The application of neural networks for BLE phase-based ranging

Student project at imec (Thesis)


What will you be doing?

The range between two BLE devices can be estimated based on three different methods: (i) Received signal strength indicator (ii) Time-of-arrival or Time-difference-of-arrival, (iii) phase evaluation of the tone exchange between two radios. The phase-based ranging in combination with super resolution algorithms is more promising than other techniques in multi-path environments. The challenge in phase-based ranging is to estimate the channel response from the IQ samples on few tones and then estimate the distance from the channel response.

In this project, you will attempt to use the neural networks to estimate the channel response from the IQ samples at both devices which perform ranging. The recurrent neural networks can be evaluated as a starting point as there is temporal structure in the channel response of different tones. The estimated channel response will be then used in combination with super resolution algorithms and/or other neural network architectures to ultimately estimate the range between two devices. Depending on the performance and quality of the researched solutions, a publication in a reputed conference or journal is possible.


Student tasks:
  • Literature survey on different architectures of neural networks used for the ranging application.

  • Identify promising architectures to estimate the channel response using phase measurement of two devices with reasonable complexity.

  • Model the system in MATLAB or Python.

  • Verify the ranging performance with some measurements.

What we do for you

You will be working on cutting-edge research on a topic that is relevant to both academic research and industrial applications. To help you in this journey, we offer a flexible environment where you can be the leader of your own research while at the same time have support of experts from signal processing and systems design to complete your tasks. As part of the IoT team in IMEC-Netherlands you will have opportunities to learn from some of the best minds in analog and digital circuits as well as other research domains.


Who you are
  • You are a MSc/BSc student in Electrical Engineering.

  • You are available for a period of 12 months.

  • You have basic knowledge of signal processing – preferably with project experience.

  • You have affinity with different architectures of neural networks.

  • You are familiar with system-modelling in MATLAB and Python.

  • You are entitled to do an internship in the Netherlands.

  • You are self-starter and able to work independently.

  • Good written and verbal English skills.


Click on 'apply here' to submit your application. You will then be redirected to e-recruiting.