{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T16:06:20Z","timestamp":1771862780732,"version":"3.50.1"},"reference-count":36,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T00:00:00Z","timestamp":1693180800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Deep learning architectures are being increasingly adopted for human activity recognition using radar technology. A majority of these architectures are based on convolutional neural networks (CNNs) and accept radar micro-Doppler signatures as input. The state-of-the-art CNN-based models employ batch normalization (BN) to optimize network training and improve generalization. In this paper, we present whitening-aided CNN models for classifying human activities with radar sensors. We replace BN layers in a CNN model with whitening layers, which is shown to improve the model\u2019s accuracy by not only centering and scaling activations, similar to BN, but also decorrelating them. We also exploit the rotational freedom afforded by whitening matrices to align the whitened activations in the latent space with the corresponding activity classes. Using real data measurements of six different activities, we show that whitening provides superior performance over BN in terms of classification accuracy for a CNN-based classifier. This demonstrates the potential of whitening-aided CNN models to provide enhanced human activity recognition with radar sensors.<\/jats:p>","DOI":"10.3390\/s23177486","type":"journal-article","created":{"date-parts":[[2023,8,29]],"date-time":"2023-08-29T08:59:05Z","timestamp":1693299545000},"page":"7486","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Whitening-Aided Learning from Radar Micro-Doppler Signatures for Human Activity Recognition"],"prefix":"10.3390","volume":"23","author":[{"given":"Zahra","family":"Sadeghi Adl","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Temple University, Philadelphia, PA 19122, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1446-5154","authenticated-orcid":false,"given":"Fauzia","family":"Ahmad","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Temple University, Philadelphia, PA 19122, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,8,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1049\/iet-rsn.2015.0038","article-title":"Application of radar to remote patient monitoring and eldercare","volume":"9","author":"Ahmad","year":"2015","journal-title":"IET Radar Sonar Navig."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1109\/MSP.2016.2514718","article-title":"Signal processing for assisted living: Developments and open problems [From the Guest Editors]","volume":"33","author":"Ahmad","year":"2016","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_3","unstructured":"Fioranelli, F., and Le Kernec, J. (November, January 31). Radar sensing for human healthcare: Challenges and results. Proceedings of the IEEE Sensors Conference, Virtual."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1109\/JERM.2019.2893587","article-title":"Adaptive radar-based human activity recognition with L1-norm linear discriminant analysis","volume":"3","author":"Markopoulos","year":"2019","journal-title":"IEEE J. Electromagn. RF Microwaves Med. Biol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1109\/MSP.2015.2502784","article-title":"Radar signal processing for elderly fall detection: The future for in-home monitoring","volume":"33","author":"Amin","year":"2016","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1016\/j.gaitpost.2021.01.021","article-title":"The accuracy and predictability of micro Doppler radar signature projection algorithm measuring functional movement in NCAA athletes","volume":"85","author":"Onks","year":"2021","journal-title":"Gait Posture"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1109\/MSP.2019.2903715","article-title":"Radar signal processing for sensing in assisted living: The challenges associated with real-time implementation of emerging algorithms","volume":"36","author":"Fioranelli","year":"2019","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"554","DOI":"10.1109\/TAP.2018.2878081","article-title":"Freezing of gait detection considering leaky wave cable","volume":"67","author":"Yang","year":"2019","journal-title":"IEEE Trans. Antennas Propag."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/j.smhl.2022.100334","article-title":"Gait variability analysis using continuous RF data streams of human activity","volume":"26","author":"Gurbuz","year":"2022","journal-title":"Smart Health"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Jang, M.h., Kang, S.w., and Lee, S. (2022, January 21\u201325). Monitoring person on bed using millimeter-wave radar sensor. Proceedings of the IEEE Radar Conference, New York, NY, USA.","DOI":"10.1109\/RadarConf2248738.2022.9764251"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Lenz, I., Rong, Y., and Bliss, D. (2023). Contactless stethoscope enabled by radar technology. Bioengineering, 10.","DOI":"10.3390\/bioengineering10020169"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1709","DOI":"10.1109\/TAES.2018.2799758","article-title":"Deep convolutional autoencoder for radar-based classification of similar aided and unaided human activities","volume":"54","year":"2018","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1109\/MSP.2018.2890128","article-title":"Radar-based human-motion recognition with deep learning: Promising applications for indoor monitoring","volume":"36","author":"Gurbuz","year":"2019","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"55336","DOI":"10.1109\/ACCESS.2019.2907925","article-title":"CapsFall: Fall detection using ultra-wideband radar and capsule network","volume":"7","author":"Sadreazami","year":"2019","journal-title":"IEEE Access"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1016\/j.dsp.2019.01.013","article-title":"Human motion recognition exploiting radar with stacked recurrent neural network","volume":"87","author":"Wang","year":"2019","journal-title":"Digit. Signal Process."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1951","DOI":"10.3390\/s21061951","article-title":"Application of deep learning on millimeter-wave radar signals: A review","volume":"21","author":"Abdu","year":"2021","journal-title":"Sensors"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Li, X., He, Y., and Jing, X. (2019). A survey of deep learning-based human activity recognition in radar. Remote Sens., 11.","DOI":"10.3390\/rs11091068"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"13364","DOI":"10.1109\/JSEN.2020.3006918","article-title":"A Millimetre-Wave Radar-Based Fall Detection Method Using Line Kernel Convolutional Neural Network","volume":"20","author":"Wang","year":"2020","journal-title":"IEEE Sens. J."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Erol, B., Gurbuz, S.Z., and Amin, M.G. (2018, January 28\u201331). Frequency-warped cepstral heatmaps for deep learning of human motion signatures. Proceedings of the 52nd Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA, USA.","DOI":"10.1109\/ACSSC.2018.8645178"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Le, H.T., Phung, S.L., Bouzerdoum, A., and Tivive, F.H.C. (2018, January 15\u201320). Human Motion Classification with Micro-Doppler Radar and Bayesian-Optimized Convolutional Neural Networks. Proceedings of the 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, AB, Canada.","DOI":"10.1109\/ICASSP.2018.8461847"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Campbell, C., and Ahmad, F. (2020, January 28\u201330). Attention-Augmented Convolutional Autoencoder for Radar-Based Human Activity Recognition. Proceedings of the IEEE International Radar Conference, Washington, DC, USA.","DOI":"10.1109\/RADAR42522.2020.9114787"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Vishwakarma, S., Li, W., Adve, R., and Chetty, K. (2022, January 24\u201327). Learning salient features in radar micro-Doppler signatures using Attention Enhanced Alexnet. Proceedings of the International Conference on Radar Systems, Edinburgh, UK.","DOI":"10.1049\/icp.2022.2314"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"24713","DOI":"10.1109\/ACCESS.2020.2971064","article-title":"A hybrid CNN\u2013LSTM network for the classification of human activities based on micro-Doppler radar","volume":"8","author":"Zhu","year":"2020","journal-title":"IEEE Access"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Yang, X., Guendel, R.G., Yarovoy, A., and Fioranelli, F. (2022, January 21\u201325). Radar-based human activities classification with complex-valued neural networks. Proceedings of the IEEE Radar Conference, New York, NY, USA.","DOI":"10.1109\/RadarConf2248738.2022.9763903"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"24509","DOI":"10.1109\/ACCESS.2022.3150838","article-title":"Multi-view CNN-LSTM architecture for radar-based human activity recognition","volume":"10","author":"Khalid","year":"2022","journal-title":"IEEE Access"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"17262","DOI":"10.1109\/JSEN.2021.3077511","article-title":"An mmwave radar based real-time contactless fitness tracker using deep CNNs","volume":"21","author":"Tiwari","year":"2021","journal-title":"IEEE Sensors J."},{"key":"ref_27","unstructured":"Ioffe, S., and Szegedy, C. (2015, January 6\u201311). Batch normalization: Accelerating deep network training by reducing internal covariate shift. Proceedings of the 32nd International Conference on Machine Learning, Lille, France."},{"key":"ref_28","unstructured":"Santurkar, S., Tsipras, D., Ilyas, A., and Madry, A. (2018, January 3\u20138). How does batch normalization help optimization?. Proceedings of the International Conference on Neural Information Processing Systems, Montreal, QC, Canada."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Huang, L., Yang, D., Lang, B., and Deng, J. (2018, January 18\u201323). Decorrelated batch normalization. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00089"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Huang, L., Zhou, Y., Zhu, F., Liu, L., and Shao, L. (2019, January 15\u201320). Iterative normalization: Beyond standardization towards efficient whitening. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00501"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"772","DOI":"10.1038\/s42256-020-00265-z","article-title":"Concept whitening for interpretable image recognition","volume":"2","author":"Chen","year":"2020","journal-title":"Nat. Mach. Intell."},{"key":"ref_32","unstructured":"Chen, W., and Griswold, N. (1994, January 25\u201328). An efficient recursive time-varying Fourier transform by using a half-sine wave window. Proceedings of the IEEE-SP International Symposium on Time-Frequency and Time-Scale Analysis, Philadelphia, PA, USA."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1080\/00031305.2016.1277159","article-title":"Optimal Whitening and Decorrelation","volume":"72","author":"Kessy","year":"2018","journal-title":"Am. Stat."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"397","DOI":"10.1007\/s10107-012-0584-1","article-title":"A feasible method for optimization with orthogonality constraints","volume":"142","author":"Wen","year":"2013","journal-title":"Math. Program."},{"key":"ref_35","unstructured":"O\u2019Shea, K., and Nash, R. (2015). An introduction to convolutional neural networks. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1022","DOI":"10.1049\/el.2019.2378","article-title":"Radar sensing for healthcare","volume":"55","author":"Fioranelli","year":"2019","journal-title":"Electron. Lett."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/17\/7486\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:41:19Z","timestamp":1760128879000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/17\/7486"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,28]]},"references-count":36,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2023,9]]}},"alternative-id":["s23177486"],"URL":"https:\/\/doi.org\/10.3390\/s23177486","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,28]]}}}