mlsanityData to 7 Oct 2026

Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances

arXiv 2111.00418 ↗First posted 31 Oct 2021cs.HC cs.LG eess.SPcited by 54

Not on the map. Why?

Abstract (arXiv)

Mobile and wearable devices have enabled numerous applications, including activity tracking, wellness monitoring, and human--computer interaction, that measure and improve our daily lives. Many of these applications are made possible by leveraging the rich collection of low-power sensors found in many mobile and wearable devices to perform human activity recognition (HAR). Recently, deep learning has greatly pushed the boundaries of HAR on mobile and wearable devices. This paper systematically categorizes and summarizes existing work that introduces deep learning methods for wearables-based HAR and provides a comprehensive analysis of the current advancements, developing trends, and major challenges. We also present cutting-edge frontiers and future directions for deep learning-based HAR.

Key facts. Cited by 54 papers in the map (data through 7 Oct 2026). Builds on 66 of its 345 references that are in the map. First posted on arXiv 31 Oct 2021.

Builds on

66 of 345 references.

References · 66

  1. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  2. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
  3. 2017Improved Training of Wasserstein GANscited by 2,223
  4. 2019Invariant Risk Minimizationcited by 1,832
  5. 2016Generative Adversarial Text to Image Synthesiscited by 735
  6. 2017Wasserstein GANcited by 635
  7. 2018The UCR Time Series Archivecited by 421
  8. 2018The UEA multivariate time series classification archive, 2018cited by 330
  9. 2021In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learningcited by 301
  10. 2018BRITS: Bidirectional Recurrent Imputation for Time Seriescited by 288
  11. 2018A Comprehensive Survey of Deep Learning for Image Captioningcited by 213
  12. 2015Federated Optimization:Distributed Optimization Beyond the Datacentercited by 193
38 more
  1. 2018Universality of Deep Convolutional Neural Networkscited by 176
  2. 2017Deep Learning is Robust to Massive Label Noisecited by 164
  3. 2017Deep Learning for Sensor-based Activity Recognition: A Surveycited by 133
  4. 2017Data Augmentation of Wearable Sensor Data for Parkinson's Disease Monitoring using Convolutional Neural Networkscited by 130
  5. 2020Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunitiescited by 125
  6. 2016Mode Regularized Generative Adversarial Networkscited by 123
  7. 2016Semi-Supervised Learning with Generative Adversarial Networkscited by 103
  8. 2017Visual to Sound: Generating Natural Sound for Videos in the Wildcited by 98
  9. 2015Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networkscited by 94
  10. 2016Deep, Convolutional, and Recurrent Models for Human Activity Recognition using Wearablescited by 93
  11. 2016DeepSense: A Unified Deep Learning Framework for Time-Series Mobile Sensing Data Processingcited by 84
  12. 2021Federated Learning Meets Blockchain in Edge Computing: Opportunities and Challengescited by 75
  13. 2018Mobile Sensor Data Anonymizationcited by 70
  14. 2019On-Device Machine Learning: An Algorithms and Learning Theory Perspectivecited by 63
  15. 2016UniMiB SHAR: a new dataset for human activity recognition using acceleration data from smartphonescited by 54
  16. 2018Protecting Sensory Data against Sensitive Inferencescited by 45
  17. 2016Recognizing Detailed Human Context In-the-Wild from Smartphones and Smartwatchescited by 41
  18. 2014TROIKA: A General Framework for Heart Rate Monitoring Using Wrist-Type Photoplethysmographic Signals During Intensive Physical Exercisecited by 40
  19. 2018Data augmentation using synthetic data for time series classification with deep residual networkscited by 38
  20. 2019Cross-Subject Transfer Learning in Human Activity Recognition Systems using Generative Adversarial Networkscited by 35
  21. 2018T-CGAN: Conditional Generative Adversarial Network for Data Augmentation in Noisy Time Series with Irregular Samplingcited by 29
  22. 2018Understanding and Improving Recurrent Networks for Human Activity Recognition by Continuous Attentioncited by 27
  23. 2017Deep Residual Bidir-LSTM for Human Activity Recognition Using Wearable Sensorscited by 24
  24. 2021Meta-HAR: Federated Representation Learning for Human Activity Recognitioncited by 21
  25. 2017SenseGen: A Deep Learning Architecture for Synthetic Sensor Data Generationcited by 20
  26. 2020GANs May Have No Nash Equilibriacited by 20
  27. 2020Attend And Discriminate: Beyond the State-of-the-Art for Human Activity Recognition using Wearable Sensorscited by 19
  28. 2019Domain Adaptation for sEMG-based Gesture Recognition with Recurrent Neural Networkscited by 15
  29. 2020DanHAR: Dual Attention Network For Multimodal Human Activity Recognition Using Wearable Sensorscited by 14
  30. 2015Deep Activity Recognition Models with Triaxial Accelerometerscited by 13
  31. 2018Deep Auto-Set: A Deep Auto-Encoder-Set Network for Activity Recognition Using Wearablescited by 12
  32. 2019NeckSense: A Multi-Sensor Necklace for Detecting Eating Activities in Free-Living Conditionscited by 12
  33. 2016Deep Recurrent Neural Network for Mobile Human Activity Recognition with High Throughputcited by 10
  34. 2018Online Human Activity Recognition using Low-Power Wearable Devicescited by 10
  35. 2019Attention-based Convolutional Neural Network for Weakly Labeled Human Activities Recognition with Wearable Sensorscited by 10
  36. 2021Personalized Semi-Supervised Federated Learning for Human Activity Recognitioncited by 9
  37. 2018Semi-Supervised Convolutional Neural Networks for Human Activity Recognitioncited by 8
  38. 2018Distributionally Robust Semi-Supervised Learning for People-Centric Sensingcited by 8

50 most cited of 66 All 66 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 14; 2024: 12; 2025: 13; 2026: 12.

54 papers.

Sort:

By area:

  1. 2022GLOBEM Dataset: Multi-Year Datasets for Longitudinal Human Behavior Modeling Generalizationcited by 28
  2. 2025TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learningcited by 16
  3. 2023Recent Advances and Applications of Machine Learning in Experimental Solid Mechanics: A Reviewcited by 15
  4. 2022Human Activity Recognition Using Tools of Convolutional Neural Networks: A State of the Art Review, Data Sets, Challenges and Future Prospectscited by 10
  5. 2024A Survey on Multimodal Wearable Sensor-based Human Action Recognitioncited by 10
  6. 2023Artificial intelligence in digital pathology: a systematic review and meta-analysis of diagnostic test accuracycited by 9
  7. 2025TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devicescited by 8
  8. 2023Unleashing the Power of Shared Label Structures for Human Activity Recognitioncited by 6
  9. 2023Large Scale Foundation Models for Intelligent Manufacturing Applications: A Surveycited by 6
  10. 2024Diverse Intra- and Inter-Domain Activity Style Fusion for Cross-Person Generalization in Activity Recognitioncited by 6
  11. 2024Towards LLM-Powered Ambient Sensor Based Multi-Person Human Activity Recognitioncited by 5
  12. 2024IMUDiffusion: A Diffusion Model for Multivariate Time Series Synthetisation for Inertial Motion Capturing Systemscited by 5
38 more
  1. 2022Self-Supervised Human Activity Recognition with Localized Time-Frequency Contrastive Representation Learningcited by 4
  2. 2024A Survey of IMU Based Cross-Modal Transfer Learning in Human Activity Recognitioncited by 4
  3. 2023cGAN-Based High Dimensional IMU Sensor Data Generation for Enhanced Human Activity Recognition in Therapeutic Activitiescited by 2
  4. 2024SoK: Behind the Accuracy of Complex Human Activity Recognition Using Deep Learningcited by 2
  5. 2023Fruit Picker Activity Recognition with Wearable Sensors and Machine Learningcited by 1
  6. 2023A Survey on Multi-Resident Activity Recognition in Smart Environmentscited by 1
  7. 2025Improving Out-of-distribution Human Activity Recognition via IMU-Video Cross-modal Representation Learningcited by 1
  8. 2025Classification of 24-hour movement behaviors from wrist-worn accelerometer data: from handcrafted features to deep learning techniquescited by 1
  9. 2025Reducing Label Dependency in Human Activity Recognition with Wearables: From Supervised Learning to Novel Weakly Self-Supervised Approachescited by 1
  10. 2026Graph Vector Field: A Unified Framework for Multimodal Health Risk Assessment from Heterogeneous Wearable and Environmental Data Streamscited by 1
  11. 2026Prediction of Challenging Behaviors Associated with Profound Autism in a Classroom Setting Using Wearable Sensorscited by 1
  12. 2023Navigating the reporting guideline environment for computational pathology: A reviewcited by 0
  13. 2023Sleep Quality Prediction from Wearables using Convolution Neural Networks and Ensemble Learningcited by 0
  14. 2023rWISDM: Repaired WISDM, a Public Dataset for Human Activity Recognitioncited by 0
  15. 2023Robust Activity Recognition for Adaptive Worker-Robot Interaction using Transfer Learningcited by 0
  16. 2023Design of Recognition and Evaluation System for Table Tennis Players' Motor Skills Based on Artificial Intelligencecited by 0
  17. 2023The Potential of Wearable Sensors for Assessing Patient Acuity in Intensive Care Unit (ICU)cited by 0
  18. 2023Distributed Agent-Based Collaborative Learning in Cross-Individual Wearable Sensor-Based Human Activity Recognitioncited by 0
  19. 2024DiTMoS: Delving into Diverse Tiny-Model Selection on Microcontrollerscited by 0
  20. 2024Wearable-based behaviour interpolation for semi-supervised human activity recognitioncited by 0
  21. 2024UserBoost: Generating User-specific Synthetic Data for Faster Enrolment into Behavioural Biometric Systemscited by 0
  22. 2024Leveraging Hybrid Intelligence Towards Sustainable and Energy-Efficient Machine Learningcited by 0
  23. 2024Raising the Bar(ometer): Identifying a User's Stair and Lift Usage Through Wearable Sensor Data Analysiscited by 0
  24. 2024WearableMil: An End-to-End Framework for Military Activity Recognition and Performance Monitoringcited by 0
  25. 2025In Shift and In Variance: Assessing the Robustness of HAR Deep Learning Models against Variabilitycited by 0
  26. 2025Enhancing Wearable Tap Water Audio Detection through Subclass Annotation in the HD-Epic Datasetcited by 0
  27. 2025Confidence-driven Gradient Modulation for Multimodal Human Activity Recognition: A Dynamic Contrastive Dual-Path Learning Approachcited by 0
  28. 2025Reinforcement Learning Driven Generalizable Feature Representation for Cross-User Activity Recognitioncited by 0
  29. 2025OVGrasp: Open-Vocabulary Grasping Assistance via Multimodal Intent Detectioncited by 0
  30. 2025Artificial Intelligence-driven Intelligent Wearable Systems: A full-stack Integration from Material Design to Personalized Interactioncited by 0
  31. 2025MMA: A Momentum Mamba Architecture for Human Activity Recognition with Inertial Sensorscited by 0
  32. 2025DETACH : Decomposed Spatio-Temporal Alignment for Exocentric Video and Ambient Sensors with Staged Learningcited by 0
  33. 2026Integrating Temporal Context into Streaming Data for Human Activity Recognition in Smart Homecited by 0
  34. 2026Summary of the Unusual Activity Recognition Challenge for Developmental Disability Supportcited by 0
  35. 2026BabyMamba-HAR: Lightweight Selective State Space Models for Efficient Human Activity Recognition on Resource Constrained Devicescited by 0
  36. 2026Resource-Efficient Gesture Recognition through Convexified Attentioncited by 0
  37. 2026Modular Retrieval-Augmented Generalization for Human Action Recognitioncited by 0
  38. 2026WHAR Arena: Benchmarking the State of the Art in Efficient Wearable Human Activity Recognitioncited by 0

50 most cited of 54 All 54 (JSON)