The Unit of Medical Technology and Intelligent Information Systems has performed extensive research on the use of intelligent image and signal analysis techniques to address numerous problems, the majority of which are associated with a disease or a medical condition. The aim is to construct decision support systems and provide automated diagnosis focusing on problems ranging from heart diseases to car driver’s status assessment.

The motivation for monitoring the fetus during pregnancy is to recognize pathologic conditions, typically decreased oxygen saturation, with sufficient warning to enable intervention by the clinician before irreversible changes set in. Fetal heart rate (fHR) monitoring is a proven means of assessing fetal health during the antenatal period. The Unit of Medical Technology and Intelligent Information Systems has significant experience in the extraction of fHR from multichannel abdECG recordings. Currently, our research focus on the development of methodologies for monitoring the fetal cardiac health status during pregnancy, through effective and non-invasive monitoring of the abdECG recordings of the mother.
(more details…)

Automatic arrhythmia detection and classification is critical in clinical cardiology, especially when performed in real time. This is achieved through the analysis of the electrocardiogram (ECG) and its extracted features. Our Unit focuses on the development of efficient methods for arrhythmia beat classification and arrhythmic episode detection and classification based on fuzzy expert systems and data mining.
(more details…)

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder for which there is no a single test for its diagnosis. A properly trained physician can diagnose the disease based on laboratory tests, genotyping, patient’s history, clinical observations, cognitive testing and brain imaging such as PET, MRI and Functional Magnetic Resonance Images (fMRI). The aim of our research work is to exploit all possible features, that can be extracted from fMRI experiment and express AD related changes, in order to classify a person as healthy or AD and to classify the stages of the disease.
(more details…)

According to studies a large number of accidents is related with driver’s physiological state. Such states related to accidents are mainly fatigue (drowsiness or mental fatigue) as well as stress. The US Department of Transportation's investigations into fatigue in the 1990s, the extent of fatigue-related fatal accidents is estimated to be around 30%. Stress is also considered to be an accident factor. In routine driving tasks, stress may cause failures of memory and attention. Both video and signal monitoring of driver have both advantages and disadvantages. The main advantage of video monitoring is the non-intrusiveness which a very important factor for real commercial applications. On the other hand, signal monitoring lacks of the main advantage of non-intrusiveness. The advantage is that signals give information on driver’s physiological states.
(more details…)

Facial expressions are the result of the deformations in a human face due to muscle movement. The importance of automating the task to analyse facial expressions by computing systems is apparent and can be beneficial to many different scientific subjects such as psychology, neurology, psychiatry as well as applications for everyday life such as driver monitoring systems, automated tutoring systems or smart environments and human-computer interaction. Advances in topics such as face detection, face tracking and recognition, psychological studies as well as the processing power of modern computer systems make the automatic analysis of facial expressions possible for use with real world examples where responsiveness (i.e. real time processing) is required along with sensitivity (i.e. being able to detect various day to day emotional states and visual cues) and the ability to tolerate head movements or sudden changes.
(more details…)

Statistical processing of biosignal is used for studying problems of spike enhancement, signal denoising, source separation with application to fetal ECG and fMRI data analysis. To solve the above problems the linear model and the dynamic linear models have been used.
(more details…)