A data clustering algorithm for stratified data partitioning in artificial neural network

• Published in: Expert systems with applications Vol. 39; no. 8; pp. 7004 - 7014
• Main Authors: Sahoo, Ajit K., Zuo, Ming J., Tiwari, M.K.
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 15.06.2012
• Subjects: Algorithms; Artificial neural network; Clustering; Clusters; Custom design clustering algorithm; Data clustering; Data partitioning; Fuzzy clustering; Genetic algorithm; Genetic algorithms; Mathematical analysis; ODP; Partitioning; Self organizing map; Training; Data partitioning; Fuzzy clustering; Self organizing map; Genetic algorithm; Data clustering; Artificial neural network; Custom design clustering algorithm
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2012.01.047

The statistical properties of training, validation and test data play an important role in assuring optimal performance in artificial neural networks (ANNs). Researchers have proposed optimized data partitioning (ODP) and stratified data partitioning (SDP) methods to partition of input data into training, validation and test datasets. ODP methods based on genetic algorithm (GA) are computationally expensive as the random search space can be in the power of twenty or more for an average sized dataset. For SDP methods, clustering algorithms such as self organizing map (SOM) and fuzzy clustering (FC) are used to form strata. It is assumed that data points in any individual stratum are in close statistical agreement. Reported clustering algorithms are designed to form natural clusters. In the case of large multivariate datasets, some of these natural clusters can be big enough such that the furthest data vectors are statistically far away from the mean. Further, these algorithms are computationally expensive as well. We propose a custom design clustering algorithm (CDCA) to overcome these shortcomings. Comparisons are made using three benchmark case studies, one each from classification, function approximation and prediction domains. The proposed CDCA data partitioning method is evaluated in comparison with SOM, FC and GA based data partitioning methods. It is found that the CDCA data partitioning method not only perform well but also reduces the average CPU time.