In this paper, we propose a novel method to classify five ambulatory activities, i.e., level ground, incline descent, incline ascent, stair descent, and stair ascent walking using smart shoes which contain eight plantar-pressure sensors on each shoe. Pressure data are collected using an insole-based monitoring system regarding the walking activities conducted by participants at their self-imposed “normal” speed. We present three new features based on an analysis of step patterns to characterize the ambulatory activities and utilize a k-nearest neighbor algorithm to classify the activities from the created features. In experimental results, we obtain walking activity-recognition error rates of 2.16% at the sixth walking step. Furthermore, a proposed method outperforms two reference methods in terms of F1-score and overall accuracy rate.

Human activity recognition and pedestrian dead reckoning are an interesting field because of their importance utilities in daily life healthcare. Currently, these fields are facing many challenges, one of which is the lack of a robust algorithm with high performance. This paper proposes a new method to implement a robust step detection and adaptive distance estimation algorithm based on the classification of five daily wrist activities during walking at various speeds using a smart band. The key idea is that the non-parametric adaptive distance estimator is performed after two activity classifiers and a robust step detector. In this study, two classifiers perform two phases of recognizing five wrist activities during walking. Then, a robust step detection algorithm, which is integrated with an adaptive threshold, peak and valley correction algorithm, is applied to the classified activities to detect the walking steps. In addition, the misclassification activities are fed back to the previous layer. Finally, three adaptive distance estimators, which are based on a non-parametric model of the average walking speed, calculate the length of each strike. The experimental results show that the average classification accuracy is about 99%, and the accuracy of the step detection is 98.7%. The error of the estimated distance is 2.2–4.2% depending on the type of wrist activities.