The DOI matches its Crossref record; 41 of the 41 references it cites were found in a registry or an index.
ProtoHAR: Prototype Guided Personalized Federated Learning for Human Activity Recognition
Abstract
Federated Learning (FL) has recently attracted great interest in sensor-based human activity recognition (HAR) tasks. However, in real-world environment, sensor data on devices is non-independently and identically distributed (Non-IID), e.g., activity data recorded by most devices is sparse, and sensor data distribution for each client may be inconsistent. As a result, the traditional FL methods in the heterogeneous environment may incur a drifted global model that causes slow convergence and a heavy communication burden. Although some FL methods are gradually being applied to HAR, they are designed for overly ideal scenarios and do not address such Non-IID problem in the real-world setting. It is still a question whether they can be applied to cross-device FL. To tackle this challenge, we propose ProtoHAR, a prototype-guided FL framework for HAR, which aims to decouple the representation and classifier in the heterogeneous FL setting efficiently. It leverages the global prototype to correct the activity feature representation to make the prototype knowledge flow among clients without leaking privacy while solving a better classifier to avoid excessive drift of the local model in personalized training. Extensive experiments are conducted on four publicly available datasets: USC-HAD, UNIMIB-SHAR, PAMAP2, and HARBOX, which are collected in both controlled environments and real-world scenarios. The results show that compared with the state-of-the-art FL algorithms, ProtoHAR achieves the best performance and faster convergence speed in HAR datasets.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“This distributed strategy permits healthcare institutions to collectively take advantage of large-scale ML without sharing raw patient data, thus preserving privacy and agreements with data protection protocols [2].”
From Federated Learning in Smart Healthcare: A Comprehensive Review on Privacy, Security, and Predictive Analytics with IoT Integration (2024) · cites this paper as [2]
In the citing paper
“Furthermore, this decentralized arrangement introduces special security challenges that must be addressed for FL to be reliably implemented in healthcare. Key problems involve adversarial attacks, data poisoning, model inversion, and secure aggregation of model updates [2].”
From Federated Learning in Smart Healthcare: A Comprehensive Review on Privacy, Security, and Predictive Analytics with IoT Integration (2024) · cites this paper as [2]
In the citing paper
“This strategy expands controlled noise to model updates, ensuring that individual data points cannot be reconstructed from the unified model, thus protecting patient privacy [2].”
From Federated Learning in Smart Healthcare: A Comprehensive Review on Privacy, Security, and Predictive Analytics with IoT Integration (2024) · cites this paper as [2]
In the citing paper
“Both methods first trained a general model and then fine-tuned personalized models on client devices.”
From Towards User-Generalizable Wearable-Sensor-Based Human Activity Recognition: A Multi-Task Contrastive Learning Approach (2025) · cites this paper as [44]
In the citing paper
“However, they still require new user data to be collected and labeled, followed by local re-training—again, a two-stage process.”
From Towards User-Generalizable Wearable-Sensor-Based Human Activity Recognition: A Multi-Task Contrastive Learning Approach (2025) · cites this paper as [44]
2 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Communication-Efficient Learning of Deep Networks from Decentralized Data
McMahan, H. B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. Y. (2016) · arXiv · doi:10.48550/arxiv.1602.05629 · Cited by 14,215 · cited 6×
“, the computational cost is ignored); FedAvg [5]: The original federated averaging algorithm selects a subset of clients for local training during each round to ensure communication efficiency while sharing a global model; FedProx [8]: Based on FedAvg, a regularization term is added to restrain the distance between th…”
BackgroundMethodInfluentialAdvances and Open Problems in Federated Learning
Kairouz, P., & McMahan, H. B. (2021) · Foundations and Trends in Machine Learning · doi:10.1561/2200000083 · Cited by 7,772
Federated Machine Learning: Concept and Applications
Yang, Q., Liu, Y., Chen, T., & Tong, Y. (2019) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3298981 · Cited by 6,322
Prototypical Networks for Few-shot Learning
Snell, J., Swersky, K., & Zemel, R. S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.05175 · Cited by 4,755 · cited 4×
“Inspired by the concept of prototype learning [16], we conjecture that averaging feature representations from different data distributions on heterogeneous clients can form latent prototype knowledge.”
BackgroundInfluentialFederated Optimization in Heterogeneous Networks
Li, T., Sahu, A. K., Zaheer, M., Sanjabi, M., Talwalkar, A., & Smith, V. (2018) · arXiv · doi:10.48550/arxiv.1812.06127 · Cited by 4,023 · cited 4×
“…algo-rithm selects a subset of clients for local training during each round to ensure communication efficiency while sharing a global model; FedProx [8]: Based on FedAvg, a regularization term is added to restrain the distance between the local and global model; MOON [21]: The local update is…”
BackgroundMethodInfluentialDeep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition
Ordóñez, F., & Roggen, D. (2016) · Sensors · doi:10.3390/s16010115 · Cited by 2,761 · cited 1×
“During the past decade, several mainstream deep neural networks such as convolutional networks, LSTM, residual networks, and autoencoders [2], [22], [23] have been widely applied to address sensor-based HAR problem.”
BackgroundFederated Learning with Non-IID Data
Zhao, Y., Li, M., Lai, L., Suda, N., Civin, D., & Chandra, V. (2018) · arXiv · doi:10.48550/arxiv.1806.00582 · Cited by 2,077 · cited 3×
“It has been proved theoretically [11] and experimentally [9] that traditional FL does not work well in such heterogeneous scenario.”
BackgroundSCAFFOLD: Stochastic Controlled Averaging for Federated Learning
Karimireddy, S. P., Kale, S., Mohri, M., Reddi, S. J., Stich, S. U., & Suresh, A. T. (2019) · arXiv · doi:10.48550/arxiv.1910.06378 · Cited by 1,734
A tutorial on human activity recognition using body-worn inertial sensors
Bulling, A., Blanke, U., & Schiele, B. (2014) · ACM Computing Surveys · doi:10.1145/2499621 · Cited by 1,668 · cited 1×
“T ODAY, the popularity of cell phones and smart bracelets has made them easier to collect sensor data, which has greatly stimulated researches for sensor-based Human Activity Recognition (HAR) [1].”
BackgroundOn the Convergence of FedAvg on Non-IID Data
Li, X., Huang, K., Yang, W., Wang, S., & Zhang, Z. (2019) · arXiv · doi:10.48550/arxiv.1907.02189 · Cited by 1,575 · cited 2×
“It has been proved theoretically [11] and experimentally [9] that traditional FL does not work well in such heterogeneous scenario.”
Background
Cited by
Abbas, S. R., Abbas, Z., Zahir, A., & Lee, S. W. (2024) · Healthcare · doi:10.3390/healthcare12242587 · Cited by 228
IMUGPT 2.0: Language-Based Cross Modality Transfer for Sensor-Based Human Activity Recognition
Leng, Z., Bhattacharjee, A., Rajasekhar, H., Zhang, L., Bruda, E., Kwon, H., & Plötz, T. (2024) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3678545 · Cited by 61
Self-citationHuman activity recognition: A comprehensive review
Kaur, H., Rani, V., & Kumar, M. (2024) · Expert Systems · doi:10.1111/exsy.13680 · Cited by 66
“…a comprehensive examination of current research in activity recognition and hence reviewed several recent deep learning literatures in HAR (Cheng et al., 2023; Han et al., 2022; Huang, Zhang, Wang, et al., 2022; Huang, Zhang, Wu, et al., 2022; Kaseris et al., 2024; Nikpour et al., 2024;…”
An ensemble deep learning model for human activity analysis using wearable sensory data
Batool, S., Khan, M. H., & Farid, M. S. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.111599 · Cited by 55
A DCNN-LSTM based human activity recognition by mobile and wearable sensor networks
Jameer, S., & Syed, H. (2023) · Alexandria Engineering Journal · doi:10.1016/j.aej.2023.09.013 · Cited by 58
Metadata
- Authors
- Cheng, D., Zhang, L., Bu, C., Wang, X., Wu, H., & Song, A.
- Affiliations
- Nanjing Normal University (CN)
- Yunnan University (CN)
- Southeast University (CN)
- Venue
- IEEE Journal of Biomedical and Health Informatics
- Published
- 2023-08
- Volume
- 27
- Issue
- 8
- Pages
- 3900-3911
- ISSN
- 2168-2194 (ISSN-L)
- 2168-2208
- OpenAlex
- W4376225158
- Cited by
- 92
- References
- 39
- Citations by year
- 2026: 25 · 2025: 30 · 2024: 30 · 2023: 7
- FWCI
- 8.14
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Journal of Biomedical and Health Informatics (publishedVersion)
- PubMed (publishedVersion)
- Funders
- National Natural Science Foundation of China (61962061)
- Natural Science Foundation of Jiangsu Province (BK20191371)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- federated learning, human activity recognition, non-IID data, personalized federated learning, cross-device federated learning, privacy preservation, wearable sensor data
- MeSH terms
- Algorithms, Communication, Environment, Controlled, Humans, Human Activities, Knowledge
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: ProtoHAR: Prototype Guided Personalized Federated Learning for Human Activity Recognition. https://app.cochat.ai/papers/10.1109/jbhi.2023.3275438
- The paper
- Cheng, D., Zhang, L., Bu, C., Wang, X., Wu, H., & Song, A. (2023). ProtoHAR: Prototype Guided Personalized Federated Learning for Human Activity Recognition. IEEE Journal of Biomedical and Health Informatics. https://doi.org/10.1109/jbhi.2023.3275438
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.