An Efficient SVM-Based Feature Selection Model for Cancer Classification Using High-Dimensional Microarray Data

Abstract

Feature selection is critical in analyzing microarray data, which has many features (genes) or dimensions. However, with only a few samples, the large search space and time consumed during their selection make selecting relevant and informative genes that improve classification performance a complex task. This paper proposed a hybrid model for gene selection known as (SVM-mRMRe). The proposed model provides a framework for combining filter-based, ensemble, and embedded methods to select the most relevant and informative genes from high-dimensional microarray data by fusing embedded SVM coefficients (features ranking) with ensemble mRMRe. Eight of the most commonly used microarray datasets for various types of cancer were used to evaluate the model. The selected subset feature is evaluated by four different types of classifiers: random forest (RF), multilayer perceptron (MLP), k-nearest neighbors (k-NN), and Support Vector Machine (SVM). The experimental results show that the proposed model reduces time consumption and dimensionality and improves the differentiation of cancer tissues from benign tissues. Furthermore, the selected genes for the brain cancer dataset are biologically interpreted, and it agrees with the findings of relevant biomedical studies and plays an important role in patient prognosis.

A robust ensemble feature selection technique for high‐dimensional datasets based on minimum weight threshold method

“…The best‐achieved value was 0.832, which is less than the performance achieved in our study. An efficient SVM‐based FS model was proposed for Microarray‐based cancer diagnosis in the study 58 . The proposed method was a hybrid method called SVM‐mRMRe, which provided a framework for combining filter‐based, ensemble, and embedded methods to select the relevant features.…”

“…However, this could be a consequence of the experimental setup because the entire dataset was used for gene selection and then again, the entire dataset was used for model training and evaluation, which could lead to feature selection bias. As a result, when two studies are compared, this difference between the experimental setups should be considered 58 …”

Monitoring corporate credit risk with multiple data sources

“…Formula (10) is the theoretical optimal classification hyperplane obtained for solving the linear separable problems, which can be used to complete the classification and recognition of data samples. With nonlinear problems, SVM introduces kernel function to solve the problems of the linear inseparability of original spatial data by mapping the vector X from n-dimensional original space to higher-dimensional space (El Kafrawy et al. , 2021; Ming, 2015).…”

“…With nonlinear problems, SVM introduces kernel function to solve the problems of the linear inseparability of original spatial data by mapping the vector X from n-dimensional original space to higher-dimensional space (El Kafrawy et al, 2021;Ming, 2015).…”

Deep Neural Network Technique Based Field Digitizing Units (FDUs) Instruments Fault Detection and Isolation

“…The more sophisticated a system is, the more prone it is to failure and the greater the risk of it collapsing. Failures must be identified, isolated, and fixed as soon as possible in order to keep the system from becoming troublesome, necessitating the employment of proper Fault Detection and Isolation (FDI) approaches [1][2][3]. If an instrument malfunctions, immediate measures should be taken.…”