Visible to the public Sensor data validation and abnormal behavior detection in the Internet of Things

TitleSensor data validation and abnormal behavior detection in the Internet of Things
Publication TypeConference Paper
Year of Publication2017
AuthorsSándor, H., Genge, B., Szántó, Z.
Conference Name2017 16th RoEduNet Conference: Networking in Education and Research (RoEduNet)
Keywordsabnormal behavior, actuators, anomaly detection, composability, Human Behavior, human factors, Internet of Things, Logic gates, Metrics, Monitoring, pubcrawl, Resiliency, security, sensor data flow, sensor security, temperature, Temperature measurement, Temperature sensors
AbstractInternet of Things (IoT) and its various application domains are radically changing the lives of people, providing smart services which will ultimately constitute integral components of the living environment. The services of IoT operate based on the data flows collected from the different sensors and actuators. In this respect, the correctness and security of the sensor data transported over the IoT system is a crucial factor in ensuring the correct functioning of the IoT services. In this work, we present a method that can detect abnormal sensor events based on “apriori” knowledge of the behavior of the monitored process. The main advantage of the proposed methodology is that it builds on well-established theoretical works, while delivering a practical technique with low computational requirements. As a result, the developed technique can be hosted on various components of an IoT system. The developed approach is evaluated through real-world use-cases.
DOI10.1109/ROEDUNET.2017.8123740
Citation Keysandor_sensor_2017