Restricted Optimal Modeling Method Supervised by Expectation Error

Relation between the possible minimum error (i.e. expectation error) of empirical model and data quality information (e.g., data scale and noise intensity) is analyzed quantitatively, a concept of “restricted optimal model” is proposed, methods to estimate expectation error are introduced, an idea to optimize model using expectation error is proposed. Based on this idea, an optimal Neural Network modeling method is proposed. Its availability and superiority is verified by simulation experiment. Furthermore, a new evaluation index of model, namely error average power (EAP), is proposed, which is suitable to evaluate different modeling methods in simulation experiment.

[1]  宋彦坡,et al.  Approach based on wavelet analysis for detecting and amending anomalies in dataset , 2006 .

[2]  Yanpo Song,et al.  Approach based on wavelet analysis for detecting and amending anomalies in dataset , 2006 .

[3]  Stephen D. Bay,et al.  Mining distance-based outliers in near linear time with randomization and a simple pruning rule , 2003, KDD '03.

[4]  Ning Wang,et al.  Fuzzy nonparametric regression based on local linear smoothing technique , 2007, Inf. Sci..

[5]  Gustavo E. A. P. A. Batista,et al.  An analysis of four missing data treatment methods for supervised learning , 2003, Appl. Artif. Intell..

[6]  Dug Hun Hong,et al.  Extended fuzzy regression models using regularization method , 2004, Inf. Sci..

[7]  Chengqi Zhang,et al.  POP algorithm: Kernel-based imputation to treat missing values in knowledge discovery from databases , 2009, Expert Syst. Appl..

[8]  Hussein Baher,et al.  Analog and Digital Signal Processing , 1990 .

[9]  Ashok Ambardar,et al.  Analog and Digital Signal Processing , 1995 .

[10]  Erhard Rahm,et al.  Data Cleaning: Problems and Current Approaches , 2000, IEEE Data Eng. Bull..

[11]  Shuyuan Yang,et al.  Ridgelet kernel regression , 2007, Neurocomputing.

[12]  Chee Peng Lim,et al.  A modified fuzzy min-max neural network with rule extraction and its application to fault detection and classification , 2008, Appl. Soft Comput..

[13]  Chenghu Zhou,et al.  An improved kernel regression method based on Taylor expansion , 2007, Appl. Math. Comput..

[14]  Malik Magdon-Ismail,et al.  No Free Lunch for Early Stopping , 1999, Neural Computation.