Support vector machine for classification of walking conditions using miniature kinematic sensors

Abstract

A portable gait analysis and activity-monitoring system for the evaluation of activities of daily life could facilitate clinical and research studies. This current study developed a small sensor unit comprising an accelerometer and a gyroscope in order to detect shank and foot segment motion and orientation during different walking conditions. The kinematic data obtained in the pre-swing phase were used to classify five walking conditions: stair ascent, stair descent, level ground, upslope and downslope. The kinematic data consisted of anterior-posterior acceleration and angular velocity measured from the shank and foot segments. A machine learning technique known as support vector machine (SVM) was applied to classify the walking conditions. SVM was also compared with other machine learning methods such as artificial neural network (ANN), radial basis function network (RBF) and Bayesian belief network (BBN). The SVM technique was shown to have a higher performance in classification than the other three methods. The results using SVM showed that stair ascent and stair descent could be distinguished from each other and from the other walking conditions with 100% accuracy by using a single sensor unit attached to the shank segment. For classification results in the five walking conditions, performance improved from 78% using the kinematic signals from the shank sensor unit to 84% by adding signals from the foot sensor unit. The SVM technique with the portable kinematic sensor unit could automatically recognize the walking condition for quantitative analysis of the activity pattern.

Identification of Characteristics of Land Cover in Mangkauk Catchment Area Using Support Vector Machine (SVM) And Artificial Neural Network (ANN)

“…SVM is a method to seek the best hyper planes which serve as the separator of two classes in input space (Hsu et al, 2008;Guo, 2014). ANN method works with the learning process conducted by taking samples first and then comparing them with the expected results (Halgamuge and Wang, 2005;Lau et al, 2008). If there is a difference between the two, the weights will be changed until an acceptable value is reached.…”

“…(Buono et al, 2004) in their research entitled Classification of Land Cover on Multispectral Image Landsat TM using Probabilistic Neural Networks, the value of the accuracy was 64.2%. (Baret and Samuel, 2008;Discriminants, 2010;Lau et al, 2008;Santosa, 1995;Sharma et al, 2011;Wang et al, 2012) state that SVM is a technique to make predictions, both in classification and in regression where the SVM was in one class with Neural Network and both were in the supervised learning class. The concept of SVM can be explained simply as an attempt to find the best dividing line (hyperplane) of sharing the possible alternative hyperplane (Campbell and Ying, 2011;Hsu et al, 2008;Gao et al, 2012;Guan et al, 2013;Ibrikci et al, 2012;Liao et al, 2012;Pandey et al, 2010).…”

Fifty years of publishing in biomedical engineering: reflections after 7-year editorship

“…To give some insight onto the best-cited original papers, we selected the top ten from the periods 2008-2009 and 2010-2011. Out of these 20 papers, 7 are in the area of the circulation [8,9,15,20,24,25,27], 7 in the area of rehabilitation including brain computer interface [6,7,11,14,16,17,28], 2 related to sleep [19,35], 2 to tissue engineering and nanotechnology and 2 to electroporation [4,21]. Obviously the distribution of these subjects of publications are somewhat influenced by the special issues we had over this period [2,5,12,18,26,31,32].…”

Limb Movements Classification Using Wearable Wireless Transceivers

“…Most of them are based on traces collected using accelerometers and gyroscopes. Techniques range from feed-forward back propagation neural networks [8 ] to discrete wavelet transforms [10], support vector machine (SVM) techniques [12,13] and hidden Markov models [14]. In this paper Support Vector Machine (SVM) and K-Nearest [12,13].…”