Zhiwei SHI, Ph.D.
Mindray Beijing Research Institute
Address:
Chuangye Road 8, Shangdi, Haidian District, Beijing, China(100085)
E-Mail: shizhiwei@mindray.com or zhiweishi@gmail.com
Brief Biography:
Zhiwei SHI was born in Luoyang, a beautiful city in central China.
In 1998, Zhiwei SHI became a university student at Zhengzhou University, and received Bachelor Degree in Electric Automatization in 2002. In the same year, Zhiwei SHI began his master degree program at Dalian Univ. of Technology, and in 2004 he became a PHD Candidate at Intelligent Control and Information Processing Research Group (ICIP Group) in Dalian Univ. of Technology.
In the summer of 2008, he became a research and development engineer at Mindray Beijing Research Institute, and now his work and research are focused on medical ultrasound imaging.
Research Interests:
Signal Processing and Optimization in Medical Ultrasound Imaging,
Neural nets especially Recurrent Net and Reservoir Computing,
Support Vector Machines and Kernel Method,
Nonlinear Time Series Analysis and Prediction.
Selected Publications:
Zhiwei Shi and Min Han, γ–C plane and robustness in static reservoir for nonlinear regression estimation, Neurocomputing, 2009. Article in Press(doi:10.1016/j.neucom.2008.08.002).
Drop me any comments about the new algorithm
| shi2008ncing.pdf |
γ–C plane in a static reservoir (Software Download)
The proposed method inherits the basic idea from support vector echo-state machines(SVESMs), but applies for static nonlinear regression estimation problem. Based on the experience of echo state networks(ESN) and extreme learning machine(ELM), the global scaling parameter γ and the regularization parameter C are used to characterize a reservoir, and the proper reservoir is identified on the γ-C plane.
The left figure is the “γ-C” plane in a static reservoir for the Abalone regression datasets.
Zhiwei Shi. Research on Chaotic Time Series Prediction and Reservoir Machine Learning Method. Phd. Thesis, 2008. (In Chinese) Asking for a fulltext
Zhiwei Shi and Min Han, Tikhonov-Type Regularization in Local Model for Noisy Chaotic Time Series Prediction. in Proceedings of the 46th IEEE Conference on Decision and Control, New Orleans, Louisiana, United States, 2007:2223-2228.
| cdc2007shi.pdf |
Zhiwei Shi and Min Han, Support Vector Echo-State Machine for Chaotic Time Series Prediction, IEEE Trans. on Neural Networks, vol.18, no.2, 2007, pp.359-372.
| shi2007tnn.pdf |
Zhiwei Shi and Min Han, Ridge regression learning in ESN for Chaotic time series prediction, Control and Decision, vol. 22, no.3, 2007, pp.258-261+267. (in Chinese)
| shi2007kzyjc.pdf |
Min Han, Zhiwei Shi and Wei Guo, Reservoir neural state reconstruction and chaotic time series prediction. Acta Physica Sinica, vo.56, no.1, 2007, pp.43-50. (in Chinese)
| han2007wuli.pdf |
Min Han, Zhiwei Shi, Jianhui Xi, Learning the trajectories of periodic attractor using recurrent neural network, Control Theory and Applications, vol.23, no.4, 2006, pp.497-502. (in Chinese)
| han2006kzllyyy.pdf |
Zhiwei Shi, Min Han, and Jianhui Xi, Exploring the Neural State Space Learning from One-Dimension Chaotic Time Series, in Proceedings of IEEE International Conference on Networking, Sensing and Control, Tucson, AZ, MAR 19-22, 2005. pp.437-442.
| shi2005icnsc.pdf |
Jianhui Xi, Zhiwei Shi, Min Han. Analyzing the State Space Property of Echo State Networks for Chaotic System Prediction, in Proceedings of IEEE International Joint Conference on Neural Networks (IJCNN 2005), Montreal, CAMBODIA, Jul 31-Aug 04, 2005. pp.1412-1417.
| xi2005ijcnn.pdf |
Min Han, Zhiwei Shi, Application of recurrent neural network to earthquake response analysis of rock-fill dam, Xitong Fangzhen Xuebao, vol.17, no.10, 2005, pp. 2533-2536+2540 (in Chinese)
Min Han, Zhiwei. Shi, and Wei Wang, Modeling dynamic system by recurrent neural network with state variables, in Advances in Neural Networks - ISNN 2004, Pt 2, Vol. 3174, Lecture Notes in Computer Science. Berlin: SPRINGER-VERLAG BERLIN, 2004, pp. 200-205.
