{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:27:55Z","timestamp":1774538875722,"version":"3.50.1"},"reference-count":48,"publisher":"Association for Computing Machinery (ACM)","issue":"5s","license":[{"start":{"date-parts":[[2021,9,17]],"date-time":"2021-09-17T00:00:00Z","timestamp":1631836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSF CAREER","award":["CNS-2114499"],"award-info":[{"award-number":["CNS-2114499"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Embed. Comput. Syst."],"published-print":{"date-parts":[[2021,10,31]]},"abstract":"<jats:p>\n            Rehabilitation is a crucial process for patients suffering from motor disorders. The current practice is performing rehabilitation exercises under clinical expert supervision. New approaches are needed to allow patients to perform prescribed exercises at their homes and alleviate commuting requirements, expert shortages, and healthcare costs. Human joint estimation is a substantial component of these programs since it offers valuable visualization and feedback based on body movements. Camera-based systems have been popular for capturing joint motion. However, they have high-cost, raise serious privacy concerns, and require strict lighting and placement settings. We propose a millimeter-wave (mmWave)-based assistive rehabilitation system (MARS) for motor disorders to address these challenges. MARS provides a low-cost solution with a competitive object localization and detection accuracy. It first maps the 5D time-series point cloud from mmWave to a lower dimension. Then, it uses a convolution neural network (CNN) to estimate the accurate location of human joints. MARS can reconstruct 19 human joints and their skeleton from the point cloud generated by mmWave radar. We evaluate MARS using ten specific rehabilitation movements performed by four human subjects involving all body parts and obtain an average mean absolute error of 5.87 cm for all joint positions. To the best of our knowledge, this is the first rehabilitation movements dataset using mmWave point cloud. MARS is evaluated on the Nvidia Jetson Xavier-NX board. Model inference takes only 64\n            <jats:inline-formula>\n              <jats:alternatives>\n                <jats:tex-math>\n                  \n                <\/jats:tex-math>\n              <\/jats:alternatives>\n            <\/jats:inline-formula>\n            s and consumes 442\n            <jats:inline-formula>\n              <jats:alternatives>\n                <jats:tex-math>\n                  \n                <\/jats:tex-math>\n              <\/jats:alternatives>\n            <\/jats:inline-formula>\n            J energy. These results demonstrate the practicality of MARS on low-power edge devices.\n          <\/jats:p>","DOI":"10.1145\/3477003","type":"journal-article","created":{"date-parts":[[2021,9,17]],"date-time":"2021-09-17T18:36:51Z","timestamp":1631903811000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":90,"title":["MARS: mmWave-based Assistive Rehabilitation System for Smart Healthcare"],"prefix":"10.1145","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9211-4886","authenticated-orcid":false,"given":"Sizhe","family":"An","sequence":"first","affiliation":[{"name":"University of Wisconsin-Madison, USA"}]},{"given":"Umit Y.","family":"Ogras","sequence":"additional","affiliation":[{"name":"University of Wisconsin-Madison, USA"}]}],"member":"320","published-online":{"date-parts":[[2021,9,17]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"Mart\u00edn Abadi et\u00a0al. 2015. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. http:\/\/tensorflow.org\/Software available from tensorflow.org.  Mart\u00edn Abadi et\u00a0al. 2015. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. http:\/\/tensorflow.org\/Software available from tensorflow.org."},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1155\/2014\/617495"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parkreldis.2015.09.005"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.4218\/etrij.2017-0241"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818072"},{"key":"e_1_2_1_6_1","volume-title":"Proc. of Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. 1\u201311","author":"Rahman Ahad Md Atiqur","year":"2019","unstructured":"Md Atiqur Rahman Ahad , Anindya Das Antar , and Omar Shahid . 2019 . Vision-based action understanding for assistive healthcare: A short review . In Proc. of Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. 1\u201311 . Md Atiqur Rahman Ahad, Anindya Das Antar, and Omar Shahid. 2019. Vision-based action understanding for assistive healthcare: A short review. In Proc. of Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. 1\u201311."},{"key":"e_1_2_1_7_1","volume-title":"Prof. of The British Machine Vision Conference (BMVC). 332","author":"Antunes Jo\u00e3o","unstructured":"Jo\u00e3o Antunes , Alexandre Bernardino , Asim Smailagic , and Daniel P. Siewiorek . 2018. AHA-3D: A labelled dataset for senior fitness exercise recognition and segmentation from 3D skeletal data . In Prof. of The British Machine Vision Conference (BMVC). 332 . Jo\u00e3o Antunes, Alexandre Bernardino, Asim Smailagic, and Daniel P. Siewiorek. 2018. AHA-3D: A labelled dataset for senior fitness exercise recognition and segmentation from 3D skeletal data. In Prof. of The British Machine Vision Conference (BMVC). 332."},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2014.2326254"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2462830"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/MDAT.2019.2906110"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.3103\/S0735272711080061"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"e_1_2_1_13_1","unstructured":"Fran\u00e7ois Chollet et\u00a0al. 2015. Keras. https:\/\/keras.io.  Fran\u00e7ois Chollet et\u00a0al. 2015. Keras. https:\/\/keras.io."},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parkreldis.2011.10.011"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2009.2019584"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITB.2009.2028020"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.medengphy.2008.09.005"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_2_1_20_1","volume-title":"Realsense sensor. https:\/\/www.intelrealsense.com\/. accessed","year":"2020","unstructured":"Intel. 2014. Realsense sensor. https:\/\/www.intelrealsense.com\/. accessed 29 Sep. 2020 . Intel. 2014. Realsense sensor. https:\/\/www.intelrealsense.com\/. accessed 29 Sep. 2020."},{"key":"e_1_2_1_21_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2014","unstructured":"Diederik P. Kingma and Jimmy Ba . 2014 . Adam : A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_2_1_22_1","first-page":"173","article-title":"Six-month functional recovery of stroke patients: A multi-time-point study. Intl","volume":"38","author":"\u00a0al Kyoung Bo","year":"2015","unstructured":"Kyoung Bo Lee et \u00a0al . 2015 . Six-month functional recovery of stroke patients: A multi-time-point study. Intl . Journal of Rehabilitation Research. Internationale Zeitschrift fur Rehabilitationsforschung. Revue internationale de recherches de readaptation 38 , 2 (2015), 173 . Kyoung Bo Lee et\u00a0al. 2015. Six-month functional recovery of stroke patients: A multi-time-point study. Intl. Journal of Rehabilitation Research. Internationale Zeitschrift fur Rehabilitationsforschung. Revue internationale de recherches de readaptation 38, 2 (2015), 173.","journal-title":"Journal of Rehabilitation Research. Internationale Zeitschrift fur Rehabilitationsforschung. Revue internationale de recherches de readaptation"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2013.51"},{"key":"e_1_2_1_24_1","volume-title":"Proc. of Intl. Wireless Communications and Mobile Computing Conference. 1033\u20131038","author":"\u00a0al Filip Lemic","year":"2016","unstructured":"Filip Lemic et \u00a0al . 2016 . Localization as a feature of mmWave communication . In Proc. of Intl. Wireless Communications and Mobile Computing Conference. 1033\u20131038 . Filip Lemic et\u00a0al. 2016. Localization as a feature of mmWave communication. In Proc. of Intl. Wireless Communications and Mobile Computing Conference. 1033\u20131038."},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3432235"},{"key":"e_1_2_1_26_1","volume-title":"Proc. of AAAI Conference on Artificial Intelligence","volume":"34","author":"\u00a0al Zhen Meng","year":"2020","unstructured":"Zhen Meng et \u00a0al . 2020 . Gait recognition for co-existing multiple people using millimeter wave sensing . In Proc. of AAAI Conference on Artificial Intelligence , Vol. 34 . 849\u2013856. Zhen Meng et\u00a0al. 2020. Gait recognition for co-existing multiple people using millimeter wave sensing. In Proc. of AAAI Conference on Artificial Intelligence, Vol. 34. 849\u2013856."},{"key":"e_1_2_1_27_1","volume-title":"Kinect sensor. https:\/\/developer.microsoft.com\/en-us\/windows\/kinect\/. accessed","year":"2020","unstructured":"Microsoft. 2014. Kinect sensor. https:\/\/developer.microsoft.com\/en-us\/windows\/kinect\/. accessed 29 Sep. 2020 . Microsoft. 2014. Kinect sensor. https:\/\/developer.microsoft.com\/en-us\/windows\/kinect\/. accessed 29 Sep. 2020."},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/575491"},{"key":"e_1_2_1_29_1","volume-title":"Jetson Xavier NX Developer Kit. https:\/\/developer.nvidia.com\/embedded\/jetson-xavier-nx-devkit. accessed","year":"2020","unstructured":"Nvidia. 2014. Jetson Xavier NX Developer Kit. https:\/\/developer.nvidia.com\/embedded\/jetson-xavier-nx-devkit. accessed 29 Sep. 2020 . Nvidia. 2014. Jetson Xavier NX Developer Kit. https:\/\/developer.nvidia.com\/embedded\/jetson-xavier-nx-devkit. accessed 29 Sep. 2020."},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1186\/1743-0003-9-21"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.335"},{"key":"e_1_2_1_32_1","unstructured":"Sandeep Rao. 2017. Introduction to mmWave sensing: FMCW radars. Texas Instruments (TI) mmWave Training Series (2017).  Sandeep Rao. 2017. Introduction to mmWave sensing: FMCW radars. Texas Instruments (TI) mmWave Training Series (2017)."},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2020.2991741"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2013.2276144"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0189161"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3349624.3356768"},{"key":"e_1_2_1_37_1","volume-title":"https:\/\/github.com\/SizheAn\/MARS. accessed","author":"Sizhe An.","year":"2021","unstructured":"Sizhe An. 2021. MARS. https:\/\/github.com\/SizheAn\/MARS. accessed 8 Jul. 2021 . Sizhe An. 2021. MARS. https:\/\/github.com\/SizheAn\/MARS. accessed 8 Jul. 2021."},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-7433-7"},{"key":"e_1_2_1_39_1","volume-title":"Vigour: smart textile services to support rehabilitation. Nordes 1, 5","author":"Bh\u00f6mer Martijn Ten","year":"2013","unstructured":"Martijn Ten Bh\u00f6mer , Oscar Tomico , and Caroline Hummels . 2013. Vigour: smart textile services to support rehabilitation. Nordes 1, 5 ( 2013 ). Martijn Ten Bh\u00f6mer, Oscar Tomico, and Caroline Hummels. 2013. Vigour: smart textile services to support rehabilitation. Nordes 1, 5 (2013)."},{"key":"e_1_2_1_40_1","volume-title":"https:\/\/www.ti.com\/lit\/ds\/symlink\/iwr1443.pdf. accessed","author":"Instruments Texas","year":"2021","unstructured":"Texas Instruments . 2014. Datasheet. https:\/\/www.ti.com\/lit\/ds\/symlink\/iwr1443.pdf. accessed 8 Apr. 2021 . Texas Instruments. 2014. Datasheet. https:\/\/www.ti.com\/lit\/ds\/symlink\/iwr1443.pdf. accessed 8 Apr. 2021."},{"key":"e_1_2_1_41_1","volume-title":"https:\/\/www.ti.com\/tool\/IWR1443BOOST. accessed","author":"Instruments Texas","year":"2020","unstructured":"Texas Instruments . 2014. IWR1443 BOOST. https:\/\/www.ti.com\/tool\/IWR1443BOOST. accessed 29 Sep. 2020 . Texas Instruments. 2014. IWR1443BOOST. https:\/\/www.ti.com\/tool\/IWR1443BOOST. accessed 29 Sep. 2020."},{"key":"e_1_2_1_42_1","volume-title":"mmWavetutorial. https:\/\/www.ti.com\/lit\/pdf\/swra553. accessed","author":"Instruments Texas","year":"2020","unstructured":"Texas Instruments . 2014. mmWavetutorial. https:\/\/www.ti.com\/lit\/pdf\/swra553. accessed 29 Sep. 2020 . Texas Instruments. 2014. mmWavetutorial. https:\/\/www.ti.com\/lit\/pdf\/swra553. accessed 29 Sep. 2020."},{"key":"e_1_2_1_43_1","volume-title":"https:\/\/www.ti.com\/lit\/pdf\/tiduea7. accessed","author":"Instruments Texas","year":"2021","unstructured":"Texas Instruments . 2018. Zone Occupancy . https:\/\/www.ti.com\/lit\/pdf\/tiduea7. accessed 8 Apr. 2021 . Texas Instruments. 2018. Zone Occupancy. https:\/\/www.ti.com\/lit\/pdf\/tiduea7. accessed 8 Apr. 2021."},{"key":"e_1_2_1_44_1","volume-title":"mmWavefundamentals. https:\/\/www.ti.com\/lit\/spyy005. accessed","author":"Instruments Texas","year":"2021","unstructured":"Texas Instruments . 2020. mmWavefundamentals. https:\/\/www.ti.com\/lit\/spyy005. accessed 8 Apr. 2021 . Texas Instruments. 2020. mmWavefundamentals. https:\/\/www.ti.com\/lit\/spyy005. accessed 8 Apr. 2021."},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.3390\/data3010002"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12984-017-0229-y"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.gaitpost.2018.10.018"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/2942358.2942381"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230579"}],"container-title":["ACM Transactions on Embedded Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477003","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3477003","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:46Z","timestamp":1750188646000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477003"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,17]]},"references-count":48,"journal-issue":{"issue":"5s","published-print":{"date-parts":[[2021,10,31]]}},"alternative-id":["10.1145\/3477003"],"URL":"https:\/\/doi.org\/10.1145\/3477003","relation":{},"ISSN":["1539-9087","1558-3465"],"issn-type":[{"value":"1539-9087","type":"print"},{"value":"1558-3465","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,17]]},"assertion":[{"value":"2021-04-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-07-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-09-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}