Huang, Kaizhu's homepage

Email: A@B. A=K. Huang B=bris.ac.uk

 Profile              

I am currently a Postdoc researcher working with Dr. Colin Campbell at Dept. of Engineering Mathematics, University of Bristol. I worked as a Research Fellow  at Dept. of Computer Science and Engineering of the Chinese University of Hongkong. from 2007.10 to 2008.9. I got Bachelor of Engineering from Xi'an Jiaotong University  in 1997. At that time I was one of the Special Class for Gifted Children. I got Master of Engineering from Institute of Automation, Chinese Academy of Sciences, (Beijing, China)  in July 2000. I obtained my Ph.D. from The Chinese Univ. of Hong Kong in 2004. After that, I worked as a researcher at Fujitsu Research Center from 2004 to 2007.

 Research Interests

My main research topics are Statistical Machine Learning, Bioinformatics, Pattern Recognition, Information Retrieval, and Image Processing.

 Books

• Kaizhu Huang, Haiqin Yang, Irwin King, Michael R. Lyu,  Machine Learning: Modeling Data Locally and Globally,  Springer Verlag Heidelberg New York  (Oversea Edition)/ Zhejiang University Press (Mainland China edition)   ISBN 3540794514.

 Selected Journal Publications  

• Kaizhu Huang, Danian Zheng, Irwin King, Michael R. Lyu, Arbitrary Norm Support Vector Machines, Neural Computation, to appear, 2008.
• Kaizhu Huang,  Haiqin Yang, Irwin King, Michael R. Lyu. M^4: Learning Large Margin Machines Locally and Globally, IEEE Trans. on Neural Networks, Vol 19, iss.2, pp. 260-272, 2008.
• Kaizhu Huang, Haiqin Yang, Irwin King, and Michael R. Lyu, Maximizing Sensitivity in Medical Diagnosis Using Biased Minimax Probability Machine. IEEE Trans. Biomedical Engineering, Vol 53, Issue 5, 821- 831, May 2006.
• Kaizhu Huang, Haiqin Yang, Irwin King, and Michael R. Lyu, Imbalanced Learning With Biased Minimax Probability Machine. IEEE Trans. System Man, Cybnetics, Part B, Vol 36, No 4, 913 - 923 August, 2006.
• Kaizhu Huang, Haiqin Yang, Irwin King, Michael R. Lyu, and Laiwan Chan. The Minimum Error Minimax Probability Machine. Journal of Machine Learning Research, Vol. 5, pp. 1253-1286, October 2004.

 Selected Conference Publications  

• Kaizhu Huang, Zenglin Xu, Irwin King, and Michael R. Lyu, Semi-supervised Learning from General Unlabeled Data. To appear in theEighth IEEE International Conference on Data Mining (ICDM'2008), Pisa, Italy, 2008. (Regular paper, acceptance rate: 70/724 (9%))
• Kaizhu Huang, Irwin King, and Michael R. Lyu, Direct Zero-norm Optimization for Feature Selection. To appear in the Eighth IEEE International Conference on Data Mining (ICDM'2008), Pisa, Italy, 2008. (Short paper, acceptance rate: 144/724 (20%))
• Zenglin Xu,  Rong Jin, Kaizhu Huang, Irwin King, Michael R. Lyu, "Semi-supervised Text Categorization by Active Search," in  Proceedings to the ACM 17th Conference on Information and Knowledge Management (CIKM2008), Napa Valley, USA, 2008.(Acceptance rate:  256/772 (33%))
• Kaizhu Huang, Haiqin Yang, Irwin King, Michael R. Lyu. Learning Classifiers from Imbalanced Data Based on Biased Minimax Probability Machine. Proceedings IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR' 2004), Washington, DC, June 27 -July 2, 2004. (Acceptance rate: ~200/~1200 (~17%))
• Kaizhu Huang, Haiqin Yang, Irwin King, Michael R. Lyu. Learning Large Margin Machines Locally and Globally. Proceedings international Conference on Machine Learning (ICML' 2004), Banff, Canada, 2004. ((Acceptance rate: 32%)

Click here for full publication list

Softwares

• Matlab toolbox1.0: CSL: A Comprehensive Sparse Learning Package

This is a comprehensive matlab toolbox which implemented most sparse learning algorithms in the literature so far. Six sparse learning algorithms are implemented. They are (1) Two-norm SVM (2) Zero-norm SVM (3) One-norm SVM (Linear Programming SVM and Sparse Controlled SVM) (4) Relevance Vector Machine (Using M. Tipping’s code) (5) Sparse Probit Classifier.

• Matlab toolbox 1.0 for BMPM model and MEMPM model

 This is a MATLAB toolbox to demonstrate two classification models: Minimum Error Minimax Probability Machine (MEMPM) and Biased Minimax Probability Machine (BMPM). MEMPM and BMPM are derived from Minimax Probability Machine (MPM). For convenient comparison, we implement the MEMPM and the BMPM using the same data format to the MPM. The advantages of MEMPM and BMPM are:

ü      MEMPM is a worst-case distribution-free Bayes optimal classifier. It converges to the true Bayes optimal classifier when Gaussian distribution is assumed.

ü      MEMPM provides a lower bound on the probability of correct classification of future data being a class of data with given mean and covariance matrix. This bound is superior to the bound of MPM.

ü      BMPM can be used to the biased classification. It achieves the bias by maximizing the worst-case probability of correct classification on one class while keeping the worst-case probability of correct classification on the other acceptable.

ü      BMPM provides the corresponding lower bound for a classification accuracy indicator.

Patents

• Kaizhu Huang, Jun Sun, Yoshinobu Hotta, Satoshi Naoi, Address Recognition Methods and Apparatus, Application Num: 200510089537.0, China
• Kaizhu Huang, Jun Sun, Yoshinobu Hotta, Satoshi Naoi, Address Recognition Methods and Apparatus with and without Key Characters. Application Num: 200710089131.1, China
• Kaizhu Huang,Jun Sun, Yoshinobu Hotta, Satoshi Naoi, Character Recognition Apparatus and Method Using Differential Features. Application Num: 200710078767.6, China
• Jun Sun, Kaizhu Huang, Yoshinobu Hotta, Satoshi Naoi, Degraded Character Recognition Apparatus and Method. Internal No. 06-53478, China 
• Danian Zheng, Kaizhu Huang, Jun Sun, Yoshinobu Hotta, Satoshi Naoi, Sparse Support Vector Machine Methods and Apparatus. Application Num: 200710146535.X, China
• Kaizhu Huang,Danian Zheng, Jun Sun, Yoshinobu Hotta, Satoshi Naoi, Image Based Keyword Search Methods and Apparatus. Internal No.: 07-52540, China.

 Awards

• National "Three 100" Best Book Award, General Administration of Press and Publication of China, 2008
• Postdoc Fellowship, Faculty of Engineering, The Chinese Univ. of Hong Kong, 2007
• Special Award for Best Research Output  Fujitsu R&D Centre, 2007 (3 persons/year)
• Award of Q-finity, Fujitsu Corporation. 2006
• President Award, Fujitsu Laboratories, 2006 (Top award)
• Excellent Award for Best Research Output  Fujitsu R&D Centre, 2006  (2 persons/year)
• Special Award for Best Research Output  Fujitsu R&D Centre, 2005 (3 persons/year)
• Postgraduate Scholarship, CUHK Hong Kong, 2001~2004
• Logic Prize for Outstanding Students, XJTU,(top 1%), 1996
• Excellent Student Award, XJTU (top 1 %), 1996
• The Second Prize Scholarship (3 times) XJTU (top 7%), 1993~1995
• Gifted Youth Fellowship, XJTU (top 1%), 1992

 My Link