Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Abstract

An evaluation method that includes continuous activities in a daily-living environment was developed for Wearable Mobility Monitoring Systems (WMMS) that attempt to recognize user activities. Participants performed a pre-determined set of daily living actions within a continuous test circuit that included mobility activities (walking, standing, sitting, lying, ascending/descending stairs), daily living tasks (combing hair, brushing teeth, preparing food, eating, washing dishes), and subtle environment changes (opening doors, using an elevator, walking on inclines, traversing staircase landings, walking outdoors).To evaluate WMMS performance on this circuit, fifteen able-bodied participants completed the tasks while wearing a smartphone at their right front pelvis. The WMMS application used smartphone accelerometer and gyroscope signals to classify activity states. A gold standard comparison data set was created by video-recording each trial and manually logging activity onset times. Gold standard and WMMS data were analyzed offline. Three classification sets were calculated for each circuit: (i) mobility or immobility, ii) sit, stand, lie, or walking, and (iii) sit, stand, lie, walking, climbing stairs, or small standing movement. Sensitivities, specificities, and F-Scores for activity categorization and changes-of-state were calculated.The mobile versus immobile classification set had a sensitivity of 86.30% ± 7.2% and specificity of 98.96% ± 0.6%, while the second prediction set had a sensitivity of 88.35% ± 7.80% and specificity of 98.51% ± 0.62%. For the third classification set, sensitivity was 84.92% ± 6.38% and specificity was 98.17 ± 0.62. F1 scores for the first, second and third classification sets were 86. 17 ± 6.3, 80.19 ± 6.36, and 78.42 ± 5.96, respectively. This demonstrates that WMMS performance depends on the evaluation protocol in addition to the algorithms. The demonstrated protocol can be used and tailored for evaluating human activity recognition systems in rehabilitation medicine where mobility monitoring may be beneficial in clinical decision-making. Video LinkThe video component of this article can be found at

Measurement of Sit-Stand Desk Usage by Desk-Mounted Sensors

“…The reliability of other groups using accelerometer-based measures ranges between 78.4% and 97.2% using comparable criteria to our bootstrapping cross-validation technique (Johnston et al, 2019; Kozey-Keadle et al, 2011; Lemaire et al, 2015). Our reported agreement, accuracy, sensitivity, and specificity are in the upper end of this range while having the benefit of being unobtrusive and not encumbering the user.…”

“…We constructed and tested a desk-mounted sensor that can predict sit-stand desk configurations with an estimated 94% agreement for an exemplar subject, comparable or better than more encumbering direct-measurement approaches (Kozey-Keadle et al, 2011; Lemaire et al, 2015). Obtaining this estimate required documenting a wide range sitting and standing desk heights, prompting our pilot survey.…”

Monitoring Occupational Sitting, Standing, and Stepping in Office Employees With the W@W-App and the MetaWearC Sensor: Validation Study

“…Evidence has identified mobile phones as a potential alternative to accurately self-monitor PA and SB via inbuilt inertial sensors [ 12 - 15 ]. However, battery life and mobile phone location have been major issues that have compromised usability and long-term monitoring.…”

Monitoring Occupational Sitting, Standing, and Stepping in Office Employees With the W@W-App and the MetaWearC Sensor: Validation Study (Preprint)

“…Evidence has identified mobile phones as a potential alternative to accurately self-monitor PA and SB via inbuilt inertial sensors [12][13][14][15]. However, battery life and mobile phone location have been major issues that have compromised usability and long-term monitoring.…”