论文信息 - The Nuclear Techniques and the Selection of Model Parameters in Big Data

The Nuclear Techniques and the Selection of Model Parameters in Big Data

Now a large scale of data every day, the large-scale data is usually in the form of database storage. The law of the people wants to find useful or knowledge, thus was born the Data Mining technology. SVM (Support Vector Machine, SVM) is a very useful method in data mining, this paper mainly discusses the Support Vector Machine (SVM) play a key role in nuclear techniques and the selection of model parameters is analyzed and evaluated. This article some methods about how to construct the kernel function is introduced for the model to find suitable kernel function is to provide some reference strategies and proposed kernel function method for the simulation analysis.

Wang Chunhong

[1] Yunzhou Li,et al. Optimal linear precoding for opportunistic spectrum sharing under arbitrary input distributions assumption , 2013, EURASIP J. Adv. Signal Process..

[2] David E. Goldberg,et al. Genetic algorithms and Machine Learning , 1988, Machine Learning.

[3] F. McNeill,et al. Grid search: an innovative method for the estimation of the rates of lead exchange between body compartments. , 2005, Journal of environmental monitoring : JEM.

[4] Gisbert Schneider,et al. Support vector machine applications in bioinformatics. , 2003, Applied bioinformatics.

[5] Yingjie Tian,et al. Leave-one-out bounds for support vector ordinal regression machine , 2008, Neural Computing and Applications.

[6] S. Aiguo,et al. Evolving Gaussian RBF network for nonlinear time series modelling and prediction , 1998 .

[7] Bernhard Schölkopf,et al. Falsificationism and Statistical Learning Theory: Comparing the Popper and Vapnik-Chervonenkis Dimensions , 2009 .

[8] Volume Ps. EEE TRANSACTIONS ON , 1986 .

[9] Mingsheng Liao,et al. A learning-based target decomposition method using Kernel KSVD for polarimetric SAR image classification , 2012, EURASIP J. Adv. Signal Process..