Steffen Leonhardt

Lukas Ortmann, Dawei Shi, Eyal Dassau et al.

The insulin sensitivity (IS) of the human body changes with a circadian rhythm. This adds to the time-varying feature of the glucose metabolism process and places challenges on the blood glucose (BG) control of patients with Type 1 Diabetes Mellitus. This paper presents a Model Predictive Controller that takes the periodic IS into account, in order to enhance BG control. The future effect of the IS is predicted using a machine learning technique, namely, a customized Gaussian Process (GP), based on historical training data. The training data for the GP is continuously updated during closed-loop control, which enables the control scheme to learn and adapt to intra-individual and inter-individual changes of the circadian IS rhythm. The necessary state information is provided by an Unscented Kalman Filter. The closed-loop performance of the proposed control scheme is evaluated for different scenarios (including fasting, announced meals and skipped meals) through in silico studies on simulation models of Göttingen Minipigs.

Nicky Nirlipta Sahoo, Balamurali Murugesan, Ayantika Das et al.

Preterm babies in the Neonatal Intensive Care Unit (NICU) have to undergo continuous monitoring of their cardiac health. Conventional monitoring approaches are contact-based, making the neonates prone to various nosocomial infections. Video-based monitoring approaches have opened up potential avenues for contactless measurement. This work presents a pipeline for remote estimation of cardiopulmonary signals from videos in NICU setup. We have proposed an end-to-end deep learning (DL) model that integrates a non-learning based approach to generate surrogate ground truth (SGT) labels for supervision, thus refraining from direct dependency on true ground truth labels. We have performed an extended qualitative and quantitative analysis to examine the efficacy of our proposed DL-based pipeline and achieved an overall average mean absolute error of 4.6 beats per minute (bpm) and root mean square error of 6.2 bpm in the estimated heart rate.

Christian S. Pilz, Benjamin Clemens, Inka C. Hiss et al.

We study the statistical properties of facial behaviour altered by the regulation of brain arousal in the clinical domain of psychiatry. The underlying mechanism is linked to the empirical interpretation of the vigilance continuum as behavioral surrogate measurement for certain states of mind. Referring to the classical scalp-based obtrusive measurements, we name the presented method Opto-Electronic Encephalography (OEG) which solely relies on modern camera-based real-time signal processing and computer vision. Based upon a stochastic representation as coherence of the face dynamics, reflecting the hemifacial asymmetry in emotion expressions, we demonstrate an almost flawless distinction between patients and healthy controls as well as between the mental disorders depression and schizophrenia and the symptom severity. In contrast to the standard diagnostic process, which is time-consuming, subjective and does not incorporate neurobiological data such as real-time face dynamics, the objective stochastic modeling of the affective responsiveness only requires a few minutes of video-based facial recordings. We also highlight the potential of the methodology as a causal inference model in transdiagnostic analysis to predict the outcome of pharmacological treatment. All results are obtained on a clinical longitudinal data collection with an amount of 99 patients and 43 controls.

Christian S. Pilz, Vladimir Blazek, Steffen Leonhardt

We study the vector space of visible wavelength intensities from face videos widely used as input features in Photoplethysmography Imaging (PPGI). Based upon theoretical principles of Group invariance in the Euclidean space we derive a change of the topology where the corresponding distance between successive measurements is defined as geodesic on a Riemannian manifold. This lower dimensional embedding of the sensor signal unifies the invariance properties with respect to translation of the features as discussed by several former approaches. The resulting operator acts implicit on the feature space without requiring any kind of prior knowledge and does not need parameter tuning. The resulting feature's time varying quasi-periodic shaping naturally occurs in form of the canonical state space representation according to the known Diffusion process of blood volume changes. The computational complexity is low and the implementation becomes fairly simple. During experiments the operator achieved robust and competitive estimation performance of heart rate from face videos on two public databases.