A Sparse-Modeling Based Approach for Class Specific Feature Selection

被引:14
|
作者
Nardone, Davide [1 ]
Ciaramella, Angelo [1 ]
Staiano, Antonino [1 ]
机构
[1] Univ Napoli Parthenope, Dipartimento Sci & Tecnol, Naples, Italy
关键词
Feature selection; Sparse coding; Bioinformatics; Dictionary learning; Ensemble learning; MOLECULAR CLASSIFICATION; MUTUAL INFORMATION; EXPRESSION; CARCINOMAS; CANCER;
D O I
10.7717/peerj-cs.237
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this work, we propose a novel Feature Selection framework called Sparse-Modeling Based Approach for Class Specific Feature Selection (SMBA-CSFS), that simultaneously exploits the idea of Sparse Modeling and Class-Specific Feature Selection. Feature selection plays a key role in several fields (e.g., computational biology), making it possible to treat models with fewer variables which, in turn, are easier to explain, by providing valuable insights on the importance of their role, and likely speeding up the experimental validation. Unfortunately, also corroborated by the no free lunch theorems, none of the approaches in literature is the most apt to detect the optimal feature subset for building a final model, thus it still represents a challenge. The proposed feature selection procedure conceives a two-step approach: (a) a sparse modeling-based learning technique is first used to find the best subset of features, for each class of a training set; (b) the discovered feature subsets are then fed to a class-specific feature selection scheme, in order to assess the effectiveness of the selected features in classification tasks. To this end, an ensemble of classifiers is built, where each classifier is trained on its own feature subset discovered in the previous phase, and a proper decision rule is adopted to compute the ensemble responses. In order to evaluate the performance of the proposed method, extensive experiments have been performed on publicly available datasets, in particular belonging to the computational biology field where feature selection is indispensable: the acute lymphoblastic leukemia and acute myeloid leukemia, the human carcinomas, the human lung carcinomas, the diffuse large B-cell lymphoma, and the malignant glioma. SMBA-CSFS is able to identify/retrieve the most representative features that maximize the classification accuracy. With top 20 and 80 features, SMBA-CSFS exhibits a promising performance when compared to its competitors from literature, on all considered datasets, especially those with a higher number of features. Experiments show that the proposed approach may outperform the state-of-the-art methods when the number of features is high. For this reason, the introduced approach proposes itself for selection and classification of data with a large number of features and classes.
引用
收藏
页码:1 / 25
页数:25
相关论文
共 50 条
  • [1] A Study on Sparse-Modeling based Approach for Betweenness Centrality Estimation
    Matsuo, Ryotaro
    Nakamura, Ryo
    Ohsaki, Hiroyuki
    2018 IEEE 42ND ANNUAL COMPUTER SOFTWARE AND APPLICATIONS CONFERENCE (COMPSAC), VOL 1, 2018, : 973 - 976
  • [2] Sparse Bayesian Approach for Feature Selection
    Li, Chang
    Chen, Huanhuan
    2014 IEEE Symposium on Computational Intelligence in Big Data (CIBD), 2014, : 7 - 13
  • [3] SPARSE REPRESENTATION-BASED APPROACH FOR UNSUPERVISED FEATURE SELECTION
    Su, Ya-Ru
    Li, Chuan-Xi
    Wang, Ru-Jing
    Chen, Peng
    INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 2014, 28 (03)
  • [4] Class-Specific Feature Selection With Local Geometric Structure and Discriminative Information Based on Sparse Similar Samples
    Chen, Xi
    Gu, Yanfeng
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2015, 12 (07) : 1392 - 1396
  • [5] Class Specific GMM Based Sparse Feature for Speech Units Classification
    Sharma, Pulkit
    Abrol, Vinayak
    Dileep, A. D.
    Sao, Anil Kumar
    2017 25TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2017, : 528 - 532
  • [6] A Class-specific Ensemble Feature Selection Approach for Classification Problems
    Soares, Caio
    Williams, Philicity
    Gilbert, Juan E.
    Dozier, Gerry
    PROCEEDINGS OF THE 48TH ANNUAL SOUTHEAST REGIONAL CONFERENCE (ACM SE 10), 2010, : 174 - 179
  • [7] Feature Selection Based on Sparse Imputation
    Xu, Jin
    Yin, Yafeng
    Man, Hong
    He, Haibo
    2012 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2012,
  • [8] A novel approach to feature selection based on analysis of class regions
    Thawonmas, R
    Abe, S
    IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 1997, 27 (02): : 196 - 207
  • [9] Class-specific feature selection based on uniform dirichlet priors
    Lynch, RS
    Willett, PK
    SIGNAL PROCESSING, SENSOR FUSION, AND TARGET RECOGNITION IX, 2000, 4052 : 94 - 101
  • [10] A Feature Selection Method based on the Sparse Multi-Class SVM for Fingerprinting Localization
    Li, Pan
    Meng, Huadong
    Wang, Xiqin
    2014 IEEE 80TH VEHICULAR TECHNOLOGY CONFERENCE (VTC FALL), 2014,