyunggon

N1 - Funding Information: 00024, Supervised Agile Machine Learning Techniques for Network Automation based on Network Data Analytics Function) and supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT)(No. NRF-2017R1A2B4005041). Funding Information: This work was partly supported by Institute of Information AND communications Technology Planning AND Evaluation (IITP) grant funded by the Korea government(MSIT) (No. 2019-0-00024 Funding Information: This work was partly supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government(MSIT) (No. 2019-0- Publisher Copyright: © 2019 IEEE.

PY - 2019/7

Y1 - 2019/7

N2 - In this paper, we propose an iterative algorithm of key feature selection for multi-class classification problems, where the data includes a large number of features but the amount of data is limited. For efficient classification, the proposed algorithm first extracts a set of key feature candidates based on Boruta algorithm and then iteratively adopts conventional machine learning based classification algorithms to determine key features. Simulation results show that the proposed algorithm can effectively determine key features, leading to improved classification accuracy compared to direct adoption of multi-class classification algorithms.

AB - In this paper, we propose an iterative algorithm of key feature selection for multi-class classification problems, where the data includes a large number of features but the amount of data is limited. For efficient classification, the proposed algorithm first extracts a set of key feature candidates based on Boruta algorithm and then iteratively adopts conventional machine learning based classification algorithms to determine key features. Simulation results show that the proposed algorithm can effectively determine key features, leading to improved classification accuracy compared to direct adoption of multi-class classification algorithms.

KW - feature extraction

KW - feature selection

KW - machine learning

KW - multi-class classification

KW - omics data

UR - http://www.scopus.com/inward/record.url?scp=85071834526&partnerID=8YFLogxK

U2 - 10.1109/ICUFN.2019.8806074

DO - 10.1109/ICUFN.2019.8806074

M3 - Conference contribution

AN - SCOPUS:85071834526

T3 - International Conference on Ubiquitous and Future Networks, ICUFN

SP - 523

EP - 525

BT - ICUFN 2019 - 11th International Conference on Ubiquitous and Future Networks

PB - IEEE Computer Society

T2 - 11th International Conference on Ubiquitous and Future Networks, ICUFN 2019

Y2 - 2 July 2019 through 5 July 2019

ER -

An Iterative Algorithm of Key Feature Selection for Multi-class Classification

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Fingerprint

Cite this