{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T20:01:47Z","timestamp":1784318507974,"version":"3.55.0"},"reference-count":47,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2023,2,20]],"date-time":"2023-02-20T00:00:00Z","timestamp":1676851200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"\u201cLegge provinciale 6\/99 sugli incentivi alle imprese\u201d (L.P. 6\/99) della Provincia Autonoma di Trento","award":["L.P. 6\/99"],"award-info":[{"award-number":["L.P. 6\/99"]}]},{"name":"\u201cLegge provinciale 6\/99 sugli incentivi alle imprese\u201d (L.P. 6\/99) della Provincia Autonoma di Trento","award":["ECS00000043"],"award-info":[{"award-number":["ECS00000043"]}]},{"name":"European Union Next-GenerationEU","award":["L.P. 6\/99"],"award-info":[{"award-number":["L.P. 6\/99"]}]},{"name":"European Union Next-GenerationEU","award":["ECS00000043"],"award-info":[{"award-number":["ECS00000043"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Industrial assets often feature multiple sensing devices to keep track of their status by monitoring certain physical parameters. These readings can be analyzed with machine learning (ML) tools to identify potential failures through anomaly detection, allowing operators to take appropriate corrective actions. Typically, these analyses are conducted on servers located in data centers or the cloud. However, this approach increases system complexity and is susceptible to failure in cases where connectivity is unavailable. Furthermore, this communication restriction limits the approach\u2019s applicability in extreme industrial environments where operating conditions affect communication and access to the system. This paper proposes and evaluates an end-to-end adaptable and configurable anomaly detection system that uses the Internet of Things (IoT), edge computing, and Tiny-MLOps methodologies in an extreme industrial environment such as submersible pumps. The system runs on an IoT sensing Kit, based on an ESP32 microcontroller and MicroPython firmware, located near the data source. The processing pipeline on the sensing device collects data, trains an anomaly detection model, and alerts an external gateway in the event of an anomaly. The anomaly detection model uses the isolation forest algorithm, which can be trained on the microcontroller in just 1.2 to 6.4 s and detect an anomaly in less than 16 milliseconds with an ensemble of 50 trees and 80 KB of RAM. Additionally, the system employs blockchain technology to provide a transparent and irrefutable repository of anomalies.<\/jats:p>","DOI":"10.3390\/s23042344","type":"journal-article","created":{"date-parts":[[2023,2,20]],"date-time":"2023-02-20T06:37:59Z","timestamp":1676875079000},"page":"2344","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":85,"title":["An Adaptable and Unsupervised TinyML Anomaly Detection System for Extreme Industrial Environments"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1685-0264","authenticated-orcid":false,"given":"Mattia","family":"Antonini","sequence":"first","affiliation":[{"name":"Fondazione Bruno Kessler, Via Sommarive 18, 38123 Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5847-2145","authenticated-orcid":false,"given":"Miguel","family":"Pincheira","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler, Via Sommarive 18, 38123 Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4426-8220","authenticated-orcid":false,"given":"Massimo","family":"Vecchio","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler, Via Sommarive 18, 38123 Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5221-7752","authenticated-orcid":false,"given":"Fabio","family":"Antonelli","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler, Via Sommarive 18, 38123 Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,2,20]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"100118","DOI":"10.1016\/j.iot.2019.100118","article-title":"Transformative effects of IoT, Blockchain and Artificial Intelligence on cloud computing: Evolution, vision, trends and open challenges","volume":"8","author":"Gill","year":"2019","journal-title":"Internet Things"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"67594","DOI":"10.1109\/ACCESS.2018.2877523","article-title":"Smart Audio Sensors in the Internet of Things Edge for Anomaly Detection","volume":"6","author":"Antonini","year":"2018","journal-title":"IEEE Access"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1109\/IOTM.0001.1900029","article-title":"Fog Computing Architectures: A Reference for Practitioners","volume":"2","author":"Antonini","year":"2019","journal-title":"IEEE Internet Things Mag."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1109\/MPRV.2009.82","article-title":"The Case for VM-Based Cloudlets in Mobile Computing","volume":"8","author":"Satyanarayanan","year":"2009","journal-title":"IEEE Pervasive Comput."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Pincheira, M., Antonini, M., and Vecchio, M. (2022). Integrating the IoT and Blockchain Technology for the Next Generation of Mining Inspection Systems. Sensors, 22.","DOI":"10.3390\/s22030899"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"2462","DOI":"10.1109\/COMST.2020.3009103","article-title":"Edge Computing in Industrial Internet of Things: Architecture, Advances and Challenges","volume":"22","author":"Qiu","year":"2020","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Saboor, A., Hassan, M.F., Akbar, R., Shah, S.N.M., Hassan, F., Magsi, S.A., and Siddiqui, M.A. (2022). Containerized Microservices Orchestration and Provisioning in Cloud Computing: A Conceptual Framework and Future Perspectives. Appl. Sci., 12.","DOI":"10.3390\/app12125793"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1109\/MS.2017.24","article-title":"Microservices in practice, part 1: Reality check and service design","volume":"34","author":"Pautasso","year":"2017","journal-title":"IEEE Softw."},{"key":"ref_9","unstructured":"Data on Kubernetes Community (2021). Data on Kubernetes 2021\u2014Research Report, Data on Kubernetes Community. Technical Report."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Norris, D.J. (2020). Machine Learning with the Raspberry Pi, Apress.","DOI":"10.1007\/978-1-4842-5174-4"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"\u00c1lvarez, J.L., Mozo, J.D., and Dur\u00e1n, E. (2021). Analysis of Single Board Architectures Integrating Sensors Technologies. Sensors, 21.","DOI":"10.3390\/s21186303"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Pau, D., and Ambrose, P.K. (2022, January 14\u201316). Automated Neural and On-Device Learning for Micro Controllers. Proceedings of the IEEE 21st Mediterranean Electrotechnical Conference (MELECON), Palermo, Italy.","DOI":"10.1109\/MELECON53508.2022.9843050"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Antonini, M., Pincheira, M., Vecchio, M., and Antonelli, F. (2022, January 7\u20139). A TinyML approach to non-repudiable anomaly detection in extreme industrial environments. Proceedings of the IEEE International Workshop on Metrology for Industry 4.0 & IoT (MetroInd4.0&IoT), Trento, Italy.","DOI":"10.1109\/MetroInd4.0IoT54413.2022.9831517"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Yu, Y., and Ding, B. (2020, January 23\u201325). Towards MLOps: A Case Study of ML Pipeline Platform. Proceedings of the International Conference on Artificial Intelligence and Computer Engineering (ICAICE), Beijing, China.","DOI":"10.1109\/ICAICE51518.2020.00102"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Han, H., and Siebert, J. (2022, January 21\u201324). TinyML: A Systematic Review and Synthesis of Existing Research. Proceedings of the International Conference on Artificial Intelligence in Information and Communication (ICAIIC), Jeju Island, Republic of Korea.","DOI":"10.1109\/ICAIIC54071.2022.9722636"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Antonini, M., Pincheira, M., Vecchio, M., and Antonelli, F. (2022, January 25\u201326). Tiny-MLOps: A framework for orchestrating ML applications at the far edge of IoT systems. Proceedings of the IEEE International Conference on Evolving and Adaptive Intelligent Systems (EAIS), Larnaca, Cyprus.","DOI":"10.1109\/EAIS51927.2022.9787703"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Kim, D., Cha, J., Oh, S., and Jeong, J. (2021, January 4\u20136). AnoGAN-Based Anomaly Filtering for Intelligent Edge Device in Smart Factory. Proceedings of the 15th International Conference on Ubiquitous Information Management and Communication (IMCOM), Seoul, Republic of Korea.","DOI":"10.1109\/IMCOM51814.2021.9377409"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"8977","DOI":"10.1109\/TII.2022.3167478","article-title":"Privacy-Preserving Anomaly Detection in Cloud Manufacturing Via Federated Transformer","volume":"18","author":"Ma","year":"2022","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"G\u00fcltekin, O., Cinar, E., \u00d6zkan, K., and Yaz\u0131c\u0131, A. (2022). Real-Time Fault Detection and Condition Monitoring for Industrial Autonomous Transfer Vehicles Utilizing Edge Artificial Intelligence. Sensors, 22.","DOI":"10.3390\/s22093208"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Pham, D.A., Le, A.D., Pham, D.T., and Vo, H.B. (2021, January 21\u201322). AlertTrap: On Designing An Edge-Computing Remote Insect Monitoring System. Proceedings of the 8th NAFOSTED Conference on Information and Computer Science (NICS), Hanoi, Vietnam.","DOI":"10.1109\/NICS54270.2021.9701558"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Saradopoulos, I., Potamitis, I., Ntalampiras, S., Konstantaras, A.I., and Antonidakis, E.N. (2022). Edge Computing for Vision-Based, Urban-Insects Traps in the Context of Smart Cities. Sensors, 22.","DOI":"10.3390\/s22052006"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"10719","DOI":"10.1007\/s00521-022-07007-9","article-title":"CDNet: A real-time and robust crosswalk detection network on Jetson nano based on YOLOv5","volume":"34","author":"Zhang","year":"2022","journal-title":"Neural Comput. Appl."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Schizas, N., Karras, A., Karras, C., and Sioutas, S. (2022). TinyML for Ultra-Low Power AI and Large Scale IoT Deployments: A Systematic Review. Future Internet, 14.","DOI":"10.3390\/fi14120363"},{"key":"ref_24","unstructured":"Sudharsan, B., Salerno, S., Nguyen, D.D., Yahya, M., Wahid, A., Yadav, P., Breslin, J.G., and Ali, M.I. (July, January 14). TinyML Benchmark: Executing Fully Connected Neural Networks on Commodity Microcontrollers. Proceedings of the IEEE 7th World Forum on Internet of Things (WF-IoT), New Orleans, LA, USA."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1016\/j.ins.2022.07.129","article-title":"TiWS-iForest: Isolation forest in weakly supervised and tiny ML scenarios","volume":"610","author":"Barbariol","year":"2022","journal-title":"Inf. Sci."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Liu, F.T., Ting, K.M., and Zhou, Z.H. (2008, January 15\u201319). Isolation Forest. Proceedings of the 8th IEEE International Conference on Data Mining, Pisa, Italy.","DOI":"10.1109\/ICDM.2008.17"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Andrade, P., Silva, I., Signoretti, G., Silva, M., Dias, J., Marques, L., and Costa, D.G. (2021, January 7\u20139). An Unsupervised TinyML Approach Applied for Pavement Anomalies Detection Under the Internet of Intelligent Vehicles. Proceedings of the IEEE International Workshop on Metrology for Industry 4.0 & IoT (MetroInd4.0&IoT), Rome, Italy.","DOI":"10.1109\/MetroInd4.0IoT51437.2021.9488546"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Angelov, P. (2014, January 9\u201312). Anomaly detection based on eccentricity analysis. Proceedings of the IEEE Symposium on Evolving and Autonomous Learning Systems (EALS), Orlando, FL, USA.","DOI":"10.1109\/EALS.2014.7009497"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Alati, M.F., Fortino, G., Morales, J., Cecilia, J.M., and Manzoni, P. (2022, January 8\u201311). Time series analysis for temperature forecasting using TinyML. Proceedings of the IEEE 19th Annual Consumer Communications & Networking Conference (CCNC), Las Vegas, NV, USA.","DOI":"10.1109\/CCNC49033.2022.9700573"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Xu, K., Zhang, H., Li, Y., Zhang, Y., Lai, R., and Liu, Y. (2023). An Ultra-low Power TinyML System for Real-time Visual Processing at Edge. IEEE Trans. Circuits Syst. II Express Briefs.","DOI":"10.1109\/TCSII.2023.3239044"},{"key":"ref_31","unstructured":"Doyu, H., and Morabito, R. (2023, January 24). TinyML as-a-Service: What Is It and What Does It Mean for the IoT Edge?. Available online: https:\/\/www.ericsson.com\/en\/blog\/2019\/12\/tinyml-as-a-service-iot-edge."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Ren, H., Anicic, D., and Runkler, T.A. (2021, January 18\u201322). TinyOL: TinyML with Online-Learning on Microcontrollers. Proceedings of the International Joint Conference on Neural Networks (IJCNN), Shenzhen, China.","DOI":"10.1109\/IJCNN52387.2021.9533927"},{"key":"ref_33","first-page":"11285","article-title":"TinyTL: Reduce Memory, Not Parameters for Efficient On-Device Learning","volume":"Volume 33","author":"Larochelle","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Sudharsan, B., Breslin, J.G., and Ali, M.I. (2020, January 6\u20139). Edge2train: A framework to train machine learning models (svms) on resource-constrained iot edge devices. Proceedings of the 10th International Conference on the Internet of Things (IoT\u201920), Malm\u00f6, Sweden.","DOI":"10.1145\/3410992.3411014"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Sudharsan, B., Yadav, P., Breslin, J.G., and Intizar Ali, M. (2021, January 18\u201321). Train++: An Incremental ML Model Training Algorithm to Create Self-Learning IoT Devices. Proceedings of the IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Internet of People and Smart City Innovation (SmartWorld\/SCALCOM\/UIC\/ATC\/IOP\/SCI), Atlanta, GA, USA.","DOI":"10.1109\/SWC50871.2021.00023"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"100437","DOI":"10.1016\/j.iot.2021.100437","article-title":"AnoML-IoT: An end to end re-configurable multi-protocol anomaly detection pipeline for Internet of Things","volume":"16","author":"Kayan","year":"2021","journal-title":"Internet Things"},{"key":"ref_37","unstructured":"Treveil, M., Omont, N., Stenac, C., Lefevre, K., Phan, D., Zentici, J., Lavoillotte, A., Miyazaki, M., and Heidmann, L. (2020). Introducing MLOps, O\u2019Reilly Media, Inc."},{"key":"ref_38","unstructured":"(2011). Standard No. Standard CENELEC EN 50065-1:2011."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"105889","DOI":"10.1016\/j.compag.2020.105889","article-title":"Cost-effective IoT devices as trustworthy data sources for a blockchain-based water management system in precision agriculture","volume":"180","author":"Pincheira","year":"2021","journal-title":"Comput. Electron. Agric."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Pincheira, M., and Vecchio, M. (2020, January 7\u201311). Towards Trusted Data on Decentralized IoT Applications: Integrating Blockchain in Constrained Devices. Proceedings of the IEEE International Conference on Communications Workshops (ICC Workshops), Dublin, Ireland.","DOI":"10.1109\/ICCWorkshops49005.2020.9145328"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1676","DOI":"10.1109\/COMST.2018.2886932","article-title":"Applications of Blockchains in the Internet of Things: A Comprehensive Survey","volume":"21","author":"Ali","year":"2018","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_42","unstructured":"Prieto, J., Ben\u00edtez Mart\u00ednez, F.L., Ferretti, S., Arroyo Guarde\u00f1o, D., and Tom\u00e1s Nevado-Batalla, P. (2022, January 13\u201315). SmartTwin: A Blockchain-Based Software Framework for Digital Twins Using IoT. Proceedings of the 4th International Congress of Blockchain and Applications, L\u2019Aquila, Italy."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","article-title":"Array programming with NumPy","volume":"585","author":"Harris","year":"2020","journal-title":"Nature"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python","volume":"17","author":"Virtanen","year":"2020","journal-title":"Nat. Methods"},{"key":"ref_45","unstructured":"Banbury, C., Reddi, V.J., Torelli, P., Holleman, J., Jeffries, N., Kiraly, C., Montino, P., Kanter, D., Ahmed, S., and Pau, D. (2021, January 6\u201314). MLPerf Tiny Benchmark. Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, Virtual Conference."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Antonini, M., Vu, T.H., Min, C., Montanari, A., Mathur, A., and Kawsar, F. (2019, January 10\u201313). Resource Characterisation of Personal-Scale Sensing Models on Edge Accelerators. Proceedings of the First International Workshop on Challenges in Artificial Intelligence and Machine Learning for Internet of Things\u2014AIChallengeIoT\u201919, New York, NY, USA.","DOI":"10.1145\/3363347.3363363"},{"key":"ref_47","unstructured":"Prieto, J., Ben\u00edtez Mart\u00ednez, F.L., Ferretti, S., Arroyo Guarde\u00f1o, D., and Tom\u00e1s Nevado-Batalla, P. (2022, January 13\u201315). Towards an Infrastructure Cost Model for Blockchain-Based Applications. Proceedings of the 4th International Congress of Blockchain and Applications, L\u2019Aquila, Italy."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/4\/2344\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:37:16Z","timestamp":1760121436000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/4\/2344"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,20]]},"references-count":47,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2023,2]]}},"alternative-id":["s23042344"],"URL":"https:\/\/doi.org\/10.3390\/s23042344","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,20]]}}}