machine learning

The presentation series “Train your engineering network” on diverse topics of Machine Learning addresses all interested persons at TUHH, from MLE partners as well as from the Hamburg region in general and aims at promoting the exchange of information and knowledge between these persons as well as their networking in a relaxed atmosphere. Thereby, the machine learning activities within MLE, TUHH and in the wider environment shall be made more visible, cooperations shall be promoted and also interested students shall be given an insight.

Johanna Gleichauf

The monitoring of vital signs and increasing patient comfort are cornerstones of modern neonatal intensive care. Commonly used monitoring methods are based on skin contact which can cause irritations and discomfort in preterm neonates. Therefore, non-contact approaches are the subject of current research aiming to resolve this dichotomy. Robust neonatal face detection is essential for the reliable detection of heart rate, respiratory rate and body temperature. While solutions for adult face detection are established, the unique neonatal proportions require a tailored approach. Additionally, sufficient open-source data of neonates on the NICU is lacking. We set out to train neural networks with the thermal-RGB-fusion data of neonates. We propose a novel indirect fusion approach including the sensor fusion of a thermal and RGB camera based on a 3D time-of-flight (ToF) camera. Unlike other approaches, this method is tailored for close distances encountered in neonatal incubators. Two neural networks were used with the fusion data and compared to RGB and thermal networks. For the class “head” we reached average precision values of 0.9958 (RetinaNet) and 0.9455 (YOLOv3) for the fusion data. Compared with the literature, similar precision was achieved, but we are the first to train a neural network with fusion data of neonates. The advantage of this approach is in calculating the detection area directly from the fusion image for the RGB and thermal modality. This increases data efficiency by 66%. Our results will facilitate the future development of non-contact monitoring to further improve the standard of care for preterm neonates.

All talks will be streamed via Zoom
Meeting-ID: 852 0319 5489
Code: 827469

The presentation series “Train your engineering network” on diverse topics of Machine Learning addresses all interested persons at TUHH, from MLE partners as well as from the Hamburg region in general and aims at promoting the exchange of information and knowledge between these persons as well as their networking in a relaxed atmosphere. Thereby, the machine learning activities within MLE, TUHH and in the wider environment shall be made more visible, cooperations shall be promoted and also interested students shall be given an insight.

Marcus Venzke 

The talk presents a new technique for unsupervised learning of repeatedly occurring process states from a suite of time series derived from preprocessed sensor data recorded from a fixed process. As a first application we consider the process of moving a good along a path in an industrial environment. The goal is to identify individual sections of the path while they are being traversed. The technique determines thresholds in time series leading to the same succession of increasing and decreasing intersections for all paths of the training data. The trained model is a so-called “threshold tree”. It consists of thresholds for the different time series splitting a path into its sections to be recognized. The execution of threshold trees has a low CPU and memory footprint allowing their use on micro-controllers, e.g. in embedded systems. Due to their intuitive comprehensibility "threshold trees" belong to the category of explainable AI.

All talks will be streamed via Zoom using https://tuhh.zoom.us/j/85203195489?pwd=K21saVMvZHc0d2NoNHd2bDZ6TmdDUT09
Meeting-ID: 852 0319 5489
Code: 827469

Techniques of machine learning (ML) find a rapidly increasing range of applications touching upon social, economic, and technological aspects of everyday life. They are also being used with great enthusiasm to fill in gaps in our scientific knowledge by data-based modelling approaches. I have followed these developments for a while with interest, concern, and mounting disappointment. When these technologies are employed to take over decisive functionality in safety-critical applications, we would like to exactly know how to guarantee their compliance with pre-defined guardrails and limitations. Moreover, when they are utilized as building blocks in scientific research, it would violate scientific standards -in my opinion- if these building blocks were used without a throrough understanding of their functionality, including inaccuracies, uncertainties, and other pitfalls. In this context, I will juxtapose (a subset of) deep neural network methods with the family of entropy-optimal Sparse Probabilistic Approximation (sSPA) techniques developed recently by Illia Horenko (RPTU Kaiserslautern-Landau) and colleagues.

bAIome Center for biomedical AI (UKE) and Bernhard Nocht Institute for Tropical Medicine (BNITM) will host the seminar series entitled “AI in biology and Medicine”. This series aims to capture a broad audience and promote cross institutional collaboration. Our expert speakers will give an overview and insight into particular AI/data science methods being developed in key areas of biology and medicine. We will have drinks and snacks following each seminar to facilitate exchange.

Olga Zolotareva, Institute for Computational Systems Biology, UHH

For further details and hybrid links, please go to the webpage AI in Biology & Medicine