Support vector machines with the known feature-evolution priors

Y. Zhang; G. Wang; F-L Chung; S. Wang

doi:10.1016/j.knosys.2021.107048

Back

Support vector machines with the known feature-evolution priors

Journal article

Peer reviewed

Support vector machines with the known feature-evolution priors

Y. Zhang, G. Wang, F-L Chung and S. Wang

Knowledge-Based Systems, Vol.223, Article 107048

2021

DOI: https://doi.org/10.1016/j.knosys.2021.107048

Files and links (1)

url

Link to Published Version *Subscription may be requiredView

Abstract

In traditional SVMs (support vector machines), each feature involved in an object is assumed to contribute equally to the classification accuracy. However, the equal importance assumption for each feature is inappropriate for classifying the objects. The existing weighting strategies usually utilize the fixed scaling factors to measure the importance of each feature and hence they are not good fits for feature evolution. In this paper, with the assumption that a Known Feature-Evolution Prior (KFEP) can be employed to capture importance distribution from the perspective of both feature granularity and object granularity, SVM-based machines called KFEP-SVMs are developed to capture the importance of features dynamically. Also, it is revealed that SVMs with the known feature-evolution priors are equivalent to SVMs on a higher feature space. Besides, we theoretically demonstrate that the proposed machines KFEP-SVMs with the known feature-evolution prior indeed have enhanced generalization ability, compared with the classic SVMs. Experimental results show the effectiveness of the proposed machines KFEP-SVMs.

Details

Title: Support vector machines with the known feature-evolution priors
Authors/Creators: Y. Zhang (Author/Creator) - Hong Kong Polytechnic University
G. Wang (Author/Creator) - Murdoch University
F-L Chung (Author/Creator) - Hong Kong Polytechnic University
S. Wang (Author/Creator) - Jiangnan University
Publication Details: Knowledge-Based Systems, Vol.223, Article 107048
Publisher: Elsevier BV
Identifiers: 991005543186307891
Murdoch Affiliation: Information Technology, Mathematics and Statistics
Language: English
Resource Type: Journal article

Metrics

41 Record Views

11 Times Cited - Web of Science

InCites Highlights

These are selected metrics from InCites Benchmarking & Analytics tool, related to this output

Collaboration types: Domestic collaboration; International collaboration
Citation topics: 4 Electrical Engineering, Electronics & Computer Science; 4.61 Artificial Intelligence & Machine Learning; 4.61.145 Classification Algorithms
Web Of Science research areas: Computer Science, Artificial Intelligence
ESI research areas: Computer Science