Predicting cervical hyperextension injury: A covariance guided sine cosine support vector machine

Abstract

This study proposes an effective intelligent predictive model for prediction of cervical hyperextension injury. The prediction model is constructed by combing an improved sine cosine algorithm (SCA) with support vector machines (SVM), which is named COSCA-SVM. The core of the developed model is the COSCA method that combines the opposition-based learning mechanism and covariance mechanism to boost and recover the exploratory competence of SCA. The proposed COSCA approach is utilized to optimize the two critical parameters of the SVM, and it is also employed to catch the optimal feature subset. Based on the optimal parameter combination and feature subset, COSCA-SVM is able to make self-directed prediction of cervical hyperextension injury. The proposed COSCA was compared with other well-known and effective methods using 23 benchmark problems. Simulation results verify that the proposed COSCA is significantly superior to studied methods in dealing with majority of benchmark problems. Meanwhile, the proposed COSCA-SVM is compared with six other machine learning approaches considering a real-life dataset. Results have shown that the proposed COSCA-SVM can achieve better classification routine and higher stability on all four indicators. Therefore, we can expect that COSCA-SVM can be a promising building block for predicting cervical hyperextension injury. © 2013 IEEE.