{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T00:03:17Z","timestamp":1784851397559,"version":"3.55.0"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T00:00:00Z","timestamp":1779321600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T00:00:00Z","timestamp":1784851200000},"content-version":"vor","delay-in-days":64,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100010665","name":"H2020 Marie Sk\u0142odowska-Curie Actions","doi-asserted-by":"publisher","award":["691135"],"award-info":[{"award-number":["691135"]}],"id":[{"id":"10.13039\/100010665","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Rail fastener defects threaten track integrity and operational safety, making reliable automated inspection essential. This study develops an energy-efficient real-time railway fastener detection framework for UAV-based monitoring by integrating Spiking Neural Networks (SNN) into a modified Spiking-YOLOv8 architecture. Unlike conventional CNNs, the event-driven SNN processes only informative visual changes, reducing redundant computation, and achieving a better accuracy\u2013energy balance for on-board inspection. A dataset of 173 images of ballasted railway tracks captured by UAVs was used for data augmentation, resulting in a total of 2,061 training images. The dataset is used to compare SNN and CNN performance under identical conditions, measuring accuracy, latency, and energy per inference. Results show that SNN achieves near CNN accuracy (mAP@0.5\u2009=\u20090.975 vs. 0.995) while reducing energy consumption by about 80% (0.50\u00a0J vs. 2.50\u00a0J) and maintaining real-time inference speed (~\u200934ms per frame). The approach demonstrates a 4.9 times improvement in accuracy-per-joule, supporting longer UAV endurance for inspection and more autonomous railway inspections.<\/jats:p>","DOI":"10.1038\/s41598-026-53237-5","type":"journal-article","created":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T11:26:08Z","timestamp":1779362768000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Energy-efficient, real-time detection of railway fastening systems from drone-based imagery using spiking neural networks"],"prefix":"10.1038","volume":"16","author":[{"given":"Sakdirat","family":"Kaewunruen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zibo","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aryadhatu","family":"Dhaniswara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zahid","family":"Hamarat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,21]]},"reference":[{"key":"53237_CR1","unstructured":"Thompson, D. Railway Noise and Vibration: Mechanisms, Modelling and Means of Control\/David Thompson Second edition. (Academic Press, 2024)."},{"key":"53237_CR2","unstructured":"AREMA. Manual for Railway Engineering. Chapter 5: Track (Lanham, 2023)."},{"key":"53237_CR3","unstructured":"CEN EN 13481-2:2022 Railway applications. Track. Performance requirements for fastening systems. Part 2: Fastening systems for concrete sleepers in ballasted track, Brussels, Belgium, (2022)."},{"key":"53237_CR4","unstructured":"CEN EN 13146-3:2012. Railway applications. Track. Test methods for fastening systems. Determination of attenuation of impact loads (2019)."},{"key":"53237_CR5","doi-asserted-by":"publisher","DOI":"10.3390\/ma15072675","author":"Y Xiao","year":"2022","unstructured":"Xiao, Y. et al. Evaluating the effect of rail fastener failure on dynamic responses of train-ballasted track-subgrade coupling system for smart track condition assessment. Materials https:\/\/doi.org\/10.3390\/ma15072675 (2022).","journal-title":"Materials"},{"key":"53237_CR6","doi-asserted-by":"publisher","DOI":"10.3390\/su132112051","author":"P Chandran","year":"2021","unstructured":"Chandran, P., Asber, J., Thiery, F., Odelius, J. & Rantatalo, M. An investigation of railway fastener detection using image processing and augmented deep learning. Sustainability https:\/\/doi.org\/10.3390\/su132112051 (2021).","journal-title":"Sustainability"},{"key":"53237_CR7","unstructured":"V. A. Profillidis. Railway Management and Engineering. (Ashgate Publishing Limited, 2014)."},{"key":"53237_CR8","unstructured":"CEN EN 13146-6:2012 Railway applications. Track. Test methods for fastening systems. Part 6: Effect of severe environmental conditions., Brussels, Belgium, (2012)."},{"issue":"3","key":"53237_CR9","doi-asserted-by":"publisher","first-page":"4019007","DOI":"10.1061\/AJRUA6.0001012","volume":"5","author":"S Kaewunruen","year":"2019","unstructured":"Kaewunruen, S., Osman, M. H. & Eric, W. H. C. Risk-based maintenance planning for rail fastening systems. ASCE-ASME J. Risk Uncertain. Eng. Syst. A Civ. Eng. 5(3), 4019007. https:\/\/doi.org\/10.1061\/AJRUA6.0001012 (2019).","journal-title":"ASCE-ASME J. Risk Uncertain. Eng. Syst. A Civ. Eng."},{"key":"53237_CR10","doi-asserted-by":"publisher","DOI":"10.3390\/app112412074","author":"S-H Kim","year":"2021","unstructured":"Kim, S.-H., Fang, X.-J., Park, Y.-C. & Sim, H.-B. Evaluation of structural behavior and fatigue performance of a KR-Type rail clip. Appl. Sci. https:\/\/doi.org\/10.3390\/app112412074 (2021).","journal-title":"Appl. Sci."},{"key":"53237_CR11","unstructured":"Romero, M. J. G. et al. Advancements in fastening system design for north American concrete crossties in heavy-haul service. In AREMA 2010 Annual Conference & Exposition, Orlando, Florida: American Railway Engineering and Maintenance-of-Way Association (2010)."},{"key":"53237_CR12","unstructured":"CEN EN 13481-1:2012 Railway applications. Track. Performance requirements for fastening systems. Part 1: Definitions, Brussels, Belgium, (2012)."},{"key":"53237_CR13","unstructured":"CEN EN 13146-9:2020 Railway applications. Track. Test methods for fastening systems. Part 9: Determination of stiffness, Brussels, Beligum, (2020)."},{"key":"53237_CR14","doi-asserted-by":"publisher","DOI":"10.3390\/drones6060147","author":"SAH Mohsan","year":"2022","unstructured":"Mohsan, S. A. H., Khan, M. A., Noor, F., Ullah, I. & Alsharif, M. H. Towards the unmanned aerial vehicles (UAVs): A comprehensive review. Drones https:\/\/doi.org\/10.3390\/drones6060147 (2022).","journal-title":"Drones"},{"key":"53237_CR15","doi-asserted-by":"publisher","DOI":"10.3390\/drones6060147","author":"SAH Mohsan","year":"2022","unstructured":"Mohsan, S. A. H., Khan, M. A., Noor, F., Ullah, I. & Alsharif, M. H. Towards the unmanned aerial vehicles (UAVs): A comprehensive review. Drones https:\/\/doi.org\/10.3390\/drones6060147 (2022).","journal-title":"Drones"},{"key":"53237_CR16","unstructured":"Desislavov, R., Mart\\\u2019{\\i}nez-Plumed, F. & Hern\u00e1ndez-Orallo, J. Compute and Energy Consumption Trends in Deep Learning Inference, CoRR, https:\/\/arxiv.org\/abs\/2109.05472 (2021)."},{"issue":"3","key":"53237_CR17","doi-asserted-by":"publisher","first-page":"731","DOI":"10.1109\/TETCI.2022.3214509","volume":"7","author":"M Dampfhoffer","year":"2023","unstructured":"Dampfhoffer, M., Mesquida, T., Valentian, A. & Anghel, L. Are SNNs really more energy-efficient than ANNs? An in-depth hardware-aware study. IEEE Trans. Emerg. Top. Comput. Intell. 7(3), 731\u2013741. https:\/\/doi.org\/10.1109\/TETCI.2022.3214509 (2023).","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"issue":"10","key":"53237_CR18","doi-asserted-by":"publisher","first-page":"2742","DOI":"10.1109\/LWC.2024.3443295","volume":"13","author":"C Shang","year":"2024","unstructured":"Shang, C., Thai Hoang, D., Hao, M., Niyato, D. & Yu, J. Energy-efficient decentralized federated learning for UAV swarm with spiking neural networks and leader election mechanism. IEEE Wirel. Commun. Lett. 13(10), 2742\u20132746. https:\/\/doi.org\/10.1109\/LWC.2024.3443295 (2024).","journal-title":"IEEE Wirel. Commun. Lett."},{"issue":"30","key":"53237_CR19","doi-asserted-by":"publisher","first-page":"18897","DOI":"10.1007\/s00521-024-10191-5","volume":"36","author":"F Barchi","year":"2024","unstructured":"Barchi, F., Parisi, E., Zanatta, L., Bartolini, A. & Acquaviva, A. Energy efficient and low-latency spiking neural networks on embedded microcontrollers through spiking activity tuning. Neural Comput. Appl. 36(30), 18897\u201318917. https:\/\/doi.org\/10.1007\/s00521-024-10191-5 (2024).","journal-title":"Neural Comput. Appl."},{"issue":"5","key":"53237_CR20","doi-asserted-by":"publisher","DOI":"10.1007\/s42452-024-05880-8","volume":"6","author":"S Kaewunruen","year":"2024","unstructured":"Kaewunruen, S., Adesope, A. A., Huang, J., You, R. & Li, D. AI-based technology to prognose and diagnose complex crack characteristics of railway concrete sleepers. Discov. Appl. Sci. 6(5), 217. https:\/\/doi.org\/10.1007\/s42452-024-05880-8 (2024).","journal-title":"Discov. Appl. Sci."},{"key":"53237_CR21","doi-asserted-by":"crossref","unstructured":"Grossi, E. & Buscema, M. Introduction to artificial neural networks. Eur. J. Gastroenterol. Hepatol. 19(12), (2007).","DOI":"10.1097\/MEG.0b013e3282f198a0"},{"key":"53237_CR22","doi-asserted-by":"publisher","DOI":"10.3390\/s20154325","author":"T Wang","year":"2020","unstructured":"Wang, T., Yang, F. & Tsui, K.-L. Real-time detection of railway track component via one-stage deep learning networks. Sensors https:\/\/doi.org\/10.3390\/s20154325 (2020).","journal-title":"Sensors"},{"issue":"12","key":"53237_CR23","doi-asserted-by":"publisher","first-page":"6999","DOI":"10.1109\/TNNLS.2021.3084827","volume":"33","author":"Z Li","year":"2022","unstructured":"Li, Z., Liu, F., Yang, W., Peng, S. & Zhou, J. A survey of convolutional neural networks: Analysis, applications, and prospects. IEEE Trans. Neural Netw. Learn. Syst. 33(12), 6999\u20137019. https:\/\/doi.org\/10.1109\/TNNLS.2021.3084827 (2022).","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"53237_CR24","doi-asserted-by":"publisher","DOI":"10.3390\/app122010572","author":"K Oh","year":"2022","unstructured":"Oh, K. et al. A review of deep learning applications for railway safety. Appl. Sci. https:\/\/doi.org\/10.3390\/app122010572 (2022).","journal-title":"Appl. Sci."},{"key":"53237_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.conbuildmat.2023.132687","volume":"401","author":"L Han","year":"2023","unstructured":"Han, L., Liao, Y., Wang, H. & Zhang, H. Long-term prediction for railway track geometry based on an optimised DNN method. Constr. Build. Mater. 401, 132687. https:\/\/doi.org\/10.1016\/j.conbuildmat.2023.132687 (2023).","journal-title":"Constr. Build. Mater."},{"key":"53237_CR26","doi-asserted-by":"publisher","DOI":"10.3390\/app122311981","author":"N H\u00fctten","year":"2022","unstructured":"H\u00fctten, N., Meyes, R. & Meisen, T. Vision transformer in industrial visual inspection. Appl. Sci. https:\/\/doi.org\/10.3390\/app122311981 (2022).","journal-title":"Appl. Sci."},{"key":"53237_CR27","unstructured":"Deng, S., Lin, H., Li, Y. & Gu, S. Surrogate module learning: reduce the gradient error accumulation in training spiking neural networks. In Proceedings of the 40th International Conference on Machine Learning (eds Krause, A. et al.) Vol. 202, 7645\u20137657. https:\/\/proceedings.mlr.press\/v202\/deng23d.html (PMLR, 2023)."},{"key":"53237_CR28","doi-asserted-by":"publisher","unstructured":"Bendig, K., Schuster, R. & Stricker, D. On the Future of Training Spiking Neural Networks. 466\u2013473. https:\/\/doi.org\/10.5220\/0011745500003411 (2023).","DOI":"10.5220\/0011745500003411"},{"key":"53237_CR29","unstructured":"Kromydas, B. Convolutional Neural Network: A complete guide. https:\/\/learnopencv.com\/understanding-convolutional-neural-networks-cnn\/ (2023)."},{"key":"53237_CR30","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2025.1536771","author":"W Liao","year":"2025","unstructured":"Liao, W., Chen, F., Liu, C., Wang, W. & Liu, H. SpikeAtConv: An integrated spiking-convolutional attention architecture for energy-efficient neuromorphic vision processing. Front. Neurosci. https:\/\/doi.org\/10.3389\/fnins.2025.1536771 (2025).","journal-title":"Front. Neurosci."},{"key":"53237_CR31","doi-asserted-by":"crossref","unstructured":"Luo, X. et al. Integer-valued training and spike-driven inference spiking neural network for high-performance and energy-efficient object detection. In Computer Vision \u2013 ECCV 2024, (eds Leonardis Ale\u0161, V. G. et al.) 253\u2013272 (Springer Nature Switzerland, 2025).","DOI":"10.1007\/978-3-031-73411-3_15"},{"issue":"6","key":"53237_CR32","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1109\/MSP.2007.906024","volume":"24","author":"M Vasilescu","year":"2007","unstructured":"Vasilescu, M. & Terzopoulos, D. Multilinear (tensor) image synthesis, analysis, and recognition [exploratory DSP]. IEEE Signal Process. Mag. 24(6), 118\u2013123. https:\/\/doi.org\/10.1109\/MSP.2007.906024 (2007).","journal-title":"IEEE Signal Process. Mag."},{"key":"53237_CR33","doi-asserted-by":"publisher","unstructured":"Bernoulli Distribution. Encyclopedia of Research Design. https:\/\/doi.org\/10.4135\/9781412961288.n26 (SAGE Publications, Inc., 2010).","DOI":"10.4135\/9781412961288.n26"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-53237-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-53237-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-53237-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T00:00:13Z","timestamp":1784851213000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-53237-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,21]]},"references-count":33,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["53237"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-53237-5","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,21]]},"assertion":[{"value":"7 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"23196"}}