Module and Programme Catalogue

Search site

Find information on

Useful links

2017/18 Taught Postgraduate Module Catalogue

TRAN5340M Transport Data Science

15 creditsClass Size: 30

Module manager: Dr Charles Fox
Email: c.w.fox@leeds.ac.uk

Taught: Semester 2 (Jan to Jun) View Timetable

Year running 2017/18

This module is not approved as an Elective

Module summary

The quantity, diversity and availability of transport data is increasing rapidly, requiring skills in the management and interrogation of data and databases. Recent years have seen a new wave of 'big data' and 'data science' changing the world, with the Harvard Business Review describing Data Science as the 'sexiest job of the 21st century'. Transport researchers need to be able to use data (and databases) in order to establish quantitative, empirical facts, and to validate/challenge their mathematical models.This module takes a highly practical approach to learning about 'data science' tools and their application to investigating transport issues. The focus is on team work with real data and tools rather than theory.

Objectives

Understand the concepts of classical database design, and problems and limitations.
Understand how to obtain, clean and store transport related data.
Gain proficiency in industry-standard SQL language for database operation.
Experience basic machine learning / data mining tools
Produce data visualizations
Understand 'big data' tools and concepts, the need for them, and how they differ from classical databases
Learn how to set up and solve transport problems in teams; sourcing and interrogating data, applying statistical modelling tools, visualising data and results.

Learning outcomes
Students should become confident to enter a team-based data science consulting environment, selecting appropriate tools to set up and solve business questions using data. Such projects typically include:
Finding the right question to ask, including ethical issues
Obtaining the right data
Data cleaning
Conceptual database design
Computational database issues, include 'big data' systems
Statistics and machine learning analytics
Visualisation and presentation
Appreciate the relevance and limitations of data-centric analysis applied to transport problems, compared with other types of modelling and forecasting.


Syllabus

Practical database manipulation with SQL
Classical relational database design
Data for transport [e.g. flows, incidents, origin/destination, GIS]
Data scraping from semi-structured web sources
Machine learning tools
Bayesian networks
Ontological issues in database design
Beyond SQL the big data revolution and the Hadoop stack
Data visualization
Professional and ethical issues of big data in transport
Transport data analysis

Teaching methods

Delivery typeNumberLength hoursStudent hours
Lecture51.005.00
Practical121.5018.00
Seminar81.008.00
Private study hours119.00
Total Contact hours31.00
Total hours (100hr per 10 credits)150.00

Private study

Students are expected to spend their study time on background reading for lectures, preparatory work for workshops and assessed coursework.
Unsupervised teamwork practical sessions will be arranged each week.

Opportunities for Formative Feedback

Progress will be monitored informally during supervised practical sessions.

Methods of assessment


Coursework
Assessment typeNotes% of formal assessment
PortfolioProject Portfolio100.00
Total percentage (Assessment Coursework)100.00

20% of the mark for the assessment of the portfolio will be determined as an initial assessment after week 5. Feedback will be provided. The remaining 80% will be awarded in respect of the final submitted portfolio. Students who fail the portfolio will be required to resit those elements deemed to fail to meet the pass standard.

Reading list

The reading list is available from the Library website

Last updated: 17/03/2016

Disclaimer

Browse Other Catalogues

Errors, omissions, failed links etc should be notified to the Catalogue Team.PROD

© Copyright Leeds 2019