We propose a walking distance estimation method based on an adaptive step-length estimator at various walking speeds using a smartphone. First, we apply a fast Fourier transform (FFT)-based smoother on the acceleration data collected by the smartphone to remove the interference signals. Then, we analyze these data using a set of step-detection rules in order to detect walking steps. Using an adaptive estimator, which is based on a model of average step speed, we accurately obtain the walking step length. To evaluate the accuracy of the proposed method, we examine the distance estimation for four different distances and three speed levels. The experimental results show that the proposed method significantly outperforms conventional estimation methods in terms of accuracy.

This paper proposes a novel method of estimating walking distance based on a precise counting of walking strides using insole sensors. We use an inertial triaxial accelerometer and eight pressure sensors installed in the insole of a shoe to record walkers’ movement data. The data is then transmitted to a smartphone to filter out noise and determine stance and swing phases. Based on phase information, we count the number of strides traveled and estimate the movement distance. To evaluate the accuracy of the proposed method, we created two walking databases on seven healthy participants and tested the proposed method. The first database, which is called the short distance database, consists of collected data from all seven healthy subjects walking on a 16 m distance. The second one, named the long distance database, is constructed from walking data of three healthy subjects who have participated in the short database for an 89 m distance. The experimental results show that the proposed method performs walking distance estimation accurately with the mean error rates of 4.8% and 3.1% for the short and long distance databases, respectively. Moreover, the maximum difference of the swing phase determination with respect to time is 0.08 s and 0.06 s for starting and stopping points of swing phases, respectively. Therefore, the stride counting method provides a highly precise result when subjects walk.

Human Activity Recognition (HAR) is a challenging task in the field of human-related signal processing. Owing to the development of wearable sensing technology, an emerging research approach in HAR is to identify user-performed tasks by using data collected from wearable sensors. In this paper, we propose a novel system for monitoring and recognizing daily living activities using an off-the-shelf smart band and two smart shoes. The system aims at providing a useful tool for solving problems regarding body part placement, fusion of multimodal sensors and feature selection for a specific set of activities. The system collects inertial and plantar pressure data at wrist and foot to analyze and then, extract, select important features for recognition. We construct and compare two predictive models of classifying activities from the reduced feature set. A comparison of the classification for each wearable device and a fusion scheme is provided to identify the best body part for activity recognition: either the wrist or the feet. This comparison also demonstrated the effective HAR performance of the proposed system.

In this letter, we propose a novel method for classifying daily wrist activities by using a smart band. Triaxial acceleration data are collected by built-in sensors of the smart band during experiments regarding five activities, i.e., texting, calling, placing a hand in a pocket, carrying a suitcase, and swinging a hand. We analyze patterns in the sensor signals during these activities based on three types of features, i.e., norm, norm-variance, and frequency-domain features. After extracting the significant features, a multi-class support vector machine (SVM) algorithm is applied to classify these activities. We obtained recognition error rates of approximately 2.7% by applying the proposed method to the experimental dataset.

This paper proposes a novel approach to recognize activities based on sensor-placement feature selection. The method is designed to address a problem of multisensor fusion information of wearable sensors which are located in different positions of a human body. Precisely, the approach can extract the best feature set that characterizes each activity regarding a body-sensor location to recognize daily living activities. We firstly preprocess the raw data by utilizing a low-pass filter. After extracting various features, feature selection algorithms are applied separately on feature sets of each sensor to obtain the best feature set for each body position. Then, we investigate the correlation of the features in each set to optimize the feature set. Finally, a classifier is applied to an optimized feature set, which contains features from four body positions to classify thirteen activities. In experimental results, we obtain an overall accuracy of 99.13% by applying the proposed method to the benchmark dataset. The results show that we can reduce the computation time for the feature selection step and achieve a high accuracy rate by performing feature selection for the placement of each sensor. In addition, our proposed method can be used for a multiple-sensor configuration to classify activities of daily living. The method is also expected to deploy to an activity classification system-based big data platform since each sensor node only sends essential information characterizing itself to a cloud server.

In this paper, we propose a novel method for ambulatory activity recognition and pedestrian identification based on temporally adaptive weighting accumulation-based features extracted from categorical plantar pressure. The method relies on three pressure-related features, which are calculated by accumulating the pressure of the standing foot in each step over three different temporal weighting forms. In addition, we consider a feature reflecting the pressure variation. These four features characterize the standing posture in a step by differently weighting step pressure data over time. We use these features to analyze the standing foot during walking and then recognize ambulatory activities and identify pedestrians based on multilayer multiclass support vector machine classifiers. Experimental results show that the proposed method achieves 97% accuracy for the two tasks when analyzing eight consecutive steps. For faster processing, the method reaches 89.9% and 91.3% accuracy for ambulatory activity recognition and pedestrian identification considering two consecutive steps, respectively, whereas the accuracy drops to 83.3% and 82.3% when considering one step for the respective tasks. Comparative results demonstrated the high performance of the proposed method regarding accuracy and temporal sensitivity.