{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T17:47:10Z","timestamp":1767116830852,"version":"3.41.0"},"reference-count":78,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"US National Science Foundation","doi-asserted-by":"crossref","award":["1622741"],"award-info":[{"award-number":["1622741"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Internet Things"],"published-print":{"date-parts":[[2024,2,29]]},"abstract":"<jats:p>Radar collision prediction systems can play a crucial role in safety critical applications, such as autonomous vehicles and smart helmets for contact sports, by predicting an impending collision just before it will occur. Collision prediction algorithms use the velocity and range measurements provided by radar to calculate time to collision. However, radar measurements used in such systems contain significant clutter, noise, and inaccuracies which hamper reliability. Existing solutions to reduce clutter are based on static filtering methods. In this paper, we present a deep learning approach using frequency modulated continuous wave (FMCW) radar and inertial sensing that learns the environmental and user-specific conditions that lead to future collisions. We present a process of converting raw radar samples to range-Doppler matrices (RDMs) and then training a deep convolutional neural network that outputs predictions (impending collision vs. none) for any measured RDM. The system is retrained to work in dynamically changing environments and maintain prediction accuracy. We demonstrate the effectiveness of our approach of using the information from radar data to predict impending collisions in real-time via real-world experiments, and show that our method achieves an F1-score of 0.91 and outperforms a traditional approach in accuracy and adaptability.<\/jats:p>","DOI":"10.1145\/3616018","type":"journal-article","created":{"date-parts":[[2023,8,26]],"date-time":"2023-08-26T10:37:35Z","timestamp":1693046255000},"page":"1-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Online Learning for Dynamic Impending Collision Prediction using FMCW Radar"],"prefix":"10.1145","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0279-1187","authenticated-orcid":false,"given":"Aarti","family":"Singh","sequence":"first","affiliation":[{"name":"Washington University in St. Louis, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3440-2043","authenticated-orcid":false,"given":"Neal","family":"Patwari","sequence":"additional","affiliation":[{"name":"Washington University in St. Louis, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,12,16]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2553042"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-28169-3_13"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2020.3023243"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2009.2018966"},{"key":"e_1_3_1_6_2","volume-title":"Conference on Uncertainty in Artificial Intelligence (UAI)","author":"Aravkin A.","year":"2014","unstructured":"A. Aravkin, S. Becker, V. Cevher, and P. Olsen. 2014. A variational approach to stable principal component pursuit. In Conference on Uncertainty in Artificial Intelligence (UAI)."},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2018.2823588"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/RoboSoft48309.2020.9116034"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2005.1545407"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/RADAR.2014.6875604"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.sbspro.2011.08.075"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2882768"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-28169-3_12"},{"key":"e_1_3_1_14_2","article-title":"SMOTE: Synthetic minority over-sampling technique","volume":"1106","author":"Chawla N.","year":"2002","unstructured":"N. Chawla, K. Bowyer, Lawrence O. Hall, and W. Philip Kegelmeyer. 2002. SMOTE: Synthetic minority over-sampling technique. ArXiv abs\/1106.1813 (2002).","journal-title":"ArXiv"},{"key":"e_1_3_1_15_2","first-page":"2812","article-title":"Heart rate sensing with a robot mounted mmWave radar","author":"Chen Changhao","year":"2020","unstructured":"Changhao Chen, A. Markham, Niki Trigoni, Bing Wang, Linhai Xie, and Peijun Zhao. 2020. Heart rate sensing with a robot mounted mmWave radar. 2020 IEEE International Conference on Robotics and Automation (ICRA) (2020), 2812\u20132818.","journal-title":"2020 IEEE International Conference on Robotics and Automation (ICRA)"},{"key":"e_1_3_1_16_2","unstructured":"Zhe Chen Cai Chao Tianyue Zheng Jun Luo Jie Xiong and Xin Wang. 2021. RF-based human activity recognition using signal adapted convolutional neural network. (102021)."},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csm.2010.08.006"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1007\/11669463_14"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3384419.3430735"},{"key":"e_1_3_1_20_2","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1007\/978-3-030-93049-3_9","volume-title":"Artificial Intelligence","author":"Fan Lei","year":"2021","unstructured":"Lei Fan, Qi Yang, Yang Zeng, Bin Deng, and Hongqiang Wang. 2021. Real-time collision warning and status classification based camera and millimeter wave-radar fusion. In Artificial Intelligence, Lu Fang, Yiran Chen, Guangtao Zhai, Jane Wang, Ruiping Wang, and Weisheng Dong (Eds.). Springer International Publishing, Cham, 103\u2013114."},{"key":"e_1_3_1_21_2","article-title":"Frequency-modulated continuous-wave radar in automotive applications","author":"Guerrero-Men\u00e9ndez E.","year":"2018","unstructured":"E. Guerrero-Men\u00e9ndez. 2018. Frequency-modulated continuous-wave radar in automotive applications. Guerrero-Men\u00e9ndez (2018).","journal-title":"Guerrero-Men\u00e9ndez"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1136\/bjsports-2012-091941"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMTT.2011.2178427"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793982"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/DSP.2009.4785968"},{"key":"e_1_3_1_26_2","article-title":"Near-miss determination through use of a scale of danger","author":"Hayward John C.","year":"1972","unstructured":"John C. Hayward. 1972. Near-miss determination through use of a scale of danger. Highway Research Record (1972).","journal-title":"Highway Research Record"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2008.4633969"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_1_29_2","unstructured":"Andrew Howard Menglong Zhu Bo Chen Dmitry Kalenichenko Weijun Wang Tobias Weyand Marco Andreetto and Hartwig Adam. 2017. MobileNets: Efficient convolutional neural networks for mobile vision applications. (042017)."},{"key":"e_1_3_1_30_2","volume-title":"Designing Machine Learning Systems: An Iterative Process for Production-ready Applications","author":"Huyen C.","year":"2022","unstructured":"C. Huyen. 2022. Designing Machine Learning Systems: An Iterative Process for Production-ready Applications. O\u2019Reilly Media, Incorporated. https:\/\/books.google.com\/books?id=BAy_zgEACAAJ"},{"key":"e_1_3_1_31_2","volume-title":"Collision Avoidance Theory: With Application to Automotive Collision Mitigation","author":"Jansson Jonas","year":"2005","unstructured":"Jonas Jansson. 2005. Collision Avoidance Theory: With Application to Automotive Collision Mitigation. Ph. D. Dissertation. Link\u00f6ping University Electronic Press."},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.3233\/IDA-2002-6504"},{"key":"e_1_3_1_33_2","first-page":"4804","volume-title":"International Conference on Machine Learning","author":"Jiang Lu","year":"2020","unstructured":"Lu Jiang, Di Huang, Mason Liu, and Weilong Yang. 2020. Beyond synthetic noise: Deep learning on controlled noisy labels. In International Conference on Machine Learning. PMLR, 4804\u20134815."},{"key":"e_1_3_1_34_2","unstructured":"Kaggle. 2011. Snapdragon Neural Processing Engine SDKr. https:\/\/www.kaggle.com\/c\/GiveMeSomeCredit"},{"key":"e_1_3_1_35_2","article-title":"FearNet: Brain-inspired model for incremental learning","volume":"1711","author":"Kemker Ronald","year":"2018","unstructured":"Ronald Kemker and Christopher Kanan. 2018. FearNet: Brain-inspired model for incremental learning. ArXiv abs\/1711.10563 (2018).","journal-title":"ArXiv"},{"key":"e_1_3_1_36_2","article-title":"YOLO-based simultaneous target detection and classification in automotive FMCW radar systems","volume":"20","author":"Kim Woosuk","year":"2020","unstructured":"Woosuk Kim, Hyun-Woong Cho, Jongseok Kim, Byungkwan Kim, and Seongwook Lee. 2020. YOLO-based simultaneous target detection and classification in automotive FMCW radar systems. Sensors (Basel, Switzerland) 20 (2020).","journal-title":"Sensors (Basel, Switzerland)"},{"key":"e_1_3_1_37_2","article-title":"Adam: A method for stochastic optimization","volume":"1412","author":"Kingma Diederik P.","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. CoRR abs\/1412.6980 (2015).","journal-title":"CoRR"},{"key":"e_1_3_1_38_2","first-page":"25","article-title":"Handling imbalanced datasets: A review","volume":"30","author":"Kotsiantis Sotiris","year":"2005","unstructured":"Sotiris Kotsiantis, D. Kanellopoulos, and P. Pintelas. 2005. Handling imbalanced datasets: A review. GESTS International Transactions on Computer Science and Engineering 30 (112005), 25\u201336.","journal-title":"GESTS International Transactions on Computer Science and Engineering"},{"key":"e_1_3_1_39_2","volume-title":"Machine Learning Design Patterns","author":"Lakshmanan Valliappa","year":"2020","unstructured":"Valliappa Lakshmanan, Sara Robinson, and Michael Munn. 2020. Machine Learning Design Patterns. O\u2019Reilly Media."},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2016.2537878"},{"key":"e_1_3_1_41_2","unstructured":"David Lewis Jason Catlett W. Cohen and Haym Hirsh. 1996. Heterogeneous uncertainty sampling for supervised learning. (1996)."},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925953"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-64214-3"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3384419.3430776"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196600"},{"key":"e_1_3_1_46_2","article-title":"Impactful robots: Evaluating visual and audio warnings to help users brace for impact in human robot interaction","author":"Luttmer Nathaniel G.","year":"2022","unstructured":"Nathaniel G. Luttmer, Takara E. Truong, Alicia M. Boynton, Andrew S. Merryweather, David R. Carrier, and Mark A. Minor. 2022. Impactful robots: Evaluating visual and audio warnings to help users brace for impact in human robot interaction. arXiv preprint arXiv:2207.13835 (2022).","journal-title":"arXiv preprint arXiv:2207.13835"},{"key":"e_1_3_1_47_2","first-page":"55","volume-title":"International Conference on Sensor Systems and Software","author":"Magno Michele","year":"2016","unstructured":"Michele Magno, Angelo D\u2019Aloia, Tommaso Polonelli, Lorenzo Spadaro, and Luca Benini. 2016. Shelmet: An intelligent self-sustaining multi sensors smart helmet for bikers. In International Conference on Sensor Systems and Software. Springer, 55\u201367."},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19186-2_11"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0079-7421(08)60536-8"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2013.2238376"},{"key":"e_1_3_1_51_2","unstructured":"Optitrack. 2022. Motion Capture Systems. https:\/\/optitrack.com\/software\/motive\/"},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2016.2628914"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.3390\/s141019582"},{"key":"e_1_3_1_54_2","unstructured":"Qualcomm. 2023. Snapdragon Neural Processing Engine SDKr. https:\/\/developer.qualcomm.com\/sites\/default\/files\/docs\/snpe\/overview.html"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/2030613.2030623"},{"key":"e_1_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/2750858.2804280"},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICEESE.2013.6895036"},{"key":"e_1_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"e_1_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/CoCoNet.2015.7411281"},{"issue":"3","key":"e_1_3_1_60_2","first-page":"237","article-title":"Active learning literature survey","volume":"10","author":"Settles Burr","year":"1995","unstructured":"Burr Settles. 1995. Active learning literature survey. Science 10, 3 (1995), 237\u2013304.","journal-title":"Science"},{"key":"e_1_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.7910\/DVN\/80XS3Y"},{"key":"e_1_3_1_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICAS49788.2021.9551118"},{"key":"e_1_3_1_63_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2700628"},{"key":"e_1_3_1_64_2","volume-title":"Electromagnetic Theory","author":"Stratton J. A.","year":"1941","unstructured":"J. A. Stratton. 1941. Electromagnetic Theory. McGraw-Hill Book Company Inc."},{"key":"e_1_3_1_65_2","unstructured":"Harry Thornburg. 2022. Adafruit BNO055 absolute orientation sensor. http:\/\/ccrma.stanford.edu\/jos\/bayes\/bayes.html"},{"key":"e_1_3_1_66_2","unstructured":"Tijmen Tieleman and Geoffrey Hinton. 2012. Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude. COURSERA: Neural Networks for Machine Learning 4 2 (2012) 26\u201331."},{"key":"e_1_3_1_67_2","unstructured":"Ivan Tomek. 1976. Two modifications of CNN."},{"key":"e_1_3_1_68_2","unstructured":"UCI. 2023. UCI Repository of Machine Learning Databases. https:\/\/archive.ics.uci.edu\/ml\/datasets\/statlog+(heart)"},{"key":"e_1_3_1_69_2","unstructured":"UserManual.wiki. 2016. Ancortek Manual. https:\/\/usermanual.wiki\/Document\/AncortekManual.401224494"},{"issue":"86","key":"e_1_3_1_70_2","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten Laurens van der","year":"2008","unstructured":"Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of Machine Learning Research 9, 86 (2008), 2579\u20132605. http:\/\/jmlr.org\/papers\/v9\/vandermaaten08a.html","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_1_71_2","doi-asserted-by":"publisher","DOI":"10.3390\/s21165397"},{"key":"e_1_3_1_72_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3003933"},{"key":"e_1_3_1_73_2","article-title":"Cross-domain few-shot learning with unlabelled data","volume":"2101","author":"Yao Fupin","year":"2021","unstructured":"Fupin Yao. 2021. Cross-domain few-shot learning with unlabelled data. ArXiv abs\/2101.07899 (2021).","journal-title":"ArXiv"},{"key":"e_1_3_1_74_2","doi-asserted-by":"publisher","DOI":"10.1145\/2984511.2984515"},{"key":"e_1_3_1_75_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2665658"},{"key":"e_1_3_1_76_2","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512148"},{"key":"e_1_3_1_77_2","first-page":"1389","article-title":"Domain-adaptive few-shot learning","author":"Zhao An","year":"2020","unstructured":"An Zhao, Mingyu Ding, Zhiwu Lu, Tao Xiang, Yulei Niu, Jiechao Guan, Ji-Rong Wen, and Ping Luo. 2020. Domain-adaptive few-shot learning. 2021 IEEE Winter Conference on Applications of Computer Vision (WACV) (2020), 1389\u20131398.","journal-title":"2021 IEEE Winter Conference on Applications of Computer Vision (WACV)"},{"key":"e_1_3_1_78_2","first-page":"33","article-title":"mID: Tracking and identifying people with millimeter wave radar","author":"Zhao Peijun","year":"2019","unstructured":"Peijun Zhao, Chris Xiaoxuan Lu, Jianan Wang, Changhao Chen, Wei Wang, Agathoniki Trigoni, and A. Markham. 2019. mID: Tracking and identifying people with millimeter wave radar. 2019 15th International Conference on Distributed Computing in Sensor Systems (DCOSS) (2019), 33\u201340.","journal-title":"2019 15th International Conference on Distributed Computing in Sensor Systems (DCOSS)"},{"key":"e_1_3_1_79_2","doi-asserted-by":"publisher","DOI":"10.1177\/1687814017725246"}],"container-title":["ACM Transactions on Internet of Things"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3616018","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3616018","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:36:30Z","timestamp":1750178190000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3616018"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":78,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,2,29]]}},"alternative-id":["10.1145\/3616018"],"URL":"https:\/\/doi.org\/10.1145\/3616018","relation":{},"ISSN":["2691-1914","2577-6207"],"issn-type":[{"type":"print","value":"2691-1914"},{"type":"electronic","value":"2577-6207"}],"subject":[],"published":{"date-parts":[[2023,12,16]]},"assertion":[{"value":"2022-10-31","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-07-24","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-12-16","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}