Cascading Reasoning: an Efficient and Scalable Solution for Decision Making on Heterogeneous Data Streams

It is expected that by 2025, the number of connected devices in the Internet of Things (IoT) will exceed 20 billion, where many of these devices are edge devices. We are at a tipping point where more data is being produced than can be meaningfully processed. High value is contained in this data, as real-time processing allows advanced applications in domains like smart cities, pervasive health or industry 4.0. IoT data is challenging to process as it is heterogeneous, voluminous and produced at high frequencies. Semantic web technologies have proven to be ideal for the integration of these heterogeneous data. Semantic reasoning is able to derive high-level knowledge, enabling actionable insights. However, reasoning is too computationally expensive, compared to the velocity of the IoT data. The objective of this proposal is to tackle these IoT challenges with Cascading Reasoning (CR), i.e. a layered reasoning approach consisting of various levels of complexity. CR naturally matches the edge processing paradigm, as the low complexity processing techniques can be pushed down to the edge. I will investigate highly efficient and scalable reasoning techniques that can deal with the velocity of the IoT. Furthermore, I will investigate how high-level queries can automatically be translated to the various levels of the cascade, allowing to translate Information Needs in a fully declarative way. Lastly, I will investigate how reasoning can be speed up by predicting certain steps.