Embedded Artificial intelligence

MSc Program›MSc Electrical Engineering

 

Budapest University of Technology and Economics (BME)

PROGRAMME WEBSITE

Programme Lead: Tamás Dabóczi daboczi@mit.bme.hu

SPECIALIZATION: Embedded Artificial Intelligence

The specialisation aims to educate engineers who develop intelligent applications based on embedded systems, using artificial intelligence methods. Application examples include (1) from the automotive field Advanced Driver Assistance Systems (ADAS) and support for different levels of autonomous driving; (2) from the healthcare field medical signal processing and sports/lifestyle support using wearable electronics; (3) from  the smart manufacturing field predictive maintenance; (4) from the development field model-in-the-loop, hardware-in-the-loop, and software-in-the-loop testing. Engineers active in this area should have an understanding of hardware platforms including programmable circuits and hardware accelerators, as well as the intelligent signal processing methods and the artificial intelligence algorithms running on them.

The specialisation has the following main goals:

  • It aims to present the sensing of physical signals and the methods for pre-processing the raw sensor data in embedded systems. It introduces the most commonly used sensors and the disturbing and distorting effects in sensing, and introduces the common steps of signal processing, independent of the applications.
  • It presents artificial intelligence based algorithms for information processing in embedded systems. Its special focus is the understanding of data derived from physical processes. In the implementation of algorithms it addresses the possibility of implementing them on embedded hardware platforms and accelerators.
  • The specialisation also presents methods for developing intelligent embedded systems that are critical from the point of view of functional safety. Students learn about the life cycle models of safety-critical systems as defined in development standards, design principles, safety and reliability analysis to justify design decisions, and systematic testing and verification methods.

 

3rd Semester - Compulsory Courses (26 ECTS)

4th Semester - Compulsory Courses (25 ECTS)

Elective Courses (two from the following set, min. 9 ECTS)

Total credits for the whole exit year: min. 60 ECTS

 

There is a strong cooperation with the industry in the field of intelligent embedded systems. The most appropriate link to this cooperation is the thesis work at industry partners. Many large automotive research centres reside in Budapest (thyssenkrupp, Bosch, Knorr-Bremse, Continental), and also other embedded system developers like Ericsson.

 

 

Prof. Tamás Dabóczi is the Head of the Department of Measurement and Information Systems, Budapest University of Technology and Economics, Budapest, Hungary. Besides coordinating the EIT Digital Master School’s former Critical Embedded Systems and the current Embedded Artificial Intelligence specialisation, he has been involved in developing four new Embedded Systems (ES) specialisations both at BSc and MSc level in the past years. He teaches Applications of data processing, Real-time systems, Embedded and ambient systems, and Information processing within ES tracks.

His research area is embedded systems, with special emphasis on information processing and numerical correction of distortions. He has published around 80 papers in areas of signal processing, intelligent embedded systems, and cyber-physical systems. He has been visiting scientist at Swiss Federal Institute of Technology (ETH, Zürich, Switzerland), at Technical University of Karlsruhe (Karlsruhe, Germany), and at National Institute of Standards and Technology (NIST, Gaithersburg, MD, USA). He cooperates with the leading international R&D companies in Budapest like thyssenkrupp, Bosch and Ericsson. Prof. Dabóczi has led many national and international research- and industrial development projects.

 

For further information contact:

Prof, Tamás Dabóczi, coordinator
e-mail
website

© 2010-2024 BME MIT