A comparison of neural networks and support vector machines for recognizing young-old gait patterns

The aim of this paper is to apply artificial intelligence techniques (neural networks (NN), and support vector machines (SVM)) for the automatic identification of young-old gait types from their respective gait measures. The ability of such discrimination has many advantages including, early identification of at-risk gait for falls prevention in the older population. The gaits of 12 young and 12 elderly participants were recorded and analysed using a synchronised PEAK 3D motion analysis system and a force platform during normal walking. Altogether, 24 gait parameters (features) were extracted for training and testing the NN and SVM systems. The test results. indicate that the generalization ability of the SVM is better than the NN (91.7% vs 83.3%) in its capacity to distinguish between young and elderly gait patterns. These results indicate that SVMs are a good gait classifier for recognizing gait patterns of the young and the elderly, and have the potential for applications in gait identification for falls-risk minimization in the elderly.