{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T06:36:01Z","timestamp":1784010961139,"version":"3.55.0"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T00:00:00Z","timestamp":1776470400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T00:00:00Z","timestamp":1776470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SN COMPUT. SCI."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The growth of high-velocity data flows in security-important fields, such as network cybersecurity or big-data scientific computing, has generated an acute demand among smart systems that can handle data within strict operational deadline limits. Although deep learning (DL) models provide unprecedented levels of analysis power, their computational intensity also makes them unsuitable in applications where any break in the decision deadline can result in disastrous outcomes. The current literature has either concentrated on soft real-time systems or fixed-point optimisation of models, and a large gap in the literature that provides dynamic, adaptive frameworks to ensure performance within strict latency constraints remains open. The paper presents the Dynamic Gated Temporal Convolutional Network (DG-TCN), a new integrative architecture that combines an efficient feature extractor, a lightweight Temporal Convolutional Network (TCN), with a Deep Reinforcement Learning (DRL) agent to dynamically modulate the architecture in real time in a manner that is both practical and scalable. The DRL agent dynamically adjusts the computational graph of the TCN\u2014selectively activating or bypassing convolutional blocks\u2014to actively manage the trade-off between inference accuracy and latency on a per-batch basis. We empirically validate the DG-TCN on two disparate, high-volume public datasets: the CSE-CIC-IDS2018 for cybersecurity threat detection and the HIGGS dataset for scientific particle classification. Our results demonstrate that the DG-TCN outperforms, across evaluated conditions, both high-accuracy static models and low-latency static models, reducing deadline miss rates by up to 78% while maintaining an F1-score within 3% of the much larger, non-real-time model. The theoretical contributions include a new paradigm for deadline-constrained, adaptive-depth deep learning, while the practical benefits manifest in a practically deployable solution for latency-sensitive, security-critical decision-making systems.<\/jats:p>","DOI":"10.1007\/s42979-026-04968-9","type":"journal-article","created":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T03:33:07Z","timestamp":1776483187000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Hard Real-Time Deep Learning for Security-Critical Streams: An Integrative Algorithmic Framework for Cybersecurity, Scientific Analytics, and Decision Making"],"prefix":"10.1007","volume":"7","author":[{"given":"Bekim","family":"Fetaji","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4118-2480","authenticated-orcid":false,"given":"Debabrata","family":"Samanta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,18]]},"reference":[{"key":"4968_CR1","doi-asserted-by":"crossref","unstructured":"Gnanasundari P, Krishnamoorthy P, Padmavathi A. Integration of IoT sensor data and deep learning for early warning systems in critical infrastructure. In Deep Neural Networks for Predictive Analytics and Proactive Decision-Making in Securing Critical Infrastructure, 2025, pp. 293\u2013318.","DOI":"10.71443\/9788197933684-12"},{"key":"4968_CR2","doi-asserted-by":"crossref","unstructured":"Indumathi LK, Rais A, Begum J. Introduction to machine learning for data analytics. In Machine Learning for Business Analytics, 2022, pp. 1\u201316.","DOI":"10.4324\/9781003206316-1"},{"key":"4968_CR3","doi-asserted-by":"crossref","unstructured":"Sarker IH. Learning technologies: toward machine learning and deep learning for cybersecurity. In AI-Driven Cybersecurity and Threat Intelligence, 2024, pp. 43\u201359.","DOI":"10.1007\/978-3-031-54497-2_3"},{"key":"4968_CR4","doi-asserted-by":"crossref","unstructured":"Saravanan S, Shyry SD. Foundations of deep neural networks for predictive analytics in critical infrastructure security. In Deep Neural Networks for Predictive Analytics and Proactive Decision-Making in Securing Critical Infrastructure, 2025, pp. 12\u201337.","DOI":"10.71443\/9788197933684-01"},{"key":"4968_CR5","doi-asserted-by":"crossref","unstructured":"Hephzipah SMJJ, Saravanakumar C. Application of convolutional neural networks in real-time monitoring and anomaly detection. In Deep Neural Networks for Predictive Analytics and Proactive Decision-Making in Securing Critical Infrastructure, 2025, pp. 91\u2013114.","DOI":"10.71443\/9788197933684-04"},{"key":"4968_CR6","doi-asserted-by":"crossref","unstructured":"Devasena A. S. D, and K. S. Ensemble deep learning models for proactive threat identification in critical systems. In Deep Neural Networks for Predictive Analytics and Proactive Decision-Making in Securing Critical Infrastructure, 2025, pp. 115\u201338.","DOI":"10.71443\/9788197933684-05"},{"key":"4968_CR7","doi-asserted-by":"crossref","unstructured":"Straub J. Real time machine learning and decision-making with hardware expert systems and gradient descent trained expert systems. In Real-Time Image Processing and Deep Learning 2023, 2023, p. 21.","DOI":"10.1117\/12.2670081"},{"key":"4968_CR8","first-page":"43","volume":"13","author":"V Shypovskyi","year":"2023","unstructured":"Shypovskyi V. Decision-making process model for cybersecurity protection of critical infrastructure objects under the hybrid threats influence. J Sci Papers Social Dev Secur. 2023;13:43\u201355.","journal-title":"J Sci Papers Social Dev Secur"},{"key":"4968_CR9","doi-asserted-by":"crossref","unstructured":"Raja V, Kung J. Adaptive machine learning models for dynamic environments: a mathematical framework for real-time decision making, Preprints, 2025.","DOI":"10.20944\/preprints202501.0428.v1"},{"key":"4968_CR10","doi-asserted-by":"crossref","unstructured":"Dhage V, Ponnusamy S. Deep federated learning for real-time decision making in autonomous vehicles. In Advances in Information Security, Privacy, and Ethics, 2025, pp. 229\u201340.","DOI":"10.4018\/979-8-3373-0563-9.ch014"},{"key":"4968_CR11","doi-asserted-by":"crossref","unstructured":"Pandi JJVS, Perarasi M. Real-time decision-making frameworks using deep reinforcement learning in infrastructure management. In Deep Neural Networks for Predictive Analytics and Proactive Decision-Making in Securing Critical Infrastructure, 2025, pp. 217\u201341.","DOI":"10.71443\/9788197933684-09"},{"key":"4968_CR12","doi-asserted-by":"crossref","unstructured":"Ashlam AA, Badii A, Stahl F. Multi-phase algorithmic framework to prevent SQL injection attacks using improved machine learning and deep learning to enhance database security in real-time. In 2022 15th International Conference on Security of Information and Networks (SIN), 2022, pp. 01\u201304.","DOI":"10.1109\/SIN56466.2022.9970504"},{"key":"4968_CR13","doi-asserted-by":"publisher","first-page":"100626","DOI":"10.1016\/j.dajour.2025.100626","volume":"16","author":"RB Syah","year":"2025","unstructured":"Syah RB, Elveny M. An adaptive analytics framework for customer retention through integrative feature optimization and ensemble learning. Decis Analytics J. 2025;16:100626.","journal-title":"Decis Analytics J"},{"key":"4968_CR14","doi-asserted-by":"crossref","unstructured":"Hemachandran K, Khanra S, Rodriguez RV, Jaramillo JR. Machine learning for business analytics. 2022.","DOI":"10.4324\/9781003206316"},{"key":"4968_CR15","doi-asserted-by":"crossref","unstructured":"Kissell RL. Algorithmic decision-making framework. In Algorithmic Trading Methods, 2021, pp. 323\u201348.","DOI":"10.1016\/B978-0-12-815630-8.00013-2"},{"key":"4968_CR16","doi-asserted-by":"crossref","unstructured":"Kagzi M. Role of machine learning in promoting sustainability. In Machine Learning for Business Analytics, 2022, pp. 17\u201327.","DOI":"10.4324\/9781003206316-2"},{"key":"4968_CR17","doi-asserted-by":"crossref","unstructured":"Heggond S. Artificial intelligence and machine learning for smart construction: enhancing real-time monitoring and decision making. Deep Science Publishing; 2025.","DOI":"10.70593\/978-93-49307-33-9"},{"key":"4968_CR18","doi-asserted-by":"crossref","unstructured":"Sirineni H, Santosh T, Deepajothi S. Artificial intelligence in agriculture: a review. In Machine Learning for Business Analytics, 2022, pp. 87\u201395.","DOI":"10.4324\/9781003206316-7"},{"key":"4968_CR19","first-page":"83","volume":"26","author":"L Tan","year":"2025","unstructured":"Tan L. Transforming educational data analytics: developing a reinforcement learning framework for real-time decision-making and resource optimisation. Int J Inf Commun Technol. 2025;26:83\u2013106.","journal-title":"Int J Inf Commun Technol"},{"key":"4968_CR20","doi-asserted-by":"crossref","unstructured":"Azad MA. Leveraging supply chain analytics for real-time decision making in apparel manufacturing, TechRxiv, 2025.","DOI":"10.36227\/techrxiv.175459831.14441929\/v1"},{"key":"4968_CR21","doi-asserted-by":"publisher","first-page":"100221","DOI":"10.1016\/j.dajour.2023.100221","volume":"7","author":"J Kim","year":"2023","unstructured":"Kim J, Mavris D. Flight data clustering for offline evaluation of real-time trajectory optimization framework. Decis Analytics J. 2023;7:100221.","journal-title":"Decis Analytics J"},{"key":"4968_CR22","doi-asserted-by":"crossref","unstructured":"Jagadeesh M, Baranidharan B. Evaluating deep learning techniques for real-time facial expression recognition from video streams. In 2024 8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC), 2024, pp. 1433\u201337.","DOI":"10.1109\/I-SMAC61858.2024.10714855"},{"key":"4968_CR23","doi-asserted-by":"crossref","unstructured":"Bremnavas I, Jasmine J, Hussain MM. Scalable cloud-based architectures for deploying predictive analytics in infrastructure security. In Deep Neural Networks for Predictive Analytics and Proactive Decision-Making in Securing Critical Infrastructure, 2025, pp. 345\u201368.","DOI":"10.71443\/9788197933684-14"},{"key":"4968_CR24","doi-asserted-by":"publisher","first-page":"7563","DOI":"10.55248\/gengpi.5.1124.3426","volume":"5","author":"S Nwagwughiagwu","year":"2024","unstructured":"Nwagwughiagwu S, Nwaga PC. Revolutionizing cybersecurity with deep learning: procedural detection and hardware security. Crit Infrastructure Int J Res Publication Reviews. 2024;5:7563\u201382.","journal-title":"Crit Infrastructure Int J Res Publication Reviews"},{"key":"4968_CR25","doi-asserted-by":"publisher","first-page":"69","DOI":"10.54216\/JCIM.120205","volume":"12","author":"R Nair","year":"2023","unstructured":"Nair R. Unraveling the decision-making process interpretable deep learning IDS for transportation network security. J Cybersecur Inform Manage. 2023;12:69\u201382.","journal-title":"J Cybersecur Inform Manage"},{"key":"4968_CR26","doi-asserted-by":"crossref","unstructured":"Prabh SJSD. Transfer learning for rapid deployment of predictive models in dynamic security environments. In Deep Neural Networks for Predictive Analytics and Proactive Decision-Making in Securing Critical Infrastructure, 2025, pp. 165\u201390.","DOI":"10.71443\/9788197933684-07"},{"key":"4968_CR27","doi-asserted-by":"crossref","unstructured":"Pandi VS, Sarala SD. Multi-modal data fusion with deep neural networks for holistic security assessments. In Deep Neural Networks for Predictive Analytics and Proactive Decision-Making in Securing Critical Infrastructure, 2025, pp. 319\u201344.","DOI":"10.71443\/9788197933684-13"},{"key":"4968_CR28","first-page":"4646","volume":"16","author":"TT Subalakshmi","year":"2025","unstructured":"Subalakshmi TT. Development of an adaptive machine learning framework for real-time anomaly detection in cybersecurity. Sci Temper. 2025;16:4646\u201354.","journal-title":"Sci Temper"},{"key":"4968_CR29","doi-asserted-by":"crossref","unstructured":"Anjum A and R S. Asynchronous deep reinforcement learning for real-time adaptation in resource-constrained autonomous. In Deep Reinforcement Learning Applications in Autonomous Systems and Decision Making, 2025, pp. 210\u201342.","DOI":"10.71443\/9789349552982-08"},{"key":"4968_CR30","doi-asserted-by":"crossref","unstructured":"Phuc D, Hieu D, Hoang N, Khoa T. Apply deep learning in real-time customer detection and classification system for advertisement decision making at supermarket. In Proceedings of the 11th International Conference on Smart Cities and Green ICT Systems, 2022, pp. 94\u2013102.","DOI":"10.5220\/0010993600003203"},{"key":"4968_CR31","doi-asserted-by":"crossref","unstructured":"Teerapittayanon S, McDanel B, Kung HT. BranchyNet: fast inference via early exiting from deep neural networks. In 23rd International Conference on Pattern Recognition (ICPR), 2016. [Added in response to reviewer baseline scope comment.].","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"4968_CR32","unstructured":"Huang G, Chen D, Li T, Wu F, van der Maaten L, Weinberger KQ. Multi-scale dense networks for resource efficient image classification. In International Conference on Learning Representations (ICLR), 2018. [Added in response to reviewer baseline scope comment.]."}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-026-04968-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-026-04968-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-026-04968-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T22:19:39Z","timestamp":1781648379000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-026-04968-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,18]]},"references-count":32,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["4968"],"URL":"https:\/\/doi.org\/10.1007\/s42979-026-04968-9","relation":{},"ISSN":["2661-8907"],"issn-type":[{"value":"2661-8907","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,18]]},"assertion":[{"value":"4 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no known conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}],"article-number":"371"}}