{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T19:06:09Z","timestamp":1768417569313,"version":"3.49.0"},"reference-count":44,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2021,1,23]],"date-time":"2021-01-23T00:00:00Z","timestamp":1611360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100017186","name":"Ohio Supercomputer Center","doi-asserted-by":"crossref","award":["PAS1090"],"award-info":[{"award-number":["PAS1090"]}],"id":[{"id":"10.13039\/100017186","id-type":"DOI","asserted-by":"crossref"}]},{"name":"IIT Delhi HPC facility"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Sen. Netw."],"published-print":{"date-parts":[[2021,5,31]]},"abstract":"<jats:p>Edge sensing with micro-power pulse-Doppler radars is an emergent domain in monitoring and surveillance with several smart city applications. Existing solutions for the clutter versus multi-source radar classification task are limited in terms of either accuracy or efficiency, and in some cases, struggle with a tradeoff between false alarms and recall of sources. We find that this problem can be resolved by learning the classifier across multiple time-scales. We propose a multi-scale, cascaded recurrent neural network architecture, MSC-RNN, composed of an efficient multi-instance learning (MIL) Recurrent Neural Network (RNN) for clutter discrimination at a lower tier and a more complex RNN classifier for source classification at the upper tier. By controlling the invocation of the upper RNN with the help of the lower tier conditionally, MSC-RNN achieves an overall accuracy of 0.972. Our approach holistically improves the accuracy and per-class recalls over machine learning models suitable for radar inferencing. Notably, we outperform cross-domain handcrafted feature engineering with purely time-domain deep feature learning, while also being up to \u223c3\u00d7 more efficient than a competitive solution.<\/jats:p>","DOI":"10.1145\/3439957","type":"journal-article","created":{"date-parts":[[2021,1,23]],"date-time":"2021-01-23T11:06:40Z","timestamp":1611400000000},"page":"1-27","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["One Size Does Not Fit All"],"prefix":"10.1145","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1605-5423","authenticated-orcid":false,"given":"Dhrubojyoti","family":"Roy","sequence":"first","affiliation":[{"name":"The Ohio State University, Columbus, Ohio, USA"}]},{"given":"Sangeeta","family":"Srivastava","sequence":"additional","affiliation":[{"name":"The Ohio State University, Columbus, Ohio, USA"}]},{"given":"Aditya","family":"Kusupati","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, Washington, USA"}]},{"given":"Pranshu","family":"Jain","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Delhi, Hauz Khas, New Delhi, India"}]},{"given":"Manik","family":"Varma","sequence":"additional","affiliation":[{"name":"Microsoft Research India, India and Indian Institute of Technology Delhi, Hauz Khas, New Delhi, India"}]},{"given":"Anish","family":"Arora","sequence":"additional","affiliation":[{"name":"The Ohio State University, USA and The Samraksh Company, Dublin, Ohio, USA"}]}],"member":"320","published-online":{"date-parts":[[2021,1,23]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"CMSIS-DSP Software Library","unstructured":"2020. CMSIS-DSP Software Library . Arm Ltd . Retrieved from http:\/\/www.keil.com\/pack\/doc\/CMSIS\/DSP\/html\/index.htm 2020. CMSIS-DSP Software Library. Arm Ltd. Retrieved from http:\/\/www.keil.com\/pack\/doc\/CMSIS\/DSP\/html\/index.htm"},{"key":"e_1_2_1_2_1","volume-title":"Olentangy Trail usage","unstructured":"[n.d.]. Olentangy Trail usage , Columbus, OH . The city of Columbus. Retrieved from https:\/\/www.columbus.gov\/recreationandparks\/trails\/Future-Trails-(Updated)\/. [n.d.]. Olentangy Trail usage, Columbus, OH. The city of Columbus. Retrieved from https:\/\/www.columbus.gov\/recreationandparks\/trails\/Future-Trails-(Updated)\/."},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPSN.2018.00047"},{"key":"e_1_2_1_4_1","volume-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271","author":"Bai Shaojie","year":"2018","unstructured":"Shaojie Bai , J. Zico Kolter , and Vladlen Koltun . 2018. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271 ( 2018 ). Shaojie Bai, J. Zico Kolter, and Vladlen Koltun. 2018. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271 (2018)."},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3224204"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3063386.3063771"},{"key":"e_1_2_1_7_1","unstructured":"Ohio Supercomputer Center. 1987. Ohio Supercomputer Center. Retrieved from http:\/\/osc.edu\/ark:\/19495\/f5s1ph73.  Ohio Supercomputer Center. 1987. Ohio Supercomputer Center. Retrieved from http:\/\/osc.edu\/ark:\/19495\/f5s1ph73."},{"key":"e_1_2_1_8_1","volume-title":"Dzmitry Bahdanau, and Yoshua Bengio.","author":"Cho Kyunghyun","year":"2014","unstructured":"Kyunghyun Cho , Bart Van Merri\u00ebnboer , Dzmitry Bahdanau, and Yoshua Bengio. 2014 . On the properties of neural machine translation: Encoder-decoder approaches. arXiv preprint arXiv:1409.1259 (2014). Kyunghyun Cho, Bart Van Merri\u00ebnboer, Dzmitry Bahdanau, and Yoshua Bengio. 2014. On the properties of neural machine translation: Encoder-decoder approaches. arXiv preprint arXiv:1409.1259 (2014)."},{"key":"e_1_2_1_9_1","volume-title":"Hierarchical multiscale recurrent neural networks. arXiv preprint arXiv:1609.01704","author":"Chung Junyoung","year":"2016","unstructured":"Junyoung Chung , Sungjin Ahn , and Yoshua Bengio . 2016. Hierarchical multiscale recurrent neural networks. arXiv preprint arXiv:1609.01704 ( 2016 ). Junyoung Chung, Sungjin Ahn, and Yoshua Bengio. 2016. Hierarchical multiscale recurrent neural networks. arXiv preprint arXiv:1609.01704 (2016)."},{"key":"e_1_2_1_10_1","volume-title":"Proceedings of the International Conference on Advances in Neural Information Processing Systems. 10953--10964","author":"Dennis Don","year":"2018","unstructured":"Don Dennis , Chirag Pabbaraju , Harsha Vardhan Simhadri , and Prateek Jain . 2018 . Multiple instance learning for efficient sequential data classification on resource-constrained devices . In Proceedings of the International Conference on Advances in Neural Information Processing Systems. 10953--10964 . Don Dennis, Chirag Pabbaraju, Harsha Vardhan Simhadri, and Prateek Jain. 2018. Multiple instance learning for efficient sequential data classification on resource-constrained devices. In Proceedings of the International Conference on Advances in Neural Information Processing Systems. 10953--10964."},{"key":"e_1_2_1_11_1","unstructured":"Don Kurian Dennis Yash Gaurkar Sridhar Gopinath Chirag Gupta Moksh Jain Ashish Kumar Aditya Kusupati Chris Lovett Shishir G. Patil and Harsha Vardhan Simhadri. 2017. EdgeML: Machine Learning for resource-constrained edge devices. Retrieved from https:\/\/github.com\/Microsoft\/EdgeML.  Don Kurian Dennis Yash Gaurkar Sridhar Gopinath Chirag Gupta Moksh Jain Ashish Kumar Aditya Kusupati Chris Lovett Shishir G. Patil and Harsha Vardhan Simhadri. 2017. EdgeML: Machine Learning for resource-constrained edge devices. Retrieved from https:\/\/github.com\/Microsoft\/EdgeML."},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1049\/iet-rsn.2013.0165"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1029\/RS023i004p00713"},{"key":"e_1_2_1_14_1","volume-title":"Dally","author":"Han Song","year":"2015","unstructured":"Song Han , Huizi Mao , and William J . Dally . 2015 . Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding. arXiv preprint arXiv:1510.00149 (2015). Song Han, Huizi Mao, and William J. Dally. 2015. Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding. arXiv preprint arXiv:1510.00149 (2015)."},{"key":"e_1_2_1_15_1","volume-title":"Proceedings of the IEEE International Conference on Pervasive Computing and Communications (PerCom\u201914)","author":"He Jin","year":"2014","unstructured":"Jin He and Anish Arora . 2014 . A regression-based radar-mote system for people counting . In Proceedings of the IEEE International Conference on Pervasive Computing and Communications (PerCom\u201914) . IEEE, 95--102. Jin He and Anish Arora. 2014. A regression-based radar-mote system for people counting. In Proceedings of the IEEE International Conference on Pervasive Computing and Communications (PerCom\u201914). IEEE, 95--102."},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2668332.2668381"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(90)90002-H"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2014.2311819"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/RADAR.2016.7485147"},{"key":"e_1_2_1_21_1","volume-title":"Proceedings of the IEEE Antennas and Propagation Society International Symposium. IEEE, 1--4.","author":"Kim Youngwook","year":"2008","unstructured":"Youngwook Kim and Hao Ling . 2008 . Human activity classification based on micro-Doppler signatures using an artificial neural network . In Proceedings of the IEEE Antennas and Propagation Society International Symposium. IEEE, 1--4. Youngwook Kim and Hao Ling. 2008. Human activity classification based on micro-Doppler signatures using an artificial neural network. In Proceedings of the IEEE Antennas and Propagation Society International Symposium. IEEE, 1--4."},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2016.2617282"},{"key":"e_1_2_1_23_1","volume-title":"Deep multi-instance transfer learning. arXiv preprint arXiv:1411.3128","author":"Kotzias Dimitrios","year":"2014","unstructured":"Dimitrios Kotzias , Misha Denil , Phil Blunsom , and Nando de Freitas . 2014. Deep multi-instance transfer learning. arXiv preprint arXiv:1411.3128 ( 2014 ). Dimitrios Kotzias, Misha Denil, Phil Blunsom, and Nando de Freitas. 2014. Deep multi-instance transfer learning. arXiv preprint arXiv:1411.3128 (2014)."},{"key":"e_1_2_1_24_1","volume-title":"Proceedings of the International Conference on Advances in Neural Information Processing Systems. 1097--1105","author":"Krizhevsky Alex","unstructured":"Alex Krizhevsky , Ilya Sutskever , and Geoffrey E. Hinton . 2012. Imagenet classification with deep convolutional neural networks . In Proceedings of the International Conference on Advances in Neural Information Processing Systems. 1097--1105 . Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Proceedings of the International Conference on Advances in Neural Information Processing Systems. 1097--1105."},{"key":"e_1_2_1_25_1","volume-title":"Proceedings of the 34th International Conference on Machine Learning","volume":"70","author":"Kumar Ashish","year":"2017","unstructured":"Ashish Kumar , Saurabh Goyal , and Manik Varma . 2017 . Resource-efficient machine learning in 2 KB RAM for the Internet of Things . In Proceedings of the 34th International Conference on Machine Learning , Vol. 70 . JMLR. org, 1935--1944. Ashish Kumar, Saurabh Goyal, and Manik Varma. 2017. Resource-efficient machine learning in 2 KB RAM for the Internet of Things. In Proceedings of the 34th International Conference on Machine Learning, Vol. 70. JMLR. org, 1935--1944."},{"key":"e_1_2_1_26_1","volume-title":"Proceedings of the IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW\u201919)","author":"Kumari Sangeeta","year":"2019","unstructured":"Sangeeta Kumari , Dhrubojyoti Roy , Mark Cartwright , Juan Pablo Bello , and Anish Arora . 2019 . EdgeL3: Compressing L3-Net for mote scale urban noise monitoring . In Proceedings of the IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW\u201919) . IEEE, 877--884. Sangeeta Kumari, Dhrubojyoti Roy, Mark Cartwright, Juan Pablo Bello, and Anish Arora. 2019. EdgeL3: Compressing L3-Net for mote scale urban noise monitoring. In Proceedings of the IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW\u201919). IEEE, 877--884."},{"key":"e_1_2_1_27_1","volume-title":"Proceedings of the International Conference on Machine Learning.","author":"Kusupati Aditya","year":"2020","unstructured":"Aditya Kusupati , Vivek Ramanujan , Raghav Somani , Mitchell Wortsman , Prateek Jain , Sham Kakade , and Ali Farhadi . 2020 . Soft threshold weight reparameterization for learnable sparsity . In Proceedings of the International Conference on Machine Learning. Aditya Kusupati, Vivek Ramanujan, Raghav Somani, Mitchell Wortsman, Prateek Jain, Sham Kakade, and Ali Farhadi. 2020. Soft threshold weight reparameterization for learnable sparsity. In Proceedings of the International Conference on Machine Learning."},{"key":"e_1_2_1_28_1","volume-title":"Proceedings of the International Conference on Advances in Neural Information Processing Systems. 9017--9028","author":"Kusupati Aditya","year":"2018","unstructured":"Aditya Kusupati , Manish Singh , Kush Bhatia , Ashish Kumar , Prateek Jain , and Manik Varma . 2018 . FastGRNN: A fast, accurate, stable and tiny kilobyte sized gated recurrent neural network . In Proceedings of the International Conference on Advances in Neural Information Processing Systems. 9017--9028 . Aditya Kusupati, Manish Singh, Kush Bhatia, Ashish Kumar, Prateek Jain, and Manik Varma. 2018. FastGRNN: A fast, accurate, stable and tiny kilobyte sized gated recurrent neural network. In Proceedings of the International Conference on Advances in Neural Information Processing Systems. 9017--9028."},{"key":"e_1_2_1_29_1","volume-title":"Proceedings of the 5th International Conference on Pervasive Computing Technologies for Healthcare (PervasiveHealth\u201911) and Workshops. IEEE, 222--225","author":"Liu Liang","year":"2011","unstructured":"Liang Liu , Mihail Popescu , Marjorie Skubic , Marilyn Rantz , Tarik Yardibi , and Paul Cuddihy . 2011 . Automatic fall detection based on Doppler radar motion signature . In Proceedings of the 5th International Conference on Pervasive Computing Technologies for Healthcare (PervasiveHealth\u201911) and Workshops. IEEE, 222--225 . Liang Liu, Mihail Popescu, Marjorie Skubic, Marilyn Rantz, Tarik Yardibi, and Paul Cuddihy. 2011. Automatic fall detection based on Doppler radar motion signature. In Proceedings of the 5th International Conference on Pervasive Computing Technologies for Healthcare (PervasiveHealth\u201911) and Workshops. IEEE, 222--225."},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/MILCOM.2016.7795448"},{"key":"e_1_2_1_31_1","volume-title":"Proceedings of the International Conference on Advances in Neural Information Processing Systems. 275--282","author":"Mozer Michael C.","year":"1992","unstructured":"Michael C. Mozer . 1992 . Induction of multiscale temporal structure . In Proceedings of the International Conference on Advances in Neural Information Processing Systems. 275--282 . Michael C. Mozer. 1992. Induction of multiscale temporal structure. In Proceedings of the International Conference on Advances in Neural Information Processing Systems. 275--282."},{"key":"e_1_2_1_32_1","volume-title":"Proceedings of the International Conference on Machine Learning. 1310--1318","author":"Pascanu Razvan","year":"2013","unstructured":"Razvan Pascanu , Tomas Mikolov , and Yoshua Bengio . 2013 . On the difficulty of training recurrent neural networks . In Proceedings of the International Conference on Machine Learning. 1310--1318 . Razvan Pascanu, Tomas Mikolov, and Yoshua Bengio. 2013. On the difficulty of training recurrent neural networks. In Proceedings of the International Conference on Machine Learning. 1310--1318."},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2005.159"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/MASS.2017.54"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3360322.3361000"},{"key":"e_1_2_1_36_1","unstructured":"Dhrubojyoti Roy Sangeeta Srivastava Aditya Kusupati Pranshu Jain Manik Varma and Anish Arora. 2019. Micro-power pulse-Doppler radar clutter and displacement source classification dataset. DOI:https:\/\/doi.org\/10.5281\/zenodo.3451407  Dhrubojyoti Roy Sangeeta Srivastava Aditya Kusupati Pranshu Jain Manik Varma and Anish Arora. 2019. Micro-power pulse-Doppler radar clutter and displacement source classification dataset. DOI:https:\/\/doi.org\/10.5281\/zenodo.3451407"},{"key":"e_1_2_1_37_1","unstructured":"Dhrubojyoti Roy Sangeeta Srivastava Aditya Kusupati Pranshu Jain Manik Varma and Anish Arora. 2019. MSC-RNN: Multi-Scale Cascaded RNNs for Radar Classification. DOI:https:\/\/github.com\/dhruboroy29\/MSCRNN  Dhrubojyoti Roy Sangeeta Srivastava Aditya Kusupati Pranshu Jain Manik Varma and Anish Arora. 2019. MSC-RNN: Multi-Scale Cascaded RNNs for Radar Classification. DOI:https:\/\/github.com\/dhruboroy29\/MSCRNN"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3360322.3360860"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.2.234"},{"key":"e_1_2_1_40_1","unstructured":"The Samraksh Company. [n.d.]. BumbleBee Radar. Retrieved from https:\/\/goo.gl\/ViMSiJ.  The Samraksh Company. [n.d.]. BumbleBee Radar. Retrieved from https:\/\/goo.gl\/ViMSiJ."},{"key":"e_1_2_1_41_1","unstructured":"The Samraksh Company. [n.d.]. .NOW with eMote. Retrieved from https:\/\/goo.gl\/C4CCv4.  The Samraksh Company. [n.d.]. .NOW with eMote. Retrieved from https:\/\/goo.gl\/C4CCv4."},{"key":"e_1_2_1_42_1","unstructured":"UrbanCCD. 2018. Array of Things. Retrieved from https:\/\/medium.com\/array-of-things\/five-years-100-nodes-and-more-to-come-d3802653db9f.  UrbanCCD. 2018. Array of Things. Retrieved from https:\/\/medium.com\/array-of-things\/five-years-100-nodes-and-more-to-come-d3802653db9f."},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298968"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00977"}],"container-title":["ACM Transactions on Sensor Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3439957","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3439957","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:01:53Z","timestamp":1750197713000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3439957"}},"subtitle":["Multi-scale, Cascaded RNNs for Radar Classification"],"short-title":[],"issued":{"date-parts":[[2021,1,23]]},"references-count":44,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2021,5,31]]}},"alternative-id":["10.1145\/3439957"],"URL":"https:\/\/doi.org\/10.1145\/3439957","relation":{},"ISSN":["1550-4859","1550-4867"],"issn-type":[{"value":"1550-4859","type":"print"},{"value":"1550-4867","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1,23]]},"assertion":[{"value":"2020-06-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-11-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-01-23","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}