A REINFORCEMENT LEARNING APPROACH TO ENHANCE PHYSICAL ACTIVITY AND REDUCE FALL RISK IN OLDER ADULTS

Chang Liu, Ladda Thiamwong, Tho Nguyen, Jethro Raphael Suarez, Joon-Hyuk Park, Qian Lou, Rui Xie · 2024

Read A REINFORCEMENT LEARNING APPROACH TO ENHANCE PHYSICAL ACTIVITY AND REDUCE FALL RISK IN OLDER ADULTS by Chang Liu, Ladda Thiamwong, Tho Nguyen, Jethro Raphael Suarez, Joon-Hyuk Park, Qian Lou, Rui Xie (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11692831.txt.

Description

Chang Liu and six co-authors apply reinforcement learning to raise activity and cut fall risk in older adults, in work from 2024. Minute-level wearable data came from 134 people in a feedback exercise program and a control group, over a million observations in all. Participants were mostly women in their mid-seventies, many with no fall history, drawn from low-income settings.

A policy network learned from steps and movement size, rewarding moderate to vigorous activity and penalizing sedentary time, with standing as the target action. The program group showed a higher chance of the target action than controls. Chances peaked in daytime hours and fell after early evening for both groups.

Catalog record

CREATORChang Liu, Ladda Thiamwong, Tho Nguyen, Jethro Raphael Suarez, Joon-Hyuk Park, Qian Lou, Rui Xie
YEAR2024
COLLECTIONPAPERS
FORMATTXT
FILE SIZE2 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC11692831

Browse the full library · About the Tower of Babel