Related Experiment Video
Updated: Dec 26, 2025
Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable
Published on: May 17, 2024
Hidden Markov model-based activity recognition for toddlers
Mark V Albert1, Albert Sugianto, Katherine Nickele
1Department of Computer Science and Engineering, University of North Texas, Denton, TX, United States of America. Department of Biomedical Engineering, University of North Texas, Denton, TX, United States of America. Department of Computer Science, Loyola University Chicago, Chicago, IL, United States of America. Department of Physical Medicine and Rehabilitation, Northwestern University Feinberg School of Medicine, Chicago, IL, United States of America. Author to whom any correspondence should be addressed.
Insights
Accurately measuring toddler physical activity is crucial for long-term health. This study developed a new activity recognition classifier, improving accuracy for tracking young children's movements and health outcomes.
Area of Science:
- Pediatrics
- Biomedical Engineering
- Public Health
Background:
- Long-term health outcomes in adults are linked to physical activity, yet toddler physical activity measurement remains under-researched.
- Understanding and predicting future health requires accurate quantification of physical activity in early childhood.
- Toddlers exhibit unique movement patterns necessitating specialized activity recognition approaches distinct from adults and older children.
Purpose of the Study:
- To develop and validate an accurate activity recognition system for toddlers.
- To improve the measurement of physical activity types and durations in young children.
- To lay the groundwork for better prediction and influence of toddler health outcomes through physical activity monitoring.
Main Methods:
- 22 toddlers wore waist-worn accelerometers during guided play sessions.
- Toddler movements were recorded via video and annotated into eight activity classes: lying, being carried, stroller riding, sitting, standing, running/walking, crawling, and climbing.
- Accelerometer data were segmented into 2-second windows and paired with corresponding annotated activities.
Main Results:
- A random forest classifier achieved an initial accuracy of 63.8% for activity recognition.
- Integrating a hidden Markov model (HMM) with static classifier predictions improved accuracy to 64.8%.
- Collapsing three frequently misclassified activities (sitting, standing, stroller riding) boosted accuracy to 79.3%.
Conclusions:
- Refined toddler activity recognition classifiers can lead to more precise physical activity measurements.
- Accurate monitoring of toddler physical activity is essential for improving their future health.
- This research provides a foundation for enhanced health outcome prediction and intervention in early childhood.
Objective:
Physical activity has been shown to impact future health outcomes in adults, but little is known about the long-term impact of physical activity in toddlers. Accurately measuring the specific types and amounts of physical activity in toddlers will help us to understand, predict, and better affect their future health outcomes. Although activity recognition has been extensively developed for adults as well as older children, toddlers move in ways that are significantly different from older children, indicating the need for a more tailored approach.
Approach:
In this study, 22 toddlers wore Actigraph waist-worn accelerometers which recorded their movements during guided play. The toddlers were videotaped and their activities were later annotated for the following eight distinct activity classes: lying down, being carried, riding in a stroller, sitting, standing, running/walking, crawling, and climbing up/down. Accelerometer data were extracted in 2 s signal windows and paired with the activities the toddlers were performing during that time interval.
Main Results:
A variety of classifiers were tuned to a validation set. A random forest classifier was found to achieve the highest accuracy of 63.8% in a test set. To improve the accuracy, a hidden Markov model (HMM) was applied by providing the predictions of the static classifiers as observations. The HMM was able to improve the accuracy to 64.8% with all five classifiers increasing the accuracy an average of 1.3% points (95% confidence interval = 0.7-1.9, p < 0.01). When the three most misclassified activities (sitting, standing, and riding in a stroller) were collapsed together, the accuracy increased to 79.3%.
Significance:
Further refinement of the toddler activity recognition classifier will enable more accurate measurements of toddler activity and improve future health outcomes of toddlers.
