{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T16:32:26Z","timestamp":1776357146654,"version":"3.51.2"},"reference-count":30,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2023,3,16]],"date-time":"2023-03-16T00:00:00Z","timestamp":1678924800000},"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>Radar-based human activity recognition (HAR) provides a non-contact method for many scenarios, such as human\u2013computer interaction, smart security, and advanced surveillance with privacy protection. Feeding radar-preprocessed micro-Doppler signals into a deep learning (DL) network is a promising approach for HAR. Conventional DL algorithms can achieve high performance in terms of accuracy, but the complex network structure causes difficulty for their real-time embedded application. In this study, an efficient network with an attention mechanism is proposed. This network decouples the Doppler and temporal features of radar preprocessed signals according to the feature representation of human activity in the time\u2013frequency domain. The Doppler feature representation is obtained in sequence using the one-dimensional convolutional neural network (1D CNN) following the sliding window. Then, HAR is realized by inputting the Doppler features into the attention-mechanism-based long short-term memory (LSTM) as a time sequence. Moreover, the activity features are effectively enhanced using the averaged cancellation method, which improves the clutter suppression effect under the micro-motion conditions. Compared with the traditional moving target indicator (MTI), the recognition accuracy is improved by about 3.7%. Experiments based on two human activity datasets confirm the superiority of our method compared to traditional methods in terms of expressiveness and computational efficiency. Specifically, our method achieves an accuracy close to 96.9% on both datasets and has a more lightweight network structure compared to algorithms with similar recognition accuracy. The method proposed in this article has great potential for real-time embedded applications of HAR.<\/jats:p>","DOI":"10.3390\/s23063185","type":"journal-article","created":{"date-parts":[[2023,3,17]],"date-time":"2023-03-17T02:59:26Z","timestamp":1679021966000},"page":"3185","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":35,"title":["Radar Human Activity Recognition with an Attention-Based Deep Learning Network"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9883-7508","authenticated-orcid":false,"given":"Sha","family":"Huan","sequence":"first","affiliation":[{"name":"School of Electronics and Communication Engineering, Guangzhou University, Guangzhou 510006, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0299-0864","authenticated-orcid":false,"given":"Limei","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Guangzhou University, Guangzhou 510006, China"}]},{"given":"Man","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Guangzhou University, Guangzhou 510006, China"}]},{"given":"Zhaoyue","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Guangzhou University, Guangzhou 510006, China"}]},{"given":"Chao","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Guangzhou University, Guangzhou 510006, China"}]}],"member":"1968","published-online":{"date-parts":[[2023,3,16]]},"reference":[{"key":"ref_1","unstructured":"Zhang, B., Xu, G., Zhou, R., Zhang, H., and Hong, W. (2022). IEEE Journal of Selected Topics in Signal Processing, IEEE."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1328","DOI":"10.1109\/TGRS.2009.2012849","article-title":"Human Activity Classification Based on Micro-Doppler Signatures Using a Support Vector Machine","volume":"47","author":"Kim","year":"2009","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1049\/iet-rsn.2013.0165","article-title":"Classification of human motions using empirical mode decomposition of human micro-Doppler signatures","volume":"8","author":"Fairchild","year":"2014","journal-title":"IET Radar Sonar Navig."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1289","DOI":"10.1007\/s12524-020-01155-y","article-title":"Flood Mapping Using Relevance Vector Machine and SAR Data: A Case Study from Aqqala, Iran","volume":"48","author":"Sharifi","year":"2020","journal-title":"J. Indian Soc. Remote Sens."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1109\/LGRS.2015.2491329","article-title":"Human Detection and Activity Classification Based on Micro-Doppler Signatures Using Deep Convolutional Neural Networks","volume":"13","author":"Kim","year":"2016","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"669","DOI":"10.1109\/LGRS.2018.2806940","article-title":"Personnel Recognition and Gait Classification Based on Multistatic Micro-Doppler Signatures Using Deep Convolutional Neural Networks","volume":"15","author":"Chen","year":"2018","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"25950","DOI":"10.1109\/JSEN.2021.3118836","article-title":"Human Activity Recognition Based on Mixed CNN With Radar Multi-Spectrogram","volume":"21","author":"Tang","year":"2021","journal-title":"IEEE Sens. J."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"12350","DOI":"10.1109\/JIOT.2021.3063504","article-title":"Lightweight Deep Learning Model in Mobile-Edge Computing for Radar-Based Human Activity Recognition","volume":"8","author":"Zhu","year":"2021","journal-title":"IEEE Internet Things J."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Hou, M., Shi, X., and Zhou, F. (2019, January 26\u201329). Pedestrian Gait Classification Based on Parallel Channel Identity Initialized Recurrent Neural Network. Proceedings of the 2019 6th Asia-Pacific Conference on Synthetic Aperture Radar (APSAR), Xiamen, China.","DOI":"10.1109\/APSAR46974.2019.9048541"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Sun, Y., Hang, R., Li, Z., Jin, M., and Xu, K. (2019, January 1\u20134). Privacy-Preserving Fall Detection with Deep Learning on mmWave Radar Signal. Proceedings of the 2019 IEEE Visual Communications and Image Processing (VCIP), Sydney, Australia.","DOI":"10.1109\/VCIP47243.2019.8965661"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1191","DOI":"10.1109\/JSEN.2019.2946095","article-title":"Bi-LSTM Network for Multimodal Continuous Human Activity Recognition and Fall Detection","volume":"20","author":"Li","year":"2020","journal-title":"IEEE Sens. J."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"13607","DOI":"10.1109\/JSEN.2020.3006386","article-title":"Continuous Human Activity Classification From FMCW Radar With Bi-LSTM Networks","volume":"20","author":"Shrestha","year":"2020","journal-title":"IEEE Sens. J."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Jiang, H., Fioranelli, F., Yang, S., Romain, O., and Le Kernec, J. (2020, January 4\u20136). Human activity classification using radar signal and RNN networks. Proceedings of the IET International Radar Conference (IET IRC 2020), Chongqing, China.","DOI":"10.1049\/icp.2021.0556"},{"key":"ref_14","unstructured":"Minto, M.R.I., Tan, B., Sharifzadeh, S., Riihonen, T., and Valkama, M. (2020, January 20\u201322). Shallow Neural Networks for mmWave Radar Based Recognition of Vulnerable Road Users. Proceedings of the 2020 12th International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP), Porto, Portugal."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1273","DOI":"10.1109\/JBHI.2020.3027967","article-title":"Fall Detection With UWB Radars and CNN-LSTM Architecture","volume":"25","author":"Maitre","year":"2021","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Yang, Z., Wang, H., Ni, P., Wang, P., Cao, Q., and Fang, L. (2021, January 1\u20134). Real-time Human Activity Classification From Radar With CNN-LSTM Network. Proceedings of the 2021 IEEE 16th Conference on Industrial Electronics and Applications (ICIEA), Chengdu, China.","DOI":"10.1109\/ICIEA51954.2021.9516401"},{"key":"ref_17","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_18","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_19","doi-asserted-by":"crossref","first-page":"5115215","DOI":"10.1109\/TGRS.2022.3189746","article-title":"Continuous Human Activity Recognition With Distributed Radar Sensor Networks and CNN\u2013RNN Architectures","volume":"60","author":"Zhu","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"120522","DOI":"10.1109\/ACCESS.2019.2929211","article-title":"Attention-Based Character-Word Hybrid Neural Networks With Semantic and Structural Information for Identifying of Urgent Posts in MOOC Discussion Forums","volume":"7","author":"Guo","year":"2019","journal-title":"IEEE Access"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1007\/s12524-021-01475-7","article-title":"Agricultural Field Extraction with Deep Learning Algorithm and Satellite Imagery","volume":"50","author":"Sharifi","year":"2022","journal-title":"J. Indian Soc. Remote Sens."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Wang, C., Chen, Z., Chen, X., Tang, X., and Liang, F. (2021, January 28\u201330). Detection of MMW Radar Target Based on Doppler Characteristics and Deep Learning. Proceedings of the 2021 IEEE International Conference on Artificial Intelligence and Industrial Design (AIID), Guangzhou, China.","DOI":"10.1109\/AIID51893.2021.9456497"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Campbell, C., and Ahmad, F. (2020, January 21\u201325). Attention-Augmented Convolutional Autoencoder for Radar-Based Human Activity Recognition. Proceedings of the 2020 IEEE International Radar Conference (RADAR), Florence, Italy.","DOI":"10.1109\/RADAR42522.2020.9114787"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"8648","DOI":"10.1109\/JSEN.2022.3156762","article-title":"Activity Classification Based on Feature Fusion of FMCW Radar Human Motion Micro-Doppler Signatures","volume":"22","author":"Abdu","year":"2022","journal-title":"IEEE Sens. J."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Hua, W., Wang, X., Zhang, C., and Jin, X. (2022, January 7\u201322). Attention-Based Deep Sequential Network for Polsar Image Classification. Proceedings of the IGARSS 2022\u20132022 IEEE International Geoscience and Remote Sensing Symposium, Kuala Lumpur, Malaysia.","DOI":"10.1109\/IGARSS46834.2022.9883634"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"3844","DOI":"10.1109\/JBHI.2021.3072644","article-title":"Attention-Based LSTM for Non-Contact Sleep Stage Classification Using IR-UWB Radar","volume":"25","author":"Kwon","year":"2021","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"2000","DOI":"10.1109\/LCOMM.2020.2995842","article-title":"Radar Emitter Classification With Attention-Based Multi-RNNs","volume":"24","author":"Li","year":"2020","journal-title":"IEEE Commun. Lett."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Xu, C., Li, Y., Ji, C., Huang, Y., Wang, H., and Xia, Y. (2017, January 6\u20139). An improved CFAR algorithm for target detection. Proceedings of the 2017 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), Xiamen, China.","DOI":"10.1109\/ISPACS.2017.8266600"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"4167","DOI":"10.1109\/JSEN.2018.2823588","article-title":"On the Application of Digital Moving Target Indication Techniques to Short-Range FMCW Radar Data","volume":"18","author":"Ash","year":"2018","journal-title":"IEEE Sens. J."},{"key":"ref_30","unstructured":"Fioranelli, F., and Le Kernec, J. (2021). Proceedings of the 2021 IEEE Sensors, Virtual Conference, 31 October\u20134 November 2021, IEEE."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/6\/3185\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:56:57Z","timestamp":1760122617000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/6\/3185"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,16]]},"references-count":30,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2023,3]]}},"alternative-id":["s23063185"],"URL":"https:\/\/doi.org\/10.3390\/s23063185","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,16]]}}}