Spherical Classification of Data, a New Rule-Based Learning Method

Zhengyu Ma; Hong Seo Ryoo

doi:10.1007/s00357-019-09355-z

Spherical Classification of Data, a New Rule-Based Learning Method

Zhengyu Ma, Hong Seo Ryoo

School of Industrial Management Engineering

Research output: Contribution to journal › Article › peer-review

Abstract

This paper presents a new rule-based classification method that partitions data under analysis into spherical patterns. The forte of the method is twofold. One, it exploits the efficiency of distance metric-based clustering to fast collect similar data into spherical patterns. The other, spherical patterns are each a trait shared among one type of data only, hence are built for classification of new data. Numerical studies with public machine learning datasets from Lichman (2013), in comparison with well-established classification methods from Boros et al. (IEEE Transactions on Knowledge and Data Engineering, 12, 292–306, 2000) and Waikato Environment for Knowledge Analysis (http://www.cs.waikato.ac.nz/ml/weka/), demonstrate the aforementioned utilities of the new method well.

Original language	English
Pages (from-to)	44-71
Number of pages	28
Journal	Journal of Classification
Volume	38
Issue number	1
DOIs	https://doi.org/10.1007/s00357-019-09355-z
Publication status	Published - 2021 Apr

Keywords

Classification
Rule induction
Spherical pattern
Supervised learning

ASJC Scopus subject areas

Mathematics (miscellaneous)
Psychology (miscellaneous)
Statistics, Probability and Uncertainty
Library and Information Sciences

Access to Document

10.1007/s00357-019-09355-z

Cite this

@article{99b6901236204d5c83fc5268a56c0c4b,

title = "Spherical Classification of Data, a New Rule-Based Learning Method",

abstract = "This paper presents a new rule-based classification method that partitions data under analysis into spherical patterns. The forte of the method is twofold. One, it exploits the efficiency of distance metric-based clustering to fast collect similar data into spherical patterns. The other, spherical patterns are each a trait shared among one type of data only, hence are built for classification of new data. Numerical studies with public machine learning datasets from Lichman (2013), in comparison with well-established classification methods from Boros et al. (IEEE Transactions on Knowledge and Data Engineering, 12, 292–306, 2000) and Waikato Environment for Knowledge Analysis (http://www.cs.waikato.ac.nz/ml/weka/), demonstrate the aforementioned utilities of the new method well.",

keywords = "Classification, Rule induction, Spherical pattern, Supervised learning",

author = "Zhengyu Ma and Ryoo, {Hong Seo}",

note = "Funding Information: This work was supported by research grant awarded to H.S. Ryoo by Samsung Science and Technology Foundation under Project Number SSTF-BA1501-03 and by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (Grant Number: 2017R1D1A1A02018729). Publisher Copyright: {\textcopyright} 2020, The Classification Society.",

year = "2021",

month = apr,

doi = "10.1007/s00357-019-09355-z",

language = "English",

volume = "38",

pages = "44--71",

journal = "Journal of Classification",

issn = "0176-4268",

publisher = "Springer New York",

number = "1",

}

TY - JOUR

T1 - Spherical Classification of Data, a New Rule-Based Learning Method

AU - Ma, Zhengyu

AU - Ryoo, Hong Seo

N1 - Funding Information: This work was supported by research grant awarded to H.S. Ryoo by Samsung Science and Technology Foundation under Project Number SSTF-BA1501-03 and by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (Grant Number: 2017R1D1A1A02018729). Publisher Copyright: © 2020, The Classification Society.

PY - 2021/4

Y1 - 2021/4

N2 - This paper presents a new rule-based classification method that partitions data under analysis into spherical patterns. The forte of the method is twofold. One, it exploits the efficiency of distance metric-based clustering to fast collect similar data into spherical patterns. The other, spherical patterns are each a trait shared among one type of data only, hence are built for classification of new data. Numerical studies with public machine learning datasets from Lichman (2013), in comparison with well-established classification methods from Boros et al. (IEEE Transactions on Knowledge and Data Engineering, 12, 292–306, 2000) and Waikato Environment for Knowledge Analysis (http://www.cs.waikato.ac.nz/ml/weka/), demonstrate the aforementioned utilities of the new method well.

AB - This paper presents a new rule-based classification method that partitions data under analysis into spherical patterns. The forte of the method is twofold. One, it exploits the efficiency of distance metric-based clustering to fast collect similar data into spherical patterns. The other, spherical patterns are each a trait shared among one type of data only, hence are built for classification of new data. Numerical studies with public machine learning datasets from Lichman (2013), in comparison with well-established classification methods from Boros et al. (IEEE Transactions on Knowledge and Data Engineering, 12, 292–306, 2000) and Waikato Environment for Knowledge Analysis (http://www.cs.waikato.ac.nz/ml/weka/), demonstrate the aforementioned utilities of the new method well.

KW - Classification

KW - Rule induction

KW - Spherical pattern

KW - Supervised learning

UR - http://www.scopus.com/inward/record.url?scp=85079821274&partnerID=8YFLogxK

U2 - 10.1007/s00357-019-09355-z

DO - 10.1007/s00357-019-09355-z

M3 - Article

AN - SCOPUS:85079821274

VL - 38

SP - 44

EP - 71

JO - Journal of Classification

JF - Journal of Classification

SN - 0176-4268

IS - 1

ER -

Spherical Classification of Data, a New Rule-Based Learning Method

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this