Improving Feature Selection Using Elite Breeding QPSO on Gene Data set for Cancer Classification

This paper focuses on feature set selection on microarray gene expression for cancer classification. The gene expression data are incommensurate when it comes to number of genes and number of samples. This imbalance makes it important to study feature selection algorithms from the complex gene expression data. We conducted a research with quantum particle swarm optimization with elitist breeding (EBQPSO) on gene data sets. To the best of our knowledge, the exploration of the elitist is not taken into account for deep searching and classification applications with genetic data sets. Our contribution in this paper is to use EBQPSO algorithm on gene data sets for classification of cancer. The algorithm is tested with supervised and unsupervised learning approach, viz. support vector machine, J48 and neural network. The results show that EBQPSO outperforms particle swarm optimization (PSO) and quantum particle swarm optimization (QPSO) algorithms in terms of precision and recall value.

[1]  Angus K. M. Wu,et al.  An Improved Quantum-Behaved Particle Swarm Optimization Algorithm with Elitist Breeding for Unconstrained Optimization , 2015, Comput. Intell. Neurosci..

[2]  D. Ramyachitra,et al.  Interval-value Based Particle Swarm Optimization algorithm for cancer-type specific gene selection and sample classification , 2015, Genomics data.

[3]  Clive R Taylor,et al.  Practicing Pathology in the Era of Big Data and Personalized Medicine , 2014, Applied immunohistochemistry & molecular morphology : AIMM.

[4]  Andries Petrus Engelbrecht,et al.  Particle Swarm Convergence: Standardized Analysis and Topological Influence , 2014, ANTS Conference.

[5]  Changsheng Xu,et al.  Inductive Robust Principal Component Analysis , 2012, IEEE Transactions on Image Processing.

[6]  Vikrant Bhateja,et al.  An Improved Mammogram Classification Approach Using Back Propagation Neural Network , 2018 .

[7]  Enrique Alba,et al.  Gene selection in cancer classification using PSO/SVM and GA/SVM hybrid algorithms , 2007, 2007 IEEE Congress on Evolutionary Computation.

[8]  Iftikhar Ahmad,et al.  Feature Selection Using Particle Swarm Optimization in Intrusion Detection , 2015, Int. J. Distributed Sens. Networks.

[9]  Jing Zhao,et al.  A Binary Quantum-behaved Particle Swarm Optimization Algorithm with Cooperative Approach , 2013 .

[10]  Malaya K. Nath,et al.  Independent Component Analysis of Real Data , 2009, 2009 Seventh International Conference on Advances in Pattern Recognition.

[11]  Bernhard Schölkopf,et al.  Nonlinear Component Analysis as a Kernel Eigenvalue Problem , 1998, Neural Computation.

[12]  Niu Dongxiao,et al.  Application of Gauss Radial Kernel Function Principal Component Analysis Model in the Industrial Enterprise's Wastewater Treatment , 2007, 2007 2nd IEEE Conference on Industrial Electronics and Applications.

[13]  Nadeem Javaid,et al.  Delay-Sensitive Routing Schemes for Underwater Acoustic Sensor Networks , 2015, Int. J. Distributed Sens. Networks.

[14]  Li Liu,et al.  Cancer Feature Selection and Classification Using a Binary Quantum-Behaved Particle Swarm Optimization and Support Vector Machine , 2016, Comput. Math. Methods Medicine.

[15]  Baisa L. Gunjal,et al.  Particle Swarm Optimization- Best Feature Selection method for Face Images , 2012 .

[16]  Ioan Cristian Trelea,et al.  The particle swarm optimization algorithm: convergence analysis and parameter selection , 2003, Inf. Process. Lett..

[17]  Wenbo Xu,et al.  Particle swarm optimization with particles having quantum behavior , 2004, Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753).

[18]  Baisakhi Chakraborty,et al.  Early Skin Cancer Detection Using Computer Aided Diagnosis Techniques , 2016, J. Integr. Des. Process. Sci..

[19]  Duncan Fyfe Gillies,et al.  A Review of Feature Selection and Feature Extraction Methods Applied on Microarray Data , 2015, Adv. Bioinformatics.