Activity Number:
|
119
- Statistics for Mobile and Wearable Device Data
|
Type:
|
Invited
|
Date/Time:
|
Monday, August 8, 2022 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Business and Economic Statistics Section
|
Abstract #320541
|
|
Title:
|
Smartphone-Based Human Activity Recognition
|
Author(s):
|
Jukka-Pekka Onnela*
|
Companies:
|
Harvard T.H. Chan School of Public Health
|
Keywords:
|
smartphone;
physical activity;
accelerometer;
digital phenotyping;
human activity recognition
|
Abstract:
|
Smartphones with 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) methods aimed at translating measurements from smartphones into various types of physical activity. I will first provide an overview of existing approaches to smartphone-based HAR. I will then introduce our new walking recognition algorithm, which has been validated using various publicly available labelled datasets. I will also discuss its applications to central nervous system disorders.
|
Authors who are presenting talks have a * after their name.