{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T19:47:47Z","timestamp":1775764067161,"version":"3.50.1"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T00:00:00Z","timestamp":1761523200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T00:00:00Z","timestamp":1761523200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Hum-Cent Intell Syst"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Technologies that run on resource-constrained environments such as edge devices or locally hosted servers, led us towards a search for computationally lightweight models. In the present scenario, Human Activity Recognition (HAR) based on accelerometer and gyroscope sensors is one such domain where near real-time response is required and hence, we need to deploy the system to a local edge device. However, deep learning models that are often executed for activity prediction are not suitable for such resource constrained environment. To overcome this challenge, we have proposed an approach that combines the potential of data dimensionality and distillation of knowledge from a three-layer deep Convolutional Neural Network (CNN) model to train a single-layer CNN model. The novelty of the work lies in exploration of data dimensionality in a way that enables a student model to better generalize the knowledge captured by the teacher model. This proposed training pipeline allows us to implement simple models that attempt to mimic the performance of gigantic deep learning models without overfitting it. This methodology was tested on three different HAR benchmark datasets, UCI-HAR, WISDM and MHEALTH and they achieved overall classification accuracies of 96.78%, 90.01% and 99.12% respectively with more than 4 times less trainable parameter size.<\/jats:p>","DOI":"10.1007\/s44230-025-00112-7","type":"journal-article","created":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T16:16:33Z","timestamp":1761581793000},"page":"450-466","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Exploring Dimensionality with Knowledge Distillation for Human Activity Recognition"],"prefix":"10.1007","volume":"5","author":[{"given":"Dipannyta","family":"Nandi","sequence":"first","affiliation":[]},{"given":"Pawan Kumar","family":"Singh","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2949-9573","authenticated-orcid":false,"given":"Chandreyee","family":"Chowdhury","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"112_CR1","unstructured":"Hinton G, Vinyals O, Dean J. Distilling the knowledge in a neural network. arXiv:1503.02531 2015"},{"key":"112_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2025.117308","author":"H Shah","year":"2025","unstructured":"Shah H, Holia MS. Hybrid feature extraction and knowledge distillation based deep learning model for human activity recognition system. Signal Process Image Commun. 2025. https:\/\/doi.org\/10.1016\/j.image.2025.117308.","journal-title":"Signal Process Image Commun"},{"issue":"4","key":"112_CR3","doi-asserted-by":"publisher","first-page":"82","DOI":"10.3390\/jimaging9040082","volume":"9","author":"H Ullah","year":"2023","unstructured":"Ullah H, Munir A. A 3dcnn-based knowledge distillation framework for human activity recognition. J Imaging. 2023;9(4):82.","journal-title":"J Imaging"},{"key":"112_CR4","doi-asserted-by":"publisher","first-page":"5573","DOI":"10.1109\/TIP.2021.3086590","volume":"30","author":"Y Liu","year":"2021","unstructured":"Liu Y, Wang K, Li G, Lin L. Semantics-aware adaptive knowledge distillation for sensor-to-vision action recognition. IEEE Trans Image Process. 2021;30:5573\u201388. https:\/\/doi.org\/10.1109\/TIP.2021.3086590.","journal-title":"IEEE Trans Image Process"},{"key":"112_CR5","doi-asserted-by":"publisher","unstructured":"Ni J, Sarbajna R, Liu Y, Ngu AHH, Yan Y. Cross-modal knowledge distillation for vision-to-sensor action recognition. In: ICASSP 2022\u20142022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4448\u20134452. 2022. https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9746752","DOI":"10.1109\/ICASSP43922.2022.9746752"},{"key":"112_CR6","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-63195-5","author":"Z Yuan","year":"2024","unstructured":"Yuan Z, Yang Z, Ning H, Tang X. Multiscale knowledge distillation with attention based fusion for robust human activity recognition. Sci Rep. 2024. https:\/\/doi.org\/10.1038\/s41598-024-63195-5.","journal-title":"Sci Rep"},{"issue":"11","key":"112_CR7","doi-asserted-by":"publisher","first-page":"6318","DOI":"10.1109\/JBHI.2023.3298932","volume":"28","author":"S Deng","year":"2024","unstructured":"Deng S, Chen J, Teng D, Yang C, Chen D, Jia T, et al. Lhar: lightweight human activity recognition on knowledge distillation. IEEE J Biomed Health Inform. 2024;28(11):6318\u201328. https:\/\/doi.org\/10.1109\/JBHI.2023.3298932.","journal-title":"IEEE J Biomed Health Inform"},{"key":"112_CR8","doi-asserted-by":"publisher","DOI":"10.3390\/s23010006","author":"G Gad","year":"2023","unstructured":"Gad G, Fadlullah Z. Federated learning via augmented knowledge distillation for heterogenous deep human activity recognition systems. Sensors. 2023. https:\/\/doi.org\/10.3390\/s23010006.","journal-title":"Sensors."},{"issue":"10","key":"112_CR9","doi-asserted-by":"publisher","first-page":"4334","DOI":"10.1109\/TII.2018.2789925","volume":"14","author":"Z Chen","year":"2018","unstructured":"Chen Z, Zhang L, Cao Z, Guo J. Distilling the knowledge from handcrafted features for human activity recognition. IEEE Trans Industr Inf. 2018;14(10):4334\u201342. https:\/\/doi.org\/10.1109\/TII.2018.2789925.","journal-title":"IEEE Trans Industr Inf"},{"issue":"11","key":"112_CR10","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, et al. Generative adversarial networks. Commun ACM. 2020;63(11):139\u201344.","journal-title":"Commun ACM"},{"key":"112_CR11","unstructured":"Tan M, Le Q. Efficientnet: Rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114, 2019. PMLR"},{"key":"112_CR12","unstructured":"Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations 2015."},{"key":"112_CR13","unstructured":"Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448\u2013456. 2015. PMLR"},{"key":"112_CR14","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778. 2016.","DOI":"10.1109\/CVPR.2016.90"},{"key":"112_CR15","unstructured":"McMahan B, Moore E, Ramage D, Hampson S, Arcas BA. Communication-efficient learning of deep networks from decentralized data. In: Artificial Intelligence and Statistics, pp. 1273\u20131282. 2017. PMLR"},{"key":"112_CR16","doi-asserted-by":"publisher","unstructured":"Ni J, Ngu AHH, Yan Y. Progressive cross-modal knowledge distillation for human action recognition. In: Proceedings of the 30th ACM International Conference on Multimedia. MM \u201922, pp. 5903\u20135912. Association for Computing Machinery, New York, NY, USA. 2022. https:\/\/doi.org\/10.1145\/3503161.3548238","DOI":"10.1145\/3503161.3548238"},{"issue":"8","key":"112_CR17","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput. 1997;9(8):1735\u201380. https:\/\/doi.org\/10.1162\/neco.1997.9.8.1735.","journal-title":"Neural Comput"},{"key":"112_CR18","doi-asserted-by":"publisher","unstructured":"Sharma D, Roy A, Bag SP, Singh PK, Badr Y. In: Rivera, G., Rosete, A., Dorronsoro, B., Rangel-Valdez, N. (eds.) A hybrid deep learning-based approach for human activity recognition using wearable sensors, pp. 231\u2013259. Springer, Cham. 2023. https:\/\/doi.org\/10.1007\/978-3-031-40688-1_11","DOI":"10.1007\/978-3-031-40688-1_11"},{"issue":"6","key":"112_CR19","doi-asserted-by":"publisher","first-page":"393","DOI":"10.3390\/bios12060393","volume":"12","author":"D Bhattacharya","year":"2022","unstructured":"Bhattacharya D, Sharma D, Kim W, Ijaz MF, Singh PK. Ensem-har: an ensemble deep learning model for smartphone sensor-based human activity recognition for measurement of elderly health monitoring. Biosensors. 2022;12(6):393.","journal-title":"Biosensors"},{"issue":"1","key":"112_CR20","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1007\/s11036-023-02117-7","volume":"29","author":"M Mallik","year":"2024","unstructured":"Mallik M, Sarkar G, Chowdhury C. A deep learning framework for smartphone based human activity recognition. Mob Netwo Appl. 2024;29(1):29\u201341.","journal-title":"Mob Netwo Appl"},{"key":"112_CR21","doi-asserted-by":"publisher","unstructured":"Kalimuthu S, Perumal T, Yaakob R, Marlisah E, Babangida L. Human activity recognition based on smart home environment and their applications, challenges. In: 2021 International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE), pp. 815\u2013819. 2021. https:\/\/doi.org\/10.1109\/ICACITE51222.2021.9404753","DOI":"10.1109\/ICACITE51222.2021.9404753"},{"key":"112_CR22","doi-asserted-by":"publisher","unstructured":"Natani A, Sharma A, Peruma T, Sukhavasi S. Deep learning for multi-resident activity recognition in ambient sensing smart homes. In: 2019 IEEE 8th Global Conference on Consumer Electronics (GCCE), pp. 340\u2013341. 2019. https:\/\/doi.org\/10.1109\/GCCE46687.2019.9015212","DOI":"10.1109\/GCCE46687.2019.9015212"},{"issue":"2","key":"112_CR23","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1109\/72.279188","volume":"5","author":"JT Connor","year":"1994","unstructured":"Connor JT, Martin RD, Atlas LE. Recurrent neural networks and robust time series prediction. IEEE Trans Neural Netw. 1994;5(2):240\u201354.","journal-title":"IEEE Trans Neural Netw"},{"key":"112_CR24","doi-asserted-by":"publisher","unstructured":"Perumal T, Chui YL, Ahmadon MAB, Yamaguchi S. Iot based activity recognition among smart home residents. In: 2017 IEEE 6th Global Conference on Consumer Electronics (GCCE), pp. 1\u20132. 2017. https:\/\/doi.org\/10.1109\/GCCE.2017.8229478","DOI":"10.1109\/GCCE.2017.8229478"},{"key":"112_CR25","unstructured":"Bayes T. Naive bayes classifier. Article Sources and Contributors, 1\u20139. 1968"},{"key":"112_CR26","doi-asserted-by":"publisher","unstructured":"Perez-Cruz F. Kullback\u2013leibler divergence estimation of continuous distributions. In: 2008 IEEE International Symposium on Information Theory, pp. 1666\u20131670. 2008. https:\/\/doi.org\/10.1109\/ISIT.2008.4595271","DOI":"10.1109\/ISIT.2008.4595271"},{"key":"112_CR27","unstructured":"Anguita D, Ghio A, Oneto L, Parra X, Reyes-Ortiz JL. A public domain dataset for human activity recognition using smartphones. In: The European Symposium on Artificial Neural Networks. 2013. https:\/\/api.semanticscholar.org\/CorpusID:6975432"},{"issue":"2","key":"112_CR28","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1145\/1964897.1964918","volume":"12","author":"JR Kwapisz","year":"2011","unstructured":"Kwapisz JR, Weiss GM, Moore SA. Activity recognition using cell phone accelerometers. SIGKDD Explor Newsl. 2011;12(2):74\u201382. https:\/\/doi.org\/10.1145\/1964897.1964918.","journal-title":"SIGKDD Explor Newsl"},{"key":"112_CR29","doi-asserted-by":"crossref","unstructured":"Ba\u00f1os O, Garc\u00eda R, Terriza JAH, Damas M, Pomares H, Rojas I, Saez A, Villalonga C. mhealthdroid: a novel framework for agile development of mobile health applications. In: International Workshop on Ambient Assisted Living and Home Care. 2014. https:\/\/api.semanticscholar.org\/CorpusID:9757468","DOI":"10.1007\/978-3-319-13105-4_14"},{"key":"112_CR30","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778. 2016.","DOI":"10.1109\/CVPR.2016.90"},{"issue":"6","key":"112_CR31","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Commun ACM. 2017;60(6):84\u201390. https:\/\/doi.org\/10.1145\/3065386.","journal-title":"Commun ACM"},{"key":"112_CR32","doi-asserted-by":"crossref","unstructured":"Friedman JH. Greedy function approximation: a gradient boosting machine. Ann Stat. 1189\u20131232. 2001.","DOI":"10.1214\/aos\/1013203451"},{"issue":"2","key":"112_CR33","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1023\/A:1009715923555","volume":"2","author":"CJ Burges","year":"1998","unstructured":"Burges CJ. A tutorial on support vector machines for pattern recognition. Data Min Knowl Disc. 1998;2(2):121\u201367.","journal-title":"Data Min Knowl Disc"},{"key":"112_CR34","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L. Random forests. Mach Learn. 2001;45:5\u201332.","journal-title":"Mach Learn"},{"key":"112_CR35","doi-asserted-by":"publisher","unstructured":"Haifley T. Linear logistic regression: an introduction. In: IEEE International Integrated Reliability Workshop Final Report, 2002., pp. 184\u2013187. 2002. https:\/\/doi.org\/10.1109\/IRWS.2002.1194264","DOI":"10.1109\/IRWS.2002.1194264"},{"issue":"1","key":"112_CR36","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1186\/s40537-024-00973-y","volume":"11","author":"RK Halder","year":"2024","unstructured":"Halder RK, Uddin MN, Uddin MA, Aryal S, Khraisat A. Enhancing k-nearest neighbor algorithm: a comprehensive review and performance analysis of modifications. J Big Data. 2024;11(1):113.","journal-title":"J Big Data"},{"key":"112_CR37","doi-asserted-by":"publisher","unstructured":"Lu Y, Ye T, Zheng J. Decision tree algorithm in machine learning. In: 2022 IEEE International Conference on Advances in Electrical Engineering and Computer Applications (AEECA), pp. 1014\u20131017. 2022. https:\/\/doi.org\/10.1109\/AEECA55500.2022.9918857","DOI":"10.1109\/AEECA55500.2022.9918857"},{"issue":"18","key":"112_CR38","doi-asserted-by":"publisher","first-page":"10121","DOI":"10.1016\/j.jfranklin.2021.10.005","volume":"358","author":"X Ding","year":"2021","unstructured":"Ding X, Liu J, Yang F, Cao J. Random radial basis function kernel-based support vector machine. J Franklin Inst. 2021;358(18):10121\u201340. https:\/\/doi.org\/10.1016\/j.jfranklin.2021.10.005.","journal-title":"J Franklin Inst"},{"issue":"1","key":"112_CR39","first-page":"7316954","volume":"2018","author":"Y Zhao","year":"2018","unstructured":"Zhao Y, Yang R, Chevalier G, Xu X, Zhang Z. Deep residual bidir-lstm for human activity recognition using wearable sensors. Math Probl Eng. 2018;2018(1):7316954.","journal-title":"Math Probl Eng"},{"key":"112_CR40","doi-asserted-by":"publisher","unstructured":"Sikder N, Chowdhury MS, Arif ASM, Nahid A-A. Human activity recognition using multichannel convolutional neural network. In: 2019 5th International Conference on Advances in Electrical Engineering (ICAEE), pp. 560\u2013565. 2019. https:\/\/doi.org\/10.1109\/ICAEE48663.2019.8975649","DOI":"10.1109\/ICAEE48663.2019.8975649"},{"issue":"1","key":"112_CR41","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1007\/s42486-020-00026-2","volume":"2","author":"F Cruciani","year":"2020","unstructured":"Cruciani F, Vafeiadis A, Nugent C, Cleland I, McCullagh P, Votis K, et al. Feature learning for human activity recognition using convolutional neural networks: A case study for inertial measurement unit and audio data. CCF Trans Pervasive Comput Inter. 2020;2(1):18\u201332.","journal-title":"CCF Trans Pervasive Comput Inter"},{"key":"112_CR42","doi-asserted-by":"publisher","first-page":"68985","DOI":"10.1109\/ACCESS.2021.3078184","volume":"9","author":"M Ronald","year":"2021","unstructured":"Ronald M, Poulose A, Han DS. isplinception: An inception-resnet deep learning architecture for human activity recognition. IEEE Access. 2021;9:68985\u20139001. https:\/\/doi.org\/10.1109\/ACCESS.2021.3078184.","journal-title":"IEEE Access"},{"key":"112_CR43","doi-asserted-by":"crossref","unstructured":"Dhanasekaran P, Geetha AV, Mala T. Fusednet: A fusion of time series and imaging based human activity recognition using resnet. In: Pati B, Panigrahi CR, Mohapatra P, Li KC (eds.) Proceedings of the 7th International Conference on Advance Computing and Intelligent Engineering, pp. 411\u2013422. Springer, Singapore; 2024.","DOI":"10.1007\/978-981-99-5015-7_35"},{"key":"112_CR44","unstructured":"Seelwal P, Prasad N A, Srinivas C, V S R. Human activity recognition using wisdom datasets. J Online Eng Educ 2023;14(1s), 88\u201394. https:\/\/doi.org\/10.52783\/joee.v14i1s.92"},{"key":"112_CR45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/JTEHM.2022.3177710","volume":"10","author":"MA Khatun","year":"2022","unstructured":"Khatun MA, Yousuf MA, Ahmed S, Uddin MZ, Alyami SA, Al-Ashhab S, et al. Deep cnn-lstm with self-attention model for human activity recognition using wearable sensor. IEEE J Transl Eng Health Med. 2022;10:1\u201316. https:\/\/doi.org\/10.1109\/JTEHM.2022.3177710.","journal-title":"IEEE J Transl Eng Health Med"},{"issue":"1","key":"112_CR46","doi-asserted-by":"publisher","first-page":"30979","DOI":"10.1038\/s41598-024-82045-y","volume":"14","author":"NA Chandramouli","year":"2024","unstructured":"Chandramouli NA, Natarajan S, Alharbi AH, Kannan S, Khafaga DS, Raju SK, et al. Enhanced human activity recognition in medical emergencies using a hybrid deep cnn and bi-directional lstm model with wearable sensors. Sci Rep. 2024;14(1):30979.","journal-title":"Sci Rep"}],"container-title":["Human-Centric Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44230-025-00112-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44230-025-00112-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44230-025-00112-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T09:09:03Z","timestamp":1765962543000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44230-025-00112-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":46,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["112"],"URL":"https:\/\/doi.org\/10.1007\/s44230-025-00112-7","relation":{},"ISSN":["2667-1336"],"issn-type":[{"value":"2667-1336","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"3 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 September 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 October 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 October 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that there is no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"NA","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"NA","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"All authors have given their consent.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}]}}