{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T20:01:34Z","timestamp":1770753694566,"version":"3.50.0"},"reference-count":64,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2022,12,20]],"date-time":"2022-12-20T00:00:00Z","timestamp":1671494400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"New Frontiers in Research Fund (NFRF)","award":["NFRFE-2019-00313"],"award-info":[{"award-number":["NFRFE-2019-00313"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Deep learning-based Human Activity Recognition (HAR) systems received a lot of interest for health monitoring and activity tracking on wearable devices. The availability of large and representative datasets is often a requirement for training accurate deep learning models. To keep private data on users\u2019 devices while utilizing them to train deep learning models on huge datasets, Federated Learning (FL) was introduced as an inherently private distributed training paradigm. However, standard FL (FedAvg) lacks the capability to train heterogeneous model architectures. In this paper, we propose Federated Learning via Augmented Knowledge Distillation (FedAKD) for distributed training of heterogeneous models. FedAKD is evaluated on two HAR datasets: A waist-mounted tabular HAR dataset and a wrist-mounted time-series HAR dataset. FedAKD is more flexible than standard federated learning (FedAvg) as it enables collaborative heterogeneous deep learning models with various learning capacities. In the considered FL experiments, the communication overhead under FedAKD is 200X less compared with FL methods that communicate models\u2019 gradients\/weights. Relative to other model-agnostic FL methods, results show that FedAKD boosts performance gains of clients by up to 20 percent. Furthermore, FedAKD is shown to be relatively more robust under statistical heterogeneous scenarios.<\/jats:p>","DOI":"10.3390\/s23010006","type":"journal-article","created":{"date-parts":[[2022,12,20]],"date-time":"2022-12-20T03:56:08Z","timestamp":1671508568000},"page":"6","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":34,"title":["Federated Learning via Augmented Knowledge Distillation for Heterogenous Deep Human Activity Recognition Systems"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9177-9950","authenticated-orcid":false,"given":"Gad","family":"Gad","sequence":"first","affiliation":[{"name":"Department of Computer Science, Lakehead University, Thunder Bay, ON P7B 5E1, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4785-2425","authenticated-orcid":false,"given":"Zubair","family":"Fadlullah","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Lakehead University, Thunder Bay, ON P7B 5E1, Canada"},{"name":"Thunder Bay Regional Health Research Institute (TBRHRI), Thunder Bay, ON P7B 7A5, Canada"}]}],"member":"1968","published-online":{"date-parts":[[2022,12,20]]},"reference":[{"key":"ref_1","unstructured":"(2022, October 22). About One-in-Five Americans Use a Smart Watch or Fitness Tracker. Available online: https:\/\/www.pewresearch.org\/fact-tank\/2020\/01\/09\/about-one-in-five-americans-use-a-smart-watch-or-fitness-tracker\/."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"698","DOI":"10.1016\/j.procs.2019.08.100","article-title":"Human activity recognition: A survey","volume":"155","author":"Jobanputra","year":"2019","journal-title":"Procedia Comput. Sci."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"210816","DOI":"10.1109\/ACCESS.2020.3037715","article-title":"Human activity recognition using inertial, physiological and environmental sensors: A comprehensive survey","volume":"8","author":"Demrozi","year":"2020","journal-title":"IEEE Access"},{"key":"ref_4","first-page":"1","article-title":"Deep learning for sensor-based human activity recognition: Overview, challenges, and opportunities","volume":"54","author":"Chen","year":"2021","journal-title":"ACM Comput. Surv."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"315","DOI":"10.1002\/rse2.245","article-title":"Real-time insect tracking and monitoring with computer vision and deep learning","volume":"8","author":"Bjerge","year":"2022","journal-title":"Remote Sens. Ecol. Conserv."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"725","DOI":"10.1007\/s00330-021-08132-0","article-title":"Deep learning to automate the labelling of head MRI datasets for computer vision applications","volume":"32","author":"Wood","year":"2022","journal-title":"Eur. Radiol."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Ramasamy, L.K., Khan, F., Shah, M., Prasad, B.V.V.S., Iwendi, C., and Biamba, C. (2022). Secure smart wearable computing through artificial intelligence-enabled internet of things and cyber-physical systems for health monitoring. Sensors, 22.","DOI":"10.3390\/s22031076"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"108309","DOI":"10.1016\/j.sigpro.2021.108309","article-title":"A review on early wildfire detection from unmanned aerial vehicles using deep learning-based computer vision algorithms","volume":"190","author":"Bouguettaya","year":"2022","journal-title":"Signal Process."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1016\/j.neucom.2021.05.103","article-title":"An introduction to deep learning in natural language processing: Models, techniques, and tools","volume":"470","author":"Lauriola","year":"2022","journal-title":"Neurocomputing"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"18289","DOI":"10.1007\/s00521-022-07665-9","article-title":"A review of machine learning-based human activity recognition for diverse applications","volume":"34","author":"Kulsoom","year":"2022","journal-title":"Neural Comput. Appl."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Zhang, S., Li, Y., Zhang, S., Shahabi, F., Xia, S., Deng, Y., and Alshurafa, N. (2022). Deep learning in human activity recognition with wearable sensors: A review on advances. Sensors, 22.","DOI":"10.3390\/s22041476"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1192","DOI":"10.1109\/SURV.2012.110112.00192","article-title":"A survey on human activity recognition using wearable sensors","volume":"15","author":"Lara","year":"2012","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2499621","article-title":"A tutorial on human activity recognition using body-worn inertial sensors","volume":"46","author":"Bulling","year":"2014","journal-title":"ACM Comput. Surv."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Li, Y., and Wang, L. (2022). Human Activity Recognition Based on Residual Network and BiLSTM. Sensors, 22.","DOI":"10.3390\/s22020635"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3569482","article-title":"IF-ConvTransformer: A Framework for Human Activity Recognition Using IMU Fusion and ConvTransformer","volume":"6","author":"Zhang","year":"2022","journal-title":"Proc. ACM Interactive Mobile Wearable Ubiquitous Technol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"787","DOI":"10.1016\/j.acha.2019.06.004","article-title":"Universality of deep convolutional neural networks","volume":"48","author":"Zhou","year":"2020","journal-title":"Appl. Comput. Harmon. Anal."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Sch\u00e4fer, A.M., and Zimmermann, H.G. (2006). Recurrent neural networks are universal approximators. International Conference on Artificial Neural Networks, Springer.","DOI":"10.1007\/11840817_66"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Chung, S., Lim, J., Noh, K.J., Kim, G.G., and Jeong, H.T. (2018, January 17\u201319). Sensor positioning and data acquisition for activity recognition using deep learning. Proceedings of the 2018 International Conference on Information and Communication Technology Convergence (ICTC), Jeju Island, Korea.","DOI":"10.1109\/ICTC.2018.8539473"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.hroo.2020.02.002","article-title":"Atrial fibrillation detection from raw photoplethysmography waveforms: A deep learning application","volume":"1","author":"Aschbacher","year":"2020","journal-title":"Heart Rhythm O2"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"100082","DOI":"10.1016\/j.smhl.2019.100082","article-title":"ActiPPG: Using deep neural networks for activity recognition from wrist-worn photoplethysmography (PPG) sensors","volume":"14","author":"Boukhechba","year":"2019","journal-title":"Smart Health"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Mekruksavanich, S., and Jitpattanakul, A. (2022). CNN-Based Deep Learning Network for Human Activity Recognition During Physical Exercise from Accelerometer and Photoplethysmographic Sensors. Computer Networks, Big Data and IoT, Springer.","DOI":"10.1007\/978-981-19-0898-9_42"},{"key":"ref_22","first-page":"1","article-title":"Federated learning","volume":"13","author":"Yang","year":"2019","journal-title":"Synth. Lect. Artif. Intell. Mach. Learn."},{"key":"ref_23","unstructured":"McMahan, B., Moore, E., Ramage, D., Hampson, S., and y Arcas, B.A. (2017, January 20\u201322). Communication-efficient learning of deep networks from decentralized data. Proceedings of the Artificial Intelligence and Statistics, Fort Lauderdale, FL, USA."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Ouyang, X., Xie, Z., Zhou, J., Xing, G., and Huang, J. (2022). ClusterFL: A Clustering-based Federated Learning System for Human Activity Recognition. ACM Transactions on Sensor Networks (TOSN), ACM.","DOI":"10.1145\/3554980"},{"key":"ref_25","unstructured":"Diao, E., Ding, J., and Tarokh, V. (2020). HeteroFL: Computation and communication efficient federated learning for heterogeneous clients. arXiv."},{"key":"ref_26","unstructured":"Li, D., and Wang, J. (2019). Fedmd: Heterogenous federated learning via model distillation. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","article-title":"Knowledge distillation: A survey","volume":"129","author":"Gou","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"ref_28","unstructured":"Zhu, Z., Hong, J., and Zhou, J. (2021, January 18\u201324). Data-free knowledge distillation for heterogeneous federated learning. Proceedings of the International Conference on Machine Learning, Virtual."},{"key":"ref_29","unstructured":"Anguita, D., Ghio, A., Oneto, L., Parra Perez, X., and Reyes Ortiz, J.L. (2013, January 5\u20137). A public domain dataset for human activity recognition using smartphones. Proceedings of the 21th International European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges, Belgium."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Anguita, D., Ghio, A., Oneto, L., Parra, X., and Reyes-Ortiz, J.L. (2012). Human activity recognition on smartphones using a multiclass hardware-friendly support vector machine. International Workshop on Ambient Assisted Living, Springer.","DOI":"10.1007\/978-3-642-35395-6_30"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Sun, L., Zhang, D., Li, B., Guo, B., and Li, S. (2010). Activity recognition on an accelerometer embedded mobile phone with varying positions and orientations. International Conference on Ubiquitous Intelligence and Computing, Springer.","DOI":"10.1007\/978-3-642-16355-5_42"},{"key":"ref_32","first-page":"146","article-title":"Activity recognition using k-nearest neighbor algorithm on smartphone with tri-axial accelerometer","volume":"1","author":"Kaghyan","year":"2012","journal-title":"Int. J. Inform. Model. Anal. ITHEA Int. Sci. Soc. Bulg."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"D\u00edaz, S., Stephenson, J.B., and Labrador, M.A. (2019). Use of wearable sensor technology in gait, balance, and range of motion analysis. Appl. Sci., 10.","DOI":"10.3390\/app10010234"},{"key":"ref_34","first-page":"1","article-title":"An introduction to sensor fusion","volume":"502","author":"Elmenreich","year":"2002","journal-title":"Vienna Univ. Technol. Austria"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Laidig, D., Schauer, T., and Seel, T. (2017, January 17\u201320). Exploiting kinematic constraints to compensate magnetic disturbances when calculating joint angles of approximate hinge joints from orientation estimates of inertial sensors. Proceedings of the 2017 International Conference on Rehabilitation Robotics (ICORR), London, UK.","DOI":"10.1109\/ICORR.2017.8009375"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1136\/jnnp.2009.173740","article-title":"The instrumented timed up and go test: Potential outcome measure for disease modifying therapies in Parkinson\u2019s disease","volume":"81","author":"Zampieri","year":"2010","journal-title":"J. Neurol. Neurosurg. Psychiatry"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Bhattacharya, D., Sharma, D., Kim, W., Ijaz, M.F., and Singh, P.K. (2022). Ensem-HAR: An Ensemble Deep Learning Model for Smartphone Sensor-Based Human Activity Recognition for Measurement of Elderly Health Monitoring. Biosensors, 12.","DOI":"10.3390\/bios12060393"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Zeng, M., Gao, H., Yu, T., Mengshoel, O.J., Langseth, H., Lane, I., and Liu, X. (2018, January 8\u201312). Understanding and improving recurrent networks for human activity recognition by continuous attention. Proceedings of the 2018 ACM International Symposium on Wearable Computers, Singapore.","DOI":"10.1145\/3267242.3267286"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Doshi, K., and Yilmaz, Y. (2022, January 18\u201322). Federated learning-based driver activity recognition for edge devices. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPRW56347.2022.00377"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Bhat, G., Deb, R., Chaurasia, V.V., Shill, H., and Ogras, U.Y. (2018, January 5\u20138). Online human activity recognition using low-power wearable devices. Proceedings of the 2018 IEEE\/ACM International Conference on Computer-Aided Design (ICCAD), San Diego, CA, USA.","DOI":"10.1145\/3240765.3240833"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Tapia, E.M., Intille, S.S., Haskell, W., Larson, K., Wright, J., King, A., and Friedman, R. (2007, January 11\u201313). Real-time recognition of physical activities and their intensities using wireless accelerometers and a heart rate monitor. Proceedings of the 2007 11th IEEE International Symposium on Wearable Computers, Boston, MA, USA.","DOI":"10.1109\/ISWC.2007.4373774"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Bao, L., and Intille, S.S. (2004). Activity recognition from user-annotated acceleration data. International Conference on Pervasive Computing, Springer.","DOI":"10.1007\/978-3-540-24646-6_1"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1109\/TITB.2005.856863","article-title":"Activity classification using realistic data from wearable sensors","volume":"10","author":"Parkka","year":"2006","journal-title":"IEEE Trans. Inf. Technol. Biomed."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"717","DOI":"10.1016\/j.pmcj.2011.06.004","article-title":"Centinela: A human activity recognition system based on acceleration and vital sign data","volume":"8","author":"Lara","year":"2012","journal-title":"Pervasive Mob. Comput."},{"key":"ref_45","unstructured":"Hecht-Nielsen, R. (1992). Theory of the backpropagation neural network. Neural Networks for Perception, Elsevier."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Goyal, M., Goyal, R., Venkatappa Reddy, P., and Lall, B. (2020). Activation functions. Deep Learning: Algorithms and Applications, Springer.","DOI":"10.1007\/978-3-030-31760-7_1"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.neunet.2021.01.026","article-title":"A survey on modern trainable activation functions","volume":"138","author":"Apicella","year":"2021","journal-title":"Neural Netw."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Sozinov, K., Vlassov, V., and Girdzijauskas, S. (2018, January 11\u201313). Human activity recognition using federated learning. Proceedings of the 2018 IEEE International Conference on Parallel & Distributed Processing with Applications, Ubiquitous Computing & Communications, Big Data & Cloud Computing, Social Computing & Networking, Sustainable Computing & Communications (ISPA\/IUCC\/BDCloud\/SocialCom\/SustainCom), Guangzhou, China.","DOI":"10.1109\/BDCloud.2018.00164"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Tu, L., Ouyang, X., Zhou, J., He, Y., and Xing, G. (2021, January 15\u201317). Feddl: Federated learning via dynamic layer sharing for human activity recognition. Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems, Coimbra, Portugal.","DOI":"10.1145\/3485730.3485946"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"107338","DOI":"10.1016\/j.knosys.2021.107338","article-title":"A federated learning system with enhanced feature extraction for human activity recognition","volume":"229","author":"Xiao","year":"2021","journal-title":"Knowl.-Based Syst."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"115391","DOI":"10.1016\/j.apenergy.2020.115391","article-title":"Near-real-time plug load identification using low-frequency power data in office spaces: Experiments and applications","volume":"275","author":"Tekler","year":"2020","journal-title":"Appl. Energy"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"1627","DOI":"10.1021\/ac60214a047","article-title":"Smoothing and differentiation of data by simplified least squares procedures","volume":"36","author":"Savitzky","year":"1964","journal-title":"Anal. Chem."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"1401","DOI":"10.1109\/TITS.2020.2970229","article-title":"Commercial vehicle activity prediction with imbalanced class distribution using a hybrid sampling and gradient boosting approach","volume":"22","author":"Low","year":"2020","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Graves, A. (2012). Long short-term memory. Supervised Sequence Labelling with Recurrent Neural Networks, Springer.","DOI":"10.1007\/978-3-642-24797-2"},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Kiranyaz, S., Ince, T., Abdeljaber, O., Avci, O., and Gabbouj, M. (2019, January 12\u201317). 1D convolutional neural networks for signal processing applications. Proceedings of the ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK.","DOI":"10.1109\/ICASSP.2019.8682194"},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Lawrence, S., and Giles, C.L. (2000, January 27). Overfitting and neural networks: Conjugate gradient and backpropagation. Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium, Como, Italy.","DOI":"10.1109\/IJCNN.2000.857823"},{"key":"ref_57","unstructured":"Baldi, P., and Sadowski, P.J. (2013). Understanding dropout. Adv. Neural Inf. Process. Syst., 26."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1007\/s41745-019-0098-4","article-title":"Stochastic gradient descent and its variants in machine learning","volume":"99","author":"Netrapalli","year":"2019","journal-title":"J. Indian Inst. Sci."},{"key":"ref_59","doi-asserted-by":"crossref","unstructured":"Zhang, Z. (2018, January 4\u20136). Improved adam optimizer for deep neural networks. Proceedings of the 2018 IEEE\/ACM 26th International Symposium on Quality of Service (IWQoS), Banff, AB, Canada.","DOI":"10.1109\/IWQoS.2018.8624183"},{"key":"ref_60","unstructured":"Mukkamala, M.C., and Hein, M. (2017, January 6\u201311). Variants of rmsprop and adagrad with logarithmic regret bounds. Proceedings of the International conference on machine learning, Sydney, Australia."},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"109689","DOI":"10.1016\/j.buildenv.2022.109689","article-title":"Occupancy prediction using deep learning approaches across multiple space types: A minimum sensing strategy","volume":"226","author":"Tekler","year":"2022","journal-title":"Build. Environ."},{"key":"ref_62","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., and Lopez-Paz, D. (May, January 30). mixup: Beyond Empirical Risk Minimization. Proceedings of the International Conference on Learning Representations, Vancouver, BC, Canada."},{"key":"ref_63","doi-asserted-by":"crossref","first-page":"2211","DOI":"10.1109\/LCOMM.2020.3003693","article-title":"Mix2FLD: Downlink federated learning after uplink federated distillation with two-way mixup","volume":"24","author":"Oh","year":"2020","journal-title":"IEEE Commun. Lett."},{"key":"ref_64","unstructured":"Buolamwini, J., and Gebru, T. (2018, January 23\u201324). Gender shades: Intersectional accuracy disparities in commercial gender classification. Proceedings of the Conference on Fairness, Accountability and Transparency, New York, NY, USA."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/1\/6\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:44:30Z","timestamp":1760147070000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/1\/6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,20]]},"references-count":64,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,1]]}},"alternative-id":["s23010006"],"URL":"https:\/\/doi.org\/10.3390\/s23010006","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,20]]}}}