Half-day courses offered on 22 April 2024 at the Hyatt Regency hotel are:

Statistical and Hybrid Techniques for Process Monitoring, Control and Optimization, John Mack and Rafay Ashar, Applied Materials 
 

For many years the process industries have used techniques that are now considered Machine Learning (MVA, multivariate optimization etc.). This course will look at the challenges that make the implementation of these techniques in the process industries unique, and then go on to discuss what other techniques from the ever-expanding ML toolbox are gaining traction in industry with associated case studies.

 
Machine Learning for PAT, Barry Wise, Eigenvector Research Inc.
 

Machine Learning for Calibration and Classification is aimed at spectroscopists and other scientists who want to be able to use machine learning methods to develop their own linear and non-linear models for calibration/regression or sample classification. It is recommended that participants be familiar with Principal Components Analysis (PCA) and multivariate regression methods such as Partial Least Squares (PLS).  The course addresses linear methods briefly but will focus on machine learning methods designed to deal with non-linear data. Emphasis will be on applying these techniques to spectroscopic, especially NIR and Raman data. Methods for instrument calibration, sample classification and exploratory data analysis will be covered. The course will be led by Eigenvector President and PLS_Toolbox creator Barry M. Wise. Dr. Wise has delivered over 200 chemometrics courses at scientific conferences, on-site for companies, on-line and at open sites.

Multivariate Analysis for Spectroscopy, Chuck Miller, Aspen Technology Inc.
 
Multivariate methods have been key enablers of analytical and spectroscopic methods, whether they are lab-based, at-line, on-line or field-based. This course provides the student with both the background and the practical tools to make the most of their multivariate analytical systems. Methods for spectral preprocessing, exploratory analysis, multivariate calibration, and validation are reviewed, with emphasis on understanding the basis of these methods. Hands-on exercises are also provided, to get better acquainted with these methods and workflows.
 

Fees are: $200 for those attending the APACT conference and $400 for those attending a course only.