Training with Input Selection and Testing (TWIST) Algorithm: A Significant Advance in Pattern Recognition Performance of Machine Learning

This article shows the efficacy of TWIST, a methodology for the design of training and testing data subsets extracted from given dataset associated with a problem to be solved via ANNs. The methodology we present is embedded in algorithms and actualized in computer software. Our methodology as implemented in software is compared to the current standard methods of random cross validation: 10-Fold CV, random split into two subsets and the more advanced T&T. For each strategy, 13 learning machines, representing different families of the main algorithms, have been trained and tested. All algorithms were implemented using the well-known WEKA software package. On one hand a falsification test with randomly distributed dependent variable has been used to show how T&T and TWIST behaves as the other two strategies: when there is no information available on the datasets they are equivalent. On the other hand, using the real Statlog (Heart) dataset, a strong difference in accuracy is experimentally proved. Our results show that TWIST is superior to current methods. Pairs of subsets with similar probability density functions are generated, without coding noise, according to an optimal strategy that extracts the most useful information for pattern classification.

[1]  Massimo Buscema,et al.  Appropriateness Guidelines and Predictive Rules to Select Patients for Upper Endoscopy: A Nationwide Multicenter Study , 2009, The American Journal of Gastroenterology.

[2]  David G. Stork,et al.  Pattern Classification , 1973 .

[3]  Jack Sklansky,et al.  A note on genetic algorithms for large-scale feature selection , 1989, Pattern Recognition Letters.

[4]  Subhash C. Bagui,et al.  Combining Pattern Classifiers: Methods and Algorithms , 2005, Technometrics.

[5]  Michael Fairhurst,et al.  Feature selection in automatic signature verification , 1994 .

[6]  Léon Personnaz,et al.  Neural-network construction and selection in nonlinear modeling , 2003, IEEE Trans. Neural Networks.

[7]  Enzo Grossi,et al.  Polymorphisms in folate-metabolizing genes, chromosome damage, and risk of Down syndrome in Italian women: identification of key factors using artificial neural networks , 2010, BMC Medical Genomics.

[8]  M. Buscema,et al.  Introduction to artificial neural networks. , 2007, European journal of gastroenterology & hepatology.

[9]  Enzo Grossi,et al.  Placental determinants of fetal growth: identification of key factors in the insulin-like growth factor and cytokine systems using artificial neural networks , 2008, BMC pediatrics.

[10]  Paul Leahy,et al.  Structural optimisation and input selection of an artificial neural network for river level prediction , 2008 .

[11]  G. Kim,et al.  FEATURE SELECTION USING GENETIC ALGORITHMS FOR HANDWRITTEN CHARACTER RECOGNITION , 2004 .

[12]  Hiroshi Motoda,et al.  Feature Extraction, Construction and Selection: A Data Mining Perspective , 1998 .

[13]  Yuehui Chen,et al.  Feature Selection and Intrusion Detection Using Hybrid Flexible Neural Tree , 2005, ISNN.

[14]  Antonio González Muñoz,et al.  Table Ii Tc Pattern Recognition Result for 120 Eir Satellite Image Cases Selection of Relevant Features in a Fuzzy Genetic Learning Algorithm , 2001 .

[15]  John Scott Bridle,et al.  Probabilistic Interpretation of Feedforward Classification Network Outputs, with Relationships to Statistical Pattern Recognition , 1989, NATO Neurocomputing.

[16]  Ian Witten,et al.  Data Mining , 2000 .

[17]  Paolo Massimo Buscema,et al.  New application of intelligent agents in sporadic amyotrophic lateral sclerosis identifies unexpected specific genetic background , 2008, BMC Bioinformatics.

[18]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[19]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[20]  RokachLior.  Taxonomy for characterizing ensemble methods in classification tasks , 2009 .

[21]  Thomas G. Dietterich.  Approximate Statistical Tests for Comparing Supervised Classification Learning Algorithms , 1998, Neural Computation.

[22]  Mineichi Kudo,et al.  Comparison of algorithms that select features for pattern classifiers , 2000, Pattern Recognit..

[23]  Shian-Shyong Tseng,et al.  A two-phase feature selection method using both filter and wrapper , 1999, IEEE SMC'99 Conference Proceedings. 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.99CH37028).

[24]  Ron Kohavi,et al.  Irrelevant Features and the Subset Selection Problem , 1994, ICML.

[25]  Yves Chauvin,et al.  Backpropagation: theory, architectures, and applications , 1995 .

[26]  Paolo Massimo Buscema,et al.  Genetic doping algorithm (GenD): theory and applications , 2004, Expert Syst. J. Knowl. Eng..

[27]  Jack Sklansky,et al.  A note on genetic algorithms for large-scale feature selection , 1989, Pattern Recognit. Lett..

[28]  Hiroshi Motoda,et al.  Feature Extraction, Construction and Selection , 1998 .

[29]  M Buscema,et al.  International experience on the use of artificial neural networks in gastroenterology. , 2007, Digestive and liver disease : official journal of the Italian Society of Gastroenterology and the Italian Association for the Study of the Liver.

[30]  Lior Rokach,et al.  Taxonomy for characterizing ensemble methods in classification tasks: A review and annotated bibliography , 2009, Comput. Stat. Data Anal..

[31]  Massimo Buscema,et al.  Artificial neural networks in the recognition of the presence of thyroid disease in patients with atrophic body gastritis. , 2008, World journal of gastroenterology.

[32]  อนิรุธ สืบสิงห์,et al.  Data Mining Practical Machine Learning Tools and Techniques , 2014 .

[33]  Massimo Buscema,et al.  Artificial Neural Networks for Early Prediction of Mortality in Patients with Non Variceal Upper GI Bleeding (UGIB) , 2008, Biomedical informatics insights.

[34]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[35]  C Babiloni,et al.  The I.F.A.S.T. model allows the prediction of conversion to Alzheimer disease in patients with mild cognitive impairment with high degree of accuracy. , 2010, Current Alzheimer research.

[36]  M Buscema,et al.  Assessment of the Role of Genetic Polymorphism in Venous Thrombosis Through Artificial Neural Networks , 2005, Annals of human genetics.

[37]  Philipp Slusallek,et al.  Introduction to real-time ray tracing , 2005, SIGGRAPH Courses.

[38]  Donald E. Brown,et al.  Fast generic selection of features for neural network classifiers , 1992, IEEE Trans. Neural Networks.

[39]  Massimo Buscema,et al.  Artificial neural networks accurately predict mortality in patients with nonvariceal upper GI bleeding. , 2011, Gastrointestinal endoscopy.

[40]  Enzo Grossi,et al.  Is it possible to clinically differentiate erosive from nonerosive reflux disease patients? A study using an artificial neural networks-assisted algorithm , 2010, European journal of gastroenterology & hepatology.

[41]  Paolo Massimo Buscema,et al.  An optimized experimental protocol based on neuro-evolutionary algorithms: Application to the classification of dyspeptic patients and to the prediction of the effectiveness of their treatment , 2005, Artif. Intell. Medicine.

[42]  N. Chaikla,et al.  Genetic algorithms in feature selection , 1999, IEEE SMC'99 Conference Proceedings. 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.99CH37028).

[43]  M. Narasimha Murty,et al.  On the Scalability of Genetic Algorithms to Very Large-Scale Feature Selection , 2000, EvoWorkshops.