ELEC50009 Information Processing (shared wi ELEC50013 S&S in Autumn)Lecturer(s): Prof Patrick Naylor; Dr Christos Bouganis Aims
The aim of this topic is to take data and transform it or analyse it. This may be timeseries data, spatial data, or unstructured data. The unifying idea of the module is that there are certain fundamental ideas such as sampling and transforms that apply throughout, and then there are many different mathematical and applied tools which could be used to implement them in different scenarios.
Learning Outcomes
Upon successful completion of this module, you will be able to:
1. Model a data filtering problem as a transfer function 2. Classify realworld data into different types of signals 3. Design a continuous audio filter using LCR components 4. Create a digital video filter using the FFT 5. Describe the circumstances when it is appropriate to use Fourier, FIR, or IIR solutions 6. Apply nonlinear regression to model dataseries 7. Use a machine learning toolbox to train a model Syllabus
Signals and Data
Types of data and signals Types of analysis Sampling Transfer functions LTI systems Filtering FIR IIR Fourier methods Image filtering Audio filtering Data analysis Regression Prediction Learning toolboxes Exam Duration: N/A Coursework contribution: 50% Term: Autumn & Spring Closed or Open Book (end of year exam): N/A Coursework Requirement: Laboratory Experiment Nonassessed problem sheets Oral Exam Required (as final assessment): no Prerequisite module(s): None required Course Homepage: unavailable Book List:
