Support Vector Machines for Automated Gait Classification

TLDR

Ageing alters gait patterns, increasing balance‑control risks, and automated gait recognition can enable early detection of at‑risk gait and monitor treatment progress. The study applies support vector machines to automatically classify young and elderly gait patterns from their gait‑pattern data. Minimum foot‑clearance features were extracted from histogram and Poincaré plots of 58 participants’ treadmill walks, used to train an SVM whose performance was evaluated with ROC AUC and optimized via hill‑climbing feature selection and a radial‑basis‑function kernel. Cross‑validation yielded 83.3 % accuracy (±2.9 %) for the SVM versus 75.0 % for a neural network, and a subset of 3–5 features achieved 90 % accuracy, demonstrating the SVM’s effectiveness for gait classification and its potential to reduce fall risk.

Abstract

Ageing influences gait patterns causing constant threats to control of locomotor balance. Automated recognition of gait changes has many advantages including, early identification of at-risk gait and monitoring the progress of treatment outcomes. In this paper, we apply an artificial intelligence technique [support vector machines (SVM)] for the automatic recognition of young-old gait types from their respective gait-patterns. Minimum foot clearance (MFC) data of 30 young and 28 elderly participants were analyzed using a PEAK-2D motion analysis system during a 20-min continuous walk on a treadmill at self-selected walking speed. Gait features extracted from individual MFC histogram-plot and Poincaré-plot images were used to train the SVM. Cross-validation test results indicate that the generalization performance of the SVM was on average 83.3% (+/-2.9) to recognize young and elderly gait patterns, compared to a neural network's accuracy of 75.0+/-5.0%. A "hill-climbing" feature selection algorithm demonstrated that a small subset (3-5) of gait features extracted from MFC plots could differentiate the gait patterns with 90% accuracy. Performance of the gait classifier was evaluated using areas under the receiver operating characteristic plots. Improved performance of the classifier was evident when trained with reduced number of selected good features and with radial basis function kernel. These results suggest that SVMs can function as an efficient gait classifier for recognition of young and elderly gait patterns, and has the potential for wider applications in gait identification for falls-risk minimization in the elderly.