Engineering and the Environment

ISVR6027 Introduction to Random Signals

Knowledge and understanding
Having successfully completed the module, you will be able to demonstrate knowledge and understanding of:

  • Random processes
  • Spectral analysis
  • Detection, estimation and classification theory
  • Use of statistical signal processing to solve particular problems

Cognitive (thinking) skills
Having successfully completed the module, you will be able to:

  • Read, understand and interpret the literature relating to statistical signal processing.

Practical, subject specific skills
Having successfully completed the module, you will be able to:

  • Apply spectral analysis with understanding of its limitations
  • Design and evaluate simple detection, estimation and classification systems

Key transferable skills
Having successfully completed the module, you will be able to:

  • Compare performance of various algorithms in simulation environments and real world signals.
  • Gain an understanding of the limitations of analysis tools.

Module Details

Title: Introduction to Random Signals
Code: ISVR6027
Year: MSc Sound and Vibration Studies
Semester: Semester 2

CATS points: 10 CAT points (= 100 hours) ECTS 5 ECTS points: NaN
Level: PostGradute taught
Co-ordinator(s): Professor Paul White

Pre-requisites and / or co-requisites

ISVR6032 Signal Processing

The aims of this module are to:

  • To provide an introduction to analysis tools and methodologies used in the analysis of random processes.

  • To provide an understanding of spectral analysis.
  • Give an appreciation of the inter-relationship between the problems of detection, estimation and classification.
  • To provide some experience of specific applications.

Spectral Analysis

  • Principles of random processes
  • Spectral analysis
  • Correlation and cross-correlation
  • Non-parametric spectral analysis

Hypothesis testing

  • Detection theory
  • Estimation theory
  • Classification theory

Particular applications

  • Noise suppression
  • Bayesian modeling
  • Higher order spectra
  • Independent component analysis

Study time allocation

Contact hours: 35 hours (15 Lectures plus 12 Laboratories)
Private study hours: 36 hours minimum, up to 76 hours
Total study time: NaN hours

Teaching and learning methods

3 Hours lectures a day (am) and 3 hours of computer based laboratory sessions (pm).

The students will gain experience of the algorithms through supervised testing the labs.

Resources and reading list

Secondary text

Random Data: Analysis and Measurement Procedures, J S Bendat
AG Piersol, John Wiley & Sons

Detection, Dstimation, and Modulation Theory
Vol. 1, H L Van Trees, John Wiley & Sons

Detection of Signals in Noise, A D Whalen, Academic Press

Modern Spectral Estimation: Theory and Application, S Kay, Prentice Hall

Statistical Signal Processing: Detection, Estimation, and Time Series Analysis, L Scharf, Addison-Wesley

Signal Detection and Estimation, M Barkat, Artech House

Assessment methods

Assessment method Number% contribution to final mark
Assignment1100