Non-negative Matrix Factorization and Support Vector Data Description Based One Class Classification
One class classification is widely used in many applications. Only one target class is well characterized by instances in the training data in one class classification, and no instance is available for other non-target classes, or few instances are present and they cannot form statistically representative samples for the negative concept. A two-step paradigm employing non-negative matrix factorization (NMF) and support vector data description (SVDD) for one class classification training of non-negative data is developed. Firstly, a projected gradient based NMF method is used to find the hiding structure from the training instances and the training instances are projected into a new feature space. Secondly, SVDD is employed to perform one class classification training with the projected feature data. Classification examples demonstrate that the proposed method is superior to principal component analysis (PCA) based SVDD method and other standard one class classifiers.
Keywords: Non-Negative Matrix Factorization, Support Vector Data Description, One Class Classification
Download Full-Text
ABOUT THE AUTHORS
Liyong Ma
He received the B.Sc degree from Harbin Institute of Technology, Harbin, China, in 1993, the M.Sc. degree from Harbin University of Science and Technology, Harbin, China, in 1996, and Ph.D degree from Harbin Institute of Technology in 2007, respectively. He is currently an Associate Professor at Harbin Institute of Technology at Weihai, Weihai, China. His main research areas include intelligent testing and information processing, biomedical imaging and image processing.
Naizhang Feng
He received the B.Sc. and Ph.D. degree in control engineering from Harbin Institute of Technology, Harbin, China, in 1998 and 2005, respectively. From 2005 to 2007, he was a post-doctor in Fudan University, Shanghai, China. He is currently a Professor in Harbin Institute of Technology at Weihai. His research interests include signal detection and information processing and medical ultrasound imaging.
Qi Wang
He received the B.Sc. and M.Sc. degree in electromagnetic measurement from Harbin Institute of Technology, Harbin, China, in 1967 and 1980, respectively. From 1985 to 1987 and 1993 to 1995, he visited the University of Tsukuba and the Chiba Institute of Technology, Japan, as a Researcher. He is currently a Professor at the Harbin Institute of Technology. So far, he has more than 120 papers published. His research interests include the intelligent testing instrumentation, information processing, sensor fault diagnosis, and sensor fusion.
Liyong Ma
He received the B.Sc degree from Harbin Institute of Technology, Harbin, China, in 1993, the M.Sc. degree from Harbin University of Science and Technology, Harbin, China, in 1996, and Ph.D degree from Harbin Institute of Technology in 2007, respectively. He is currently an Associate Professor at Harbin Institute of Technology at Weihai, Weihai, China. His main research areas include intelligent testing and information processing, biomedical imaging and image processing.
Naizhang Feng
He received the B.Sc. and Ph.D. degree in control engineering from Harbin Institute of Technology, Harbin, China, in 1998 and 2005, respectively. From 2005 to 2007, he was a post-doctor in Fudan University, Shanghai, China. He is currently a Professor in Harbin Institute of Technology at Weihai. His research interests include signal detection and information processing and medical ultrasound imaging.
Qi Wang
He received the B.Sc. and M.Sc. degree in electromagnetic measurement from Harbin Institute of Technology, Harbin, China, in 1967 and 1980, respectively. From 1985 to 1987 and 1993 to 1995, he visited the University of Tsukuba and the Chiba Institute of Technology, Japan, as a Researcher. He is currently a Professor at the Harbin Institute of Technology. So far, he has more than 120 papers published. His research interests include the intelligent testing instrumentation, information processing, sensor fault diagnosis, and sensor fusion.
