Software-oriented training - Solo

The following Solo courses are offered:


Using the Advanced Features of PLS_Toolbox and SOLO

Target Audience
Using the Advanced Features of PLS_Toolbox and SOLO is designed for those with a good understanding of basic chemometrics who wish to explore the power of more advanced chemometric tools.

Course Description
Using the Advanced Features of PLS_Toolbox and SOLO concentrates on "how to" perform advanced analyses and data manipulations. After an introduction to the basic interface, the course shows how to use PLS_Toolbox and SOLO to make and view PCA and PLS models. More advanced techniques are then demonstrated. The course will finish with a question and answer session.

About the Instructor
The course will be led by PLS_Toolbox creator and Eigenvector co-founder Barry M. Wise. Dr. Wise holds a doctorate in chemical engineering and has experience in a wide variety of applications spanning chemical process monitoring, modeling and analytical instrument development. He has extensive teaching experience, having presented over 100 chemometrics courses. Each spring Wise organizes and teaches at Eigenvector University, the most comprehensive offering of chemometrics classes in the world.

Course Outline

1. Introduction

1.1 Basic layout of PLS_Toolbox/Solo
1.2 Browse interface
1.3 Analysis interface
1.4 Plot control interface

2. Editing and selecting data

2.1 The DataSet Editor
2.2 Selecting data graphically
2.3 Highlighting samples and variables
2.4 Setting and displaying classes

3. An example with Principal Components Analysis

3.1 Loading data
3.2 Setting preprocessing
3.3 Selecting number of components
3.4 Viewing model parameters: scores, loadings, variance captured

4. An example with Partial Least Squares Regression

4.1 Loading calibration and test data
4.2 Selecting variable ranges
4.3 Setting preprocessing
4.4 Setting cross-validation
4.5 Selecting number of components
4.6 Viewing model parameters
4.7 Options for implementing models on-line

5. Non-linear Methods

5.1 Locally Weighted Regression
5.2 Augmenting data with non-linear terms
5.3 Support Vector Machines

6. Using the Robust Methods

6.1 Robust PCA
6.2 Robust PLS

7. Advanced Preprocessing

7.1 Preprocessing interface
7.2 Selecting and ordering steps, viewing preprocessed data
7.3 Filtering and orthogonalization methods: GLS, EPO, defining clutter
7.4 Looping

8. Orthogonalizing a PLS model—fauxPLS

8.1 Initial model development
8.2 Viewing orthogonalized model

9. Curve Resolution Approaches

9.1 Setting constraints in Multivariate Curve Resolution
9.2 The Purity approach

10. Calibration Transfer Methods

10.1 Piece-wise Direct Standardization
10.2 Generalized Least Squares
10.3 Orthogonal Signal Correction

11. Summary and Question and Answer Session

Course set-up
This is a one-day training with hands-on computer exercises. 


Getting started with Solo

This training is intended as an introduction to the program and not to the multitude of methods that are included in the software. It focuses on such things as importing and exporting data, the different aspects of the user interface, editing graphs etc..

Course objective
This course will give you a jump start in the use of Solo.

Prior knowledge
This course is mainly intended for people who know at least the basics of multivariate methods such as PCA and PCR/PLS and want to get familiar with the most powerful of all multivariate packages.

Course set-up
This half-day training is completely hands-on.

Chemometrics without Equations

Chemometrics without Equations concentrates on two areas of chemometrics: 1) exploratory data analysis and pattern recognition, and 2) regression. Participants will learn to safely apply techniques such as Principal Components Analysis (PCA), Principal Components Regression (PCR), and Partial Least Squares (PLS) Regression. Examples will include problems drawn from process monitoring and quality control, predicting product properties, and others. The target audience includes those who collect and/or manage large amounts of data that is multivariate in nature. This includes bench chemists, process engineers, and managers who would like to extract the most information from their measurements. The course will finish with a short section on how to apply these models for online predictions, Multivariate Statistical Process Control and inferential sensing.

Course objective
The objective is to teach in the simplest way possible so that participants will be better chemometrics practitioners and managers.

Target Audience
Chemometrics Without Equations (or Hardly Any) is designed for those who wish to explore the problem solving power of chemometric tools, but are discouraged by the high level of mathematics found in many software manuals and texts. Course emphasis is on proper application and interpretation of chemometric methods as applied to real-life problems.

Course contents

  • Introduction
    • what is chemometrics?
    • Resources
  • Pattern Recognition Motivation
    • what is pattern recognition?
    • relevant measurements
    • some statistical definitions
  • Principal Components Analysis
    • what is PCA?
    • scores and loadings
    • interpretation
    • supervised and unsupervised pattern recognition
    • examples
  • Regression
    • what is regression?
    • classical least squares (CLS)
    • inverse least squares (ILS)
    • principal components regression (PCR)
    • partial least squares regression (PLS)
    • examples
  • On-line application
    • clients and servers
    • available technologies (COM, ActiveX, etc.)
    • Using MATLAB and PLS_Toolbox on-line
  • Summary

Course set-up
This is a two-day training with hands-on computer exercises.