Title :
Hypersphere distribution discriminant analysis
Author :
Chiu, Yi-I ; Huang, Chun-Rong ; Chung, Pau-Choo ; Luo, Ching-Hsing
Author_Institution :
Dept. of Electr. Eng., Nation Cheng Kung Univ., Taiwan
Abstract :
Current graph embedding frameworks of supervised dimensionality reduction often preserve the intraclass local structures and maximize the interclass variance. However, this strategy fails to provide adequate results when strict within-class multimodalities contradict between-class separations. In this paper, we propose Hypersphere Distribution Discriminant Analysis (HDDA), which determines the affinity by considering not only within-class local structure but also the heteropoint distribution in the neighborhood space. If the heteropoint distribution is relatively high in the feature space, this pair should be mapped apart to avoid mixing problems. By taking both the distribution of heteropoints and the distance into account, HDDA shows more effective results compared to the state-of-the-art methods.
Keywords :
feature extraction; graph theory; learning (artificial intelligence); HDDA; between-class separations; feature space; graph embedding frameworks; heteropoint distribution; hypersphere distribution discriminant analysis; interclass variance maximization; intraclass local structures; supervised dimensionality reduction; within-class local structure; within-class multimodalities; Data visualization; Educational institutions; Heating; Interference; Kernel; Principal component analysis; Silicon; Dimensionality Reduction;
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on
Conference_Location :
Kyoto
Print_ISBN :
978-1-4673-0045-2
Electronic_ISBN :
1520-6149
DOI :
10.1109/ICASSP.2012.6288311