An Open-Source, Open Data Approach to Activity Classification from Triaxial Accelerometry in an Ambulatory Setting
Authors: Sepideh Nikookar, Edward Tian, Harrison Hoffman, Matthew Parks, J. Lucas McKay, Yashar Kiarashi, Tommy T. Thomas, Alex Hall, +2 more
Organizations: Department of Biomedical Informatics, Emory University, Atlanta, GA, USA · LifeBell AI LLC, Atlanta, GA, USA · Department of Neurology, Emory University, Atlanta, GA, USA · Department of Neurosurgery, Emory University, Atlanta, GA, USA · Department of Emergency Medicine, Emory University, Atlanta, GA, USA · Department of Biomedical Engineering, Georgia Institute of Technology, Atlanta, GA, USA
The accelerometer has become an almost ubiquitous device, providing enormous opportunities in healthcare monitoring beyond step counting or other average energy estimates in 15-60 second epochs. Objective: To develop an open data set with associated open-source code for processing 50 Hz tri-axial accelerometry-based to classify patient activity levels and natural types of movement. Approach: Data were collected from 23 healthy subjects (16 males and seven females) aged between 23 and 62 years using an ambulatory device, which included a triaxial accelerometer and synchronous lead II equivalent ECG for an average of 26 minutes each. Participants followed a standardized activity routine involving five distinct activities: lying, sitting, standing, walking, and jogging. Two classifiers were constructed: a signal processing technique to distinguish between high and low activity levels and a convolutional neural network (CNN)-based approach to classify each of the five activities. Main results: The binary (high/low) activity classifier exhibited an F1 score of 0.79. The multi-class CNN-based classifier provided an F1 score of 0.83. The code for this analysis has been made available under an open-source license together with the data on which the classifiers were trained and tested. Significance: The classification of behavioral activity, as demonstrated in this study, offers valuable context for interpreting traditional health metrics and may provide contextual information to support the future development of clinical decision-making tools for patient monitoring, predictive analytics, and personalized health interventions.
Figures & tables
Figure 1: Activity label distribution across the dataset.
Figure 2: Architecture of the deep learning model for the activity classification.
Figure 3: Histogram of Activity Count Values Separated by Activity.
Figure 4: Confusion Matrix for Active vs. Inactive Labels.
Metric
Weighted Score
Accuracy
77%
Precision
83%
Recall
77%
F1 Score
79%
Table 1: Weighted performance metrics of the CNN classifier.
Figure 6
Figure 7: Classification performance across different high-frequency cutoff values in the Butterworth filter.
Figure 8: Heatmap of Different Metric vs. Window Size and Sampling Rate.
Predictor
Coef.
Std. Err.
z
P>∣z∣
[0.025, 0.975]
Window Size 1 s vs. 12 s
-12.389
0.594
-20.853
0.000
[-13.553, -11.224]
Window Size 2 s vs. 12 s
-7.264
0.594
-12.226
0.000
[-8.428, -6.099]
Window Size 4 s vs. 12 s
-3.516
0.594
-5.919
0.000
[-4.681, -2.352]
Window Size 5 s vs. 12 s
-3.120
0.594
-5.251
0.000
[-4.284, -1.955]
Window Size 8 s vs. 12 s
-1.736
0.594
-2.923
0.003
[-2.901, -0.572]
Sampling Rate 5 Hz vs. 50 Hz
-8.786
0.485
-18.113
0.000
[-9.737, -7.835]
Table 2: Mixed Linear Model Regression Results
Figure 9: Relationship between Activity Count and Heart Rate Deviation.
Smart insoles equipped with pressure sensors, accelerometers, and gyroscopes offer a non-intrusive means of monitoring human gait and posture. We present an activity classification system based on a circular dilated convolutional neural network (CDCNN) that processes multi-modal time-series data from such insoles. The model operates on 160-frame windows with 24 channels (18 pressure, 3 accelerometer, 3 gyroscope axes), achieving 86.42% test accuracy in a subject-independent evaluation on a four-class task (Standing, Walking, Sitting, Tandem), compared with 87.83% for an extreme gradient-boosted tree (XGBoost) model trained on flattened data. Permutation feature importance reveals that inertial sensors (accelerometer and gyroscope) contribute substantially to discrimination. The approach is suitable for embedded deployment and real-time inference.
Foundation models (FMs) trained on large-scale accelerometer data have been proposed as general-purpose feature extractors for health monitoring, but systematic evidence of their advantages is lacking. We present the first comprehensive evaluation of four open-source accelerometer FMs against supervised baselines covering 19 tasks across the domains of activity recognition including activities of daily living, clinical monitoring, and physiological inference. We find task-dependent performance results: supervised models remain competitive with FMs on human action recognition (HAR), with no consistent advantage for either, while selected FMs lead on fall and stress detection and are the most robust to sensor-placement variation. As frozen feature extractors, FMs are strongest for demographic inference, whereas sleep staging performance remains near chance level for all models. The internal FM representations show strong similarity across layers, highlighting potential for future FM improvements. Linear and frozen probing reveals that UniMTS provides the strongest representations and is the only FM that surpasses the supervised baselines without finetuning. Concept discovery analysis shows all models capture high-intensity activities clearly but struggle with sedentary, complex or ambiguous activities. We provide scenario-based deployment recommendations. Furthermore, we identify FM-derived activity profile inference-moving beyond fixed category classification-as a promising research direction.
Alexander Bräuer, Benjamin Cauchi, Nils Strodthoff
Carl von Ossietzky Universität Oldenburg, Oldenburg, Lower Saxony, 26129, Germany
With each sensing modality exhibiting inherent strengths and limitations, multi-modal approaches for wearable Human Activity Recognition (HAR) are becoming increasingly relevant -- particularly for recognizing Activities of Daily Living (ADLs), where individual modalities often produce ambiguous signals for similar or complex activities. This work introduces HARMES, a multi-modal wearable dataset combining three wrist-recorded modalities: motion sensing via an Inertial Measurement Unit (IMU), atmospheric environmental sensors (humidity, temperature, and pressure), and audio. Collected from 20 participants performing household activities in their own homes, HARMES totals over 80 hours of recorded data, with approximately three hours of labeled activity data per participant across 15 ADL classes. To the best of our knowledge, HARMES is the first dataset to combine this particular sensor trio, and it is nearly six times larger than the previously largest wrist-inertial-acoustic HAR dataset. In an extensive benchmark, we evaluate cross-subject generalization and conduct an ablation study revealing that modality contributions are activity-dependent and can provide complementary value, particularly for activities that are ambiguous from motion data alone. HARMES is freely available at Zenodo, alongside example code for loading the dataset and training models on GitHub.
Robin Burchard, Pascal-André Brückner, Marius Bock +2
University of Siegen, Siegen, Germany · University of Bonn and & Lamarr Institute for Machine Learning and Artificial Intelligence, Bonn, Germany