University of Massachusetts, Amherst, MA
Please join us November 7th - 10th at CNS Summit 2021!
Check out the ActiGraph Exhibit and Spotlight Session at CNS Summit 2021Learn More
Development of Activity Type Classification Algorithms in Older Adults from Laboratory and Free-living Data
- Presented on May 30, 2014
Purpose: To compare activity type recognition rates of machine learning algorithms trained on laboratory versus free-living accelerometer data in free-living older adults.
Methods: Thirty-seven older adults (21F and 14M ; 70.8 ± 4.9 y) performed selected activities (total of 35 min) in the lab while wearing three ActiGraph GT3X+ activity monitors (dominant hip, wrist, and ankle). Monitors were initialized to collect raw acceleration data at a sampling rate of 80 Hz. Fifteen of the participants (9F and 6M; 70.0 ± 4.3 y) also wore the GT3X+ in free-living conditions and were directly observed for 2-3 hours. Time- and frequency- domain features from the accelerometer signals of each monitor were used to train random forest (RF) and support vector machine (SVM) models to classify ﬁve activity type categories: sedentary, standing, household, locomotion, and recreational activities. All algorithms were trained on lab data (RFLab and SVMLab) and free-living data (RFFL and SVMFL) using 20 s and 30 s time intervals. Prediction accuracy of both types of algorithms was tested on free-living data using a leave-one-out technique.
Results: Overall classiﬁcation accuracy using 20 s intervals for the lab-based algorithms was between 49% (wrist) to 55% (ankle) for the SVMLab algorithms, and 49% (wrist) to 54% (ankle) for RFLab algorithms. Overall classiﬁcation accuracy of SVMFL and RFFL algorithms ranged from 58% (wrist) to 69% (ankle) and from 61% (wrist) to 66% (hip and ankle), respectively. Using 30 s intervals improved classiﬁcation accuracy up to 71% (SVMFL ankle). Signiﬁcant improvements in classiﬁcation accuracy were observed for RFFL hip, RFFL wrist, and RFFL ankle algorithms (76%, 70%, and 76%) when three activity type categories were used: sedentary behavior, moving intermittently and locomotion.
Conclusion: Algorithms developed in free-living settings are more accurate in classifying activity type in free-living older adults than lab-developed algorithms. Our results suggest that future studies should consider using free-living accelerometer data to train machine-learning algorithms in older adults
- Jeffer E. Sasaki 1
- Amanda Hickey 1
- John Staudenmayer 1
- Jane Kent-Braun, FACSM
- Dinesh John 2
- Richard Van Emmerik
- Patty Freedson, FACSM 1
Northeastern University, Boston, MA.
ACSM 2014 Annual Meeting