A domain-independent methodology to analyze IoT data streams in real-time.A proof of concept implementation for anomaly detection from environmental data  

作　　者：Sergio Trilles Òscar Belmonte Sven Schade Joaquìn Huerta 

机构地区：[1]Institute of New Imaging Technologies,Universitat Jaume I,Castellóde la Plana,Spain [2]European Commission–Joint Research Centre,Institute for Environment and Sustainability,Ispra,Italy

出　　处：《International Journal of Digital Earth》2017年第1期103-120,共18页国际数字地球学报（英文）

基　　金：European Commission and Generalitat Valenciana government[ACIF/2012/112]and[BEFPI/2014/067].

摘　　要：Pushed by the Internet of Things(IoT)paradigm modern sensor networks monitor a wide range of phenomena,in areas such as environmental monitoring,health care,industrial processes,and smart cities.These networks provide a continuous pulse of the almost infinite activities that are happening in the physical space and are thus,key enablers for a Digital Earth Nervous System.Nevertheless,the rapid processing of these sensor data streams still continues to challenge traditional data-handling solutions and new approaches are being requested.We propose a generic answer to this challenge,which has the potential to support any form of distributed real-time analysis.This neutral methodology follows a brokering approach to work with different kinds of data sources and uses web-based standards to achieve interoperability.As a proof of concept,we implemented the methodology to detect anomalies in real-time and applied it to the area of environmental monitoring.The developed system is capable of detecting anomalies,generating notifications,and displaying the recent situation to the user.

关 键 词：Big data real-time analysis data streams sensor networks INTEROPERABILITY brokering approach 

分 类 号：TN9[电子电信—信息与通信工程]