A survey on event detection approaches for sensor based IoT

Abstract

Over the period, two significant advancements i.e. shrinking of the sensor size and improved communication capability, lead the sensor-based internet-of-things (SBIoT) to mature rapidly. SBIoT has various applications to make human life smarter such as health care IoT, smart cities, agriculture, automated industries, security etc. The sensor collects data by monitoring a natural phenomenon from the environment and the internet is used to communicate that to the end-user. Much research has been done to detect events in such environments. The present work surveys diverse methodologies designed to capture the events of interest from collected data in different application domains of SBIoT. This paper revisits the understanding of detecting events of interest using SBIoT framework and discusses the detailed requirements for event detection. Further, different types of events have been identified, discussed and categorization is made. The authors observed the need to put the different categories of event detection in one paper so that researchers can get idea about state of art of the domain. Previously published surveys focused on a specific domain of event detection such as Health IoT, security in SBIoT, agriculture IoT etc. Further such works defined the occurrences in the deployed field as events of interest in very narrow terms. Thus in most of the existing surveys, the event definition is mostly domain-specific and the focus is on the application area rather than techniques of event detection. Thus, there existed a gap for a holistic survey that conceptualizes different application domains into atomic categories and integrates different techniques available for SBIoT using a common thread of event detection. Hence, the event-based monitoring frameworks in SBIoT are segregated and diversified Event detection models are discussed based on the application domains. The paper describes event detection challenges and methodologies in different domains i.e rule-based, probability and statistics based, multimedia-based, intelligent system based and signal processing based methodologies. Further, the comparative analysis of various recently proposed methods has been carried out in terms of their strengths and weaknesses. The present work also discusses the existing research gaps in the domain of event detection and the authors believe that it will be helpful for researchers in academia and industry to develop new methodologies.