PhD position in data mining
Looking for candidates to a PhD position in data mining at the Dept. of Computer and Systems Sciences, Stockholm University. Ref. No. SU FV-0872-13. Apply by April 30.
At: Stockholm University
Doctoral Position in Computer and Systems Sciences with specialization in Data Mining at the Department of Computer and Systems Sciences (DSV), Stockholm University. Ref. No. SU FV-0872-13. Deadline for applications: April 30, 2013.
The Department of Computer and Systems Sciences (DSV) belongs to Stockholm University and is located in one of the world's leading ICT clusters, Kista, just outside Stockholm, Sweden. The department conducts research and education in different areas of computer and systems sciences, and it has about 200 employees and 90 doctoral students.
About the doctoral position and requirements
The announced doctoral position requires that the applicant can be admitted to the doctoral program in Computer and Systems Sciences. Both general and specific academic entry requirements must be met. See further information on the web site, www.dsv.su.se/en/research/postgrad/.
The doctoral position involves four years of full-time studies (240 ECTS), leading to a doctoral degree in Computer and Systems Sciences at Stockholm University. One year is financed by doctoral grant and three years by doctoral studentship. The position may involve administration or teaching duties up to 20% of full time; such an arrangement gives that the position is prolonged corresponding to the time of administration or teaching work. The doctoral position requires good English skills.
The research studies will be conducted within the area of data mining, through a project which is concerned with investigating how data mining can be used to predict the remaining useful life (RUL) of components in heavy trucks. The research topics will concern development, application and verification of RUL models. This involves creating and adapting data mining techniques and software tools for this task. The aim is to use the created RUL models to support decision-making in interacting with fleets of heavy trucks in such a way that the all-over utility of the fleet is maximized while reducing costs and risks of failure to individual trucks.
Top Stories Past 30 Days