Abstract
An improved genetic algorithm procedure is introduced in this work based on the theory of the most highly fit parents (both male and female) are most likely to produce healthiest offspring. It avoids the destruction of near optimal information and promotes further search around the potential region by encouraging the exchange of highly important information among the fittest solution. A novel crossover technique called Segmented Multi-chromosome Crossover is also introduced. It maintains the information contained in gene segments and allows offspring to inherit information from multiple parent chromosomes. The improved GA is applied for the automatic and simultaneous parameter optimization and feature selection of multi-layer perceptron network in medical disease diagnosis. Compared to the previous works, the average accuracy of the proposed algorithm is the best among all algorithms for diabetes and heart dataset, and the second best for cancer dataset.
Similar content being viewed by others
References
Lee, S., Lee, T., Jin, G., and Hong, J., An Implementation of Wireless Medical Image Transmission System on Mobile Devices. J. Med. Syst. 32(6):471–480, 2008. doi:10.1007/s10916-008-9153-9.
Qi, H., Kong, L., Wang, C., Miao, L. A., Hand-held Mosaicked Multispectral Imaging Device for Early Stage Pressure Ulcer Detection. J. Med. Syst. 35 (5):895–904, 2010. doi:10.1007/s10916-010-9508-x.
Daliri, M., Automated Diagnosis of Alzheimer Disease using the Scale-Invariant Feature Transforms in Magnetic Resonance Images. J. Med. Syst. 36 (2):995–1000, 2012. doi:10.1007/s10916-011-9738-6.
Wagholikar, K., Mangrulkar, S., Deshpande, A, Sundararajan, V., Evaluation of Fuzzy Relation Method for Medical Decision Support. J. Med. Syst. 36 (1):233–239, 2012. doi:10.1007/s10916-010-9472-5.
Bani Amer, M., Al-Ebbini, L. Fuzzy Approach for Determination the Optimum Therapeutic Parameters in Neuromuscular Stimulation Systems. J. Med. Syst. 34 (4):435–443, 2010. doi:10.1007/s10916-009-9256-y.
Yuan, B., Sun, G., Gomez, J., Ikemoto, Y., Gonzarlez, J., Murai, C., Acharya, U. R., Yu, W., Ino, S. The Effect of an Auxiliary Stimulation on Motor Function Restoration by FES. J. Med. Syst. 35 (5):855–861, 2011. doi:10.1007/s10916-010-9517-9.
Cybenko, G., Approximation by superpositions of a sigmoidal function. Math Control Signal 2(4):303–314, 1989. doi:10.1007/bf02551274.
Paliwal, M., and Kumar, U. A., Neural networks and statistical techniques: A review of applications. Expert Syst. Appl. 36(1):2–17, 2009.
Tian, J., Li, M., and Chen, F., Dual-population based coevolutionary algorithm for designing RBFNN with feature selection. Expert Syst. Appl. 37(10):6904–6918, 2010.
Rudy, S., and Huan, L., Neural-network feature selector. IEEE T Neural Networ. 8(3):654–662, 1997.
Monirul Kabir, M., Monirul Islam, M., and Murase, K., A new wrapper feature selection approach using neural network. Neurocomputing 73(16–18):3273–3283, 2010.
Rocha, M., Neves, J., Imam, I., Kodratoff, Y., El-Dessouki, A., and Ali, M., Preventing Premature Convergence to Local Optima in Genetic Algorithms via Random Offspring Generation. Multiple Approaches to Intelligent Systems, vol 1611. Lecture Notes in Computer Science. Springer Berlin, Heidelberg, pp. 127–136, 1999. doi:10.1007/978-3-540-48765-4_16.
Yang, W., Li, D., and Zhu, L., An improved genetic algorithm for optimal feature subset selection from multi-character feature set. Expert Syst. Appl. 38(3):2733–2740, 2011.
Marinakis, Y., Marinaki, M., A hybrid genetic - Particle Swarm Optimization Algorithm for the vehicle routing problem. Expert. Syst. Appl. 37 (2):1446–1455, 2010. doi:http://dx.doi.org/10.1016/j.eswa.2009.06.085.
Lee, C.-P., and Leu, Y., A novel hybrid feature selection method for microarray data analysis. Appl. Soft Comput. 11(1):208–213, 2011.
Hsieh, S.-T., Sun, T.-Y., and Liu, C.-C., Potential offspring production strategies: An improved genetic algorithm for global numerical optimization. Expert Syst. Appl. 36(8):11088–11098, 2009.
Liu, Q., Ullah, S., and Zhang, C., An improved genetic algorithm for robust permutation flowshop scheduling. Int. J. Adv. Manuf. Tech. 56(1):345–354, 2011. doi:10.1007/s00170-010-3149-6.
Goldberg, D., Genetic algorithms in search and optimization, Istth edition. Addison-wesley, Boston, 1989.
Whitley, D., Starkweather, T., and Bogart, C., Genetic algorithms and neural networks: optimizing connections and connectivity. Parallel Comput. 14(3):347–361, 1990. doi:10.1016/0167-8191(90)90086-O.
Saxena, A., and Saad, A., Evolving an artificial neural network classifier for condition monitoring of rotating mechanical systems. Appl. Soft Comput. 7(1):441–454, 2007. doi:10.1016/j.asoc.2005.10.001.
{UCI} Machine Learning Repository, University of California, Irvine, School of Information and Computer Sciences. http://archive.ics.uci.edu/ml, 2010.
Demuth, H., and Beale, M., Neural network toolbox user’s guide, version 4. The MathWorks Inc., Natick, 2003.
Prechelt, L., Proben1: A set of neural network benchmark problems and benchmarking rules. Technical Report, University of Karlsruhe, Karlsruhe, Germany, 1994.
Hall, M. A., Correlation-based feature selection for machine learning. Ph.D. Thesis, Department of Computer Science, University of Waikato, Hamilton, New Zealand, 1999.
Alba, E., and Chicano, J. F., Training Neural Networks with GA Hybrid Algorithms. In: Deb, K. (Ed.), Genetic and Evolutionary Computation - GECCO 2004, vol 3102. Lecture Notes in Computer Science. Springer, Berlin, pp. 852–863, 2004. doi:10.1007/978-3-540-24854-5_87.
Socha, K., and Blum, C., An ant colony optimization algorithm for continuous optimization: application to feed-forward neural network training. Neural Comput. Appl. 16(3):235–247, 2007. doi:10.1007/s00521-007-0084-z.
Acknowledgments
This project is supported by Ministry of Science, Technology & Innovation Malaysia, Science fund Grant entitle “Development of Computational Intelligent Infertility Detection System based on Sperm Motility Analysis” and Universiti Sains Malaysia Research University-Postgraduate Research Grant Scheme entitled ‘Genetic Algorithm-Artificial Neural Network Hybrid Intelligence’.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ahmad, F., Mat Isa, N.A., Hussain, Z. et al. Intelligent Medical Disease Diagnosis Using Improved Hybrid Genetic Algorithm - Multilayer Perceptron Network. J Med Syst 37, 9934 (2013). https://doi.org/10.1007/s10916-013-9934-7
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10916-013-9934-7