L2,p-norm and sample constraint based feature selection and classification for AD diagnosis

NEUROCOMPUTING

卷:195

Article

Zhang, Mingxing¹  Yang, Yang¹  Zhang, Hanwang²  Shen, Fumin¹  Zhang, Dongxiang² 

[1] Univ Elect Sci & Technol China, 2006 Xiyuan Ave, Chengduu 611731, Peoples R China

[2] Natl Univ Singapore, 21 Lower Kent Ridge Rd, Singapore 119077, Singapore

关键词: Alzheimer's Disease (AD);    Mild Cognitive Impairment (MCI);    L-2,L-1-norm;    Sparse learning;    Multi-modality learning;    Multi-task learning;   

DOI  :  10.1016/j.neucom.2015.08.111

来源: Elsevier

【 摘 要 】

Recent studies have witnessed the effectiveness of L-2,L-1-norm based methods on AD/MCI diagnosis. Nonetheless, most of them suffer from the following three main problems: (1) L-2,L-1-norm based loss function does not take into account different distances between target labels and prediction values; (2) L-2,L-1-norm based feature selection does not possess sufficient flexibility to adapt to different types of data sources and select more informative features; (3) intrinsic correlation between the processes of feature selection and classification (or regression) are inevitably ignored. In this paper, we propose a novel method which incorporates additional flexibility and adaptability by employing the more generalized L-2,L-1-norm based prediction loss function and L-2,L-1-norm based feature selection, as well as utilizes a joint model to perform feature selection and classification simultaneously. Besides, we introduce a regularizer to preserve local structure information between samples in the original feature space and prediction values in the projected space. In order to validate the effectiveness of the proposed method, we conducted extensive experiments on the ADNI dataset, and showed that the proposed method enhanced the performance of disease status classification, compared to the state-of-the-art methods. (C) 2016 Elsevier B.V. All rights reserved.

【 授权许可】

Free