Augmented Reality Driven Steady-State Visual Evoked Potentials for Wheelchair Navigation.

Medically oriented Brain Computer Interfaces (BCIs) have been proposed as a promising approach addressed to individuals suffering from severe paralysis. Steady-State Visual Evoked Potentials (SSVEPs) in particular have been proven successful in many different applications, achieving high information throughput with short or even no training. However, efficient electric wheelchair navigation combining high accuracy and comfort is still not demonstrated. In this paper, we propose the use of an SSVEP-based universal control system featuring augmented reality (AR) glasses in an attempt to increase ease of use and patient acceptability without making compromises on BCI performance. The system received positive user-feedback, reaching a mean accuracy of 90%. Merits and pitfalls of the system proposed are also addressed.

SSVEP based Wheelchair Navigation in Outdoor Environments.

A promising application of Brain Computer Interfaces (BCIs), and in particular of Steady-State Visually Evoked Potentials (SSVEP) is wheelchair navigation which can facilitate the daily life of patients suffering from severe paralysis. However, the outdoor performance of such a system is highly affected by uncontrolled environmental factors. In this paper, we present an SSVEP-based wheelchair navigation system and propose incremental learning as a method of adapting the system to changing environmental conditions.

Cuff-less blood pressure estimation using wrist photoplethysmography.

One of the most promising and at the same time rapidly growing sectors in healthcare is that of wearable medical devices. Population ageing constantly shifts towards a higher number of senior and elderly people with increased prevalence of chronic diseases often requiring long-term care and a need to decrease hospitalization time and cost. However, today most of the devices entering the market are not standardized nor medically approved, and they are highly inaccurate. In this work we present a system and a method to provide accurate measurement of systolic and diastolic blood pressure (BP) based solely on wrist photoplethysmography. We map morphological features to BP values using machine learning and propose ways to select high quality signals leading to an accuracy improvement of up to 33.5%, if compared against no signal selection, a mean absolute error of 1.1mmHg in a personalized scenario and 8.7mmHg in an uncalibrated leave-one-out scenario.

Facial geometry and speech analysis for depression detection.

Depression is one of the most prevalent mental disorders, burdening many people world-wide. A system with the potential of serving as a decision support system is proposed, based on novel features extracted from facial expression geometry and speech, by interpreting non-verbal manifestations of depression. The proposed system has been tested both in gender independent and gender based modes, and with different fusion methods. The algorithms were evaluated for several combinations of parameters and classification schemes, on the dataset provided by the Audio/Visual Emotion Challenge of 2013 and 2014. The proposed framework achieved a precision of 94.8% for detecting persons achieving high scores on a self-report scale of depressive symptomatology. Optimal system performance was obtained using a nearest neighbour classifier on the decision fusion of geometrical features in the gender independent mode, and audio based features in the gender based mode; single visual and audio decisions were combined with the OR binary operation.

Extraction of facial features as indicators of stress and anxiety.

Stress and anxiety heavily affect the human wellbeing and health. Under chronic stress, the human body and mind suffers by constantly mobilizing all of its resources for defense. Such a stress response can also be caused by anxiety. Moreover, excessive worrying and high anxiety can lead to depression and even suicidal thoughts. The typical tools for assessing these psycho-somatic states are questionnaires, but due to their shortcomings, by being subjective and prone to bias, new more robust methods based on facial expression analysis have emerged. Going beyond the typical detection of 6 basic emotions, this study aims to elaborate a set of facial features for the detection of stress and/or anxiety. It employs multiple methods that target each facial region individually. The features are selected and the classification performance is measured based on a dataset consisting 23 subjects. The results showed that with feature sets of 9 and 10 features an overall accuracy of 73% is reached.

Vision-based absence seizure detection.

In order to diagnose epilepsy, neurologists rely on their experience, performing an equal assessment of the electroencephalogram and the clinical image. Since misdiagnosis reaches a rate of 30% and more than one-third of all epilepsies are poorly understood, a need for leveraging diagnostic precision is obvious. With the aim at enhancing the clinical image assessment procedure, this paper evaluates the suitability of certain facial expression features for detecting and quantifying absence seizures. These features are extracted by means of time-varying signal analysis from signals that are gained by applying computer vision techniques, such as face detection, dense optical flow computation and averaging background subtraction. For the evaluation, video sequences of four patients with absence seizures are used. The classification performance of a C4.5 decision tree shows accuracies of up to 99.96% with a worst percentage of incorrectly classified instances of 0.14%.

RF-EMF exposure of fetus and mother during magnetic resonance imaging.

Magnetic resonance imaging (MRI) avoids risks of genetic damage but may be associated with excess heating of body tissues. To investigate the exposure to MRI radio-frequency (RF) electromagnetic fields (EMF), low-pass and high-pass birdcage coils were simulated and the whole-body pregnant woman model SILVY used to determine local and whole-body specific absorption rates (SAR) in mother and fetus. Resonant RF-EMF of MRI devices were investigated at 0.3, 1, 1.5, 2, 3 and 4 T. Results allow extrapolation also to higher fields. They showed that local SAR in mother's trunk reaches exposure limits first. However, data show that during abdominal MRI meeting exposure limits of the mother is not sufficient to protect the fetus if limits of the general populations are applied to it. In that case fetal whole-body SAR exceeds limits by 7.4-fold. It is up to the physician and/or the ethics commission to decide upon justification for abdominal MRI of pregnant women if limits are exceeded. The results indicate the need for specifically addressing fetal exposure to EMF and elaborating general recommendations by radiation protection bodies.

Current densities in a pregnant woman model induced by simultaneous ELF electric and magnetic field exposure.

The pregnant woman model SILVY was studied to ascertain to what extent the electric current densities induced by 50 Hz homogeneous electric and magnetic fields increase in the case of simultaneous exposure. By vectorial addition of the electric current densities, it could be shown that under worst case conditions the basic restrictions recommended by ICNIRP (International Commission on Non-Ionizing Radiation Protection) guidelines are exceeded within the central nervous system (CNS) of the mother, whereas in sole field exposure they are not. However, within the foetus the induced current densities do not comply with basic restrictions, either from single reference-level electric fields or from simultaneous exposure to electric and magnetic fields. Basic limits were considerably exceeded.

Fetal exposure to low frequency electric and magnetic fields.

To investigate the interaction of low frequency electric and magnetic fields with pregnant women and in particular with the fetus, an anatomical voxel model of an 89 kg woman at week 30 of pregnancy was developed. Intracorporal electric current density distributions due to exposure to homogeneous 50 Hz electric and magnetic fields were calculated and results were compared with basic restrictions recommended by ICNIRP guidelines. It could be shown that the basic restriction is met within the central nervous system (CNS) of the mother at exposure to reference level of either electric or magnetic fields. However, within the fetus the basic restriction is considerably exceeded. Revision of reference levels might be necessary.