PhD position in Radar Classification and Artificial Intelligence
We have the ambition to design and validate innovative artificial intelligence methods to characterise human kinematic and locomotion using radar data, …
- Mekelweg, Delft, Zuid-Holland
- Tijdelijk contract / Tijdelijke opdracht
- Uren per week:
- 38 - 40 uur
- € 2395 - € 3061 per maand
We have the ambition to design and validate innovative artificial intelligence methods to characterise human kinematic and locomotion using radar data, essentially the activities, movements and gestures performed by people in indoor settings.
Information on what activities a person is doing, where, and when, can help understand his/her physical and cognitive status and identify anomalies possibly related to worsening health. Why radar sensing? Because it is contactless, the person does not need to wear or carry any sensor, and there is no camera taking plain videos/pictures of people and private environments.
Radar data are intrinsically different from optical videos, pictures, language, or audio, for which artificial intelligence based methods for classification are relatively well established. Rather than simply adapting networks designed for those kinds of data, new research is needed to understand, model, and capture the intrinsic kinematic information encoded in the sequence of radar data, which is strongly related to the movements of people observed.
You will work in the NWO funded project RAD-ART (RADar-aware Activity Recognition with innovative Temporal networks). Specifically, you will tackle the challenge of accounting for the continuous and correlated nature of the radar data, as well as the relevance of contextual information. You will investigate innovative networks, for example recurrent and temporal-convolutional networks, currently underexplored in the literature regarding radar data classification. You will be also responsible for
- Experimentally verifying methods with short-range radars.
- Performing research according to the project plan.
- Preparing and writing all project deliverables within the project.
You will work in the Microwave Sensing Signals and Systems (MS3) research group at the Department of Microelectronics (see radar.tudelft.nl). The group has extensive research facilities and track record on the full pipeline of microwave and radar sensing, from hardware development to radar signal processing and methods for automatic object classification.
To be considered for the position you will have:
- A Master's degree in a relevant field, i.e. electrical/electronic engineering, computer science, physics, mathematics.
- Demonstrable knowledge and interest in radar signal processing including classification methods.
- Demonstrable knowledge and interest in AI methods, preferably deep learning techniques dealing with temporal data (e.g. audio, speech).
- Programming experience in MATLAB/Python or C/C++, preferably combined with experience in working with actual radar systems and data.
- A curiosity-driven mindset and a passion for (doing) research
- An open personality for cooperation with colleagues and co-supervision of students
- Good English language and communication skills (written and oral) in order to closely cooperate with colleagues and students as well as write project documents.
European (EU) nationality is an advantage.
TU Delft offers PhD-candidates a 4-year contract, with an official go/no go progress assessment after one year. Salary and benefits are in accordance with the Collective Labour Agreement for Dutch Universities, increasing from € 2395 per month in the first year to € 3061 in the fourth year. As a PhD candidate you will be enrolled in the TU Delft Graduate School. The TU Delft Graduate School provides an inspiring research environment with an excellent team of supervisors, academic staff and a mentor. The Doctoral Education Programme is aimed at developing your transferable, discipline-related and research skills.
The TU Delft offers a customisable compensation package, discounts on health insurance and sport memberships, and a monthly work costs contribution. Flexible work schedules can be arranged. For international applicants we offer the Coming to Delft Service and Partner Career Advice to assist you with your relocation.
If you would like more technical information about this vacancy, please contact Dr Francesco Fioranelli (F.Fioranelli@tudelft.nl) or Prof Alexander Yarovoy (A.Yarovoy@tudelft.nl).
If you would like more information about the selection procedure, please contact firstname.lastname@example.org.