{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:12:05Z","timestamp":1778256725809,"version":"3.51.4"},"reference-count":28,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2025,4,18]],"date-time":"2025-04-18T00:00:00Z","timestamp":1744934400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Future Internet"],"abstract":"<jats:p>The increasing adoption of smart home technologies has intensified the demand for real-time anomaly detection to improve security, energy efficiency, and device reliability. Traditional cloud-based approaches introduce latency, privacy concerns, and network dependency, making Edge AI a compelling alternative for low-latency, on-device processing. This paper presents an Edge AI-based anomaly detection framework that combines Isolation Forest (IF) and Long Short-Term Memory Autoencoder (LSTM-AE) models to identify anomalies in IoT sensor data. The system is evaluated on both synthetic and real-world smart home datasets, including temperature, motion, and energy consumption signals. Experimental results show that LSTM-AE achieves higher detection accuracy (up to 93.6%) and recall but requires more computational resources. In contrast, IF offers faster inference and lower power consumption, making it suitable for constrained environments. A hybrid architecture integrating both models is proposed to balance accuracy and efficiency, achieving sub-50 ms inference latency on embedded platforms such as Raspberry Pi and NVIDEA Jetson Nano. Optimization strategies such as quantization reduced LSTM-AE inference time by 76% and power consumption by 35%. Adaptive learning mechanisms, including federated learning, are also explored to minimize cloud dependency and enhance data privacy. These findings demonstrate the feasibility of deploying real-time, privacy-preserving, and energy-efficient anomaly detection directly on edge devices. The proposed framework can be extended to other domains such as smart buildings and industrial IoT. Future work will investigate self-supervised learning, transformer-based detection, and deployment in real-world operational settings.<\/jats:p>","DOI":"10.3390\/fi17040179","type":"journal-article","created":{"date-parts":[[2025,4,18]],"date-time":"2025-04-18T06:23:56Z","timestamp":1744957436000},"page":"179","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":42,"title":["Edge AI for Real-Time Anomaly Detection in Smart Homes"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8872-5721","authenticated-orcid":false,"given":"Manuel J. C. S.","family":"Reis","sequence":"first","affiliation":[{"name":"Engineering Department, University of Tr\u00e1s-os-Montes e Alto Douro, 5000-801 Vila Real, Portugal"},{"name":"IEETA\u2014Institute of Electronics and Informatics Engineering of Aveiro, 3810-193 Aveiro, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4632-9664","authenticated-orcid":false,"given":"Carlos","family":"Ser\u00f4dio","sequence":"additional","affiliation":[{"name":"Engineering Department, University of Tr\u00e1s-os-Montes e Alto Douro, 5000-801 Vila Real, Portugal"},{"name":"Algoritmi Center, 4800-058 Guimar\u00e3es, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2025,4,18]]},"reference":[{"key":"ref_1","unstructured":"Advantech Co., Ltd. (2025, February 13). Edge AI Explained: Uses, How it Works & More. Available online: https:\/\/www.advantech.com\/en-us\/resources\/industry-focus\/edge-ai."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"8514","DOI":"10.1109\/JIOT.2022.3194813","article-title":"CADeSH: Collaborative Anomaly Detection for Smart Homes","volume":"10","author":"Meidan","year":"2022","journal-title":"IEEE Int. Things J."},{"key":"ref_3","unstructured":"Gill, N.S. (2025, February 13). Edge AI for Smart Home Applications. Available online: https:\/\/www.xenonstack.com\/use-cases\/edge-ai-for-home-applications."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Xiao, J., Xu, Z., Zou, Q., Li, Q., Zhao, D., Fang, D., Li, R., Tang, W., Li, K., and Zuo, X. (2024, January 25\u201329). Make Your Home Safe: Time-aware Unsupervised User Behavior Anomaly Detection in Smart Homes via Loss-guided Mask. Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Barcelona, Spain.","DOI":"10.1145\/3637528.3671708"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"119462","DOI":"10.1109\/ACCESS.2023.3325929","article-title":"IoT Network Anomaly Detection in Smart Homes Using Machine Learning","volume":"11","author":"Sarwar","year":"2023","journal-title":"IEEE Access"},{"key":"ref_6","first-page":"45","article-title":"Enhancing unsupervised anomaly-based cyberattacks detection in smart homes through hyperparameter optimization","volume":"24","year":"2024","journal-title":"Int. J. Inf. Secur."},{"key":"ref_7","unstructured":"Holdren, W. (2022). Deep Learning Anomaly Detection Using Edge AI. [Master\u2019s Thesis, University of Central Florida]. Available online: https:\/\/stars.library.ucf.edu\/etd2020\/1026."},{"key":"ref_8","unstructured":"Arm Ltd. (2025, February 15). Edge AI, Arm|The Architecture for the Digital World. Available online: https:\/\/www.arm.com\/markets\/iot\/edge-ai."},{"key":"ref_9","unstructured":"Kotevska, O. (2025, February 15). Privacy by Design in Distributed Edge Systems: Innovating Secure Workflows for Smart Cities. Newsletter. Available online: https:\/\/smartcities.ieee.org\/newsletter\/october-november-2024\/privacy-by-design-in-distributed-edge-systems-innovating-secure-workflows-for-smart-cities."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1817","DOI":"10.1109\/JIOT.2020.3017377","article-title":"Privacy-Preserving Blockchain-Based Federated Learning for IoT Devices","volume":"8","author":"Zhao","year":"2021","journal-title":"IEEE Int. Things J."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1007\/s10462-024-10774-7","article-title":"Survey: Federated learning data security and privacy-preserving in edge-Internet of Things","volume":"57","author":"Li","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Ragab, M., Ashary, E.B., Alghamdi, B.M., Aboalela, R., Alsaadi, N., Maghrabi, L.A., and Allehaibi, K.H. (2025). Advanced artificial intelligence with federated learning framework for privacy-preserving cyberthreat detection in IoT-assisted sustainable smart cities. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-88843-2"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3679013","article-title":"When Federated Learning Meets Privacy-Preserving Computation","volume":"56","author":"Chen","year":"2024","journal-title":"ACM Comput. Surveys"},{"key":"ref_14","unstructured":"Shimillas, C., Malialis, K., Fokianos, K., and Polycarpou, M.M. (2025). Transformer-Based Multivariate Time Series Anomaly Localization. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"9179","DOI":"10.1109\/JIOT.2021.3100509","article-title":"Learning Graph Structures With Transformer for Multivariate Time-Series Anomaly Detection in IoT","volume":"9","author":"Chen","year":"2022","journal-title":"IEEE Int. Things J."},{"key":"ref_16","unstructured":"Ruff, L., Vandermeulen, R., Goernitz, N., Deecke, L., Siddiqui, S.A., Binder, A., M\u00fcller, E., and Kloft, M. (2018, January 10\u201315). Deep One-Class Classification. Proceedings of the 35th International Conference on Machine Learning, Stockholm, Sweden. Available online: https:\/\/proceedings.mlr.press\/v80\/ruff18a.html."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Rahim, A., Zhong, Y., Ahmad, T., Ahmad, S., P\u0142awiak, P., and Hammad, M. (2023). Enhancing Smart Home Security: Anomaly Detection and Face Recognition in Smart Home IoT Devices Using Logit-Boosted CNN Models. Sensors, 23.","DOI":"10.3390\/s23156979"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Liu, F.T., Ting, K.M., and Zhou, Z.-H. (2008, January 15\u201319). Isolation Forest. Proceedings of the 2008 Eighth IEEE International Conference on Data Mining, Pisa, Italy.","DOI":"10.1109\/ICDM.2008.17"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"12492","DOI":"10.1038\/ncomms12492","article-title":"Magnetic torque anomaly in the quantum limit of the Weyl semi-metal NbAs","volume":"7","author":"Moll","year":"2016","journal-title":"Nat. Commun."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Kuzdeba, S., Carmack, J., and Robinson, J. (November, January 31). RF Fingerprinting with Dilated Causal Convolutions\u2013An Inherently Explainable Architecture. Proceedings of the 2021 55th Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA, USA.","DOI":"10.1109\/IEEECONF53345.2021.9723341"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1748","DOI":"10.1016\/j.ijforecast.2021.03.012","article-title":"Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting","volume":"37","author":"Lim","year":"2020","journal-title":"Int. J. Forecast."},{"key":"ref_22","unstructured":"Mehta, S., and Rastegari, M. (2022). MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Wardana, I.N.K., Gardner, J.W., and Fahmy, S.A. (2021). Optimising Deep Learning at the Edge for Accurate Hourly Air Quality Prediction. Sensors, 21.","DOI":"10.3390\/s21041064"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Mahmud, H., Kang, P., Desai, K., Lama, P., and Prasad, S. (2024). A Converting Autoencoder Toward Low-latency and Energy-efficient DNN Inference at the Edge. arXiv.","DOI":"10.1109\/IPDPSW63119.2024.00117"},{"key":"ref_25","unstructured":"(2025, February 17). Power Consumption Benchmarks|Raspberry Pi Dramble. Available online: https:\/\/www.pidramble.com\/wiki\/benchmarks\/power-consumption?utm_source=chatgpt.com."},{"key":"ref_26","unstructured":"Eames, A. (2025, February 17). How Much Power Does the Pi4B Use? Power Measurements. RasPi.TV. Available online: https:\/\/raspi.tv\/2019\/how-much-power-does-the-pi4b-use-power-measurements."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Jaramillo-Alcazar, A., Govea, J., and Villegas-Ch, W. (2023). Anomaly Detection in a Smart Industrial Machinery Plant Using IoT and Machine Learning. Sensors, 23.","DOI":"10.3390\/s23198286"},{"key":"ref_28","unstructured":"Bohutska, J. (2025, February 17). Anomaly Detection\u2014How to Tell Good Performance from Bad. Towards Data Science. Available online: https:\/\/towardsdatascience.com\/anomaly-detection-how-to-tell-good-performance-from-bad-b57116d71a10\/."}],"container-title":["Future Internet"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-5903\/17\/4\/179\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:17:08Z","timestamp":1760030228000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-5903\/17\/4\/179"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,18]]},"references-count":28,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,4]]}},"alternative-id":["fi17040179"],"URL":"https:\/\/doi.org\/10.3390\/fi17040179","relation":{},"ISSN":["1999-5903"],"issn-type":[{"value":"1999-5903","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,18]]}}}