{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T14:20:36Z","timestamp":1772202036944,"version":"3.50.1"},"reference-count":41,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Maintaining consistent and accurate temperature is critical for the safe and effective storage of vaccines. Traditional monitoring methods often lack real-time capabilities and may not be sensitive enough to detect subtle anomalies. This paper presents a novel deep learning-based system for real-time temperature fault detection in refrigeration systems used for vaccine storage. Our system utilizes a semi-supervised Convolutional Autoencoder (CAE) model deployed on a resource-constrained ESP32 microcontroller. The CAE is trained on real-world temperature sensor data to capture temporal patterns and reconstruct normal temperature profiles. Deviations from the reconstructed profiles are flagged as potential anomalies, enabling real-time fault detection. Evaluation using real-time data demonstrates an impressive 92% accuracy in identifying temperature faults. The system\u2019s low energy consumption (0.05 watts) and memory usage (1.2\u2009MB) make it suitable for deployment in resource-constrained environments. This work paves the way for improved monitoring and fault detection in refrigeration systems, ultimately contributing to the reliable storage of life-saving vaccines.<\/jats:p>","DOI":"10.3389\/frai.2024.1429602","type":"journal-article","created":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T05:12:04Z","timestamp":1722489124000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Real-time temperature anomaly detection in vaccine refrigeration systems using deep learning on a resource-constrained microcontroller"],"prefix":"10.3389","volume":"7","author":[{"given":"Mokhtar","family":"Harrabi","sequence":"first","affiliation":[]},{"given":"Abdelaziz","family":"Hamdi","sequence":"additional","affiliation":[]},{"given":"Bouraoui","family":"Ouni","sequence":"additional","affiliation":[]},{"given":"Jamel","family":"Bel Hadj Tahar","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2024,8,1]]},"reference":[{"key":"ref1","first-page":"1","article-title":"Enhancing payment security through AI-driven anomaly detection and predictive analytics","volume":"7","author":"Agrawal","year":"2022","journal-title":"Int. J. Sustain. Infrastruct. Cities Soc."},{"key":"ref2","first-page":"101126","article-title":"Uncovering sensor faults in wind turbines: An improved multivariate statistical approach for condition monitoring using SCADA data","volume-title":"Sustainable energy, grids and networks","author":"Harrou","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"80543","DOI":"10.1109\/ACCESS.2023.3300658","article-title":"Opportunities, applications, and challenges of edge-AI enabled video analytics in smart cities: a systematic review","volume":"11","author":"Badidi","year":"2023","journal-title":"IEEE Access"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1007\/978-3-030-83819-5_7","article-title":"A review of tree-based approaches for anomaly detection","volume-title":"Control charts and machine learning for anomaly detection in manufacturing","author":"Barbariol","year":"2022"},{"key":"ref5","author":"Chalapathy","year":"2019"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"1889","DOI":"10.3390\/s23041889","article-title":"Generative adversarial network-based fault detection in semiconductor equipment with class-imbalanced data","volume":"23","author":"Choi","year":"2023","journal-title":"Sensors"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2023.3241085","article-title":"Detection of subtle thermal anomalies: deep learning applied to the ASTER global volcano dataset","volume":"61","author":"Corradino","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"18059","DOI":"10.1109\/JIOT.2024.3360882","article-title":"Neural architecture search for anomaly detection in time series data of smart buildings: a reinforcement learning approach for optimal autoencoder design","volume":"11","author":"Dissem","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"8613","DOI":"10.3390\/s23208613","article-title":"Real-time anomaly detection for water quality sensor monitoring based on multivariate deep learning technique","volume":"23","author":"El-Shafeiy","year":"2023","journal-title":"Sensors"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"5774","DOI":"10.3390\/en15165774","article-title":"Fault identification and fault impact analysis of the vapor compression refrigeration Systems in Buildings: a system reliability approach","volume":"15","author":"Fadaeefath Abadi","year":"2022","journal-title":"Energies"},{"key":"ref11","author":"Farahani","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"122157","DOI":"10.1016\/j.apenergy.2023.122157","article-title":"Enhancing anomaly detection accuracy and interpretability in low-quality and class imbalanced data: a comprehensive approach","volume":"353","author":"Gao","year":"2024","journal-title":"Appl. Energy"},{"key":"ref13","author":"Harrabi","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"102037","DOI":"10.1016\/j.rineng.2024.102037","article-title":"Detecting the signs of desertification with Landsat imagery: a semi-supervised anomaly detection approach","volume":"22","author":"Harrou","year":"2024","journal-title":"Res. Eng."},{"key":"ref15","author":"Himeur","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"3283","DOI":"10.3390\/electronics12153283","article-title":"A review of anomaly detection strategies to detect threats to cyber-physical systems","volume":"12","author":"Jeffrey","year":"2023","journal-title":"Electronics"},{"key":"ref17","author":"Ji","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"035109","DOI":"10.1088\/1361-6501\/ad11c6","article-title":"Sensor self-diagnosis method based on a graph neural network","volume":"35","author":"Jiang","year":"2023","journal-title":"Meas. Sci. Technol."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"105675","DOI":"10.1016\/j.engappai.2022.105675","article-title":"Assessment of the spatiotemporal prediction capabilities of machine learning algorithms on sea surface temperature data: a comprehensive study","volume":"118","author":"Kartal","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"495","DOI":"10.3390\/bioengineering10040495","article-title":"Point-of-interest preference model using an attention mechanism in a convolutional neural network","volume":"10","author":"Kasgari","year":"2023","journal-title":"Bioengineering"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"100504","DOI":"10.1016\/j.jii.2023.100504","article-title":"Analysis of multi-dimensional industrial IoT (IIoT) data in edge-fog-cloud based architectural frameworks: a survey on current state and research challenges","volume":"35","author":"Kumar","year":"2023","journal-title":"J. Ind. Inf. Integr."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1007\/s40745-021-00344-x","article-title":"A comprehensive comparative study of artificial neural network (ANN) and support vector machines (SVM) on stock forecasting","volume":"10","author":"Kurani","year":"2023","journal-title":"Ann. Data Sci."},{"key":"ref23","article-title":"Low runtime approach for fault detection for refrigeration systems in smart homes using wavelet transform","author":"Lemes","year":"2023","journal-title":"IEEE Trans. Consum. Electron."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"109287","DOI":"10.1016\/j.est.2023.109287","article-title":"Voltage fault diagnosis and misdiagnosis analysis of battery systems using the modified Shannon entropy in real-world electric vehicles","volume":"73","author":"Liu","year":"2023","journal-title":"J. Energy Storage"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"105013","DOI":"10.1016\/j.jobe.2022.105013","article-title":"Real-time temperature predictions via state-space model and parameters identification within rack-based cooling data centers","volume":"58","author":"Liu","year":"2022","journal-title":"J. Build. Eng."},{"key":"ref26","doi-asserted-by":"publisher","first-page":"14285","DOI":"10.1109\/JIOT.2023.3243391","article-title":"Unsupervised deep learning for IoT time series","volume":"10","author":"Liu","year":"2023","journal-title":"IEEE Internet Things J."},{"key":"ref27","author":"Mohammad","year":"2020"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.1109\/ICSSA.2018.8535867","article-title":"The implementation of IoT based smart refrigerator system","volume-title":"2018 2nd International conference on smart sensors and application (ICSSA)","author":"Nasir","year":"2018"},{"key":"ref29","first-page":"1326","article-title":"Data-driven approaches for impending fault detection of industrial systems: a review","author":"Patil","year":"2022","journal-title":"Int. J. Syst. Assur. Eng. Manag."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"100451","DOI":"10.1016\/j.mlwa.2023.100451","article-title":"Semi-supervised visual anomaly detection based on convolutional autoencoder and transfer learning","volume":"11","author":"Saeedi","year":"2023","journal-title":"Mach. Learn. Appl."},{"key":"ref31","doi-asserted-by":"publisher","first-page":"1361","DOI":"10.1038\/s41467-024-45578-4","article-title":"\u03b2-Variational autoencoders and transformers for reduced-order modelling of fluid flows","volume":"15","author":"Solera-Rico","year":"2024","journal-title":"Nat. Commun."},{"key":"ref32","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1016\/j.ijrefrig.2022.08.008","article-title":"Fault detection and diagnosis in refrigeration systems using machine learning algorithms","volume":"144","author":"Soltani","year":"2022","journal-title":"Int. J. Refrig."},{"key":"ref33","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1080\/10618600.2020.1807997","article-title":"Anomaly detection in high-dimensional data","volume":"30","author":"Talagala","year":"2021","journal-title":"J. Comput. Graph. Stat."},{"key":"ref34","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1109\/TAI.2023.3249685","article-title":"A generative neighborhood-based deep autoencoder for robust imbalanced classification","volume":"5","author":"Troullinou","year":"2023","journal-title":"IEEE Trans. Artif. Intel."},{"key":"ref35","doi-asserted-by":"publisher","first-page":"1695","DOI":"10.1016\/j.vaccine.2022.02.036","article-title":"Vaccine supply chain: resilience-by-design and resilience-by-intervention","volume":"40","author":"Trump","year":"2022","journal-title":"Vaccine"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"121297","DOI":"10.1016\/j.biomaterials.2021.121297","article-title":"Emerging biomaterial-based strategies for personalized therapeutic in situ cancer vaccines","volume":"280","author":"Viswanath","year":"2022","journal-title":"Biomaterials"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"102027","DOI":"10.1016\/j.aei.2023.102027","article-title":"Adaptive variational autoencoding generative adversarial networks for rolling bearing fault diagnosis","volume":"56","author":"Wang","year":"2023","journal-title":"Adv. Eng. Inform."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"2337128","DOI":"10.1080\/20523211.2024.2337128","article-title":"Vaccine storage and stock management practices in Vihiga County, Kenya","volume":"17","author":"Wanyonyi","year":"2024","journal-title":"J. Pharm. Policy Pract."},{"key":"ref39","doi-asserted-by":"publisher","first-page":"28745","DOI":"10.1007\/s10489-023-05029-x","article-title":"Variable-wise generative adversarial transformer in multivariate time series anomaly detection","volume":"53","author":"Yang","year":"2023","journal-title":"Appl. Intell."},{"key":"ref40","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1109\/TSMC.2020.2968516","article-title":"Anomaly detection based on convolutional recurrent autoencoder for IoT time series","volume":"52","author":"Yin","year":"2020","journal-title":"IEEE Trans. Syst. Man. Cybern. Syst."},{"key":"ref41","doi-asserted-by":"publisher","first-page":"2528","DOI":"10.3390\/s23052528","article-title":"Current status and prospects of research on sensor fault diagnosis of agricultural internet of things","volume":"23","author":"Zou","year":"2023","journal-title":"Sensors"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1429602\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T05:12:10Z","timestamp":1722489130000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1429602\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,1]]},"references-count":41,"alternative-id":["10.3389\/frai.2024.1429602"],"URL":"https:\/\/doi.org\/10.3389\/frai.2024.1429602","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,1]]},"article-number":"1429602"}}