Multi-label classification using stacked spectral kernel discriminant analysis

详细信息    查看全文

• 作者：Muhammad Atif Tahir^a ; ^c ; ^{muhammad.tahir@northumbria.ac.uk" class="auth_mail" title="E-mail the corresponding author} ; ^{mtahir@ccis.imamu.edu.sa" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Josef Kittler^b ; ^{j.kittler@surrey.ac.uk" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Ahmed Bouridane^a ; ^{ahmed.bouridane@northumbria.ac.uk" class="auth_mail" title="E-mail the corresponding author}Author Vitae
• 关键词：Multilabel classification ; Stacked Kernel Discriminant Analysis ; Leave-one-out Cross Validation ; Multi-label Nearest Neighbour Classifier
• 刊名：Neurocomputing
• 出版年：2016
• 出版时间：1 January 2016
• 年：2016
• 卷：171
• 期：Complete
• 页码：127-137
• 全文大小：1606 K

文摘

Multi-label classification is a challenging research problem due to the fact that each example may belong to a varying number of classes. This problem can be further aggravated by high dimensionality and complex correlation among labels. In this paper, a discriminant approach to multi-label classification is proposed using the concept of stacking and spectral regression based kernel discriminant analysis (SSRKDA). For effective stacked generalisation, a novel fast implementation of the leave-one-out cross-validation for SSRKDA is also presented in this paper. The proposed system is validated on several multi-label databases. The results indicate a significant boost in performance when SSRKDA is compared to other multi-label classification techniques.