GR./MT./BT.: Brainwaves modelling to support human-machine interaction in smart systems (IoT)
The main goal is to explore new ways of interacting with smart devices around us. Specifically, understand the potential of portable brainwave-readers to provide means of interacting with IoT devices. Through proper modelling of brain signals in different states (e.g., rest, active), the user of this headset should be able to give commands to a smart system and trigger predefined actions (turn on lights, close blinds, turn off the oven, etc.). It is a follow up from a recently finished master thesis on the same topic in our group.
The focus of this project is to refine our models to associate brain signals to actions and an extensive user evaluation of these models. Complementary, an IoT deployment may be used as a proof of concept to demonstrate the applicability of the model.
The headset provided for this thesis is an Emotiv EEG neuro-headset , an Emotiv EPOC flex  plus an API to access raw EEG signals.
A collection of references to similar research efforts (especially in the direction of how EEG headsets are currently exploited for different purposes) is provided to help the student contextualize the thesis and find eventual research gaps. Such list is not comprehensive and will have to be properly extended as part of the thesis work.
- Collect a large and varied amount of data, from various subjects using the provided headsets
- Evaluate the existing models on the newly collected data, aiming at improving existing results which also generalize well with a heterogeneous dataset.
- Build demos to showcase your current results
- Write your results in a scientific paper format
- Analytical thinking, with good mathematical/statistics background.
- Time Series Analysis, Machine Learning.
- Basic knowledge of IoT, sensors and embedded boards.
- Basic understanding of edge computing paradigm and concepts.
Good to have
- Good knowledge in Signal Processing.
- Experience with Python.
- Familiarity with Linux OS.
If you are interested into the thesis, please send us your CV and exams transcript.
 Chuyen Lam, Q., Anh Tuan Nguyen, L., & Khuong Nguyen, H. (n.d.). A Novel Approach for Classifying EEG Signal with Multi-Layer Neural Network. doi.org/10.1145/3175603.3175627
 Simoens, P., De Coninck, E., Vervust, T., Wijmeersch, J.-F. Van, Ingelbinck, T., & Verbelen, T. (2014). Vision: Smart Home Control with Head-Mounted Sensors for Vision and Brain Activity. doi.org/10.1145/2609908.2609945
 Zhou, L., Su, C., Chiu, W., & Yeh, K.-H. (2017). You Think, Therefore You Are: Transparent Authentication System with Brainwave-oriented Bio-features for IoT Networks. IEEE Transactions on Emerging Topics in Computing, 1–1. doi.org/10.1109/TETC.2017.2759306
 Thomas, K. P., Vinod, A. P., & Robinson, N. (2017). Online Biometric Authentication Using Subject-Specific Band Power features of EEG. Iccsp, 136–141. doi.org/10.1145/3058060.3058068
 Yu, W., Liang, F., He, X., Hatcher, W. G., Lu, C., Lin, J., & Yang, X. (2018). A Survey on the Edge Computing for the Internet of Things. IEEE Access, 6, 6900–6919. doi.org/10.1109/ACCESS.2017.2778504
 Hu, B., Mao, C., Campbell, W., Moore, P., Liu, L., & Zhao, G. (2011). A Pervasive EEG-based Biometric System. Proceedings of 2011 International Workshop on Ubiquitous Affective Awareness and Intelligent Interaction, 17–24. doi.org/10.1145/2030092.2030097