Children Abnormal Gait Analysis Based on SVM

Support Vector Machine (SVM) has become a hotspot of machine learning because of its rigorous theory background and remarkable generalization performance. Recent researches on SVM mainly concentrate on the property of SVM and variety of its applications. In this paper, an improved SVM algorithm is proposed for children abnormal gait analysis. The algorithm combines SVM with fuzzy clustering in order to improve the accuracy of SVM. Only samples that have weak relationships with all clusters are involved in SVM. Simulation experiment has been carried out to show that the algorithm based on the improved SVM may obtain better effectiveness than the normal SVM when it is applied for children abnormal gait analysis.