Gait analysis can be defined as the numerical and graphical representation of the mechanical measurements of human walking patterns and is used for two main purposes: human identification, where it is usually applied to security issues, and clinical applications, where it is used for the non-automated and automated diagnosis of various abnormalities and diseases. Automated or semi-automated systems are important in assisting physicians for diagnosis of various diseases. In this study, a semi-automated gait classification system is designed and implemented by using joint angle and time-distance data as features. Multilayer Perceptrons (MLPs) Combination classifiers are used to categorize gait data into two categories; healthy and patient with knee osteoarthritis. Two popular approaches of combining neural networks are experimented and the results are compared according to different output combining rules. In the first one, same set is used to train all networks and afterwards the features are decomposed into five different sets. These two experiments show that using entire data set produces more accurate results than using decomposed data sets, but complexity becomes an important drawback. However, when a proper combining rule is applied to decomposed sets, results are more accurate than entire set. In this experiment sum rule produces better results than majority vote and max rules as an output combining rule.
Gait analysis is used for non-automated and automated diagnosis of various neuromuskuloskeletal abnormalities. Automated systems are important in assisting physicians for diagnosis of various diseases. This study presents preliminary steps of designing a clinical decision support system for semiautomated diagnosis of knee illnesses by using temporal gait data. This study compares the gait of 111 patients with 110 age-matched normal subjects. Different feature reduction techniques, (FFT, averaging and PCA) are compared by the Mahalanobis Distance criterion and by performances of well known classifiers. The feature selection criteria used reveals that the gait measurements for different parts of the body such as knee or hip to be more effective for detection of the illnesses. Then, a set of classifiers is tested by a ten-fold cross validation approach on all datasets. It is observed that average based datasets performed better than FFT applied ones for almost all classifiers while PCA applied dataset performed better for linear classifiers. In general, nonlinear classifiers performed quite well (best error rate is about 0.035) and better than the linear ones.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.