Gaits Classification of Normal vs. Patients by Wireless Gait Sensor and Support Vector Machine (SVM) Classifier

Abstract

Due to the serious concerns of fall risks for patients with balance disorders, it is desirable to be able to objectively identify these patients in real-time dynamic gait testing using inexpensive wearable sensors. In this work, the authors took a total of 49 gait tests from 7 human subjects (3 normal subjects and 4 patients), where each person performed 7 Dynamic Gait Index (DGI) tests by wearing a wireless gait sensor on the T4 thoracic vertebra. The raw gait data is wirelessly transmitted to a near-by PC for real-time gait data collection. To objectively identify the patients from the gait data, the authors used 4 different types of Support Vector Machine (SVM) classifiers based on the 6 features extracted from the raw gait data: Linear SVM, Quadratic SVM, Cubic SVM, and Gaussian SVM. The Linear SVM, Quadratic SVM and Cubic SVM all achieved impressive 98% classification accuracy, with 95.2% sensitivity and 100% specificity in this work. However, the Gaussian SVM classifier only achieved 87.8% accuracy, 71.7% sensitivity, and 100% specificity. The results obtained with this small number of human subjects indicates that in the near future, the authors should be able to objectively identify balance-disorder patients from normal subjects during real-time dynamic gaits testing using intelligent SVM classifiers.

Data Classification of Early-Stage Diabetes Risk Prediction Datasets and Analysis of Algorithm Performance Using Feature Extraction Methods and Machine Learning Techniques

“…SVM has a solid theoretical basis and provides more accurate results when compared to other algorithms in many applications. As shown in Figure 4, SVMs use a maximal margin splitter [53]. This splitter represents the most remote control possible up to the sampling point.…”

MLGaze: Machine Learning-Based Analysis of Gaze Error Patterns in Consumer Eye Tracking Systems

“…Then, the input sample is categorized into the class of the majority in the k nearest points. Thus, if the training data is {(x 1 ,y 1 ), (x 2 ,y 2 ), …, (x N ,y N )} and x is the feature vector of an input sample, the KNN finds the class of the input sample x using a distance metric [ 41 , 42 ], which in this study is the Euclidean distance given by: (b) Support vector machines (SVMs): It is a supervised learning method [ 43 , 44 ] that works on the principle of transforming the input feature space by a nonlinear transformation to a high-dimensional feature space, and searching for an optimal separating hyperplane for the input classes in this new high-dimensional space [ 45 , 46 ]. With this separating hyperplane, the training data xi with labels yi can be classified so that the minimal distance of each point from the hyperplane is maximized.…”

“…(b) Support vector machines (SVMs): It is a supervised learning method [43,44] that works on the principle of transforming the input feature space by a nonlinear transformation to a high-dimensional feature space, and searching for an optimal separating hyperplane for the input classes in this new high-dimensional space [45,46]. With this separating hyperplane, the training data xi with labels yi can be classified so that the minimal distance of each point from the hyperplane is maximized.…”

Quantitative Autofluorescence Imaging Reveals the Potential for Cervical Cancer Detection

“…Most of the related studies achieved the best classification performance by Gaussian SVM classifier [11]. Another study showed classification method by four types of SVM classifiers and achieved the best accuracy rate by employing Linear SVM [16]. Therefore, four different types of SVM including Gaussian SVM and Linear SVM were evaluated in this present study.…”