A systematic review of smartphone-based human activity recognition methods for health research

Abstract

Smartphones are now nearly ubiquitous; their numerous built-in sensors enable continuous measurement of activities of daily living, making them especially well-suited for health research. Researchers have proposed various human activity recognition (HAR) systems aimed at translating measurements from smartphones into various types of physical activity. In this review, we summarized the existing approaches to smartphone-based HAR. For this purpose, we systematically searched Scopus, PubMed, and Web of Science for peer-reviewed articles published up to December 2020 on the use of smartphones for HAR. We extracted information on smartphone body location, sensors, and physical activity types studied and the data transformation techniques and classification schemes used for activity recognition. Consequently, we identified 108 articles and described the various approaches used for data acquisition, data preprocessing, feature extraction, and activity classification, identifying the most common practices, and their alternatives. We conclude that smartphones are well-suited for HAR research in the health sciences. For population-level impact, future studies should focus on improving the quality of collected data, address missing data, incorporate more diverse participants and activities, relax requirements about phone placement, provide more complete documentation on study participants, and share the source code of the implemented methods and algorithms.

Re-Orienting Smartphone-Collected Car Motion Data Using Least-Squares Estimation and Machine Learning

“…For example, we report some Human Activity Recognition (HAR) works and building structural monitoring research. As reported in [5], many HAR works need to assess the smartphone orientation with respect to the body in free-living experiments. Del Rosario et al [6] learn the Inertial Measurement Unit orientation during walking to acquire a reference orientation against which sitting or lying can be inferred.…”

Beiwe: A data collection platform for high-throughput digital phenotyping

“…To eliminate recall bias, some of these items may be actually measured objectively in free-living settings. For example, two of the items in ALSFRS-R are related to physical activity: walking (Item 8) and climbing stairs (Item 9), both of which can be estimated using smartphone accelerometer and gyroscope data (Straczkiewicz et al, 2021).…”

Smartphone-Based Activity Recognition Using Multistream Movelets Combining Accelerometer and Gyroscope Data

“…Human activity recognition (HAR) using smartphones has proliferated in recent years [ 10 ]. The first component of HAR is data collection, which requires careful thought about various questions, such as choosing the appropriate sensors, sampling frequency, study environment, and smartphone placement.…”

“…With improvements in technology, cost, and quality of data collection, the main challenge in HAR is shifting to data analysis, i.e., to extract the activities from the sensor data accurately and robustly [ 7 , 10 , 19 ]. In general, a given data analysis procedure can be divided into three steps: preprocessing, feature extraction, and activity classification [ 10 ]. Preprocessing prepares the data for the analysis at hand.…”