Fast Statistical Learning Algorithm for Feature Generation

Proc. of KES, Vol.III,LNAI 4694, pp.91-97,Vietrisul Mare, Italy

This paper presents an improved statistical learning algorithm for feature generation in pattern recognition and signal processing. It is approximately derived from geometrical interpretation of the Fisher linear discriminant analysis (FLDA). In this paper, further improvement is introduced into the simple-FLDA and its effectiveness is demonstrated for preliminary personal identification problem.
統計的手法である判別分析に基づき新たに提案したsimple-FLDAを用いて，高速に特徴生成を行う超高速学習型統計アルゴリズムを提案した．
共同発表者：Minoru Fukumi, Stephen
Karungaru, Satoru Tsuge, Miyoko Nakano,
Takuya Akashi, and Yasue Mitsukura