Defence of dissertation in the field of networking technology, MSc (Tech) Muneeba Raja

• Translate

Title of the dissertation is “Towards Complex 3D Movement Detection to Predict Human Behaviour Using Radio Frequency Signals”

This thesis project exploited multiple wireless technologies (1.8GHz, WiFi, mm-Wave), and their combinations to detect complex 3D movements of a driver in a car. The upper body movements are vital indicators of driver’s behavior in car, which could be used as a source to generate appropriate feedback, warnings or undergo actions to prevent any safety threatening incidence. Existing wireless-based solutions primarily focus on either big or small movements or well-defined activities. They do not consider separating large movements from small movements along with their directions within a single system. This brings the need to cater to complex natural behavioral situations, such as in a car, where we need not only to separate these movements but to classify them.

To materialize these contributions, we exploit numerous physical properties of RF signals, different hardware-software combinations and build algorithms to process and detect simple to complex body movements and introduce distinctive feature sets for machine learning techniques to find patterns in data and predict states. We evaluate our systems by performing extensive real-world studies and demonstrate how they can be utilized for in-vehicle sensing.

Our process includes wireless data collection from devices such as USRP, WLAN card and VNA, data pre-processing, signal feature extraction and human state classification. From basic to complex, we have performed several studies to prove the potential of body movements as a powerful indicator of human behavior.

Opponent: Professor Matthias Pätzold, Agder University, Norway

Custos: Professor Stephan Sigg, Department of Communications and Networking

Contact information of the doctoral candidate: Muneeba Raja, [email protected]

The public examinations will be organised remotely, via online platform. Link to the online platform (Zoom): https://aalto.zoom.us/j/6549167529Zoom quick guide: https://www.aalto.fi/en/services/zoom-quick-guideThe dissertation is publicly displayed as online display 10 days before the defence at: https://aaltodoc.aalto.fi/doc_public/eonly/riiputus/?lang=en

Link to the electronic dissertation: https://aaltodoc.aalto.fi/handle/123456789/46311