Context-Aware Activity Recognition Systems
75 works in the bibliography carry this topic. Each used an Axivity accelerometer to collect data, or evaluated one as an instrument.
2026
- Development and evaluation of wrist- and thigh-worn accelerometer algorithms using self-training machine learning models for classification of activity type and posture: towards device placement-agnostic methods in the ProPASS consortium (opens in new tab)
- Do Movement Summary Metrics Produce Comparable Outputs Across Different Accelerometer Brands in Free Living? (opens in new tab)
- Dual foundation models for accelerometry predict future health (opens in new tab)
- Evaluating Open-Source Wrist-Worn Accelerometer Models for Sedentary Time Detection Against Thigh-Worn Accelerometer Data (opens in new tab)
Feature Anchors for Time-Series Sensor-Based Human Activity Recognition
- Free-Living Human Activity Recognition (FL-HAR) using Frequency Domain Feature and Machine Learning Algorithms (opens in new tab)
- Hybrid Deep Learning Models for Free-Living Imbalanced Human Activity Recognition: Comparative Study (opens in new tab)
- Real-World Gait Analysis for Older Adults: Identifying Optimal Gait Bouts and Reconstructing Lower-Back Signals from Wrist-Worn Devices (opens in new tab)
2025
- A Methodological Framework for Analyzing and Differentiating Daily Physical Activity Across Groups Using Digital Biomarkers from the Frequency Domain (opens in new tab)
- Activity Detection of Paralympic Athletes with Lower Limb Running-Specific Prosthesis During Extended Periods of Time: Software Development and Preliminary Validation (opens in new tab)
- An Effective Approach for Wearable Sensor-Based Human Activity Recognition in Elderly Monitoring (opens in new tab)
- Classification of 24-hour movement behaviors from wrist-worn accelerometer data: from handcrafted features to deep learning techniques (opens in new tab)
- Cohort profile: baseline characteristics and design of the McMaster Monitoring My Mobility (MacM3) study – a prospective digital mobility cohort of community-dwelling older Canadians from Southern Ontario (opens in new tab)
- Exploring parameter optimisation in machine learning algorithms for locomotor task discrimination using wearable sensors (opens in new tab)
- Federated Learning for IoMT-Enhanced Human Activity Recognition with Hybrid LSTM-GRU Networks (opens in new tab)
- iPlayer: an open-source tool for time-windowed video annotation of human physical activity and behaviour (opens in new tab)
- Mesure de l’activité physique favorable à la santé : développement d’une approche objective et in situ (opens in new tab)
- Predictive performance of wearable sensors for mortality risk in older adults: a model development and validation study (opens in new tab)
- Sensor for sports applications: monitoring and assessment of intrinsic capacity enhancement in older adults during brisk walking (opens in new tab)
- Validation and comparative study of the Motus system for accurately identifying movement behaviours using different sampling frequencies (opens in new tab)
2024
- Adaptive Hierarchical Classification for Human Activity Recognition Using Inertial Measurement Unit (IMU) Time-Series Data (opens in new tab)
- An Approach for Human Posture Recognition Based on the Fusion PSE-CNN-BiGRU Model (opens in new tab)
- CAPTURE-24: A large dataset of wrist-worn activity tracker data collected in the wild for human activity recognition (opens in new tab)
- Composite activity type and stride-specific energy expenditure estimation model for thigh-worn accelerometry (opens in new tab)
- Daily physical activity in older adults across levels of care: the HUNT Trondheim 70 + study (opens in new tab)
- Development of machine learning-based algorithms for classifying physical activity intensity using wrist and thigh worn wearables (opens in new tab)
- ERG-AI: enhancing occupational ergonomics with uncertainty-aware ML and LLM feedback (opens in new tab)
- Full-Body Activity Recognition Using Inertial Signals (opens in new tab)
- Mitigating data quality challenges in ambulatory wrist-worn wearable monitoring through analytical and practical approaches (opens in new tab)
- NiMBaLWear analytics pipeline for wearable sensors: a modular, open-source platform for evaluating multiple domains of health and behaviour (opens in new tab)
- Private Data Leakage in Federated Human Activity Recognition for Wearable Healthcare Devices (opens in new tab)
- Quantitative Analysis of Mother Wavelet Function Selection for Wearable Sensors-Based Human Activity Recognition (opens in new tab)
- Self-Supervised Machine Learning to Characterize Step Counts from Wrist-Worn Accelerometers in the UK Biobank (opens in new tab)
- SelfPAB: large-scale pre-training on accelerometer data for human activity recognition (opens in new tab)
- Towards Learning Discrete Representations via Self-Supervision for Wearables-Based Human Activity Recognition (opens in new tab)
2023
- Human Activity Recognition Using Self-Supervised Representations of Wearable Data (opens in new tab)
- Reducing the Impact of Sensor Orientation Variability in Human Activity Recognition Using a Consistent Reference System (opens in new tab)
- Sensors for Human Physical Behaviour Monitoring (opens in new tab)
- Validation of an Activity Type Recognition Model Classifying Daily Physical Behavior in Older Adults: The HAR70+ Model (opens in new tab)
- Validation of Oura ring energy expenditure and steps in laboratory and free-living (opens in new tab)
2022
- A software system for the assessment of the sleep-wake rhythm using Axivity AX3 (opens in new tab)
- GGIRread: Wearable Accelerometer Data File Readers (opens in new tab)
- Investigating Wrist-Based Acceleration Summary Measures across Different Sample Rates towards 24-Hour Physical Activity and Sleep Profile Assessment (opens in new tab)
- Personalised Gait Recognition for People with Neurological Conditions (opens in new tab)
- POPULATION ANALYSIS OF MORTALITY RISK: PREDICTIVE MODELS USING MOTION SENSORS FOR 100,000 PARTICIPANTS IN THE UK BIOBANK NATIONAL COHORT (opens in new tab)
- Putting Temperature into the Equation: Development and Validation of Algorithms to Distinguish Non-Wearing from Inactivity and Sleep in Wearable Sensors (opens in new tab)
- Quantification of acceleration as activity counts in ActiGraph wearable (opens in new tab)
- Quantification of Acceleration as Activity Counts in ActiGraph Wearables (opens in new tab)
2021
- A Machine Learning Classifier for Detection of Physical Activity Types and Postures During Free-Living (opens in new tab)
- Estimation of kinetic energy harvesting potential for self-powered wearable devices with 67,000 participants from the UK Biobank (opens in new tab)
- Reallocation of time between device-measured movement behaviours and risk of incident cardiovascular disease (opens in new tab)
- Wearable Based Calibration of Contactless In-home Motion Sensors for Physical Activity Monitoring in Community-Dwelling Older Adults (opens in new tab)
2020
- Impact of Reduced Sampling Rate on Accelerometer-based Physical Activity Monitoring and Machine Learning Activity Classification (opens in new tab)
- Personalized and Weakly Supervised Learning for Parkinson's Disease Symptom Detection (opens in new tab)
- Potential of Ambient Sensor Systems for Early Detection of Health Problems in Older Adults (opens in new tab)
- Workplace activity classification from shoe-based movement sensors (opens in new tab)
2019
- A data-driven, meaningful, easy to interpret, standardised accelerometer outcome variable for global surveillance (opens in new tab)
- A Dual-Accelerometer System for Detecting Human Movement in a Free-living Environment (opens in new tab)
- Comparison of physical behavior estimates from three different thigh-worn accelerometers brands: a proof-of-concept for the Prospective Physical Activity, Sitting, and Sleep consortium (ProPASS) (opens in new tab)
- Effects of Frequency Filtering on Intensity and Noise in Accelerometer-Based Physical Activity Measurements (opens in new tab)
Ensemble Classifier Managing Uncertainty in Accelerometer Data within Human Activity Recognition Systems
- Inertial wearables as pragmatic tools in dementia (opens in new tab)
Machine learning methods for sleep-wake classification using two body-worn accelerometers
- MEx - Multi-modal Exercise Dataset for Human Activity Recognition (opens in new tab)
- P2‐220: GAIT IMPAIRMENTS IN DEMENTIA SUBTYPES: CONSIDERING THE IMPACT OF ENVIRONMENTAL CONTEXT (opens in new tab)
2018
- A Dual-Accelerometer System for Classifying Physical Activity in Children and Adults (opens in new tab)
Designing free-living quantitative reports for Parkinson’s
- TD‐P‐015: CONTINUOUS MONITORING OF GAIT: WHAT CAN IT TELL US ABOUT DEMENTIA? (opens in new tab)
2017
- Accelerometer-assessed Physical Activity in Epidemiology (opens in new tab)
- Generating ActiGraph Counts from Raw Acceleration Recorded by an Alternative Monitor (opens in new tab)
Learning deep features for kNN-based human activity recognition.
- Tea, talk and technology: patient and public involvement to improve connected health ‘wearables’ research in dementia (opens in new tab)
2016
2013
Recognizing Physical Training Exercises Using the Axivity Device.
- Wearable Recognition System for Physical Activities (opens in new tab)