Bi0034 Analysis and classification of data

Faculty of Science
Autumn 2019
Extent and Intensity
2/1/0. 3 credit(s) (plus extra credits for completion). Recommended Type of Completion: zk (examination). Other types of completion: z (credit).
Teacher(s)
RNDr. Eva Koriťáková, Ph.D. (lecturer)
prof. Ing. Jiří Holčík, CSc. (lecturer)
RNDr. Roman Vyškovský, Ph.D. (lecturer)
Guaranteed by
prof. Ing. Jiří Holčík, CSc.
RECETOX – Faculty of Science
Contact Person: RNDr. Eva Koriťáková, Ph.D.
Supplier department: RECETOX – Faculty of Science
Timetable
Wed 8:00–10:50 D29/347-RCX2
Prerequisites
It is recommended to attend the course Bi8600 Multivariate Methods or the course Bi8601 Advanced Statistical Methods beforehand.
Course Enrolment Limitations
The course is also offered to the students of the fields other than those the course is directly associated with.
fields of study / plans the course is directly associated with
Course objectives
The aim of the course is to introduce objectives and principles of data analysis and classification methods to students. During the course, the students will acquire knowledge of fundamental theoretical and methodological principles of pattern analysis and recognition methods with emphasis to processing of medical and biological data. Besides, they will master application of the methods on real-world data and interpretation of achieved results.
Learning outcomes
At the end of the course, students should be able to:
- Choose and apply appropriate data analysis method to obtain required results;
- Reduce and transform multivariate data using advanced ordination methods;
- Classify data using various classification methods;
- Design modified algorithms to process data of given particular characteristics;
- Interpret obtained results including evaluation of classification performance.
Syllabus
  • Introduction to analysis and classification of data.
  • Classification based on discriminant functions.
  • Classification based on minimal distance – deepening of knowledge about distance and similarity metrics.
  • Classification based on minimal distance.
  • Classification based on boundaries – Fisher’s Linear Discriminant Analysis (FLDA).
  • Classification based on boundaries – Support Vector Machines (SVM).
  • Sequential classification.
  • Evaluation of classification performance – cross-validation, comparison of classification results with random classification, comparison of classification performance of two or more classifiers.
  • Feature extraction – deepening of knowledge about Principal Component Analysis (PCA).
  • Advanced methods for feature extraction – Manifold Learning, Independent Component Analysis (ICA).
  • Feature selection.
  • Application of classification, pattern analysis and recognition methods on real-world data.
Literature
  • Mitchel,T.M.: Machine Learning. McGraw Hill 1997
  • Dunham,M.H.: Data Mining: Introductory and Advanced Topics. Prentice Hall 2002
  • Holčík,J.: Analýza a klasifikace signálů. [Učební texty vysokých škol] Brno, Nakladatelství VUT v Brně 1992.
Teaching methods
Lectures supported by Power Point presentations. Understanding of principles, methods and algorithms is emphasized. Students are continuously encouraged to interact with the lecturer.
Assessment methods
oral examination
Language of instruction
Czech
Further Comments
Study Materials
The course is taught annually.
The course is also listed under the following terms Autumn 2007 - for the purpose of the accreditation, Autumn 2010 - only for the accreditation, Autumn 2007, Autumn 2008, Autumn 2009, Autumn 2010, Autumn 2011, Autumn 2011 - acreditation, Autumn 2012, Autumn 2013, Autumn 2014, Autumn 2015, Autumn 2016, autumn 2017, Autumn 2018, Autumn 2020, autumn 2021.
  • Enrolment Statistics (Autumn 2019, recent)
  • Permalink: https://is.muni.cz/course/sci/autumn2019/Bi0034