Situation-awareness is the key to enabling intelligent IoT applications. Situation reasoning is used to aggregate multiple contextual information from physical and social sensors using reasoning methods, and convert them into useful high-level knowledge, i.e. situational intelligence.
There has been many attempts to empower IoT applications with situation-awareness but there is a lack of studies that deal with key challenges including: heterogeneity of IoT data, uncertainty of IoT environments, and accuracy of situation inference. Additionally, identifying situation transitions that could be highly important to a group of IoT applications is significantly under-researched.
This research aims to address the above-mentioned research gaps. It aims to investigate, classify and compare situation reasoning methods, and enhance them with capabilities to deal with different types of data (e.g. sensory data, text data and images), incorporate fuzziness of real world situations, and enable representation and inference of situation transitions. The outcome will be an online situation-awareness system for simulation and testing of situations in IoT applications.
- strong knowledge of different machine learning methods
- mobile or web development skills
- IoT applications or mobile sensing knowledge