Activity Recognition Using a Single Accelerometer Placed at the Wrist or Ankle

Abstract

PURPOSE Large physical activity surveillance projects such as the UK Biobank and NHANES are using wrist-worn accelerometer-based activity monitors that collect raw data. The goal is to increase wear time by asking subjects to wear the monitors on the wrist instead of the hip, and then to use information in the raw signal to improve activity type and intensity estimation. The purpose of this work is obtaining an algorithm to process wrist and ankle raw data and classify behavior into four broad activity classes: ambulation, cycling, sedentary and other. METHODS Participants (N = 33) wearing accelerometers on the wrist and ankle performed 26 daily activities. The accelerometer data were collected, cleaned, and preprocessed to extract features that characterize 2 s, 4 s, and 12.8 s data windows. Feature vectors encoding information about frequency and intensity of motion extracted from analysis of the raw signal were used with a support vector machine classifier to identify a subject’s activity. Results were compared with categories classified by a human observer. Algorithms were validated using a leave-one-subject-out strategy. The computational complexity of each processing step was also evaluated. RESULTS With 12.8 s windows, the proposed strategy showed high classification accuracies for ankle data (95.0%) that decreased to 84.7% for wrist data. Shorter (4 s) windows only minimally decreased performances of the algorithm on the wrist to 84.2%. CONCLUSIONS A classification algorithm using 13 features shows good classification into the four classes given the complexity of the activities in the original dataset. The algorithm is computationally-efficient and could be implemented in real-time on mobile devices with only 4 s latency.

Sedentary Behavior and Cardiovascular Morbidity and Mortality: A Science Advisory From the American Heart Association

“…Participants have traditionally worn accelerometers on a belt around their waist during waking hours and remove them for water-based activities, a methodology and protocol that has been shown to be both valid and reliable. 23,24 Wearing a device on a wrist or ankle can be helpful in quantifying behaviors that have different positions 25,26 and can be less burdensome than using a waist-worn device. The movement detected by accelerometers is converted to electrical signals or "counts" that can be summed over a period of time to quantify total sedentary time (minutes) or patterns of sedentary time (eg, duration of bouts or episodes, breaks in sedentary time).…”

“…Although wearing a device on a wrist or ankle can minimize these limitations, the validity of the data when used in this position is still being established. 25,26 Furthermore, accelerometers can be inaccurate in distinguishing sitting from standing, 14 although those that include inclinometers could mitigate this concern. New analytic techniques are being developed that identify, analyze, and visually present sedentary behaviors from wristworn triaxial accelerometers 28 and that are capable of assessing posture by including inclinometers.…”

Using Convolutional Layer Features for Indoor Human Activity Recognition based on Spatial Location Information

“…Generally, statistic features such as mean, standard deviation, entropy and correlation coefficients are the traditional hand-deigned features in AR. In addition, Fourier transforms [6], wavelet transforms [7] and discrete cosine transforms (DCT) [8,9] are the other three commonly used hand-crafted features.…”

Research and Development in Intelligent Systems XXXIII

“…For these reasons, some studies e.g. [14] have limited themselves to using single accelerometers which is also the case for SELFBACK.…”

“…Many comparative studies exist that compare activity recognition performance at these different locations [4]. The wrist is considered the least intrusive location and has been shown to produce high accuracy especially for ambulation and upper-body activities [14]. Hence, this is the chosen sensor location for our system.…”