Non-linear Machine Learning for Calibration and Classification

This half day course will be presented by Barry Wise, Eigenvector Research on the afternoon of Tuesday 13th September

While linear machine learning methods, such as Partial Least Squares (PLS) regression, work in a very wide range of problems of chemical and biological interest, there are times when the relationships between variables are complex and require non-linear modeling methods. Many non-linear machine learning methods have been developed, however, we will focus on a few that we have found quite useful. This includes Locally Weighted Regression (LWR), Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs). ANNs and SVMs for both regression and classification will be considered. The course concludes with a segment on how to choose a method

Screening & Optimisation in one; experimental efficiency through Definitive Screening Designs (DSDs)

This half day course will be presented by Matt Linsley, University of Newcastle on the afternoon of Tuesday 13th September

This half-day workshop will focus on Definitive Screening Designs (DSD), exploring how these relatively new experimental designs deliver efficiency benefits over more classical, “better-known” designs such as fractional factorials. The session will provide: - A background to Design of Experiments (DoE) and its use in industry - Overview of the theory behind DSDs - A DSD-focused case study - Practice in using statistical software for DSD design and analysis For further information please contact matthew.linsley@newcastle.ac.uk

Process Analytics – using advanced sensors and data analytics to develop relevant and impactful KPIs

This half day course will be presented by Geir Rune Flaten, Aspentech on the afternoon of Tuesday 13th September

Relevant and actionable KPIs are essential to maximise the value of any digitalisation initiative. In this course we will discuss how we can identify and use relevant data and advanced analytics to develop and implement process enhancing KPIs. How to handle different types of data, which data analytical strategies to employ and how to use statistics to establish KPIs are reviewed. It is shown how you can approach your data and relevant tools are suggested. The focus is on applications and relevant theory although mentioned is not reviewed in detail. We will use spectroscopic and process data, multivariate data analytical methods, and visualisation dashboards