13E054PO - Pattern Recognition

Course specification
Course title		Pattern Recognition
Acronym		13E054PO
Study programme		Electrical Engineering and Computing
Module
Type of study		bachelor academic studies
Lecturer (for classes)		professor PhD Željko Đurović professor PhD Aleksandra Krstić
Lecturer/Associate (for practice)		asst. professor PhD Sanja Vujnović asst. Aleksa Stojić, electrical and computer engineer Maša Tiosavljević, electrical and computer engineer
Lecturer/Associate (for OTC)		professor PhD Aleksandra Krstić Maša Tiosavljević, electrical and computer engineer
ESPB		6.0	Status	elective
Condition		none
The goal		Objective of the course is for the students to be informed about the statistical methods for pattern recognition: hypothesis testing, parametric and nonparametric classification, clustering.
The outcome		Learning outcomes of the course are following: students´ ability to generate or to collect high quality and informative training sets of data, to apply appropriate statistical pattern recognition technique (hypothesis testing, parametric or nonparametric classifier), to design system for data clustering.
Contents
URL to the subject page		http://automatika.etf.rs/sr/13e054po
Contents of lectures		Overview of random variables and vectors; Important results from linear algebra ; Hypothesis testing methods; Design of parametric classifiers; Design of nonparametric classifiers; Reduction dimension methods; Clustering techniques; Pattern recognition based on fuzzy logic and neural networks.
Contents of exercises		During the course students have to solve three practical problems: 1. Design of Bayes classifier and sequential test; 2. Design of linear and quadratic classifier; 3. Clustering of data.
Literature
Introduction to Statistical Pattern Recognition, Keinosuke Fukunaga, Prentice Hall, 1992. Script of pattern recognition (electronic form), Zeljko Djurovic, www.automatika.etf.bg.ac.yu
Number of hours per week during the semester/trimester/year
Lectures	Exercises	OTC	Study and Research	Other classes
3	1	1
Methods of teaching		3x15 hours of lectures, 1x15 hours of practical exercising with computers
Knowledge score (maximum points 100)
Pre obligations		Points	Final exam	Points
Activites during lectures		0	Test paper	70
Practical lessons		30	Oral examination	0
Projects
Colloquia		0
Seminars		0