ETRO VUB
About ETRO  |  News  |  Events  |  Vacancies  |  Contact  
Home Research Education Industry Publications About ETRO

Master theses

Current and past ideas and concepts for Master Theses.

Evaluation of AI techniques for Power Efficiency of a Network composed of Microphone Arrays

Subject

An FPGA-based Network Emulator has been recently developed in our lab. Such emulator is able to predict the accuracy and the power consumption of a certain network composed of microphone arrays. The data from each microphone array of the network is fused to generate a probability map where to locate sound sources. Each microphone array supports different modes, which determine its accuracy and power consumption. The student must propose and evaluate different AI techniques to optimize the power consumption and accuracy ratio. For instance, the use of deep learning can improve the data fusion of the data coming from the nodes by increasing the accuracy or by using a lower number of nodes/microphones.

Kind of work

- Literature study of data fusion and power efficiency techniques.

- Propose AI strategies to increase the power efficiency and accuracy ratio.

- Evaluate the most promising AI strategies in the existing FPGA-based Network Emulator.

Framework of the Thesis

This thesis is related to the research track at the RapptorLab (INDI department) in collaboration with ETRO.

[1] da Silva, Bruno, et al. "A partial reconfiguration based microphone array network emulator". In Field Programmable Logic and Applications (FPL), 2017 27th International Conference on (pp. 1-4). IEEE.

[2] da Silva, Bruno, et al. "Exploiting Partial Reconfiguration through PCIe for a Microphone Array Network Emulator." International Journal of Reconfigurable Computing 2018 (2018).

Number of Students

1

Expected Student Profile

- Following a MSc in a field related to one or more of the following: applied computer science, computer science and electrical engineering.
- Basic knowledge of/ experience in Artificial Intelligence techniques.
- Good programming skills (C/C++, Python or Matlab)

Promotor

Mr. Abdellah Touhafi

+32 (0)2 629 3774

atouhafi@etrovub.be

more info

Supervisor

Mr. Bruno da Silva Gomes

+32 (0)2 629 3768

bdasilva@etrovub.be

more info

Image

- Contact person

- IRIS

- AVSP

- LAMI

- Contact person

- Thesis proposals

- ETRO Courses

- Contact person

- Spin-offs

- Know How

- Journals

- Conferences

- Books

- Vacancies

- News

- Events

- Press

Contact

ETRO Department

info@etro.vub.ac.be

Tel: +32 2 629 29 30

©2019 • Vrije Universiteit Brussel • ETRO Dept. • Pleinlaan 2 • 1050 Brussels • Tel: +32 2 629 2930 (secretariat) • Fax: +32 2 629 2883 • WebmasterDisclaimer