Special Session 17

Uncertainty evaluation is essential in all applications that depend on measurement, as it ensures traceability and guarantees the accuracy and reliability of measurement results are understood. In Industry 4.0, the application of smart sensors and IoT technology enables industrial robots to complete tasks which used to be carried out by humans, such as data fusion, conditional monitoring and decision making. It is understandable that whenever a decision is taken based on measurement, the issue of uncertainty quantification becomes more critical than ever. In a production cycle, uncertainty contributes to every phase of the signal processing chain, starting from data sampling through data analysis until reaching the last step of decision making. The recent growing popularity of advanced clustering and machine learning methods, as well as the potential benefits of real-time processing and distributed processing techniques, have triggered a new wave of interest in uncertainty quantification and techniques for uncertainty propagation. In this special session, research works related to uncertainty evaluation for all phases in industrial applications are welcome.

Topics of interest include but are not restricted to:

• Theoretical uncertainty study
• Sampling method
• Uncertainty evaluation for supervised and unsupervised machine learning
• Big data related issues
• Uncertainty modelling in IoT applications
• Uncertainty related user-case study
• Sensitivity analysis
• Model verification and validation
• Reliability analysis and optimization
• Robust analysis and optimization
• Design of experiments

Yuhui Luo graduated with PhD degree in Signal Processing and Communications from Imperial College London, UK in 2002. From 2002 to 2004, she worked as postdoc researcher in Centre for DSP Research at King’s College London, UK. In 2005, She joined the Core Technology Group of Samsung Research Institute (SERI) UK as software engineer. From 2006 to 2015, Yuhui worked in the fields of financial futures trading and product management. Her positions include quantitative researcher at Winton Capital Management, senior researcher at China Merchant Futures and senior quantitative product manager at Guosen Securities. From 2017, Yuhui has been working as senior research scientist at Data Science Departments of National Physical Laboratory (NPL). Her research interests are in uncertainty quantification, machine learning and signal processing related applications.

Liam Wright is a researcher for the Data Science department in the National Physical Laboratory, United Kingdom. He has a background in modelling and data analysis from a number of different fields such as electron microscopy, plasmonics and gravitational waves. He obtained his Masters from The University of Glasgow and carried out his PhD as part of the Centre of Doctoral Training for Photonic Integration and Advanced Data Storage, hosted by Queen’s University Belfast and the University of Glasgow. His research interests include finite element modelling of physical systems, uncertainty evaluation, and image processing.