From treadmill to outdoor overground walking: Enhancing ground contact timing detection for older adults using transfer learning

Sansgiri, Sailee ORCID: https://orcid.org/0000-0003-1010-6872, Matikainen-Tervola, Emmi, Rantakokko, Merja, Finni, Taija, Rantalainen, Timo and Cronin, Neil J ORCID: https://orcid.org/0000-0002-5332-1188 (2026) From treadmill to outdoor overground walking: Enhancing ground contact timing detection for older adults using transfer learning. Experimental Gerontology, 215. art:113056. doi:10.1016/j.exger.2026.113056 (In Press)

Preview

Text 15847 Sansgiri et al (2026) From treadmill to outdoor overground walking.pdf - Published Version Available under License Creative Commons Attribution 4.0. Download (2MB) | Preview

Abstract

Identification of ground contact timings (GCT) is critical for monitoring mobility in older adults. Laboratory methods are precise but limited to controlled environments, restricting their applicability in real-world settings. Treadmills allow extended measurements but fail to reflect the variability of overground walking. We evaluated the performance of deep learning models trained on treadmill data from young adults and their generalizability to treadmill and outdoor walking in older adults. We also explored transfer learning to enhance predictions by fine-tuning models with older adults’ treadmill and outdoor walking data. Foot-mounted inertial measurement unit (IMU) walking data was collected from 20 young adults on treadmills and 26 older adults on treadmills and outdoor level, incline, and decline terrains. Ground truth GCTs were derived using pressure insoles (young adults) and manually-annotated motion capture (older adults). A fully connected neural network, a convolutional neural network (CNN), and a bidirectional long short-term memory network were trained on IMU data. Transfer learning was applied incrementally by fine-tuning the best-performing model with older adults’ data. Model performance was evaluated on unseen outdoor data from 6 participants using F1-score and mean absolute error (MAE). The CNN achieved the highest F1-scores (0.9864 — treadmill, 0.9637 — outdoor level, 0.9538 — incline, and 0.9029 — decline walking) and the lowest MAE. Fine-tuning improved treadmill F1-scores up to n=10, while outdoor level scores plateaued at n=5. Decline walking showed poorer performance, highlighting the need for advanced modeling strategies. These findings underscore the potential of transfer learning for real-world mobility monitoring.

Item Type:	Article
Article Type:	Article
Uncontrolled Keywords:	Ground contact timing; Deep learning; Transfer learning; Walking; Treadmill; Outdoor environment; Aging
Subjects:	G Geography. Anthropology. Recreation > GV Recreation Leisure > GV191.2 Outdoor Life. Outdoor recreation. Q Science > QP Physiology
Divisions:	Schools and Research Institutes > School of Education, Health and Sciences
Depositing User:	Charlotte Crutchlow
Date Deposited:	16 Feb 2026 10:34
Last Modified:	19 Feb 2026 15:15
URI:	https://eprints.glos.ac.uk/id/eprint/15847

University Staff: Request a correction | Repository Editors: Update this record