{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T20:39:53Z","timestamp":1773002393743,"version":"3.50.1"},"reference-count":75,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T00:00:00Z","timestamp":1763078400000},"content-version":"vor","delay-in-days":317,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Intelligent Systems"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:p>\n                    As autonomous driving (AD) systems grow more complex, their rising computational demands pose significant energy and sustainability challenges. This paper investigates spiking neural networks (SNNs) as low\u2010power alternatives to convolutional neural networks (CNNs) for regression tasks in AD. We introduce a membrane\u2010potential (\n                    <jats:italic>V<\/jats:italic>\n                    <jats:sub>mem<\/jats:sub>\n                    ) decoding framework that converts binary spike trains into continuous outputs and propose the energy\u2010to\u2010error ratio (EER), a unified metric combining prediction error with energy consumption. Three CNN architectures (PilotNet, LaksNet, and MiniNet) and their corresponding SNN variants are trained and evaluated using delta, latency, and rate encoding across varied parameter settings, with energy use and emissions logged. Delta\u2010encoded SNNs achieve the highest EER, substantial energy savings with minimal performance loss, whereas CNNs, despite slightly better MSE, incur 10\u201320\u2009\u00d7\u2009higher energy costs. Rate encoding underperforms, and latency encoding, though improving relative error, demands excessive energy. Parameter tuning (threshold\n                    <jats:italic>\u03b8<\/jats:italic>\n                    , temporal dynamics (\n                    <jats:italic>S<\/jats:italic>\n                    ), membrane time constant (\n                    <jats:italic>\u03c4<\/jats:italic>\n                    ), and gain\n                    <jats:italic>G<\/jats:italic>\n                    ) directly influences eco\u2010efficiency. All experiments run on standard GPUs, showing SNNs can surpass CNNs in eco\u2010efficiency without specialized hardware. Paired statistical tests confirm that only delta\u2010encoded SNNs achieve significant EER improvements. This work presents a practical, energy\u2010aware evaluation framework for neural architectures, establishing EER as a critical metric for sustainable machine learning in intelligent transport and beyond.\n                  <\/jats:p>","DOI":"10.1155\/int\/4879993","type":"journal-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T10:44:21Z","timestamp":1763117061000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Energy\u2010Aware Regression in Spiking Neural Networks for Autonomous Driving: A Comparative Study With Convolutional Networks"],"prefix":"10.1155","volume":"2025","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5567-3665","authenticated-orcid":false,"given":"Fernando Sevilla","family":"Mart\u00ednez","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0617-3303","authenticated-orcid":false,"given":"Jordi","family":"Casas-Roma","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8646-5463","authenticated-orcid":false,"given":"Laia","family":"Subirats","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1899-5881","authenticated-orcid":false,"given":"Ra\u00fal","family":"Parada","sequence":"additional","affiliation":[]}],"member":"311","published-online":{"date-parts":[[2025,11,14]]},"reference":[{"key":"e_1_2_11_1_2","doi-asserted-by":"crossref","unstructured":"HanB.andRoyK. Deep Spiking Neural Network: Energy Efficiency Through Time Based Coding European Conference on Computer Vision 2020 Springer 388\u2013404.","DOI":"10.1007\/978-3-030-58607-2_23"},{"key":"e_1_2_11_2_2","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2020.00439"},{"key":"e_1_2_11_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.105887"},{"key":"e_1_2_11_4_2","first-page":"1","article-title":"Topology of Deep Neural Networks","volume":"21","author":"Naitzat G.","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_11_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2022.154615"},{"key":"e_1_2_11_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2019.135237"},{"key":"e_1_2_11_7_2","doi-asserted-by":"publisher","DOI":"10.1007\/s41062-022-00763-6"},{"key":"e_1_2_11_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclepro.2018.02.302"},{"key":"e_1_2_11_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128096"},{"key":"e_1_2_11_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2022.112703"},{"key":"e_1_2_11_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.egyr.2020.04.035"},{"key":"e_1_2_11_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclepro.2021.125834"},{"key":"e_1_2_11_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3578938"},{"key":"e_1_2_11_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/mwc.2019.1800321"},{"key":"e_1_2_11_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3084827"},{"key":"e_1_2_11_16_2","doi-asserted-by":"crossref","unstructured":"YangT.-J. ChenY.-H. andSzeV. Designing Energy-Efficient Convolutional Neural Networks Using Energy-Aware Pruning Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2017 5687\u20135695.","DOI":"10.1109\/CVPR.2017.643"},{"key":"e_1_2_11_17_2","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.6064"},{"key":"e_1_2_11_18_2","unstructured":"WangH. LiY.-F. andGrylliasK. Brain-Inspired Spiking Neural Networks for Industrial Fault Diagnosis: a Survey Challenges and Opportunities 2023."},{"key":"e_1_2_11_19_2","unstructured":"YanZ. BaiZ. andWongW.-F. Reconsidering the Energy Efficiency of Spiking Neural Networks 2024 https:\/\/arxiv.org\/abs\/2409.08290."},{"key":"e_1_2_11_20_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.09.005"},{"key":"e_1_2_11_21_2","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2022.759900"},{"key":"e_1_2_11_22_2","doi-asserted-by":"publisher","DOI":"10.1088\/2515-7620\/acf81b"},{"key":"e_1_2_11_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2019.07.007"},{"key":"e_1_2_11_24_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105287"},{"key":"e_1_2_11_25_2","unstructured":"LiuL. LuS. ZhongR.et al. Computing Systems for Autonomous Driving: State-Of-The-Art and Challenges 2020 https:\/\/arxiv.org\/abs\/2009.14349."},{"key":"e_1_2_11_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2023.3257201"},{"key":"e_1_2_11_27_2","volume-title":"Neuromorphic Computing: A Path to Artificial Intelligence Through Emulating Human Brains","author":"Zins N.","year":"2023"},{"key":"e_1_2_11_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.111055"},{"key":"e_1_2_11_29_2","doi-asserted-by":"publisher","DOI":"10.1088\/2634-4386\/ad1cd7"},{"key":"e_1_2_11_30_2","unstructured":"H\u00f6ppnerS. YanY. DixiusA.et al. The Spinnaker 2 Processing Element Architecture for Hybrid Digital Neuromorphic Computing 2021 https:\/\/arxiv.org\/abs\/2103.08392."},{"key":"e_1_2_11_31_2","article-title":"Attention is all you Need","author":"Vaswani A.","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_11_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2021.3122092"},{"key":"e_1_2_11_33_2","doi-asserted-by":"crossref","unstructured":"AnkitA. SenguptaA. PandaP. andRoyK. Resparc: A Reconfigurable and energy-efficient Architecture with Memristive Crossbars for Deep Spiking Neural Networks Proceedings of the 54th Annual Design Automation Conference 2017 Proceedings of the 54th Annual Design Automation Conference 2017 1\u20136 https:\/\/doi.org\/10.1145\/3061639.3062311 2-s2.0-85023593996.","DOI":"10.1145\/3061639.3062311"},{"key":"e_1_2_11_34_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6787"},{"key":"e_1_2_11_35_2","unstructured":"KrizhevskyA.andHintonG. Learning Multiple Layers of Features from Tiny Images 2009 University of Toronto Toronto Ontario Technical Report."},{"key":"e_1_2_11_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_2_11_37_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/321"},{"key":"e_1_2_11_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/ojim.2024.3485618"},{"key":"e_1_2_11_39_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_15"},{"key":"e_1_2_11_40_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2020.102170"},{"key":"e_1_2_11_41_2","doi-asserted-by":"publisher","DOI":"10.54097\/jhq3tv19"},{"key":"e_1_2_11_42_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.12.114"},{"key":"e_1_2_11_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/LMWC.2018.2869299"},{"key":"e_1_2_11_44_2","first-page":"1","article-title":"Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning","volume":"21","author":"Henderson P.","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_11_45_2","volume-title":"Energy Efficiency in Machine Learning: Approaches to Sustainable Data Stream Mining","author":"Garc\u00eda Mart\u00edn E.","year":"2020"},{"key":"e_1_2_11_46_2","doi-asserted-by":"crossref","unstructured":"LarosJ. H.III PedrettiK. KellyS. M.et al. Energy Delay Product Energy-Efficient High Performance Computing: Measurement and Tuning 2013 51\u201355.","DOI":"10.1007\/978-1-4471-4492-2_8"},{"key":"e_1_2_11_47_2","doi-asserted-by":"publisher","DOI":"10.3390\/su15076326"},{"key":"e_1_2_11_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/mdat.2019.2952328"},{"key":"e_1_2_11_49_2","doi-asserted-by":"publisher","DOI":"10.3390\/app14146196"},{"key":"e_1_2_11_50_2","unstructured":"CourtyB. SchmidtV. KamalG.et al. mlco2\/codecarbon: V2.8.2 2024 https:\/\/doi.org\/10.5281\/zenodo.14518377."},{"key":"e_1_2_11_51_2","article-title":"End to End Learning for Self-Driving Cars","volume":"1604","author":"Bojarski M.","year":"2016","journal-title":"CoRR abs\/"},{"key":"e_1_2_11_52_2","doi-asserted-by":"crossref","unstructured":"PolamreddyL. R.andZhangY. Laksnet: An End-to-End Deep Learning Model for Self-Driving Cars in Udacity Simulator Proceedings of the Future Technologies Conference 2023 Springer 1\u201313.","DOI":"10.1007\/978-3-031-47448-4_1"},{"key":"e_1_2_11_53_2","unstructured":"Udacity Self-Driving Car Engineer Nanodegree 2022."},{"key":"e_1_2_11_54_2","unstructured":"Defense Advanced Research Projects Agency Autonomous Vehicle 2022."},{"key":"e_1_2_11_55_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.109415"},{"key":"e_1_2_11_56_2","doi-asserted-by":"publisher","DOI":"10.1162\/089976602760407955"},{"key":"e_1_2_11_57_2","volume-title":"Python and HDF5","author":"Collette A.","year":"2013"},{"key":"e_1_2_11_58_2","doi-asserted-by":"publisher","DOI":"10.5194\/GMD-12-4099-2019"},{"key":"e_1_2_11_59_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2210.03515"},{"key":"e_1_2_11_60_2","article-title":"Neural Networks and Deep Learning","volume":"10","author":"Aggarwal C. C.","year":"2018","journal-title":"Springer"},{"key":"e_1_2_11_61_2","doi-asserted-by":"publisher","DOI":"10.3390\/s23063037"},{"key":"e_1_2_11_62_2","doi-asserted-by":"crossref","unstructured":"AkibaT. SanoS. YanaseT. OhtaT. andKoyamaM. Optuna: a next-generation Hyperparameter Optimization Framework Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 2019.","DOI":"10.1145\/3292500.3330701"},{"key":"e_1_2_11_63_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2023.101968"},{"key":"e_1_2_11_64_2","unstructured":"MilaB. G. C. H. C. Codecarbon 2021 https:\/\/mlco2.github.io\/codecarbon\/index.html."},{"key":"e_1_2_11_65_2","article-title":"Pytorch Lightning","author":"Falcon W. A.","year":"2019","journal-title":"GitHub"},{"key":"e_1_2_11_66_2","unstructured":"MehlinV. SchachtS. andLanquillonC. Towards Energy-Efficient Deep Learning: An Overview of Energy-Efficient Approaches Along the Deep Learning Lifecycle 2023 https:\/\/arxiv.org\/abs\/2303.01980."},{"key":"e_1_2_11_67_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2024.132625"},{"key":"e_1_2_11_68_2","doi-asserted-by":"publisher","DOI":"10.5194\/GMD-12-4099-2019"},{"key":"e_1_2_11_69_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2210.03515"},{"key":"e_1_2_11_70_2","article-title":"Neural Networks and Deep Learning","volume":"10","author":"Aggarwal C. C.","year":"2018","journal-title":"Springer"},{"key":"e_1_2_11_71_2","doi-asserted-by":"publisher","DOI":"10.3390\/s23063037"},{"key":"e_1_2_11_72_2","doi-asserted-by":"crossref","unstructured":"AkibaT. SanoS. YanaseT. OhtaT. andKoyamaM. Optuna: A Next-Generation Hyperparameter Optimization Framework Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 2019.","DOI":"10.1145\/3292500.3330701"},{"key":"e_1_2_11_73_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2023.101968"},{"key":"e_1_2_11_74_2","unstructured":"MilaB. G. C. H. C. Codecarbon 2021 https:\/\/mlco2.github.io\/codecarbon\/index.html."},{"key":"e_1_2_11_75_2","article-title":"Pytorch Lightning","author":"Falcon W. A.","year":"2019","journal-title":"GitHub"}],"container-title":["International Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/4879993","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1155\/int\/4879993","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/4879993","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T18:13:42Z","timestamp":1772993622000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/int\/4879993"}},"subtitle":[],"editor":[{"given":"Richard","family":"Murray","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":75,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1155\/int\/4879993"],"URL":"https:\/\/doi.org\/10.1155\/int\/4879993","archive":["Portico"],"relation":{},"ISSN":["0884-8173","1098-111X"],"issn-type":[{"value":"0884-8173","type":"print"},{"value":"1098-111X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"2025-07-19","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-15","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"4879993"}}