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.

Emotion Recognition from Physiological Signals via Probabilistic Echo-State Networks

Subject

Important developments of new sensing methods and machine learning techniques have motivated an increasing research in the field of affective computing, a recent but fast evolving research discipline which focuses on applications that recognizes and adapt to the user’s emotions. In this context, affect detection turns to be the key to building systems that can advance the preclinical knowledge around affective disorders.
This thesis presents the application of echo-state techniques on physiological data as a means to provide useful information about human emotional or cognitive states.

Kind of work

The proposed research is focused on automatic detection of emotion by utilising different sensory devices like Electrocardiogram (ECG), Respiration (RSP) and Skin Conductance (SC) sensors. In addition visual features by capturing video will be used to increase the validity of the detected emotions by the physiological sensors. The student will (i) develop a scenario for emotion elicitation and data acquisition, and (ii) formulate the emotion recognition problem as a prediction of latent emotion dimensions (valence and arousal) using echo state networks (ESN) [1, 2, 3]. The development will be based on opensource data bases such as DEAP [4] and DECAF [5] : MEG-based Multimodal Database for Decoding Affective Physiological Responses.

Framework of the Thesis

[1] H. Soh, Y. Demiris. Iterative temporal learning and prediction with the sparse online echo state gaussian process. In Proc. of the IJCNN, pp.1–8, 2012.
[2] Edmondo Trentin, Stefan Scherer, and Friedhelm Schwenker. 2015. Emotion recognition from speech signals via a probabilistic echo-state network. Pattern Recogn. Lett. 66, pp. 4-12.
[3] Stefan Scherer, Mohamed Oubbati, Friedhelm Schwenker, and Günther Palm. 2008. Real-Time Emotion Recognition Using Echo State Networks. In Proceedings of PIT ང, Springer-Verlag, Berlin, Heidelberg, pp. 200-204.
[4] DEAP: A Database for Emotion Analysis using Physiological Signals: http://www.eecs.qmul.ac.uk/mmv/datasets/deap/
[5] DECAF: MEG-based Multimodal Database for Decoding Affective Physiological Responses: http://mhug.disi.unitn.it/wp-content/DECAF/DECAF.html

Expected Student Profile

• Following an MSc in a field related to one or more of the following: electrical engineering, computer science, applied mathematics, Biomedical Engineering
• Experience with image processing and signal processing.
• Experience with machine learning and statistics.
• Strong programming skills.
• Interest in performing experiments with humans including recording multimodal sensorial data from volunteer participants.
• Ability to write scientific reports and communicate research results at conferences in English.

Promotor

Prof. Hichem Sahli

+32 (0)2 629 2916

hsahli@etrovub.be

more info

Supervisor

Dr. Meshia Oveneke

+32 (0)2 629 2969

mcovenek@etrovub.be

more info

- 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