IoTracker: A probabilistic event tracking approach for data-intensive IoT Smart Applications

Abstract

Smart Applications for cities, industry, farming and healthcare use Internet of Things (IoT) approaches to improve the general quality. A dependency on smart applications implies that any misbehavior may impact our society with varying criticality levels, from simple inconveniences to life-threatening dangers. One critical challenge in this area is to overcome the side effects caused by data loss due to failures in software, hardware, and communication systems, which may also affect data logging systems. Event traceability and auditing may be impaired when an application makes automated decisions and the operating log is incomplete. In an environment where many events happen automatically, an audit system must understand, validate, and find the root causes of eventual failures. This paper presents a probabilistic approach to track sequences of events even in the face of logging data loss using Bayesian networks. The results of the performance analysis with three smart application scenarios show that this approach is valid to track events in the face of incomplete data. Also, scenarios modeled with Bayesian subnets highlight a decreasing complexity due to this divide and conquer strategy that reduces the number of elements involved. Consequently, the results improve and also reveal the potential for further advancement.