A Novel Weighted Support Vector Machine Based on Particle Swarm Optimization for Gene Selection and Tumor Classification

Abstract

We develop a detection model based on support vector machines (SVMs) and particle swarm optimization (PSO) for gene selection and tumor classification problems. The proposed model consists of two stages: first, the well-known minimum redundancy-maximum relevance (mRMR) method is applied to preselect genes that have the highest relevance with the target class and are maximally dissimilar to each other. Then, PSO is proposed to form a novel weighted SVM (WSVM) to classify samples. In this WSVM, PSO not only discards redundant genes, but also especially takes into account the degree of importance of each gene and assigns diverse weights to the different genes. We also use PSO to find appropriate kernel parameters since the choice of gene weights influences the optimal kernel parameters and vice versa. Experimental results show that the proposed mRMR-PSO-WSVM model achieves highest classification accuracy on two popular leukemia and colon gene expression datasets obtained from DNA microarrays. Therefore, we can conclude that our proposed method is very promising compared to the previously reported results.

Foundation and methodologies in computer-aided diagnosis systems for breast cancer detection

“…Available kernels for support vector machines include linear, polynomial, sigmoid and radial basis functions (Meyer, 2017[96]). Some studies have acquired that radial basis function (RBF) provide higher accuracy to other kernel functions particularly in nonlinearly separable training data (Abdi et al, 2012[3]; Anand et al, 2010[9]).…”

Computer-aided detection of lung nodules using outer surface features

“…The PSO algorithm was developed for the optimization of functions that are not continuously linear. The support vector machine used in the study was optimized by the particle swarm algorithm [44][45][46].…”

Supervised machine learning-based classification scheme to segment the brainstem on MRI in multicenter brain tumor treatment context

“…Radial basis function (RBF) kernels are one of the most used kernels to separate data in SVM classifiers in complex classification environments. Some previous works have found that RBF kernel generally provides better classification accuracy than many other kernel functions [14]. This kernel nonlinearly maps samples into a higher-dimensional space.…”