EEEN60231 15 Semester 1 Postgraduate Taught Level 6 Ognjen Marjanovic Unit coordinator Long Zhang Unit coordinator Department of Electrical & Electronic Engineering 1 FHEQ level (Framework for Higher Education Qualifications) ' Masters/Integrated Masters P4 ' European Credit Transfer & Accumulation System Rating : 7.5 <p><strong>The unit has two different parts.</strong></p><p><strong>Part A - System Identification</strong></p><ul><li>Examplar system identification problems.</li><li>Measurements and statistics.</li><li>Non-parametric methods: Time and frequency domain</li><li>Least square problem. Statistic foundation.</li><li>Parametric methods (ARX, OE).</li><li>Input design.</li><li>Optimisation: gradient method for OE.</li><li>Recursive estimation.</li><li>Validation.</li></ul><p><strong>Part B - Artificial Intelligence (for dynamic systems modelling)</strong></p><ul><li>Introduction to AI.</li><li>Neural network models (single-layer and multiple-layer neural networks).</li><li>Deep learning (neural networks).</li><li>Learning and optimisation methods.</li><li>Performance evaluation.</li></ul> <p><strong>The unit has two different parts.</strong></p><p><strong>Part A - System Identification</strong></p><ul><li>Examplar system identification problems.</li><li>Measurements and statistics.</li><li>Non-parametric methods: Time and frequency domain</li><li>Least square problem. Statistic foundation.</li><li>Parametric methods (ARX, OE).</li><li>Input design.</li><li>Optimisation: gradient method for OE.</li><li>Recursive estimation.</li><li>Validation.</li></ul><p><strong>Part B - Artificial Intelligence (for dynamic systems modelling)</strong></p><ul><li>Introduction to AI.</li><li>Neural network models (single-layer and multiple-layer neural networks).</li><li>Deep learning (neural networks).</li><li>Learning and optimisation methods.</li><li>Performance evaluation.</li></ul> <p>The unit aims to give students an understanding of how system identification and artificial intelligent algorithms can be used to find models of dynamic systems; how least squares and optimisation approaches can be used for parameter estimation; the influence of noise on the parameter estimation and the relevance of measurement theory for the identification process.</p> <p><strong>On successful completion of the course, a student will be able to:</strong></p><p><strong>ILO 1:</strong> Test and validate the neural networks models with different selecting criteria.</p><p><strong>ILO 2:</strong> Optimise the neural networks model parameters with input-output data.</p><p><strong>ILO 3: </strong>Demonstrate understanding of the potential and limitations of AI and their essential steps for dynamic system modelling, including choices of AI models and performance evaluation.</p><p><strong>ILO 4: </strong>Describe the implementation of the data-driven techniques that can be used to identify linear and nonlinear dynamic systems.</p><p><strong>ILO 5: </strong>Use statistical analysis techniques to describe random variation in measured data.</p> <p>The unit has two different parts.</p><p>Part A - System Identification</p><ul><li>Examplar system identification problems.</li><li>Measurements and statistics.</li><li>Non-parametric methods: Time and frequency domain</li><li>Least square problem. Statistic foundation.</li><li>Parametric methods (ARX, OE).</li><li>Input design.</li><li>Optimisation: gradient method for OE.</li><li>Recursive estimation.</li><li>Validation.</li></ul><p>Part B - Artificial Intelligence (for dynamic systems modelling)</p><ul><li>Introduction to AI.</li><li>Neural network models (single-layer and multiple-layer neural networks).</li><li>Deep learning (neural networks).</li><li>Learning and optimisation methods.</li><li>Performance evaluation.</li></ul> <p>Lectures, tutorial and laboratory.</p> 0 Other 10% 1 Written exam 80% 2 Written assignment (inc essay) 10% <p>Examination - feedback will be given after the exam board.</p><p>System Identifaction coursework - individual feedback is provided 3 weeks after submission.</p><p>AI coursework - individual feedback is provided 3 weeks after submission.</p> N <p>Söderström, T. (1989). System Identification. Prentice Hall.<br/>Ljung, L. (1987). System Identification: Theory for the User. Prentice-Hall.<br/>Goodwin, G.C., &amp; Payne, R.L. (Ed.). (1977). Dynamic System Identification: Experiment Design and Data Analysis. Academic Press.<br/>Goodfellow, I., Bengio, Y., &amp; Courville, A. (2016). Deep Learning. MIT Press.<br/>Alpaydin, E. (2020). Introduction to Machine Learning (4th ed.). MIT Press</p> Lectures 30 Practical classes & workshops 12 0 96