Walking Behavior Change Detector for a “Smart” Walker

Abstract

This study investigates the design of a novel real-time system to detect walking behavior changes using an accelerometer on a rollator. No sensor is required on the user. We propose a new non-invasive approach to detect walking behavior based on the motion transfer by the user on the walker. Our method has two main steps; the first is to extract a gait feature vector by analyzing the three-axis accelerometer data in terms of magnitude, gait cycle and frequency. The second is to classify gait with the use of a decision tree of multilayer perceptrons. To assess the performance of our technique, we evaluated different sampling window lengths of 1, 3 an 5 seconds and four different Neural Network architectures. The results revealed that the algorithm can distinguish walking behavior such as normal, slow and fast with an accuracy of about 86%. This research study is part of a project aiming at providing a simple and non-invasive walking behavior detector for elderly who use rollators.

An Embedded Ground Change Detector for a “Smart Walker”

“…The two classes, ground change and no change, are defined as follows: a frame is labelled positive as soon as a ground change enters the visual field and it remains positive until the user is completely on the new terrain; the frame is labelled negative, otherwise [6]. To compare the methods, we use the confusion matrix shown in Table 1, where accuracy is defined as: In our system, we have two critical values.…”

“…For the color feature, different types of color space were tested in [6]. As a result, the HSV color space demostrated to be the most suitable.…”

“…Values for n and m were determined empirically in [6]. The output layer has two neurons, one represents the detection of the ground change and the other indicates unchanged ground.…”

Towards Truly Affective AAL Systems

“…Eyewalker project targets the development of an independent solution that can be simply clipped on a rollator [86]. Eyewalker involves the determination of a user's emotional state based on movement analysis since gait itself provides relevant information about a person's affective state.…”

A Novel Walking-Aid for Paralytic Patients Caused due to Stroke

“…The walk around-mobile balance support [6] Maria was one of the inventions for the hemiparesis patients to walk without the assistance of anyone. Later many smart walkers like PAM-AID Walker [7] are invented. However these require efficient training lest the chances of tripping or falling down are very high for the patient.…”