A Segmented Local Offset Method for Imbalanced Data Classification Using Quasi-Linear Support Vector Machine

Peifeng Liang, Xin Yuan, Weite Li, Takayuki Furuzuki

研究成果: Conference contribution

抄録

Within-class imbalance problems often occur in imbalance classification which worsen the imbalance distribution problem and increase the learning concept complexity. However, most of existing methods for imbalanced classification focus on rectifying the between-class which are insufficiencies and inappropriateness in many different scenarios. This paper proposes a novel quasi-linear SVM with local offset adjustment method for imbalance classification problem. Our chief aim is to use leaning offsets of sub-clusters obtained according to imbalance ratios of sub-clusters to adjust classifier to achieve the best results. For this purpose, firstly, a geometry-based partitions method for imbalance dataset is introduced to partition the input space into several linearly separable partitions so as to construct a quasi-linear kernel and obtain an SVM classifier. Then a local offset method based on F-score value for linearly separable imbalance dataset is introduced to obtain leaning offset of each partition. At last the quasi-linear SVM with local offset adjustment is used to get the classifier for imbalance datasets. Simulation results on different real different real world datasets show that the proposed method is effective for imbalanced data classifications.

元の言語English
ホスト出版物のタイトル2018 24th International Conference on Pattern Recognition, ICPR 2018
出版者Institute of Electrical and Electronics Engineers Inc.
ページ746-751
ページ数6
2018-August
ISBN(電子版)9781538637883
DOI
出版物ステータスPublished - 2018 11 26
イベント24th International Conference on Pattern Recognition, ICPR 2018 - Beijing, China
継続期間: 2018 8 202018 8 24

Other

Other24th International Conference on Pattern Recognition, ICPR 2018
China
Beijing
期間18/8/2018/8/24

Fingerprint

Support vector machines
Classifiers
Geometry

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

これを引用

Liang, P., Yuan, X., Li, W., & Furuzuki, T. (2018). A Segmented Local Offset Method for Imbalanced Data Classification Using Quasi-Linear Support Vector Machine. : 2018 24th International Conference on Pattern Recognition, ICPR 2018 (巻 2018-August, pp. 746-751). [8545796] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPR.2018.8545796

A Segmented Local Offset Method for Imbalanced Data Classification Using Quasi-Linear Support Vector Machine. / Liang, Peifeng; Yuan, Xin; Li, Weite; Furuzuki, Takayuki.

2018 24th International Conference on Pattern Recognition, ICPR 2018. 巻 2018-August Institute of Electrical and Electronics Engineers Inc., 2018. p. 746-751 8545796.

研究成果: Conference contribution

Liang, P, Yuan, X, Li, W & Furuzuki, T 2018, A Segmented Local Offset Method for Imbalanced Data Classification Using Quasi-Linear Support Vector Machine. : 2018 24th International Conference on Pattern Recognition, ICPR 2018. 巻. 2018-August, 8545796, Institute of Electrical and Electronics Engineers Inc., pp. 746-751, 24th International Conference on Pattern Recognition, ICPR 2018, Beijing, China, 18/8/20. https://doi.org/10.1109/ICPR.2018.8545796
Liang P, Yuan X, Li W, Furuzuki T. A Segmented Local Offset Method for Imbalanced Data Classification Using Quasi-Linear Support Vector Machine. : 2018 24th International Conference on Pattern Recognition, ICPR 2018. 巻 2018-August. Institute of Electrical and Electronics Engineers Inc. 2018. p. 746-751. 8545796 https://doi.org/10.1109/ICPR.2018.8545796
Liang, Peifeng ; Yuan, Xin ; Li, Weite ; Furuzuki, Takayuki. / A Segmented Local Offset Method for Imbalanced Data Classification Using Quasi-Linear Support Vector Machine. 2018 24th International Conference on Pattern Recognition, ICPR 2018. 巻 2018-August Institute of Electrical and Electronics Engineers Inc., 2018. pp. 746-751
@inproceedings{91d179b60b2e49a6b41d94396a7927a2,
title = "A Segmented Local Offset Method for Imbalanced Data Classification Using Quasi-Linear Support Vector Machine",
abstract = "Within-class imbalance problems often occur in imbalance classification which worsen the imbalance distribution problem and increase the learning concept complexity. However, most of existing methods for imbalanced classification focus on rectifying the between-class which are insufficiencies and inappropriateness in many different scenarios. This paper proposes a novel quasi-linear SVM with local offset adjustment method for imbalance classification problem. Our chief aim is to use leaning offsets of sub-clusters obtained according to imbalance ratios of sub-clusters to adjust classifier to achieve the best results. For this purpose, firstly, a geometry-based partitions method for imbalance dataset is introduced to partition the input space into several linearly separable partitions so as to construct a quasi-linear kernel and obtain an SVM classifier. Then a local offset method based on F-score value for linearly separable imbalance dataset is introduced to obtain leaning offset of each partition. At last the quasi-linear SVM with local offset adjustment is used to get the classifier for imbalance datasets. Simulation results on different real different real world datasets show that the proposed method is effective for imbalanced data classifications.",
author = "Peifeng Liang and Xin Yuan and Weite Li and Takayuki Furuzuki",
year = "2018",
month = "11",
day = "26",
doi = "10.1109/ICPR.2018.8545796",
language = "English",
volume = "2018-August",
pages = "746--751",
booktitle = "2018 24th International Conference on Pattern Recognition, ICPR 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - A Segmented Local Offset Method for Imbalanced Data Classification Using Quasi-Linear Support Vector Machine

AU - Liang, Peifeng

AU - Yuan, Xin

AU - Li, Weite

AU - Furuzuki, Takayuki

PY - 2018/11/26

Y1 - 2018/11/26

N2 - Within-class imbalance problems often occur in imbalance classification which worsen the imbalance distribution problem and increase the learning concept complexity. However, most of existing methods for imbalanced classification focus on rectifying the between-class which are insufficiencies and inappropriateness in many different scenarios. This paper proposes a novel quasi-linear SVM with local offset adjustment method for imbalance classification problem. Our chief aim is to use leaning offsets of sub-clusters obtained according to imbalance ratios of sub-clusters to adjust classifier to achieve the best results. For this purpose, firstly, a geometry-based partitions method for imbalance dataset is introduced to partition the input space into several linearly separable partitions so as to construct a quasi-linear kernel and obtain an SVM classifier. Then a local offset method based on F-score value for linearly separable imbalance dataset is introduced to obtain leaning offset of each partition. At last the quasi-linear SVM with local offset adjustment is used to get the classifier for imbalance datasets. Simulation results on different real different real world datasets show that the proposed method is effective for imbalanced data classifications.

AB - Within-class imbalance problems often occur in imbalance classification which worsen the imbalance distribution problem and increase the learning concept complexity. However, most of existing methods for imbalanced classification focus on rectifying the between-class which are insufficiencies and inappropriateness in many different scenarios. This paper proposes a novel quasi-linear SVM with local offset adjustment method for imbalance classification problem. Our chief aim is to use leaning offsets of sub-clusters obtained according to imbalance ratios of sub-clusters to adjust classifier to achieve the best results. For this purpose, firstly, a geometry-based partitions method for imbalance dataset is introduced to partition the input space into several linearly separable partitions so as to construct a quasi-linear kernel and obtain an SVM classifier. Then a local offset method based on F-score value for linearly separable imbalance dataset is introduced to obtain leaning offset of each partition. At last the quasi-linear SVM with local offset adjustment is used to get the classifier for imbalance datasets. Simulation results on different real different real world datasets show that the proposed method is effective for imbalanced data classifications.

UR - http://www.scopus.com/inward/record.url?scp=85059735395&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059735395&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2018.8545796

DO - 10.1109/ICPR.2018.8545796

M3 - Conference contribution

VL - 2018-August

SP - 746

EP - 751

BT - 2018 24th International Conference on Pattern Recognition, ICPR 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -