{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T15:05:50Z","timestamp":1773155150916,"version":"3.50.1"},"reference-count":28,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2016,11,24]],"date-time":"2016-11-24T00:00:00Z","timestamp":1479945600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"DGIST Faculty Start-up Fund","award":["2016010060"],"award-info":[{"award-number":["2016010060"]}]},{"name":"Basic Research Program through the National Research Foundation of Korea","award":["2016R1C1B2012170"],"award-info":[{"award-number":["2016R1C1B2012170"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Accurate classification of human aquatic activities using radar has a variety of potential applications such as rescue operations and border patrols. Nevertheless, the classification of activities on water using radar has not been extensively studied, unlike the case on dry ground, due to its unique challenge. Namely, not only is the radar cross section of a human on water small, but the micro-Doppler signatures are much noisier due to water drops and waves. In this paper, we first investigate whether discriminative signatures could be obtained for activities on water through a simulation study. Then, we show how we can effectively achieve high classification accuracy by applying deep convolutional neural networks (DCNN) directly to the spectrogram of real measurement data. From the five-fold cross-validation on our dataset, which consists of five aquatic activities, we report that the conventional feature-based scheme only achieves an accuracy of 45.1%. In contrast, the DCNN trained using only the collected data attains 66.7%, and the transfer learned DCNN, which takes a DCNN pre-trained on a RGB image dataset and fine-tunes the parameters using the collected data, achieves a much higher 80.3%, which is a significant performance boost.<\/jats:p>","DOI":"10.3390\/s16121990","type":"journal-article","created":{"date-parts":[[2016,11,24]],"date-time":"2016-11-24T10:19:15Z","timestamp":1479982755000},"page":"1990","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":107,"title":["Micro-Doppler Based Classification of Human Aquatic Activities via Transfer Learning of Convolutional Neural Networks"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3612-203X","authenticated-orcid":false,"given":"Jinhee","family":"Park","sequence":"first","affiliation":[{"name":"Department of Information and Communication Engineering, Daegu-Gyeongbuk Institute of Science and Technology (DGIST), Daegu 42988, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rios","family":"Javier","sequence":"additional","affiliation":[{"name":"School of Electronics Technology, ITT Technical Institute, Clovis, CA 93612, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taesup","family":"Moon","sequence":"additional","affiliation":[{"name":"Department of Information and Communication Engineering, Daegu-Gyeongbuk Institute of Science and Technology (DGIST), Daegu 42988, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youngwook","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Lyles College of Engineerning, California State University, Fresno, CA 93740, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2016,11,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1109\/45.645833","article-title":"Motion detector radar for law enforcement","volume":"16","author":"Frazier","year":"1998","journal-title":"IEEE Potentials"},{"key":"ref_2","unstructured":"Greneker, E.F. (1998, January 13\u201315). Radar flashlight for through the wall detection of humans. Proceedings of the SPIE-Targets and Backgrounds: Characterization and Representation IV, Orlando, FL, USA."},{"key":"ref_3","first-page":"8","article-title":"High-resolution Doppler model of the human gait","volume":"4744","author":"Geisheimer","year":"2002","journal-title":"SPIE Proc. Radar Sens. Technol. Data Vis."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"356","DOI":"10.1049\/ip-rsn:20030568","article-title":"Human walking estimation with radar","volume":"150","author":"Groen","year":"2003","journal-title":"IEE Proc. Radar Sonar Navig."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1140","DOI":"10.1049\/iet-rsn.2015.0118","article-title":"Review of micro-Doppler signatures","volume":"9","author":"Tahmoush","year":"2015","journal-title":"IET Radar Sonar Navig."},{"key":"ref_6","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_7","doi-asserted-by":"crossref","first-page":"1831","DOI":"10.1109\/LGRS.2014.2311819","article-title":"Application of linear predictive coding for human activity classification based on micro-Doppler signatures","volume":"11","author":"Rios","year":"2014","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1109\/TAES.2012.6129657","article-title":"Minimum divergence approaches for robust classification of ground moving targets","volume":"48","author":"Bilik","year":"2012","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1017\/S1759078713000366","article-title":"Human motion classification using a particle filter approach: Multiple model particle filtering applied to micro-Doppler spectrum","volume":"5","author":"Groot","year":"2013","journal-title":"Int. J. Microw. Wirel. Technol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1186\/1687-6180-2013-61","article-title":"Classification of ground moving targets using bicepstrum-based features extracted from micro-Doppler radar signatures","volume":"2013","author":"Molchanov","year":"2013","journal-title":"EURASIP J. Adv. Signal Process."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1109\/TAES.2014.130762","article-title":"A novel algorithm for radar classification based on Doppler characteristics exploiting orthogonal pseudo-zernike polynomials","volume":"51","author":"Clemente","year":"2015","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"725","DOI":"10.1109\/LGRS.2016.2539386","article-title":"Performance analysis of centroid and SVD features for personnel recognition using multistatic micro-Doppler","volume":"13","author":"Fioranelli","year":"2016","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Kim, Y., and Moon, T. (2016). Classification of human activity on water through micro-Dopplers using deep convolutional neural networks. Proc. SPIE 9829 Radar Sens. Technol. XX, 9829.","DOI":"10.1117\/12.2224196"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","article-title":"Deep neural networks for acoustic modeling in speech recognition","volume":"29","author":"Hinton","year":"2012","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_15","first-page":"1090","article-title":"ImageNet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Mikolov, T., Deoras, A., Povey, D., Burget, L., and Cernocky, J. (2011, January 11\u201315). Strategies for training large scale neural network language models. Proceedings of the 2011 IEEE Workshop on Automatic Speech Recognition and Understanding, Waikoloa, HI, USA.","DOI":"10.1109\/ASRU.2011.6163930"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1109\/LGRS.2015.2491329","article-title":"Human detection and activity classification based on micro-Dopplers using deep convolutional neural networks","volume":"13","author":"Kim","year":"2016","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Jokanovic, B., Amin, M., and Ahmad, F. (2016). Radar fall motion detection using deep learning. IEEE Radar Conf., 1\u20136.","DOI":"10.1109\/RADAR.2016.7485147"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"982509","DOI":"10.1117\/12.2227947","article-title":"Using convolutional neural networks for human activity classification on micro-Doppler radar spectrograms","volume":"9825","author":"Jordan","year":"2016","journal-title":"Proc. SPIE"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"ImageNet Large Scale Visual Recognition Challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int. J. Comput. Vis."},{"key":"ref_21","unstructured":"Ram, S., and Ling, H. (2008, January 26\u201330). Simulation of human micro-Dopplers using computer animation data. Proceedings of the IEEE Radar Conference, Rome, Italy."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_23","unstructured":"Simonyan, K., and Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. arXiv.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A Survey on Transfer Learning","volume":"22","author":"Pan","year":"2010","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Karayev, S., Trentacoste, M., Han, H., Agarwala, A., Darrell, T., hertzmann, A., and Winnemoeller, H. (2014). Recognizing image style. arXiv.","DOI":"10.5244\/C.28.122"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1109\/LGRS.2015.2499239","article-title":"Deep learning earth observation classification using ImageNet pretrained networks","volume":"13","author":"Marmanis","year":"2016","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., and Darrell, T. (2014). Caffe: Convolutional architecture for fast feature embedding. arXiv.","DOI":"10.1145\/2647868.2654889"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/16\/12\/1990\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T19:27:23Z","timestamp":1760210843000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/16\/12\/1990"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,11,24]]},"references-count":28,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2016,12]]}},"alternative-id":["s16121990"],"URL":"https:\/\/doi.org\/10.3390\/s16121990","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,11,24]]}}}