SMUA4400 Transport Data Analytics Course description

With the development of sensing technologies, transport digitalization generates and provides numerous data from different resources. This course will introduce models and applications of transport systems analysis in the context of transport studies and gain deeper insight into how these models help with the decision‐making process. Topics to be covered include data preprocessing, travel studies and analysis of data; machine learning methods; transportation systems forecast and analyses. Moreover, the course will provide a brief introduction to future sensing technologies and deep learning methods. The methods cover by this course will closely link to real world transport problem, such as travel demand modelling, accessibility, last-mile problem and other related issues.

None.

No formal requirements over and above the admission requirements.

After completing the course, the student is expected to have achieved the following learning outcomes defined in terms of knowledge, skills, and general competence:

Knowledge:

Upon successful completion of the course, the student will achieve knowledge about:

• terminology and models for transport studies
• statistical and machine learning methods
• advanced sensing technologies
• future development in the transport data analytics

Skills:

Upon successful completion of the course, the student is capable of:

• understanding and applying the proper knowledge and method to collect, process, and analyze transport data
• applying statistical and machine learning methods with a proper interpretation of the methods used in transport modelling
• making use of approved terminology and standardization in the field of transport analytics
• optimum use of data analysis software (Python, R, or Weka)
• using the modelling methods to support intelligent transport system management and policy development

General competence:

Upon successful completion of the course, the student:

• has deep insight into the transport data collection and data analysis methods
• is able to apply proper methods to solve practical problems in different real-world conditions
• is able to understand and explain the results of transport models
• is able to present academic results and evaluations, both to specialists and to the general public

This course will consist of lectures, one seminar (with invited lecturers, discussions and presentations), and lab sessions to provide theoretical content and preliminary hands-on experience. The students will be involved in peer feedback and the students are given a project task to work in groups during the semester.

Two individual assignments must be approved. Students who fail to meet the coursework requirements can be given up to one re-submission opportunity.

1) Project report prepared in groups, (max 4 in the group) approx. 15 - 20 pages (excl. appendices), weighted 70%.

2) Oral presentation in the same groups and examination of the project report, weighted 30%.

All assessment parts must be awarded a pass grade (E or better) to pass the course.

Assessment parts: 1) can be appealed, 2) cannot be appealed

1) All aids are permitted, as long as the rules for source referencing are complied with.

2) None

Graded scale A-F.

1) Two internal examiner

2) Two internal examiners

External examiners are used regularly.

Chaoru Lu: chaorulu@oslomet.no