An application for emotion recognition with serious games
Going beyond conventional patient monitoring, homecare systems are being enhanced with affective computing capabilities, which are particularly valuable for both detecting and preventing dangerous situations (for example, intense stress or depression). A patient’s emotional state…
Read more →Analytics and fusion of heterogeneous medical data
Analysing different modalities of biomedical data leads to better diagnostic and prognostic models of disease. For this reason, modern electronic health record applications try to incorporate every kind of information, leading to holistic records. Most…
Read more →Using the photoplethysmographic (PPG) signal as a biometric feature
Using the photoplethysmographic (PPG) signal produced by pulse oximeters for biometric identification is a new approach to secure authentication. PPG signals can be acquired easily and at relatively low cost with the corresponding devices. The…
Read more →Automatic gesture recognition
Automatic gesture recognition is an important area of human–computer interaction. To date, recognition has mainly relied on video processing. This thesis uses smart watches, which contain motion sensors (built-in accelerometers) and offer wireless networking (mainly…
Read more →Analysis of audio recordings and context recognition
The aim of this thesis is to develop machine learning techniques that automatically classify audio signals into context classes, for outdoor and indoor sound, with the goal of recognising activity. In addition, techniques will be…
Read more →Medical image analysis with machine learning and deep neural networks on parallel systems
Developing computer systems for automated diagnosis from medical images has been an area of intense research in recent years. Digital medical images are found in the vast majority of diagnostic laboratories, which allows computer systems…
Read more →