ENGM010 | 2021 | University of Exeter

MODULE TITLE	Data-Centric Engineering	CREDIT VALUE	15
MODULE CODE	ENGM010	MODULE CONVENER	Prof Tim Dodwell (Coordinator)

DURATION: TERM	1	2	3
DURATION: WEEKS

Number of Students Taking Module (anticipated)

DESCRIPTION - summary of the module content

The next decade will see a step changes in data-driven technology, impacting all aspects of engineering and industry. By exploiting data being generated presents enormous engineering opportunities to transform both system design and control.

This problem based module will focus on using real world data sets to tackle grand challenges in engineering design across materials, built environment and sustainable energy usage, introducing students to state-of-the-art methods in Bayesian Analysis, Machine Learning and Artificial Intelligence.

AIMS - intentions of the module

The aim of the module is provide a hands on course in advanced methods for data centric engineering at the frontiers of the research of interest at Exeter and the Alan Turing Institute.

INTENDED LEARNING OUTCOMES (ILOs) (see assessment section below for how ILOs will be assessed)

ILO #	Intended Learning Outcome	*AHEP ILO - MEng**	AHEP ILO - BEng
ILO #1	Understand the difference between Frequentist and Bayesian approaches, and their relevance to engineering problems.	SM3m, SM5m, EA1m, EA2m, EA3m, D3m, D4m, ET1m, EP2m, EP4m, G1m, G2m
ILO #2	Understand principle methods for handling real world noisy data.	SM1m
ILO #3	Learn how to set up probabilistic models and approaches to training them using data
ILO #4	Understand how to apply diagnostic tools to check validity of model
ILO #5	Obtain hands on practical skills for handling data and probabilistic models using python
ILO #6	Understand the engineering implications of the models, and the ethical issues surrounding application of algorithms to make engineering decisions
ILO #7	Develop Skills to critical peer review others work	G4m
ILO #8	High level computing skills in python
ILO #9	Develop strong presentation skills of complex ideas and data – both presentation and visual/written
*Engineering Council Accreditation of Higher Education Programmes (AHEP) ILOs for MEng and BEng Degrees

SYLLABUS PLAN - summary of the structure and academic content of the module

The module will provided strong quantitative skills in data analysis and programming in what is seen as the next generation of engineering.

Application in Data Centric Engineering from Research Expertise at Exeter and the Alan Turing Institute. Guest lecture from academics working in this field will be given :

Bayesian Model Updating - Application in Structural Health Monitoring in Civil / Mechanical / Energy Useage
Classification - Image and Pattern Recognition
Bayesian Optimisation & Experimental Design - Application in Composite Analysis or Computational Fluid Dynamics

Assessment will be 100% Coursework over 5 weeks. Students will be given a choice from problems using real world data sets from one of the three application areas describe above. Assessment will require students to formulate project idea themselves.

Outputs will be two page project proposal including literature review. This will be peer-reviewed 1 week before submission and then marked by module convenor following updates from student feedback.

Final outputs will be: individual poster presented to industry / academia , presentation and documented computer program.

1: Recap on signal processing and optimisation from "Industry 4.0" in Year 2.;

2: Frequentist vs Bayesian View;

3: Probabilistic Models;

4: Loss and Generalised loss functions;

5: Stochastic Gradient Descent;

6: Maximum Likelihood (ML), Maximum a Posteriori (MAP): 7: Overfitting and Underfitting;

8: Probabilisitic Validation / Bayesian Model Selection;

9: Bayesian Regression;

10: Markov Chain Monte Carlo;

11: Interpretation, Causality and Ethics.

LEARNING AND TEACHING

LEARNING ACTIVITIES AND TEACHING METHODS (given in hours of study time)

Scheduled Learning & Teaching Activities	33	Guided Independent Study	117	Placement / Study Abroad

DETAILS OF LEARNING ACTIVITIES AND TEACHING METHODS

Category	Hours of study time	Description
Scheduled Learning and Teaching Activities	11	Lectures
Scheduled Learning and Teaching Activities	22	Tutorials
Guided Independent Study	117	Reading lecture notes; working exercises

ASSESSMENT

FORMATIVE ASSESSMENT - for feedback and development purposes; does not count towards module grade

SUMMATIVE ASSESSMENT (% of credit)

Coursework	100	Written Exams	0	Practical Exams

DETAILS OF SUMMATIVE ASSESSMENT

Form of Assessment	% of Credit	Size of Assessment (e.g. duration/length)	ILOs Assessed
Coursework - Proposal Outline	25	5 hours	1, 2, 7
Coursework - Individual Poster presented to Industry/Academics	25	5 hours	4
Coursework - Final Presentation	25	5 hours	6, 9
Coursework - Documented Programme	25	10 hours	3, 5, 8

DETAILS OF RE-ASSESSMENT (where required by referral or deferral)

RE-ASSESSMENT NOTES

Ref/Def assessment is via project report submission in August, weighted at 100%.

RESOURCES

INDICATIVE LEARNING RESOURCES - The following list is offered as an indication of the type & level of
information that you are expected to consult. Further guidance will be provided by the Module Convener

Reading list for this module:

There are currently no reading list entries found for this module.

CREDIT VALUE	15	ECTS VALUE	7.5

PRE-REQUISITE MODULES	None
CO-REQUISITE MODULES	None

NQF LEVEL (FHEQ)	7	AVAILABLE AS DISTANCE LEARNING	No
ORIGIN DATE	Friday 8th January 2021	LAST REVISION DATE	Friday 8th January 2021

KEY WORDS SEARCH	None Defined

Data-Centric Engineering - 2021 entry