{"title":"Cognitive IoT enabled by Layered Architecture and Neural Networks in a Smart Home Environment","authors":"Abdon Serianni, F. Rango, P. Raimondo","doi":"10.1109/WD52248.2021.9508326","DOIUrl":null,"url":null,"abstract":"Internet of Things (IoT) is playing an important role in a Smart Home Environment in the last few years. An IoT architecture is proposed to manage a heterogeneous set of smart devices in the home environment. The network infrastructure is improved using IoT protocols like Message Queuing Telemetry Transport (MQTT). A Cognitive Smart Object is used to support the management of thermal comfort in the Smart Home context. Neural Networks are used for suggested action prediction and anomaly detection operations based on the user’s habits. The Continuous Learning mechanism is described, which considers user feedback to shape the neural network and obtain a neural network that follows user behaviors that deviate from standard behavior.","PeriodicalId":294745,"journal":{"name":"2021 Wireless Days (WD)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 Wireless Days (WD)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/WD52248.2021.9508326","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Internet of Things (IoT) is playing an important role in a Smart Home Environment in the last few years. An IoT architecture is proposed to manage a heterogeneous set of smart devices in the home environment. The network infrastructure is improved using IoT protocols like Message Queuing Telemetry Transport (MQTT). A Cognitive Smart Object is used to support the management of thermal comfort in the Smart Home context. Neural Networks are used for suggested action prediction and anomaly detection operations based on the user’s habits. The Continuous Learning mechanism is described, which considers user feedback to shape the neural network and obtain a neural network that follows user behaviors that deviate from standard behavior.