Children Abnormal GAIT Classification Using Extreme Learning Machine
M. Pushpa Rani, G. Arumugam · 2010
Abstract-Analyzing human gait has earned considerable interest in recent computer vision researches, as it has immense use in deducing the physical well-being of people. Detection of unusual movement patterns can be performed using Support Vector Machines classification with T-Test pre-normalization. Support Vector Machine classifiers are powerful tools, specifically designed to solve large-scale classification problems. Almost all recent works broadly uses SVM method for gait analysis because of its remarkable learning ability. But when dealing with time complexity there exists a limitation with the SVM. As the computation cost for the SVM is high, the recently developed Extreme Learning Machine (ELM) is being used for the gait classification as a better option in this paper. ELM avoids problems like local minima, improper learning rate and over fitting commonly faced by previous iterative learning methods and completes the training very fast. The multi category classification performance of ELM with T-Test is evaluated with the Virginia gait dataset. The results indicate that ELM produces better classification accuracies with reduced training time and implementation complexity when compared to SVM. Keypoints-Extreme learning machine, Gait analysis, SVM classification.