Multivariate Statistics and Pattern Recognition

2019/2020

Prerequisite/Recommended prerequisite for participation in the module

BSc in Medialogy or equivalent

Content, progress and pedagogy of the module

Objectives:

When designing and developing interactive media systems and technology, one is often faced with looking for interesting patterns and trends in data of several dimensions, what is called 'multivariatedata.' This course presents theoretical concepts and practical tools for analyzing multivariate data and designing pattern recognition methods for multimedia applications. Many of these methods are used in, e.g., automatic speech recognition, face detection, web page ranking, etc. The course includes the following topics: multivariate probability density functions, Bayesian estimation and detection, Gaussian model, parameter estimation, assessment of classifiers and estimators, data fitting, supervised and unsupervised learning, parametric and non-parametric learning, feature selection and reduction, and clustering.

Learning objectives

Knowledge

Students who complete the course module will obtain the following qualifications:

  • Understand multivariate statistics and describe how to model multivariate data, e.g., using probabilistic and parametric descriptions

  • Understand Bayesian classification

  • Understand supervised and non-supervised learning methods, e.g., k-means clustering, principal component analysis, nearest neighbor

  • Understand features and the process of feature extraction from data

Skills

Students who complete the course module will obtain the following qualifications:

  • Choose, implement and apply pattern recognition tools to solve classification problems, e.g., footstep detection from accelerometers, recognition of single spoken digits

  • Apply knowledge to compare classification methods in terms of performance and complexity

  • Apply theory of multivariate statistics and analyse multimedia data, e.g., speech and music, images of faces, etc.

Competences

Students who complete the course module will obtain the following qualifications:

  • Analyse a problem in your field in the context of multivariate statistics and pattern recognition, and reflect on a variety of possibilities to recommend a solution

  • Analyse features for this problem

  • Implement and evaluate a classifier for this problem, and discuss and generalize the results

Type of instruction

Refer to the overview of instruction types listed in the start of chapter 3. The types of instruction for this course are decided in accordance with the current Framework Provisions and directions are decided and given by the Study Board for Media Technology.

Exam

Exams

Name of examMultivariate Statistics and Pattern Recognition
Type of exam
Written or oral exam
In accordance with the current Framework Provisions and directions on examination from the
Study Board for Media Technology:

Oral or written examination with internal censor. The assessment is performed in accordance with the 7-point scale.
ECTS5
Permitted aids
With certain aids:
See semester description
Assessment7-point grading scale
Type of gradingInternal examination
Criteria of assessmentThe criteria of assessment are stated in the Examination Policies and Procedures

Facts about the module

Danish titleMultivariat statistik og mønstergenkendelse
Module codeMSNMEDM1145
Module typeCourse
Duration1 semester
SemesterAutumn
ECTS5
Language of instructionEnglish
Location of the lectureCampus Aalborg, Campus Copenhagen, Campus Esbjerg
Responsible for the module

Organisation

Study BoardStudy Board of Media Technology
DepartmentDepartment of Architecture, Design and Media Technology
FacultyTechnical Faculty of IT and Design