Approximation of Missing Values for Classification and Regression

Abstract:

Missing value of dataset has become a challenging issue in data mining. Although there have been significant efforts to handle it, the methods to deal with missing values in neural networks are undeveloped. This article thus proposes an intelligent method to perform classification and regression in case of missing values. In particular, hybrid genetic algorithms and fast simulated annealing are used to predict them, and their results are further compared. The experimental results give rise to a valuable and deep insight into handling missing values in data mining application.

• Periodical: Advanced Materials Research (Volumes 734-737)
• Pages: 2938-2944
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.734-737.2938
• Online since: August 2013
• Authors: Yi Juan Su*, Zhi Zhong, Wen Jing Li
• Keywords: Classification, Miss Data, Regression

References

[1] Little R J A Rubin DB Statistical analysis with missing data. John Wiley, New York (1987).

[2] Abdella M Marwala T The use of genetic algorithms and neural networks to approximate missing data in database. Computing and Informatics (2006) 1001– 1013.

DOI: 10.1109/icccyb.2005.1511574

[3] Mohamed S Marwala T Neural network based techniques for estimating missing data in databases. 16th Annual Symposium of the Pattern Recognition Association of South Africa (2005) 27–32.

[4] Gabrys B Neuro-fuzzy approach to processing inputs with missing values in pattern recognition problems. Journal of Approximate Reasomning 30 (2002).

DOI: 10.1016/s0888-613x(02)00070-1

[5] Schafer J Graham J Missing data: Our view of the state of the art. Psychological Methods 7 (2002) 147–177.

DOI: 10.1037/1082-989x.7.2.147

[6] Marwala T Chakraverty S Fault classification in structures with incomplete measured data using autoassociative neural networks and genetic algorithm. Current Science (2006) 542–548.

[7] Carpenter G Grossberg S Markuzon N Reynolds J Rosen D Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of multidimensional maps. IEEE Transactions on Neural Networks 3 (1992) 698–713.

DOI: 10.1109/72.159059

[8] Javadpour R Knapp G A fuzzy neural network approach to condition monitoring. Sociological Methods and Research 45 (2003) 323–330.

DOI: 10.1016/s0360-8352(03)00039-1

[9] Goldberg D Genetic Algorithms in Search, Optimization and Machine Learning. Addison-Wesley, Reading, MA (1989).

[10] Davis L Handbook of Genetic Algorithms. Van Nostrand, New York (1991).

[11] McGookin E Murray-Smith D Submarine manoeuvring controllers optimisation using simulated annealing and genetic algorithms. Control Engineering Practice 14 (2006) 1–15.

DOI: 10.1016/j.conengprac.2005.01.002

[12] Tamaki, H., Kita, H., Kobayahi, S.: Multi-objective optimization by genetic algoritms: A review. in Proc. 3rd ICEC (1996) 517–522.

[13] Metropolis N Rosenbluth AW Rosenbluth M N Teller A H Teller E Equation of state calculation using fast computing machines. Journal of Chemical Physics 21 (1953) 1087–1092.

DOI: 10.1063/1.1699114

[14] McGookin, E Murray-Smith D Using correspondence analysis to combine classifiers. Machine Learning 14 (1997) 1–26.