{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T14:24:29Z","timestamp":1785421469622,"version":"3.56.0"},"reference-count":60,"publisher":"MDPI AG","issue":"21","license":[{"start":{"date-parts":[[2021,10,22]],"date-time":"2021-10-22T00:00:00Z","timestamp":1634860800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>A large number of smart devices in Internet of Things (IoT) environments communicate via different messaging protocols. Message Queuing Telemetry Transport (MQTT) is a widely used publish\u2013subscribe-based protocol for the communication of sensor or event data. The publish\u2013subscribe strategy makes it more attractive for intruders and thus increases the number of possible attacks over MQTT. In this paper, we proposed a Deep Neural Network (DNN) for intrusion detection in the MQTT-based protocol and also compared its performance with other traditional machine learning (ML) algorithms, such as a Naive Bayes (NB), Random Forest (RF), k-Nearest Neighbour (kNN), Decision Tree (DT), Long Short-Term Memory (LSTM), and Gated Recurrent Units (GRUs). The performance is proved using two different publicly available datasets, including (1) MQTT-IoT-IDS2020 and (2) a dataset with three different types of attacks, such as Man in the Middle (MitM), Intrusion in the network, and Denial of Services (DoS). The MQTT-IoT-IDS2020 contains three abstract-level features, including Uni-Flow, Bi-Flow, and Packet-Flow. The results for the first dataset and binary classification show that the DNN-based model achieved 99.92%, 99.75%, and 94.94% accuracies for Uni-flow, Bi-flow, and Packet-flow, respectively. However, in the case of multi-label classification, these accuracies reduced to 97.08%, 98.12%, and 90.79%, respectively. On the other hand, the proposed DNN model attains the highest accuracy of 97.13% against LSTM and GRUs for the second dataset.<\/jats:p>","DOI":"10.3390\/s21217016","type":"journal-article","created":{"date-parts":[[2021,10,24]],"date-time":"2021-10-24T22:07:11Z","timestamp":1635113231000},"page":"7016","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":155,"title":["A Deep Learning-Based Intrusion Detection System for MQTT Enabled IoT"],"prefix":"10.3390","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8712-5599","authenticated-orcid":false,"given":"Muhammad Almas","family":"Khan","sequence":"first","affiliation":[{"name":"Department of Computer Sciences, Quaid-i-Azam University, Islamabad 44000, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6140-1201","authenticated-orcid":false,"given":"Muazzam A.","family":"Khan","sequence":"additional","affiliation":[{"name":"Department of Computer Sciences, Quaid-i-Azam University, Islamabad 44000, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3950-4719","authenticated-orcid":false,"given":"Sana Ullah","family":"Jan","sequence":"additional","affiliation":[{"name":"School of Computing, Edinburgh Napier University, Edinburgh EH10 5DT, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6289-8248","authenticated-orcid":false,"given":"Jawad","family":"Ahmad","sequence":"additional","affiliation":[{"name":"School of Computing, Edinburgh Napier University, Edinburgh EH10 5DT, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5852-1955","authenticated-orcid":false,"given":"Sajjad Shaukat","family":"Jamal","sequence":"additional","affiliation":[{"name":"Department of Mathematics, College of Science, King Khalid University, Abha 61413, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1656-739X","authenticated-orcid":false,"given":"Awais Aziz","family":"Shah","sequence":"additional","affiliation":[{"name":"Department of Electrical and Informational Engineering (DEI), Polytechnic University of Bari, 70125 Bari, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3392-9970","authenticated-orcid":false,"given":"Nikolaos","family":"Pitropakis","sequence":"additional","affiliation":[{"name":"School of Computing, Edinburgh Napier University, Edinburgh EH10 5DT, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0809-3523","authenticated-orcid":false,"given":"William J.","family":"Buchanan","sequence":"additional","affiliation":[{"name":"School of Computing, Edinburgh Napier University, Edinburgh EH10 5DT, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,10,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"94880","DOI":"10.1109\/ACCESS.2020.2993363","article-title":"Investigating messaging protocols for the Internet of Things (IoT)","volume":"8","author":"Kalyanam","year":"2020","journal-title":"IEEE Access"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Kodali, R.K., and Soratkal, S. (2016, January 21\u201323). MQTT based home automation system using ESP8266. Proceedings of the 2016 IEEE Region 10 Humanitarian Technology Conference (R10-HTC), Agra, India.","DOI":"10.1109\/R10-HTC.2016.7906845"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Cornel-Cristian, A., Gabriel, T., Arhip-Calin, M., and Zamfirescu, A. (2019, January 3\u20136). Smart home automation with MQTT. Proceedings of the 2019 54th International Universities Power Engineering Conference (UPEC), Bucharest, Romania.","DOI":"10.1109\/UPEC.2019.8893617"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Prabaharan, J., Swamy, A., Sharma, A., Bharath, K.N., Mundra, P.R., and Mohammed, K.J. (2017, January 19\u201320). Wireless home automation and security system using MQTT protocol. Proceedings of the 2017 2nd IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT), Bangalore, India.","DOI":"10.1109\/RTEICT.2017.8256958"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Kodali, R.K., and Sarjerao, B.S. (2017, January 14\u201316). A low cost smart irrigation system using MQTT protocol. Proceedings of the 2017 IEEE Region 10 Symposium (TENSYMP), Cochin, India.","DOI":"10.1109\/TENCONSpring.2017.8070095"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Mukherji, S.V., Sinha, R., Basak, S., and Kar, S.P. (2019, January 14\u201316). Smart agriculture using internet of things and mqtt protocol. Proceedings of the 2019 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon), Faridabad, India.","DOI":"10.1109\/COMITCon.2019.8862233"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Atmoko, R.A., and Yang, D. (2018, January 8\u201310). Online monitoring & controlling industrial arm robot using mqtt protocol. Proceedings of the 2018 IEEE International Conference on Robotics, Biomimetics, and Intelligent Computational Systems (Robionetics), Bandung, Indonesia.","DOI":"10.1109\/ROBIONETICS.2018.8674672"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Safaei, B., Monazzah, A.M.H., Bafroei, M.B., and Ejlali, A. (2017, January 20\u201322). Reliability side-effects in Internet of Things application layer protocols. Proceedings of the 2017 2nd International Conference on System Reliability and Safety (ICSRS), Milan, Italy.","DOI":"10.1109\/ICSRS.2017.8272822"},{"key":"ref_9","unstructured":"Soni, D., and Makwana, A. (2017, January 6\u20138). A survey on mqtt: A protocol of internet of things (iot). Proceedings of the International Conference on Telecommunication, Power Analysis And Computing Techniques (ICTPACT-2017), Chennai, India."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Hunkeler, U., Truong, H.L., and Stanford-Clark, A. (2008, January 6\u201310). MQTT-S\u2014A publish\/subscribe protocol for Wireless Sensor Networks. Proceedings of the 2008 3rd International Conference on Communication Systems Software and Middleware and Workshops (COMSWARE\u201908), Bangalore, India.","DOI":"10.1109\/COMSWA.2008.4554519"},{"key":"ref_11","first-page":"229","article-title":"Security and privacy issues in eHealthcare systems: Towards trusted services","volume":"7","author":"Zriqat","year":"2016","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Mathur, A., Newe, T., and Rao, M. (2016). Defence against black hole and selective forwarding attacks for medical WSNs in the IoT. Sensors, 16.","DOI":"10.3390\/s16010118"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Butt, S.A., Diaz-Martinez, J.L., Jamal, T., Ali, A., De-La-Hoz-Franco, E., and Shoaib, M. (2019, January 1\u20134). IoT smart health security threats. Proceedings of the 2019 19th International Conference on Computational Science and Its Applications (ICCSA), St. Petersburg, Russia.","DOI":"10.1109\/ICCSA.2019.000-8"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Markowsky, L., and Markowsky, G. (2015, January 24\u201326). Scanning for vulnerable devices in the Internet of Things. Proceedings of the 2015 IEEE 8th International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS), Warsaw, Poland.","DOI":"10.1109\/IDAACS.2015.7340779"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Andy, S., Rahardjo, B., and Hanindhito, B. (2017, January 19\u201321). Attack scenarios and security analysis of MQTT communication protocol in IoT system. Proceedings of the 2017 4th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI), Yogyakarta, Indonesia.","DOI":"10.1109\/EECSI.2017.8239179"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Gujar, N.S. (2019, January 27\u201329). Message Queuing Telemetry Transport (MQTT) based hybrid smart streetlight system for smart applications. Proceedings of the 2019 International Conference on Smart Systems and Inventive Technology (ICSSIT), Tirunelveli, India.","DOI":"10.1109\/ICSSIT46314.2019.8987599"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Vaccari, I., Aiello, M., and Cambiaso, E. (2020). SlowITe, a novel denial of service attack affecting MQTT. Sensors, 20.","DOI":"10.3390\/s20102932"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Firdous, S.N., Baig, Z., Valli, C., and Ibrahim, A. (2017, January 21\u201323). Modelling and evaluation of malicious attacks against the iot mqtt protocol. Proceedings of the 2017 IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData), Exeter, UK.","DOI":"10.1109\/iThings-GreenCom-CPSCom-SmartData.2017.115"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Potrino, G., De Rango, F., and Santamaria, A.F. (2019, January 15\u201318). Modeling and evaluation of a new IoT security system for mitigating DoS attacks to the MQTT broker. Proceedings of the 2019 IEEE Wireless Communications and Networking Conference (WCNC), Marrakesh, Morocco.","DOI":"10.1109\/WCNC.2019.8885553"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Al Enany, M.O., Harb, H.M., and Attiya, G. (2021, January 3\u20134). A Comparative analysis of MQTT and IoT application protocols. Proceedings of the 2021 International Conference on Electronic Engineering (ICEEM), Menouf, Egypt.","DOI":"10.1109\/ICEEM52022.2021.9480384"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1016\/j.dcan.2017.10.002","article-title":"Machine learning for Internet of Things data analysis: A survey","volume":"4","author":"Mahdavinejad","year":"2018","journal-title":"Digit. Commun. Netw."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1016\/j.comnet.2019.01.023","article-title":"Internet of Things: A survey on machine learning-based intrusion detection approaches","volume":"151","author":"Papa","year":"2019","journal-title":"Comput. Netw."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2671","DOI":"10.1109\/COMST.2019.2896380","article-title":"Network intrusion detection for IoT security based on learning techniques","volume":"21","author":"Chaabouni","year":"2019","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"6516253","DOI":"10.1155\/2019\/6516253","article-title":"Multiclass classification procedure for detecting attacks on MQTT-IoT protocol","volume":"2019","author":"Benavides","year":"2019","journal-title":"Complexity"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Hindy, H., Bayne, E., Bures, M., Atkinson, R., Tachtatzis, C., and Bellekens, X. (2020, January 19\u201321). Machine learning based IoT Intrusion Detection System: An MQTT case study (MQTT-IoT-IDS2020 Dataset). Proceedings of the International Networking Conference, Online.","DOI":"10.1007\/978-3-030-64758-2_6"},{"key":"ref_26","unstructured":"Ahmadon, M.A.B., Yamaguchi, N., and Yamaguchi, S. (2019, January 15\u201318). Process-Based Intrusion Detection Method for IoT System with MQTT Protocol. Proceedings of the 2019 IEEE 8th Global Conference on Consumer Electronics (GCCE), Osaka, Japan."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1186\/s13638-019-1402-8","article-title":"Secure-MQTT: An efficient fuzzy logic-based approach to detect DoS attack in MQTT protocol for internet of things","volume":"2019","author":"Haripriya","year":"2019","journal-title":"EURASIP J. Wirel. Commun. Netw."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"777","DOI":"10.1016\/j.ins.2020.08.068","article-title":"A distributed sensor-fault detection and diagnosis framework using machine learning","volume":"547","author":"Jan","year":"2021","journal-title":"Inf. Sci."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"102983","DOI":"10.1016\/j.jnca.2021.102983","article-title":"A comprehensive survey and taxonomy of the SVM-based intrusion detection systems","volume":"178","author":"Mohammadi","year":"2021","journal-title":"J. Netw. Comput. Appl."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Jan, S.U., Vu, V.H., and Koo, I.S. (2018, January 18\u201320). Performance analysis of support vector machine-based classifier for spectrum sensing in cognitive radio networks. Proceedings of the 2018 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC), Zhengzhou, China.","DOI":"10.1109\/CyberC.2018.00075"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"12251","DOI":"10.1109\/JIOT.2021.3060878","article-title":"Semi-supervised Spatio-Temporal Deep Learning for Intrusions Detection in IoT Networks","volume":"8","author":"Hawash","year":"2021","journal-title":"IEEE Internet Things J."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Faker, O., and Dogdu, E. (2019, January 18\u201320). Intrusion detection using big data and deep learning techniques. Proceedings of the 2019 ACM Southeast Conference, Kennesaw, GA, USA.","DOI":"10.1145\/3299815.3314439"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Ciklabakkal, E., Donmez, A., Erdemir, M., Suren, E., Yilmaz, M.K., and Angin, P. (2019, January 1\u20134). ARTEMIS: An intrusion detection system for MQTT attacks in Internet of Things. Proceedings of the 2019 38th Symposium on Reliable Distributed Systems (SRDS), Lyon, France.","DOI":"10.1109\/SRDS47363.2019.00053"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Vaccari, I., Chiola, G., Aiello, M., Mongelli, M., and Cambiaso, E. (2020). MQTTset, a New Dataset for Machine Learning Techniques on MQTT. Sensors, 20.","DOI":"10.3390\/s20226578"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"41525","DOI":"10.1109\/ACCESS.2019.2895334","article-title":"Deep learning approach for intelligent intrusion detection system","volume":"7","author":"Vinayakumar","year":"2019","journal-title":"IEEE Access"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Zhong, M., Zhou, Y., and Chen, G. (2021). Sequential model based intrusion detection system for IoT servers using deep learning methods. Sensors, 21.","DOI":"10.3390\/s21041113"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Jothi, B., and Pushpalatha, M. (2021). WILS-TRS\u2014A novel optimized deep learning based intrusion detection framework for IoT networks. Pers. Ubiquitous Comput.","DOI":"10.1007\/s00779-021-01578-5"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"22351","DOI":"10.1109\/ACCESS.2021.3056614","article-title":"Benchmarking of Machine Learning for Anomaly Based Intrusion Detection Systems in the CICIDS2017 Dataset","volume":"9","author":"Maseer","year":"2021","journal-title":"IEEE Access"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"428","DOI":"10.3390\/iot2030022","article-title":"Towards a Hybrid Deep Learning Model for Anomalous Activities Detection in Internet of Things Networks","volume":"2","author":"Ullah","year":"2021","journal-title":"IoT"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Shalaginov, A., Semeniuta, O., and Alazab, M. (2019, January 2\u20135). MEML: Resource-aware MQTT-based machine learning for network attacks detection on IoT edge devices. Proceedings of the 12th IEEE\/ACM International Conference on Utility and Cloud Computing Companion, Auckland, New Zealand.","DOI":"10.1145\/3368235.3368876"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Berner, J., Grohs, P., Kutyniok, G., and Petersen, P. (2021). The Modern Mathematics of Deep Learning. arXiv.","DOI":"10.1017\/9781009025096.002"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s12046-019-1230-x","article-title":"Intrusion detection system using an optimized kernel extreme learning machine and efficient features","volume":"45","author":"Ghasemi","year":"2020","journal-title":"S\u0101dhan\u0101"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Liu, Z., Ghulam, M.U.D., Zhu, Y., Yan, X., Wang, L., Jiang, Z., and Luo, J. (2020). Deep learning approach for IDS. Fourth International Congress on Information and Communication Technology, Springer.","DOI":"10.1007\/978-981-15-0637-6_40"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Sarnovsky, M., and Paralic, J. (2020). Hierarchical intrusion detection using machine learning and knowledge model. Symmetry, 12.","DOI":"10.3390\/sym12020203"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"107417","DOI":"10.1016\/j.comnet.2020.107417","article-title":"Hybrid approach to intrusion detection in fog-based IoT environments","volume":"180","author":"Westphall","year":"2020","journal-title":"Comput. Netw."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Ibitoye, O., Shafiq, O., and Matrawy, A. (2019, January 9\u201313). Analyzing Adversarial Attacks against Deep Learning for Intrusion Detection in IoT Networks. Proceedings of the 2019 IEEE Global Communications Conference (GLOBECOM), Waikoloa, HI, USA.","DOI":"10.1109\/GLOBECOM38437.2019.9014337"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"165130","DOI":"10.1109\/ACCESS.2020.3022862","article-title":"TON_IoT telemetry dataset: A new generation dataset of IoT and IIoT for data-driven Intrusion Detection Systems","volume":"8","author":"Alsaedi","year":"2020","journal-title":"IEEE Access"},{"key":"ref_48","unstructured":"(2021, July 08). Dataset. Available online: https:\/\/joseaveleira.es\/dataset."},{"key":"ref_49","unstructured":"(2021, July 08). DoS 2017|Datasets|Research|Canadian Institute for Cybersecurity|UNB. Available online: https:\/\/www.unb.ca\/cic\/datasets\/dos-dataset.html."},{"key":"ref_50","first-page":"108","article-title":"Toward generating a new intrusion detection dataset and intrusion traffic characterization","volume":"1","author":"Sharafaldin","year":"2018","journal-title":"ICISSp"},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"699","DOI":"10.1016\/j.future.2018.07.058","article-title":"Internet of things (IoT): Operating system, applications and protocols design, and validation techniques","volume":"88","author":"Zikria","year":"2018","journal-title":"Future Gener. Comput. Syst."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"e3849","DOI":"10.1002\/dac.3849","article-title":"Survey on IoV routing protocols: Security and network architecture","volume":"32","author":"Alouache","year":"2019","journal-title":"Int. J. Commun. Syst."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"498","DOI":"10.1016\/j.cose.2006.03.001","article-title":"Security issues in SCADA networks","volume":"25","author":"Igure","year":"2006","journal-title":"Comput. Secur."},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Misbahuddin, S. (2010, January 17\u201321). Fault tolerant remote terminal units (RTUs) in SCADA systems. Proceedings of the 2010 International Symposium on Collaborative Technologies and Systems, Chicago, IL, USA.","DOI":"10.1109\/CTS.2010.5478479"},{"key":"ref_55","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_56","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"Duchi","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_57","unstructured":"Ruder, S. (2016). An overview of gradient descent optimization algorithms. arXiv."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1016\/j.icte.2020.04.010","article-title":"The effect of batch size on the generalizability of the convolutional neural networks on a histopathology dataset","volume":"6","author":"Kandel","year":"2020","journal-title":"ICT Express"},{"key":"ref_59","unstructured":"Hoffer, E., Hubara, I., and Soudry, D. (2017). Train longer, generalize better: Closing the generalization gap in large batch training of neural networks. arXiv."},{"key":"ref_60","unstructured":"Smith, S.L., Kindermans, P.J., Ying, C., and Le, Q.V. (2017). Don\u2019t decay the learning rate, increase the batch size. arXiv."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/21\/7016\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:21:42Z","timestamp":1760167302000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/21\/7016"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,22]]},"references-count":60,"journal-issue":{"issue":"21","published-online":{"date-parts":[[2021,11]]}},"alternative-id":["s21217016"],"URL":"https:\/\/doi.org\/10.3390\/s21217016","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,22]]}}}