ResearchBib Share Your Research, Maximize Your Social Impacts
Sign for Notice Everyday Sign up >> Login

2 PhD positions in Machine Learning for Social Signal Processing at TU Delft

Country/Region : Netherlands, The

Website :


Location: Delft University of Technology, The Netherlands
Deadline: July 21 (see below for application procedure)
Project Description:
An important but under-explored problem in computer science is the automated analysis of conversational dynamics in large unstructured social gatherings such as networking or mingling events. Research has shown that attending such events contributes greatly to career and personal success. While much progress has been made in the analysis of small pre-arranged conversations, scaling up robustly presents a number of fundamentally different challenges.
Unlike analysing small pre-arranged conversations, during mingling, sensor data is seriously contaminated. Moreover, determining who is talking with whom is difficult because groups can split and merge at will. A fundamentally different approach is needed to handle both the complexity of the social situation as well as the uncertainty of the sensor data when analysing such scenes.
The successful applicants will develop automated techniques to analyse multi-sensor data (video, acceleration, audio, etc) of human social behavior. They will work as part of a team on the NWO Funded Vidi project MINGLE (Modelling Group Dynamics in Complex Conversational Scenes from Non-Verbal Behaviour). They will have the opportunity to interact with researchers from both computer science and social science both locally and internationally.
The main aim of the project is to address the following question: How can multi-sensor processing and machine learning methods be developed to model the dynamics of conversational interaction in large social gatherings using only non-verbal behaviour? The two project advertised focus on developing novel computational methods; (1) to analyse of head and body behaviour ; and (2) to measure conversation quality, from multi-sensor streams in crowded environments
Job requirements:
We are looking students who have recently completed or expect very soon an MSc or equivalent degree in computer science, electrical/electronic engineering, applied mathematics, applied physics, or a related discipline. Experience in some or all of the following or related fields are preferred: audio/signal processing, computer vision, embedded sensing, machine learning, and pattern recognition.
The successful applicant will have:
- good programming skills;
- curiosity and analytical skills;
- the ability to work in a multi-disciplinary team;
- motivation to meet deadlines;
- an affinity with the relevant social science research;
- good oral and written communication skills;
- an interest in communicating their research results to a wider audience;
- proficiency in English;
The department Intelligent Systems is part of the Faculty of Electrical Engineering, Mathematics and Computer Science (EEMCS) at Delft University of Technology. The faculty offers an internationally competitive interdisciplinary setting for its 500 employees, 350 PhD students and 1700 undergraduates. Together they work on a broad range of technical innovations in the fields of sustainable energy, quantum engineering, microelectronics, intelligent systems, software technology, and applied mathematics.   
The Pattern Recognition and BioInformatics Group is one of five groups in the department, consisting of 7 faculty and over 20 postdoc and PhD students. Within this group, research is carried out in three core subjects; pattern recognition, computer vision, and bioinformatics. One of the main focuses of the group is on developing tools and theories, and gaining knowledge and understanding applicable to a broad range of general problems but typically involving sensory data, e.g. times signals, images, video streams, or other physical measurement data.
For information about the TU Delft Graduate School, please visit    
Application Procedure:
Interested applicants should send an up-to-date curriculum vitae, letter of application, and the names and the contact information (telephone number and email address) of two references to Dr Hayley Hung ( with the subject heading '[MINGLE PhD]'.
The letter of application should summarise (i) why the applicant wants to do a PhD, (ii) why the project is of interest to the applicant, (iii) evidence of suitability for the job, and (iv) what the applicant hopes to gain from the position.
The application procedure is `ongoing until the position is filled so interested candidates are encouraged to apply as soon as possible and before July 21 2017. Note that candidates who apply after this deadline may still be considered but applications before the deadline will be given priority.

Last modified: 2017-07-19 21:50:52