Proposing a Neural-genetic System for Optimized Feature Selection Applied in Medical Datasets
- Associate Professor, Department of Computer Engineering and Information Technology, Payame Noor University, Iran.
Mohammad Reza Mohammadi Khoroushani
- M.Sc. student, Department of Computer Engineering and Information Technology, Payame Noor University, Esfahan, Iran.
This paper, presents a new system for selecting the best optimized features among a collection of features by combination of neural network and genetic algorithm. Feature selection is an important issue because it has a direct impact on the performance (Specificity, sensitivity) and system efficiency.
The proposed system uses neural network for selecting the best features based on Signal to Noise Ratio (SNR), and genetic algorithm for training the neural network by determining the optimum values of weighs and other parameters. This system is a combination of a Multi-Layer Perceptron (MLP) with 3 layers and decimal genetic algorithm.
We evaluated our proposed system on 10 medical data sets and compared it with binary genetic algorithm that is used widely for feature selection. The results confirmed the superiority of the proposed system in Specificity, sensitivity and the number of selected optimized features.
- feature selection
- optimized feature selection
- neural network
- genetic algorithm.
N. Sanchez-Marono, A. Alonso-Betanzos, M. Tombilla-Sanroman, Filter methods for feature selection: a comparative study, Proceedings of the 8th international conference on Intelligent data engineering and automated learning, Birmingham, UK, Springer-Verlag, (2007), 178-187
M. Saberi, D. Safaai, Feature Selection Method Using Genetic Algorithm For The Classification Of Small and High Dimension Data, in International Journal on IEEE Transaction On Pattern Analysis And Machine Intelligence, VOL. 23, NO. 11 (2005)
M. T. Miller, A. K. Jerebko, J. D. Malley, R. M. Summers, Feature Selection for Computer-Aided Polyp Detection using Genetic Algorithms, Proceedings of SPIE, Vol. 5031 (2003)
H. Chouaib, O. R. Terrades, S. Tabbone, F. Cloppet, N. Vincent, Feature selection combining genetic algorithm and Adaboost classifiers, in 19th International Conference on Pattern Recognition(IEEE), ICPR 2008, Tampa, FL (2008)
E. P. Ephzibah, Cost Effective Approach on Feature selection Using Genetic Algorithms And Fuzzy Logic for Diabetes Diagnosis, in International Journal on Soft Computing(IJSC), 2 (2011),
I. S. Oh, J. S. Lee, B. R. Moon, Hybrid Genetic Algorithms for Feature Selection, IEEE Transaction On Pattern Analysis And Machine Intelligence, VOL. 26, NO. 11 (2004)
M. Nirooee, P. Abdolmaleki, M. Gity, Designing a Hybrid Model to Differentiate between Malignant and Benign Patterns in Breast Cancer from Mammographic Findings (Text in Persian), in Iranian Journal of Medical Physics, (2008), 67-80
S. Zanganeh, R. Javanmard, M. Ebadzadeh, A Hybrid Approach for Features Dimension Reduction of Datasets using Hybrid Algorithm Artificial Neural Network and Genetic Algorithm-in Medical Diagnosis, in 4rd Iran Data Mining Conference (IDMC), (2010)
L. Ballerini, X. Li, R. B. Fisher, J. Rees, A query-by-example content-based image retrieval system of non-melanoma skin lesions, presented at the Proceedings of the First MICCAI international conference on Medical Content-Based Retrieval for Clinical Decision Support, London, UK (2010)
A. Verikas, M. Bacauskiene, Feature selection with neural networks, in Journal Pattern Recognition Letters, 23 (2002), 1323-1335.
gems, Gene Expression Model Selector , Available: http://www.gems-system.org , (2014)
M. R. Mohammadi Khoroushani, S. Mahzounieh, Intelligent Skin Cancer Detection Software System based on the principles of telemedicine, in Journal of Hospital, 5 (2014), 55-60