Research program title
Data Analytics for System-On-Module Solutions
Smart connected devices are forecast to grow from 15.4 billion devices in 2015 to 30.7 in 2020 and 75.4 billion in 2025. System-on-module (SoM) solutions, which embed a rich set of sensors (e.g., gyroscopes, accelerometers and magnetometers) into board-level integrated circuits, are enabling the rapid advancement of these smart devices. Due to their versatility, SoMs have numerous applications to medical devices, network appliances, smart cars, wearables and other embedded devices.
However, the vast amounts of data collected by SoM sensors remains largely unexplored despite the fact that advanced data analytics could lead to groundbreaking applications.
Therefore, the goal of this project is to devise SoM-specific analytics that can be used to build activity and pattern profiles. Specifically, we will design different analytics and examine their effectiveness using techniques such as fit and accuracy. Moreover, we plan to build models that are effective in identifying different types of user activities/patterns. Various modelling techniques (e.g., statistical and machine learning-based), training techniques and model transformation techniques will be developed to ensure that our models are accurate and effective in their detection of the various activities/patterns.
Academic qualifications required
PhD in Computer Science or related fields with experience in Data Analysis and/or Software Analytics.