{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T18:15:16Z","timestamp":1781633716404,"version":"3.54.5"},"reference-count":19,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"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>Computing has undergone a significant transformation over the past two decades, shifting from a machine-based approach to a human-centric, virtually invisible service known as ubiquitous or pervasive computing. This change has been achieved by incorporating small embedded devices into a larger computational system, connected through networking and referred to as edge devices. When these devices are also connected to the Internet, they are generally named Internet-of-Thing (IoT) devices. Developing Machine Learning (ML) algorithms on these types of devices allows them to provide Artificial Intelligence (AI) inference functions such as computer vision, pattern recognition, etc. However, this capability is severely limited by the device\u2019s resource scarcity. Embedded devices have limited computational and power resources available while they must maintain a high degree of autonomy. While there are several published studies that address the computational weakness of these small systems-mostly through optimization and compression of neural networks- they often neglect the power consumption and efficiency implications of these techniques. This study presents power efficiency experimental results from the application of well-known and proven optimization methods using a set of well-known ML models. The results are presented in a meaningful manner considering the \u201creal world\u201d functionality of devices and the provided results are compared with the basic \u201cidle\u201d power consumption of each of the selected systems. Two different systems with completely different architectures and capabilities were used providing us with results that led to interesting conclusions related to the power efficiency of each architecture.<\/jats:p>","DOI":"10.3390\/s23031595","type":"journal-article","created":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T05:33:53Z","timestamp":1675229633000},"page":"1595","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":57,"title":["Power Efficient Machine Learning Models Deployment on Edge IoT Devices"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0911-5018","authenticated-orcid":false,"given":"Anastasios","family":"Fanariotis","sequence":"first","affiliation":[{"name":"Digital Systems and Media Computing Lab, School of Sciences and Technology, Hellenic Open University, 26334 Patras, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Theofanis","family":"Orphanoudakis","sequence":"additional","affiliation":[{"name":"Digital Systems and Media Computing Lab, School of Sciences and Technology, Hellenic Open University, 26334 Patras, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Konstantinos","family":"Kotrotsios","sequence":"additional","affiliation":[{"name":"Digital Systems and Media Computing Lab, School of Sciences and Technology, Hellenic Open University, 26334 Patras, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6428-7480","authenticated-orcid":false,"given":"Vassilis","family":"Fotopoulos","sequence":"additional","affiliation":[{"name":"Digital Systems and Media Computing Lab, School of Sciences and Technology, Hellenic Open University, 26334 Patras, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"George","family":"Keramidas","sequence":"additional","affiliation":[{"name":"Department of Informatics, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4971-826X","authenticated-orcid":false,"given":"Panagiotis","family":"Karkazis","sequence":"additional","affiliation":[{"name":"Digital Systems and Media Computing Lab, School of Sciences and Technology, Hellenic Open University, 26334 Patras, Greece"},{"name":"Department of Informatics and Computer Engineering, University of West Attica, 12243 Athens, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,2,1]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1016\/j.pmcj.2011.10.001","article-title":"Looking ahead in pervasive computing: Challenges and opportunities in the era of cyber\u2013physical convergence","volume":"8","author":"Conti","year":"2012","journal-title":"Pervasive Mob. Comput."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Dhingra, V., and Anita, A. (2008, January 16\u201318). Pervasive computing: Paradigm for new era computing. Proceedings of the 2008 First International Conference on Emerging Trends in Engineering and Technology, Nagpur, India.","DOI":"10.1109\/ICETET.2008.170"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Swief, A., and El-Habrouk, M. (2018, January 28\u201330). A survey of automotive driving assistance systems technologies. Proceedings of the 2018 International Conference on Artificial Intelligence and Data Processing (IDAP), Malatya, Turkey.","DOI":"10.1109\/IDAP.2018.8620826"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"12241","DOI":"10.1007\/s00500-021-05896-x","article-title":"IoT-based traffic prediction and traffic signal control system for smart city","volume":"25","author":"Neelakandan","year":"2021","journal-title":"Soft Comput."},{"key":"ref_5","unstructured":"Darling (2022, December 28). IoT vs. Edge Computing: What\u2019s the Difference? IBM Developer, 2021. Available online: https:\/\/developer.ibm.com\/articles\/iot-vs-edge-computing\/."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Ajani, T.S., Agbotiname Lucky, I., and Aderemi, A.A. (2021). An overview of machine learning within embedded and mobile devices\u2013optimizations and applications. Sensors, 21.","DOI":"10.3390\/s21134412"},{"key":"ref_7","unstructured":"Kugele, A., Pfeil, T., Pfeiffer, M., and Chicca, E. (October, January 28). Hybrid SNN-ANN: Energy-Efficient Classification and Object Detection for Event-Based Vision. Proceedings of the DAGM German Conference on Pattern Recognition, Bonn, Germany."},{"key":"ref_8","unstructured":"Han, S., Huizi, M., and William, J.D. (2015). Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Hu, P., Peng, X., Zhu, H., Aly MM, S., and Lin, J. (2021, January 2\u20139). Opq: Compressing deep neural networks with one-shot pruning-quantization. Proceedings of the AAAI Conference on Artificial Intelligence, Virtual Conference.","DOI":"10.1609\/aaai.v35i9.16950"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Chen, B., Bakhshi, A., Batista, G., Ng, B., and Chin, T.J. (2022, January 24\u201318). Update Compression for Deep Neural Networks on the Edge. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPRW56347.2022.00347"},{"key":"ref_11","unstructured":"Sudharsan, B., Sundaram, D., Patel, P., Breslin, J.G., Ali, M.I., Dustdar, S., and Ranjan, R. (2022). Multi-Component Optimization and Efficient Deployment of Neural-Networks on Resource-Constrained IoT Hardware. arXiv."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Zou, Z., Jin, Y., Nevalainen, P., Huan, Y., Heikkonen, J., and Westerlund, T. (2019, January 18\u201320). Edge and fog computing enabled AI for IoT-an overview. Proceedings of the 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS), Hsinchu, Taiwan.","DOI":"10.1109\/AICAS.2019.8771621"},{"key":"ref_13","unstructured":"Unlu, H. (2020). Efficient neural network deployment for microcontroller. arXiv."},{"key":"ref_14","unstructured":"Liberis, E., and Lane, N.D. (2019). Neural networks on microcontrollers: Saving memory at inference via operator reordering. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Kotrotsios, K., Fanariotis, A., Leligou, H.C., and Orphanoudakis, T. (2022). Design Space Exploration of a Multi-Model AI-Based Indoor Localization System. Sensors, 22.","DOI":"10.3390\/s22020570"},{"key":"ref_16","unstructured":"LeCun, Y. (2023, January 30). LeNet-5, Convolutional Neural Networks. Available online: http:\/\/yann.lecun.com\/exdb\/lenet."},{"key":"ref_17","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., and Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Pau, D., Lattuada, M., Loro, F., De Vita, A., and Licciardo, G.D. (2021, January 10\u201312). Comparing industry frameworks with deeply quantized neural networks on microcontrollers. Proceedings of the 2021 IEEE International Conference on Consumer Electronics (ICCE), Las Vegas, NV, USA.","DOI":"10.1109\/ICCE50685.2021.9427638"},{"key":"ref_19","first-page":"1595","article-title":"A review on TinyML: State-of-the-art and prospects","volume":"34","author":"Ray","year":"2021","journal-title":"J. King Saud Univ. Comp. Inf. Sci."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/3\/1595\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:21:05Z","timestamp":1760120465000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/3\/1595"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,1]]},"references-count":19,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2023,2]]}},"alternative-id":["s23031595"],"URL":"https:\/\/doi.org\/10.3390\/s23031595","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,1]]}}}