Lunch Talk: Eike Middell "Machine Learning for multimodal wearable biosensors"

During this Lunch Talk, Dr. Eike Middell from the Intelligent Biomedical Sensing (IBS) Lab at BIFOLD will dive into the realm of "Machine Learning for Multimodal Wearable Biosensors," shedding light on the fascinating intersection of technology and healthcare.

Abstract: Functional Near Infrared Spectroscopy (fNIRS) is a cost-effective and practical modality for brain imaging. It has great potential for studying the brain in naturalistic, unconstrained environments if challenges in signal acquisition and processing can be solved. The fNIRS signal is inherently confounded by systemic physiological activity in the cerebral and extra-cerebral compartments. As a result, contrast, sensitivity, and specificity of the recovered hemodynamic responses are affected – a problem worsened by natural behavior in experiments. At the Intelligent Biomedical Sensing (IBS) Lab at Technische Universität Berlin, BIFOLD, we approach these challenges by developing novel wearable neurotechnology and data-driven sensor-fusion methods that leverage additional auxiliary measurements from physiological sensors and complementary neuroimaging modalities, such as EEG, to explain variance in fNIRS signals and separate confounding components from those of interest. The talk will discuss the data science challenges we face and the software tools we create to address them.

The BIFOLD Lunch Talk series gives BIFOLD members and external partners the opportunity to engage in dialogue about their research in Machine Learning and Big Data. Each Lunch Talk offers BIFOLD members, fellows and colleagues from other research institutes the chance to present their research and to network with each other.
The Lunch Talk takes place at the TU Berlin. For further information on the Lunch Talks and registration, contact Dr. Laura Wollenweber via email.