{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T14:23:55Z","timestamp":1782224635591,"version":"3.54.5"},"reference-count":29,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2022,3,10]],"date-time":"2022-03-10T00:00:00Z","timestamp":1646870400000},"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>Artificial Intelligence (AI) in Cyber-Physical Systems allows machine learning inference on acquired data with ever greater accuracy, thanks to models trained with massive amounts of information generated by Internet of Things devices. Edge Intelligence is increasingly adopted to execute inference on data at the border of local networks, exploiting models trained in the Cloud. However, the training tasks on Edge nodes are not supported yet with flexible dynamic migration between Edge and Cloud. This paper proposes a Cloud-Edge AI microservice architecture, based on Osmotic Computing principles. Notable features include: (i) containerized architecture enabling training and inference on the Edge, Cloud, or both, exploiting computational resources opportunistically to reach the best prediction accuracy; and (ii) microservice encapsulation of each architectural module, allowing a direct mapping with Commercial-Off-The-Shelf (COTS) components. Grounding on the proposed architecture: (i) a prototype has been realized with commodity hardware leveraging open-source software technologies; and (ii) it has been then used in a small-scale intelligent manufacturing case study, carrying out experiments. The obtained results validate the feasibility and key benefits of the approach.<\/jats:p>","DOI":"10.3390\/s22062166","type":"journal-article","created":{"date-parts":[[2022,3,10]],"date-time":"2022-03-10T20:19:10Z","timestamp":1646943550000},"page":"2166","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Osmotic Cloud-Edge Intelligence for IoT-Based Cyber-Physical Systems"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7995-8494","authenticated-orcid":false,"given":"Giuseppe","family":"Loseto","sequence":"first","affiliation":[{"name":"Department of Management, Finance and Technology, LUM University \u201cGiuseppe Degennaro\u201d, Strada Statale 100 km 18, I-70010 Casamassima, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7859-9602","authenticated-orcid":false,"given":"Floriano","family":"Scioscia","sequence":"additional","affiliation":[{"name":"Department of Electrical and Information Engineering, Polytechnic University of Bari, Via E. Orabona 4, I-70125 Bari, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2125-327X","authenticated-orcid":false,"given":"Michele","family":"Ruta","sequence":"additional","affiliation":[{"name":"Department of Electrical and Information Engineering, Polytechnic University of Bari, Via E. Orabona 4, I-70125 Bari, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4162-957X","authenticated-orcid":false,"given":"Filippo","family":"Gramegna","sequence":"additional","affiliation":[{"name":"Department of Electrical and Information Engineering, Polytechnic University of Bari, Via E. Orabona 4, I-70125 Bari, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8598-5504","authenticated-orcid":false,"given":"Saverio","family":"Ieva","sequence":"additional","affiliation":[{"name":"Department of Electrical and Information Engineering, Polytechnic University of Bari, Via E. Orabona 4, I-70125 Bari, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7813-5915","authenticated-orcid":false,"given":"Corrado","family":"Fasciano","sequence":"additional","affiliation":[{"name":"Department of Electrical and Information Engineering, Polytechnic University of Bari, Via E. Orabona 4, I-70125 Bari, Italy"},{"name":"Exprivia S.p.A., Via A. Olivetti 11, I-70056 Molfetta, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8294-2445","authenticated-orcid":false,"given":"Ivano","family":"Bilenchi","sequence":"additional","affiliation":[{"name":"Department of Electrical and Information Engineering, Polytechnic University of Bari, Via E. Orabona 4, I-70125 Bari, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0182-4672","authenticated-orcid":false,"given":"Davide","family":"Loconte","sequence":"additional","affiliation":[{"name":"Department of Electrical and Information Engineering, Polytechnic University of Bari, Via E. Orabona 4, I-70125 Bari, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,3,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1109\/MC.2018.1731058","article-title":"The Cyber-Physical Systems Revolution","volume":"51","author":"Serpanos","year":"2018","journal-title":"Computer"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"885","DOI":"10.1126\/science.aay2400","article-title":"Superhuman AI for multiplayer poker","volume":"365","author":"Brown","year":"2019","journal-title":"Science"},{"key":"ref_3","unstructured":"Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"450","DOI":"10.1109\/JIOT.2017.2750180","article-title":"Mobile Edge Computing: A Survey","volume":"5","author":"Abbas","year":"2017","journal-title":"IEEE Internet Things J."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"7457","DOI":"10.1109\/JIOT.2020.2984887","article-title":"Edge Intelligence: The Confluence of Edge Computing and Artificial Intelligence","volume":"7","author":"Deng","year":"2020","journal-title":"IEEE Internet Things J."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1738","DOI":"10.1109\/JPROC.2019.2918951","article-title":"Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing","volume":"107","author":"Zhou","year":"2019","journal-title":"Proc. IEEE"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1109\/MCC.2016.124","article-title":"Osmotic Computing: A New Paradigm for Edge\/Cloud Integration","volume":"3","author":"Villari","year":"2016","journal-title":"IEEE Cloud Comput."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1016\/j.jpdc.2018.09.006","article-title":"Opportunistic computing offloading in edge clouds","volume":"123","author":"Li","year":"2019","journal-title":"J. Parallel Distrib. Comput."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Tovazzi, D., Faticanti, F., Siracusa, D., Peroni, C., Cretti, S., and Gazzini, T. (2020). GEM-Analytics: Cloud-to-Edge AI-Powered Energy Management. International Conference on the Economics of Grids, Clouds, Systems, and Services, Springer.","DOI":"10.1007\/978-3-030-63058-4_5"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1109\/MCC.2018.1081070","article-title":"Deep Osmosis: Holistic Distributed Deep Learning in Osmotic Computing","volume":"4","author":"Morshed","year":"2017","journal-title":"IEEE Cloud Comput."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"5084","DOI":"10.1109\/ACCESS.2017.2683159","article-title":"Computational Offloading for Efficient Trust Management in Pervasive Online Social Networks Using Osmotic Computing","volume":"5","author":"Sharma","year":"2017","journal-title":"IEEE Access"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Pacheco, A., Cano, P., Flores, E., Trujillo, E., and Marquez, P. (2018, January 3\u20135). A Smart Classroom based on Deep Learning and Osmotic IoT Computing. Proceedings of the 2018 Congreso Internacional de Innovaci\u00f3n y Tendencias en Ingenier\u00eda (CONIITI), Bogota, Colombia.","DOI":"10.1109\/CONIITI.2018.8587095"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Longo, A., De Matteis, A., and Zappatore, M. (2018, January 18\u201320). Urban pollution monitoring based on Mobile Crowd Sensing: An osmotic computing approach. Proceedings of the 2018 IEEE 4th International Conference on Collaboration and Internet Computing, Philadelphia, PA, USA.","DOI":"10.1109\/CIC.2018.00057"},{"key":"ref_14","unstructured":"Grzelak, D., Mey, J., and A\u00dfmann, U. (August, January 30). Design and Concept of an Osmotic Analytics Platform based on R Container. Proceedings of the International Conference on Foundations of Computer Science, Las Vegas, NV, USA."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1109\/MC.2018.2888767","article-title":"Osmosis: The Osmotic Computing Platform for Microelements in the Cloud, Edge, and Internet of Things","volume":"52","author":"Villari","year":"2019","journal-title":"Computer"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1016\/j.iot.2019.01.001","article-title":"Osmotic computing as a distributed multi-agent system: The Body Area Network scenario","volume":"5","author":"Carnevale","year":"2019","journal-title":"Internet Things"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1109\/MCC.2018.022171663","article-title":"Osmotic Message-Oriented Middleware for the Internet of Things","volume":"5","author":"Rausch","year":"2018","journal-title":"IEEE Cloud Comput."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Kaur, K., Garg, S., Kaddoum, G., Ahmed, S.H., and Jayakody, D.N.K. (2019, January 2). En-OsCo: Energy-aware Osmotic Computing Framework using Hyper-heuristics. Proceedings of the ACM MobiHoc Workshop on Pervasive Systems in the IoT Era, Catania, Italy.","DOI":"10.1145\/3331052.3332473"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"723","DOI":"10.1016\/j.future.2019.09.008","article-title":"Osmotic computing-based service migration and resource scheduling in Mobile Augmented Reality Networks (MARN)","volume":"102","author":"Sharma","year":"2020","journal-title":"Future Gener. Comput. Syst."},{"key":"ref_20","unstructured":"Banks, A., Briggs, E., Borgendale, K., and Gupta, R. (2019). MQTT Version 5.0, OASIS. Technical Report."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Shelby, Z., Hartke, K., and Bormann, C. (2014). The Constrained Application Protocol (CoAP), IETF. RFC 7252.","DOI":"10.17487\/rfc7252"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1007\/s10845-018-1433-8","article-title":"Literature review of Industry 4.0 and related technologies","volume":"31","author":"Oztemel","year":"2020","journal-title":"J. Intell. Manuf."},{"key":"ref_23","unstructured":"Magalh\u00e3es Oliveira, E. (2021, November 02). Quality Prediction in a Mining Process. Available online: https:\/\/www.kaggle.com\/edumagalhaes\/quality-prediction-in-a-mining-process."},{"key":"ref_24","unstructured":"Kingma, D.P., and Ba, J. (2015, January 7\u20139). Adam: A Method for Stochastic Optimization. Proceedings of the 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA. Conference Track Proceedings."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Deutsch, P., and Gailly, J.L. (1996). RFC1950: ZLIB Compressed Data Format Specification Version 3.3, Internet Engineering Task Force. Technical Report.","DOI":"10.17487\/rfc1950"},{"key":"ref_26","unstructured":"Bond, J. (2015). The Enterprise Cloud: Best Practices for Transforming Legacy IT, O\u2019Reilly Media, Inc."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Althnian, A., AlSaeed, D., Al-Baity, H., Samha, A., Dris, A.B., Alzakari, N., Abou Elwafa, A., and Kurdi, H. (2021). Impact of Dataset Size on Classification Performance: An Empirical Evaluation in the Medical Domain. Appl. Sci., 11.","DOI":"10.3390\/app11020796"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Scioscia, F., Ruta, M., Loseto, G., Gramegna, F., Ieva, S., Pinto, A., and Di Sciascio, E. (2018). Mini-ME matchmaker and reasoner for the Semantic Web of Things. Innovations, Developments, and Applications of Semantic Web and Information Systems, IGI Global.","DOI":"10.4018\/978-1-5225-5042-6.ch010"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"183","DOI":"10.3233\/SW-180314","article-title":"Machine learning in the Internet of Things: A semantic-enhanced approach","volume":"10","author":"Ruta","year":"2019","journal-title":"Semant. Web"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/6\/2166\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T22:34:25Z","timestamp":1760135665000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/6\/2166"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,10]]},"references-count":29,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2022,3]]}},"alternative-id":["s22062166"],"URL":"https:\/\/doi.org\/10.3390\/s22062166","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,10]]}}}