# Generalize Then Personalize: Wearable-Based Heart Rate Forecasting Under Scarce Ruck-March Data

DevFeed: [Generalize Then Personalize: Wearable-Based Heart Rate Forecasting Under Scarce Ruck-March Data](<https://devfeed.tech/articles/generalize-then-personalize-wearable-based-heart-rate-forecasting-under-scarce-ruck-march-data-132923.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.14849>)

Author: Muntaqim Ahmed Raju, Ruizhe Ma, John W. Ramsay, David J. Cornell

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>), [Predictive AI](<https://devfeed.tech/topics/predictive-ai.md>)

Tags: [army](<https://devfeed.tech/tags/army.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [forecasting](<https://devfeed.tech/tags/forecasting.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [pretraining](<https://devfeed.tech/tags/pretraining.md>), [under](<https://devfeed.tech/tags/under.md>), [wearable](<https://devfeed.tech/tags/wearable.md>)

## AI overview

In a study of eight active-duty U.S. Army medics across 13 loaded ruck-march sessions, population-pretrained fine-tuning (PPFT) produced lower mean MAE, RMSE, and endpoint MAE than population-only training (POT) or personalized-from-scratch training (PFST) across three neural architectures and 30- and 60-second forecasts. Compared with PFST, PPFT reduced trajectory MAE by 2.22-4.30 bpm; all six trajectory comparisons remained significant after Holm adjustment. Persistence had the lowest 30-second MAE, while PPFT models led on other reported horizon-and-metric combinations. The results support PPFT as a promising approach when ruck-march training data are scarce.

## Source excerpt

arXiv:2611.14849v1 Announce Type: new Abstract: Heart rate (HR) forecasting may provide advance information about near-future cardiovascular response, potentially supporting physiological monitoring and workload-management decisions during ruck marching. However, robust model development is constrained by the difficulty of collecting large-scale ruck-march datasets, creating a scarce-data problem in which models must generalize across participants while adapting to individuals from limited personal data. To address this problem, we benchmark population-only training (POT), personalized-from-scratch training (PFST), and population-pretrained fine-tuning (PPFT) for HR forecasting during loaded ruck marching using data from eight active-duty U.S. Army medics across thirteen sessions. LSTM, Attention-LSTM, and CNN-LSTM backbones were evaluated against a persistence baseline at 30 s and 60 s horizons. Across all neural architectures and horizons, PPFT yielded lower mean MAE, RMSE, and endpoint MAE than both POT and PFST. Participant-level paired analysis after averaging across three training seeds showed that, relative to PFST, PPFT reduced trajectory MAE by 2.22-4.30 bpm and endpoint MAE by 1.24-2.88 bpm. All six trajectory-MAE comparisons remained significant after Holm adjustment ($p_{adj}$ = 0.0469), while four of six endpoint-MAE comparisons remained significant after adjustment. At 30 s, persistence achieved the lowest MAE (3.555 $\pm$ 1.274 bpm), while CNN-LSTM PPFT achieved the lowest RMSE (4.669 $\pm$ 1.916 bpm); LSTM PPFT achieved the lowest endpoint MAE (5.093 $\pm$ 2.365 bpm). At 60 s, Attention-LSTM PPFT achieved the lowest MAE (5.573 $\pm$ 1.939 bpm) and RMSE (7.134 $\pm$ 2.260 bpm), while CNN-LSTM PPFT achieved the lowest endpoint MAE (7.553 $\pm$ 2.357 bpm). These results suggest that population pretraining followed by participant-specific fine-tuning may provide a practical strategy for scarce-data wearable HR forecasting.