EEE8129 : Intelligent Signal Processing

Semester 1 Credit Value: 20
ECTS Credits: 10.0


To present emerging methods for the manipulation and analysis of single, multi-dimensional and random signals. And to conduct case studies in biomedical and healthcare applications.

To provide knowledge and in-depth understanding of discrete-time signal processing algorithms and approaches to measure deterministic and random signals in frequency domain. And to provide knowledge to apply and design appropriate digital filters according to the application.

Outline Of Syllabus

1.       Introduction of Machine Perception Pattern Recognition Systems Design Cycle and Learning/Adaptation.

2.       Bayesian Decision Theory, Maximum-Likelihood and Bayesian Parameter Estimation General Theory and Problem Dimensionality.

3.       Unsupervised learning, K-means clustering, GMMs based clustering by using MLE and EM Algorithm.

4.       Describing the Deterministic Signals, Transformation of Deterministic time signal into frequency domain using DFT (Discrete Fourier Transform) and FFT (Fast Fourier Transform), Comparison of DFT and FFT Computational Loads, Derivation of the DFT and Matrix Interpretation of the DFT, Determining the Spectral Leakage in FFT, and Mitigation Approaches.

5.       Importance of Digital Filter in DSP, Realisation of Digital Filters, Design of FIR Filters, FIR Filter Design by Impulse Response Truncation, Optimality of IRT Method, Gibb's Phenomenon, FIR Filter Design Using Windows.

6.       Design of IIR Filters, Frequency Transformations, Finite Word Length Effects in IIR Filters.

7.       Describing Random Sequences, Statistical Properties related to Random Sequences.

8.       Non-parametric and Parametric Techniques for Power Spectral Estimation.

9.       Describing Filtering Algorithm to Filter Random Sequences, Concept of Wiener Filter Theory and its Application, Concept of Steepest Descent Algorithm, LMS Algorithm.

10.       Case studies in biomedical and healthcare applications.

Teaching Methods

Teaching Activities
Category Activity Number Length Student Hours Comment
Scheduled Learning And Teaching ActivitiesLecture202:0040:00N/A
Guided Independent StudyAssessment preparation and completion115:0015:00Matlab assignments and writing of report.
Guided Independent StudyAssessment preparation and completion400:3020:00Revision for final exam
Guided Independent StudyAssessment preparation and completion13:003:00Final exam
Scheduled Learning And Teaching ActivitiesPractical121:0012:00Computer Practical
Guided Independent StudyDirected research and reading215:0030:00Case studies
Guided Independent StudyIndependent study180:0080:00Reviewing lecture notes; general reading
Jointly Taught With
Code Title
EEE3004Digital Signal Processing
Teaching Rationale And Relationship

Lectures provide the fundamental concepts of the course while computer based lab experience provide an opportunity to transform all theoretical learning into practical applications. Case studies will direct research and studying state-of-the-art reading.

Assessment Methods

The format of resits will be determined by the Board of Examiners

Description Length Semester When Set Percentage Comment
Written Examination1801A80N/A
Exam Pairings
Module Code Module Title Semester Comment
EEE3004Digital Signal Processing1EEE8094 shares 10 credits with EEE3004.
Other Assessment
Description Semester When Set Percentage Comment
Practical/lab report1M20MATLAB report. 2000 words max.
Assessment Rationale And Relationship

The examination will help students to demonstrate the core understanding of course material, analysis and synthesis skills to novel situations related to DSP. Students’ lab report reflect their in-depth learning related to the contents delivered during lecture, it also demonstrate the conceptual learning by the way they deal with the problems assigned to them in labs.

Reading Lists