Student Project: The application of Generative Models for Gesture Detection Generalization

What you will do

Standardized impulse radio ultrawideband (IR-UWB) radar is used for various applications, joint communication and secure ranging, and to detect the presence of targets in the surrounding environments and to discern other targets information, from extracting vital sign information of people to recognizing their gestures. In this project, the goal is to design a gesture detection system based on neural networks that processes the IR-UWB radar measurement data to detect a set of predefined gestures for automotive industry. The gestures include but not limited to the gestures that control the touch screen in the cars. The designed system makes less distractions for the driver to use the display, which improves road safety.
The student will design a gesture detection system based on neural networks using the measurement data provided by the IR-UWB radar developed at imec. The student is involved in data collection, data pre-processing, training, and validation of the designed neural networks. This project is especially suitable for students who are passionate about employing neural networks for real-world problems.


Furthermore, the student will explore employing generative models to enrich the data set and get a trained model which generalized with different people. Using generative models is of great importance in this project as the measurement data set is limited due to practical reasons.

What we do for you

You will be working on cutting-edge research on a topic that is relevant to 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 having the support of experts from signal processing and systems design to complete your tasks. As part of the Signal Processing team in IMEC-Netherlands, you will have opportunities to learn from some of the best minds in analog and digital circuits, data science and other research domains.

Who you are

• You are a MSc/BSc student in Electrical Engineering or Data Science
• You have affinity with different architectures of neural networks (ConvNet, LSTM, etc.)
• You have basic knowledge of signal processing
• You are available for a period of 6-8 months
• You are familiar with system-modelling in MATLAB and Python
• You are self-starter and able to work independently
• You are entitled to do an internship in the Netherlands
• Good written and verbal English skills

Interested

Does this position sound like an interesting next step in your career at imec? Don’t hesitate to submit your application by clicking on ‘APPLY NOW’.
Got some questions about the recruitment process? Martijn Kohl of the Talent Acquisition Team will be happy to assist you.