PhD position Signal Processing for Edge-AI Sensing in Healthy Buildings

PhD position Signal Processing for Edge-AI Sensing in Healthy Buildings

Published Deadline Location
26 Oct 30 Nov Eindhoven

You cannot apply for this job anymore (deadline was 30 Nov 2022).

Browse the current job offers or choose an item in the top navigation above.

We have a PhD-vacancy in the group Signal Processing Systems (SPS), department Electrical Engineering.

Job description

Work environment
Eindhoven University of Technology (TU/e, is one of Europe's top technological universities, situated at the heart of a most innovative high-tech region. Thanks to a wealth of collaborations with industry and academic institutes, TU/e's research is known for its real-world impact and has worldwide a leading position in effective academic - industrial cooperation. TU/e has around 3,000 employees and 2,300 PhD students (half of which international, representing about 70 nationalities).

The candidate will work in the Signal Processing Group (SPS) at the Department of Electrical Engineering ( in a project with international academic and industrial cooperations. Within the EE department, research and education is done in domains of Telecommunication, Care and Cure, and Smart Energy systems. The SPS group has a strong track record not only in signal processing for digital communication, but also for medical applications, automotive and for intelligent IoT systems. The impact of the work of the group is evident from a very close cooperation with industrial partners and research institutes and from international recognition and awards of the team.


The project contributes to the EU grand societal challenge to increase the intelligent processing capabilities at the edge cloud. We address Artificial Intelligence in indoor spaces (e.g. in smart offices or healthy buildings) where the sensor configuration widely differs from building to building and even from room to room. Hence, their observations on the underlying processes are also different. Nonetheless, there is a need for a reliable deployment in a way that the system already works well immediately after being switched on. That is, the AI algorithms need to be robust to variations in the configuration and use of sensors. Moreover, in some cases there is the option of obtaining feedback from the user making topics such as semi-supervised online learning of interest.

Project description

The European HORIZON-project EdgeAI targets intelligent processing solutions at the edge. The 48 partners will develop new electronic components and systems, processing architectures, connectivity, software, algorithms, and middleware through the combination of microelectronics, AI, embedded systems, and edge computing.

The TU/e research activity specifically addresses AI and statistical signal processing algorithms of AI in Smart and Healthy Buildings with sensors. Challenges are:
  • Distributed AI plus federated learning: How to use AI in a distributed-sensing low-bandwidth network?
  • Transfer learning: How to expand a sensor network without having to retrain the models?
  • Robustness: How to handle sensors that are temporarily off line?
  • Online learning: How to handle feedback from users on made predictions?
  • (Semi) supervised learning for time series: How to improve performance through unsupervised learning?

EDGE AI Solutions should work under constraints in system design, such as cost-optimized coverage, power consumption and signalling complexity. According to earlier TU/e SPS work, some approaches from statistical signal processing are promising. An example of an approach can be the integration of neural networks into Hidden Markov Modesl. In fact, domain insights for instance from personalized Human Centric Lighting can to some extend be modelled as an HMM while NNs may perporm better in situations where the underlying process in not well or not fully known. 


The PhD candidate will explore flexible Edge-AI sensor configurations, the resolution of missing data, and particularly address to what extent federated learning is possible such that sensors systems can learn from labeled data but that has been gathered in situations where the configuration is different.

The PhD candidate will participate in design, analysis, engineering and implementation of a sensing and lighting control system taking into account constraints of devices. Such a systems approach will have to be design is teamwork with other partners. The candidate is expected to
  • Actively contribute to this project and meanwhile.
  • To Define directions (in collaboration) for scientific breakthroughs in the above challenges.
  • To mature these concepts in academic world (in the form of publications) and to transfer these, in the form of working building blocks tested in the EU project and in set-ups co-created with project partner(s).

The PhD candidate will regularly report about his/her work, both orally in progress meetings as well as in writing deliverable reports. He/she should cooperate with the other researchers in the project, amongst others by integrating his/her results in the joint project system demonstrator. He/she should disseminate his/her work, including transfer to project partners and via publications in scientific journals and conferences. The project tasks are done in very close cooperation with Signify and connects to other partners such as NXP. The candidate may work parts of the time at the premises of a project partner.


Eindhoven University of Technology (TU/e)


In the Signal Processing Systems group, we are looking for a candidate who is interested in and can oversee the overall system. The candidate is expected to use principles of artificial intelligence, statistical signal processing, resource-constrained IoT devices as well as physical models of processes in the real world. This requires a good understanding of these, an ability to rapidly learn these topics and to combine scientific insights and mathematical models across these areas. This is an applied research position. We expect candidate to combine their skills and knowledge in the aforementioned fields to solve complex real-world problems.

Candidate profile
  • MSc degree in electrical engineering, physics, or mathematics.
  • Solid knowledge of statistical signal processing, artificial intelligence, or related areas.
  • Proven interested in physical and human process, preferably in a smart building setting
  • Proven team-working capabilities and communication skills, preferably having some experience in academic publishing
  • Active interest in transferring meaningful innovations to industry and willingness to engages in secondments with industrial project partner.
  • English proficiency (both verbal and written)
  • Having the ambition to combine world-class academic research with meaningful industrial transfers
  • Willingness to start as soon as possible

Conditions of employment

A meaningful job in a dynamic and ambitious university, in an interdisciplinary setting and within an international network. You will work on a beautiful, green campus within walking distance of the central train station. In addition, we offer you:
  • Full-time employment for four years, with an intermediate evaluation (go/no-go) after nine months. You will spend 10% of your employment on teaching tasks.
  • Salary and benefits (such as a pension scheme, paid pregnancy and maternity leave, partially paid parental leave) in accordance with the Collective Labour Agreement for Dutch Universities, scale ... (min. €... max. €...).
  • A year-end bonus of 8.3% and annual vacation pay of 8%.
  • High-quality training programs and other support to grow into a self-aware, autonomous scientific researcher. At TU/e we challenge you to take charge of your own learning process.
  • An excellent technical infrastructure, on-campus children's day care and sports facilities.
  • An allowance for commuting, working from home and internet costs.
  • A Staff Immigration Team and a tax compensation scheme (the 30% facility) for international candidates.


  • PhD
  • Engineering
  • max. 38 hours per week
  • University graduate
  • V36.6040


Eindhoven University of Technology (TU/e)

Learn more about this employer


De Rondom 70, 5612 AP, Eindhoven

View on Google Maps

Interesting for you