Chemometrics

Code:

Q4022

Acronym:

Q4022

Level:

400

Keywords
Classification	Keyword
OFICIAL	Chemistry

Instance: 2017/2018 - 2S

Active?	Yes
Responsible unit:	Department of Chemistry and Biochemistry
Course/CS Responsible:	Master in Chemistry

Cycles of Study/Courses

Acronym	No. of Students	Study Plan	Curricular Years	Credits UCN	Credits ECTS	Contact hours	Total Time
M:BQ	1	Plano de Estudos do MBIOQ_2013-2014	1	-	6	56	162
M:Q	4	Official study plan until 2022/2023	1	-	6	56	162

Teaching language

Suitable for English-speaking students

Objectives

The objective of Chemometrics is to teach the theoretical background and use chemometric software tools for the experimental design and linear and non-linear data analysis.

Learning outcomes and competences

At the end of this unit the student will have acquired knowledge and skills to:

Knowledge:
- Summarize basic chemometric methods

- Describe techniques for data pre-preprocessing

- Develop suitable experimental designs
- Describe chemometric methods for multivariate data analysis (clustering, classification and regression)

- Understand when to use multiway decomposition techniques

Skills:
- Apply theory on real life chemical data cases
- Apply commercial software for data analysis
- Report in writing a full data analysis of a given problem including all aspects presented under Knowledge.

Competences:

- Selection of the best chemometric to solve specific chemical problems
- Discuss advantages and drawbacks of chemometric methods

Working method

Presencial

Pre-requirements (prior knowledge) and co-requirements (common knowledge)

Program

1. Data structures and data preprocessing techniques

2. Experimental design (DOE)
2.1 – Factorial analysis
2.2 – Response surface

3. Principal components analysis (PCA)

4. Factor analysis (FA)

5. Multivariate curve resolution with alternating least squares (MCR-ALS)


6. Supervised classification techniques
6.1 – Linear discriminate analysis (LDA)
6.2 – Soft independent modeling by class analogy (SIMCA)
6.3 – Parallel factor analysis (PARAFAC)
6.4 - K nearest neighbors (KNN)
6.5 – Artificial neural networks (ANN)

7. Unsupervised classification techniques
7.1 – Linear and non-linear projection techniques
7.2 – Hierarchical clustering analysis techniques (HCA)

8. Calibration techniques
8.1 – Ordinary least squares (OLS)
8.2 - Multiple linear regrassion (MLR)
8.3 – Principal components regression (PCR)
8.4 – Partial least squares (PLS)

9. Introduction to Artificial Neural Networks (ANN)

10. Kohonen self-organizing maps (SOM)
11. Genetic algorithms (GA)

Theoretical and Practical

Mandatory literature

D.L. Massart, B.G.M. Vandeginste, L.M.C. Buydens, S. De Jong, P.J. Lewi, J. Smeyers-Verbeke; Handbook of Chemometrics and Qualimetrics: Part A, Elsevier, 1997

Complementary Bibliography

K.R. Beebe, R.J. Pell, M.B. Seasholtz; Chemometrics: A Practical Guide, Wiley, 1998
E.Morgan; Chemometrics: Experimental Design, Wiley, 1991
D.C. Montgomery; Design and Analysis of Experiments, Wiley, 2001
D.L. Massart, B.G.M. Vandeginste, L.M.C. Buydens, S. De Jong, P.J. Lewi, J. Smeyers-Verbeke; Handbook of Chemometrics and Qualimetrics: Part B, Elsevier, 1997
J. Zupan, J. Gasteiger; Neural Networks for chemistry – an introduction, VCH, 1993
H. Martens, T. Naes; Multivariate calibration, Wiley, 1989
E.R. Malinowski; Factor Analysis in Chemistry, Wiley, 1991

Teaching methods and learning activities

The students will be introduced to the theory through lectures. The students will work on data analytical problems using the taught methods and software to analyze data. The results are presented in written reports which are orally defended at predetermined dates during the semester.

Evaluation Type

Distributed evaluation without final exam

Assessment Components

designation	Weight (%)
Participação presencial	10,00
Prova oral	40,00
Trabalho prático ou de projeto	50,00
Total:	100,00

Eligibility for exams

Calculation formula of final grade

Completion of four written reports and corresponding oral presentation distributed throughout the semester.
The maximum rating of each is 5 values (3 values for the report and 2 values for oral presentation).

The written work should be about topics taught and must inclde practical work with application of methods/techniques taught.

In oral presentations are evaluated three factors: quality of the support presentation; fluency in presentation; scientific quality.

Examinations or Special Assignments

Internship work/project

Special assessment (TE, DA, ...)

Classification improvement

Observations