{"title":"coSense","authors":"Stephan Schmeißer, Gregor Schiele","doi":"10.1145/3395233","DOIUrl":null,"url":null,"abstract":"We present coSense—the collaborative, fault-tolerant, and adaptive sensing middleware for the Internet-of-Things (IoT). By actively harnessing the greatest asset of the IoT, the sheer number of devices, coSense is able to provide easy data acquisition with quality-of-service-based data cleaning by combining unsupervised learning and information fusion. It can also greatly improve sensor accuracy and fault tolerance to produce measurements specifically tailored for modern data-driven IoT empowered applications. In this article, we focus on the general concepts behind coSense and evaluate the accuracy gain based on a real-world dataset.","PeriodicalId":93404,"journal":{"name":"ACM/IMS transactions on data science","volume":"125 1","pages":"1 - 21"},"PeriodicalIF":0.0000,"publicationDate":"2020-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACM/IMS transactions on data science","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3395233","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3
Abstract
We present coSense—the collaborative, fault-tolerant, and adaptive sensing middleware for the Internet-of-Things (IoT). By actively harnessing the greatest asset of the IoT, the sheer number of devices, coSense is able to provide easy data acquisition with quality-of-service-based data cleaning by combining unsupervised learning and information fusion. It can also greatly improve sensor accuracy and fault tolerance to produce measurements specifically tailored for modern data-driven IoT empowered applications. In this article, we focus on the general concepts behind coSense and evaluate the accuracy gain based on a real-world dataset.