{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T13:49:40Z","timestamp":1767966580072,"version":"3.49.0"},"reference-count":81,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T00:00:00Z","timestamp":1715385600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100002322","name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior-Brasil","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100002322","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Brazilian fostering agency CNPq","award":["405531\/2022-2"],"award-info":[{"award-number":["405531\/2022-2"]}]},{"name":"INEGI-LAETA","award":["UIDB\/50022\/2020"],"award-info":[{"award-number":["UIDB\/50022\/2020"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Embed. Comput. Syst."],"published-print":{"date-parts":[[2024,5,31]]},"abstract":"<jats:p>The Internet of Things (IoT) has made it possible to include everyday objects in a connected network, allowing them to intelligently process data and respond to their environment. Thus, it is expected that those objects will gain an intelligent understanding of their environment and be able to process data more efficiently than before. Particularly, such edge computing paradigm has allowed the execution of inference methods on resource-constrained devices such as microcontrollers, significantly changing the way IoT applications have evolved in recent years. However, although this scenario has supported the development of Tiny Machine Learning (TinyML) approaches on such devices, there are still some challenges that require further investigation when optimizing data streaming on the edge. Therefore, this article proposes a new unsupervised TinyML regression technique based on the typicality and eccentricity of the samples to be processed. Moreover, the proposed technique also exploits a Recursive Least Squares (RLS) filter approach. Combining all these features, the proposed method uses similarities between samples to identify patterns when processing data streams, predicting outcomes based on these patterns. The results obtained through the extensive experimentation utilizing vehicular data streams were highly encouraging. The proposed algorithm was meticulously compared with the RLS algorithm and Convolutional Neural Networks (CNN). It exhibited significantly superior performance, with mean squared errors that were 4.68 and 12.02 times lower, respectively, compared to the aforementioned techniques.<\/jats:p>","DOI":"10.1145\/3591356","type":"journal-article","created":{"date-parts":[[2023,4,8]],"date-time":"2023-04-08T10:32:16Z","timestamp":1680949936000},"page":"1-28","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Online Processing of Vehicular Data on the Edge Through an Unsupervised TinyML Regression Technique"],"prefix":"10.1145","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7729-9085","authenticated-orcid":false,"given":"Pedro","family":"Andrade","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0116-6489","authenticated-orcid":false,"given":"Ivanovitch","family":"Silva","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7678-9007","authenticated-orcid":false,"given":"Marianne","family":"Diniz","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2808-8529","authenticated-orcid":false,"given":"Thommas","family":"Flores","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3988-8476","authenticated-orcid":false,"given":"Daniel G.","family":"Costa","sequence":"additional","affiliation":[{"name":"Federal University of Rio Grande do Norte, Natal, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2634-8270","authenticated-orcid":false,"given":"Eduardo","family":"Soares","sequence":"additional","affiliation":[]}],"member":"320","published-online":{"date-parts":[[2024,5,11]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.3390\/sym12101663"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.3390\/s21134412"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/WorldS450073.2020.9210375"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/MetroInd4.0IoT51437.2021.9488546"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","unstructured":"Plamen Angelov. 2014. Anomaly detection based on eccentricity analysis. 2014 IEEE Symposium on Evolving and Autonomous Learning Systems. 1\u20138. DOI:DOI:10.1109\/EALS.2014.7009497","DOI":"10.1109\/EALS.2014.7009497"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-02384-3"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3527156"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE54114.2022.9774689"},{"key":"e_1_3_2_10_2","doi-asserted-by":"crossref","unstructured":"Mohammad Farhadi Bajestani Mehdi Ghasemi Sarma Vrudhula and Yezhou Yang. 2020. Enabling incremental knowledge transfer for object detection at the edge. (2020) 1591\u20131599. arXiv:2004.05746. Retrieved from https:\/\/arxiv.org\/abs\/2004.05746","DOI":"10.1109\/CVPRW50498.2020.00206"},{"key":"e_1_3_2_11_2","unstructured":"Colby Banbury Chuteng Zhou Igor Fedorov Ramon Matas Urmish Thakker Dibakar Gope Vijay Janapa Reddi Matthew Mattina and Paul Whatmough. 2021. MicroNets: Neural network architectures for deploying tinyML applications on commodity microcontrollers. In Proceedings of Machine Learning and Systems A. Smola A. Dimakis and I. Stoica (Eds.). Vol. 3 517\u2013532. https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2021\/file\/a3c65c2974270fd093ee8a9bf8ae7d0b-Paper.pdf."},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/19.536707"},{"key":"e_1_3_2_13_2","doi-asserted-by":"crossref","unstructured":"Clauber Gomes Bezerra Bruno Sielly Jales Costa Luiz Affonso Guedes and Plamen Parvanov Angelov. 2020. An evolving approach to data streams clustering based on typicality and eccentricity data analytics. Information Sciences 518 (2020) 13\u201328. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0020025519311363.","DOI":"10.1016\/j.ins.2019.12.022"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.06.035"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2009.06.034"},{"key":"e_1_3_2_16_2","volume-title":"Proceedings of the Research Symposium on Tiny Machine Learning","author":"Blouw Peter","year":"2021","unstructured":"Peter Blouw, Gurshaant Malik, Benjamin Morcos, Aaron Voelker, and Chris Eliasmith. 2021. Hardware aware training for efficient keyword spotting on general purpose and specialized hardware. In Proceedings of the Research Symposium on Tiny Machine Learning."},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13174-020-0122-y"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3073066"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2969775"},{"issue":"12","key":"e_1_3_2_20_2","first-page":"177","article-title":"Des valeurs moyennes","author":"Chebyshev P.","year":"1867","unstructured":"P. Chebyshev. 1867. Des valeurs moyennes. Liouville\u2019s J. Math. Pures Appl.12 (1867), 177\u2013184.","journal-title":"Liouville\u2019s J. Math. Pures Appl."},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3141781"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2020.106891"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2019.2952447"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2020.02.067"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3007046"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","unstructured":"Simone Disabato and Manuel Roveri. 2020. Incremental on-device tiny machine learning. In Proceedings of the 2nd International Workshop on Challenges in Artificial Intelligence and Machine Learning for Internet of Things (AIChallengeIoT\u201920 Virtual Event Japan) Association for Computing Machinery New York NY 7\u201313. 10.1145\/3417313.3429378","DOI":"10.1145\/3417313.3429378"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/VLSI-DAT52063.2021.9427352"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.iot.2021.100461"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.micpro.2019.102938"},{"key":"e_1_3_2_30_2","first-page":"4978","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Fedorov Igor","year":"2019","unstructured":"Igor Fedorov, Ryan P. Adams, Matthew Mattina, and Paul Whatmough. 2019. Sparse: Sparse architecture search for cnns on resource-constrained microcontrollers. In Proceedings of the Advances in Neural Information Processing Systems. 4978\u20134990."},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1931.10503148"},{"key":"e_1_3_2_32_2","first-page":"249","volume-title":"Proceedings of the 13th International Conference on Artificial Intelligence and Statistics.","volume":"9","author":"Glorot Xavier","year":"2010","unstructured":"Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the 13th International Conference on Artificial Intelligence and Statistics.Yee Whye Teh and Mike Titterington (Eds.), Vol. 9, PMLR, 249\u2013256. Retrieved from https:\/\/proceedings.mlr.press\/v9\/glorot10a.html."},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10710-017-9314-z"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/EAIS.2016.7502509"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICAIIC54071.2022.9722636"},{"key":"e_1_3_2_36_2","unstructured":"Song Han Huizi Mao and William J. Dally. 2016. Deep compression: Compressing deep neural networks with pruning trained quantization and huffman coding. International Conference on Learning Representations (ICLR\u201916) 1\u201314."},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-017-9746-6"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2020.106492"},{"key":"e_1_3_2_41_2","doi-asserted-by":"crossref","unstructured":"Vijay Janapa Reddi Brian Plancher Susan Kennedy Laurence Moroney Pete Warden Lara Suzuki Anant Agarwal Colby Banbury Massimo Banzi Matthew Bennett Benjamin Brown Sharad Chitlangia Radhika Ghosal Sarah Grafman Rupert Jaeger Srivatsan Krishnan Maximilian Lam Daniel Leiker Cara Mann Mark Mazumder Dominic Pajak Dhilan Ramaprasad J. Evan Smith Matthew Stewart and Dustin Tingley. 2022. Widening access to applied machine learning with TinyML. Harvard Data Science Review 4 1 (2022) 1\u201339.","DOI":"10.1162\/99608f92.762d171a"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-2877-1_34"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2015.7280528"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2016.05.012"},{"key":"e_1_3_2_45_2","first-page":"9031","volume-title":"Proceedings of the NeurIPS","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 NeurIPS. 9031\u20139042."},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3318216.3363317"},{"key":"e_1_3_2_47_2","unstructured":"Ji Lin Wei-Ming Chen Yujun Lin J. Cohn Chuang Gan and Song Han. 2020. MCUNet: Tiny deep learning on IoT devices. In Proceedings of the 34th International Conference on Neural Information Processing Systems (NIPS\u201920 Vancouver BC Canada) Curran Associates Inc. Red Hook NY."},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/SAS.2019.8706017"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-0749-3_52"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00019"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/DSD51259.2020.00090"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/SenSysML50931.2020.00011"},{"key":"e_1_3_2_53_2","doi-asserted-by":"crossref","unstructured":"Julio Oliveira Jefferson Lemos Elton Vieira Ivanovitch Silva Joilson Abrantes Danilo Barros and Daniel G. Costa. 2017. CO2 catcher: A platform for monitoring of vehicular pollution in smart cities. IEEE First Summer School on Smart Cities (S3C\u201917). Vol. 1 37\u201342.","DOI":"10.1109\/S3C.2017.8501380"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-95498-7_20"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.3389\/fams.2019.00043"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.3390\/app10010320"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2805263"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2021.3121554"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2021.11.019"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","unstructured":"Haoyu Ren Darko Anicic and Thomas Runkler. 2021. TinyOL: TinyML with online-learning on microcontrollers. International Joint Conference on Neural Networks (IJCNN\u201921) 1\u20138. DOI:10.1109\/IJCNN52387.2021.9533927","DOI":"10.1109\/IJCNN52387.2021.9533927"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.egyr.2019.10.018"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1080\/1828051X.2019.1689189"},{"key":"e_1_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.3390\/s21155218"},{"key":"e_1_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2020.3005467"},{"key":"e_1_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2009.932254"},{"key":"e_1_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2009.932254"},{"key":"e_1_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1145\/3469029"},{"key":"e_1_3_2_68_2","volume-title":"Proceedings of the Digital Signal Processing Handbook","author":"Sayed Ali H.","year":"2000","unstructured":"Ali H. Sayed and Thomas Kailath. 2000. Recursive least-squares adaptive filters. In Proceedings of the Digital Signal Processing Handbook. CRC Press, Chapter 21."},{"key":"e_1_3_2_69_2","unstructured":"Zach Shelby Jan Jongboom and Kartik Thakore. 2020. Cough Detection with TinyML on Arduino. Retrieved from https:\/\/create.arduino.cc\/projecthub\/edge-impulse\/cough-detection-with-tinyml-on-arduino-417f37. Accessed 02-08-2022."},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2016.2579198"},{"key":"e_1_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2016.2579198"},{"key":"e_1_3_2_72_2","doi-asserted-by":"publisher","DOI":"10.3390\/s21124153"},{"key":"e_1_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1109\/METROI4.2019.8792885"},{"key":"e_1_3_2_74_2","doi-asserted-by":"publisher","DOI":"10.3390\/fi11010013"},{"key":"e_1_3_2_75_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICC40277.2020.9149180"},{"key":"e_1_3_2_76_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2017.12.032"},{"key":"e_1_3_2_77_2","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-020-0285-1"},{"key":"e_1_3_2_78_2","doi-asserted-by":"publisher","unstructured":"Xiaying Wang Michele Magno Lukas Cavigelli and Luca Benini. 2020. FANN-on-MCU: An open-source toolkit for energy-efficient neural network inference at the edge of the internet of things. IEEE Internet of Things Journal 7 5 (2020) 4403\u20134417. DOI:10.1109\/JIOT.2020.2976702","DOI":"10.1109\/JIOT.2020.2976702"},{"key":"e_1_3_2_79_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2976702"},{"key":"e_1_3_2_80_2","volume-title":"TinyML: Machine Learning with TensorFlow Lite on Arduino and Ultra-low-power Microcontrollers","author":"Warden P.","year":"2020","unstructured":"P. Warden and D. Situnayake. 2020. TinyML: Machine Learning with TensorFlow Lite on Arduino and Ultra-low-power Microcontrollers. O\u2019Reilly. 2020277178"},{"key":"e_1_3_2_81_2","doi-asserted-by":"publisher","DOI":"10.1002\/int.20330"},{"key":"e_1_3_2_82_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3039359"}],"container-title":["ACM Transactions on Embedded Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3591356","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3591356","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:47:21Z","timestamp":1750178841000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3591356"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,11]]},"references-count":81,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,5,31]]}},"alternative-id":["10.1145\/3591356"],"URL":"https:\/\/doi.org\/10.1145\/3591356","relation":{},"ISSN":["1539-9087","1558-3465"],"issn-type":[{"value":"1539-9087","type":"print"},{"value":"1558-3465","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,11]]},"assertion":[{"value":"2022-07-07","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-04-03","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-05-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}