PhD scholarship in Machine Learning and Travel Behaviour Analysis

The Transport Modelling Division of the Technical University of Denmark (DTU), Department of Management Engineering, is looking for excellent applicants to pursue PhD studies, starting in November 2018.

The focus of this research is on application of Machine Learning and Transport Modelling research to Smartphone data collection methods.

In many places in the world, travel surveys are moving from the traditional pen and paper, phone call, or web-interface instruments to smartphone based ones. Consequently, we go from a procedure that is intensive in terms of user burden (e.g. respond to many questions in a few minutes, recall spatial and temporal details of recent trips) to one that is device intensive (e.g. automatically detect trips and stops, infer purpose, etc.). In this way, new transportation models can benefit from higher spatial and temporal accuracy, but also longer time windows (e.g. each user contributes with multiple days of data).

This promised revolution in data quality relies on substantial work on developing methods that are able to learn from user behaviour, process noisy data, use energy efficiently, and work robustly in a different number of settings (e.g. iOS and Android). Plenty of work exists already in this field, but some key limitations still exist. Of particularly interest to us are: learning (on an intra and inter user basis): usage of network information (e.g. map matching), perception of social interactions.

In this project we aim at complement current and upcoming smartphone travel survey technologies with improved machine learning components that address the challenges above. This may be done on an online fashion (integrated with a survey software), or a postprocessing one (where we improve the data collected).

Responsibilities and tasks

• Literature review on survey technology, machine learning for behaviour modelling;
• Design and implement one or more machine learning models;
• Test the effectiveness of the approaches on ground truth data:

 

Qualifications

• A Master's degree in computer science, management engineering, operations research, computer engineering, statistics,, statistical physics, mathematical modelling or related
• Excellent programming capabilities, in at least one scientific language (e.g. Python, Matlab, R, Julia)
• Excellent background in statistics and probabilities

 

Knowledge about app development for smart phones are preferable.

The following soft skills are also important:

• Curiosity and interest about current and future mobility challenges (e.g. autonomous mobility, traffic prediction, travel behaviour)
• Good communication skills in English, both written and orally
• Willingness to engage in group-work with a multi-national team

 

Approval and Enrolment

The scholarships for the PhD degree are subject to academic approval, and the candidates will be enrolled in one of the general degree programmes of DTU. For information about the general requirements for enrolment and the general planning of the scholarship studies, please see the DTU PhD Guide.

Assessment

The assessment of the applicants will be made by 30 September 2018.

We offer

DTU is a leading technical university globally recognized for the excellence of its research, education, innovation and scientific advice. We offer a rewarding and challenging job in an international environment. We strive for academic excellence in an environment characterized by collegial respect and academic freedom tempered by responsibility.

Salary and appointment terms

The appointment will be based on the collective agreement with the Danish Confederation of Professional Associations. The allowance will be agreed upon with the relevant union. The period of employment is 3 years.

This project involves an extended stay in Singapore of 1 year, during those 3 years.

You can read more about career paths at DTU here.

Further information

For more information, please contact Francisco C. Pereira (camara@dtu.dk), +45 4525 1496

You can read more about DTU in www.dtu.dk.

DTU Management Engineering contributes actively to the development of management tools and optimization of processes by using and re-thinking theoretical engineering perspectives, models and methods. Through our research and teaching, we ensure an innovative, competitive and sustainable organization and use of technologies within areas such as energy and climate, transportation, production, and health, both domestic and abroad. DTU Management Engineering has 340 employees; including an academic staff of 190 and 68 PhD students. More than 20% of our employees are from abroad and a total of 38 different nationalities are represented at the Department.

DTU is a technical university providing internationally leading research, education, innovation and scientific advice. Our staff of 6,000 advance science and technology to create innovative solutions that meet the demands of society, and our 11,200 students are being educated to address the technological challenges of the future. DTU is an independent academic university collaborating globally with business, industry, government and public agencies.