Digital Health – PsychoSense

The Digital Health – PsychoSense research group aims to explore the potential of digital technologies in psychological research to better understand human psychology and behavior. Many psychological research areas still rely on “traditional” methods, such as laboratory protocols or the collection of self-reports or obtrusive, often invasive biomarkers which lack of digital solutions and might limit the advancements of these areas. Thus, our goal is to tackle this issue by working at the intersection of technology, health, and psychology. The research projects of our group include the development of mobile apps, wearable and contactless sensing paradigms, machine learning algorithms, or other digital platforms that can assist in the assessment, induction, or intervention of various psychological states. We also explore the use of virtual reality, biofeedback, and other novel technologies for enhancing emotional regulation, stress management, or cognitive performance.

In addition, we are strong advocates for open science and adopt a range of open science practices in our research. We want our research to be reproduced, built upon, and used in final applications. Thus, we develop and publish open-source software frameworks (for example, have a look here, here, or here) that enable other researchers to actually use our work to facilitate and advance their own research. Additionally, we also make our datasets and corresponding analyses available, aiming to help promote scientific rigor, reduce the risk of bias, and enable others to build on our group’s work. By embracing the principles of open science, our research group is contributing to a broader movement within the scientific community that seeks to promote greater transparency and accountability in research, while also promoting collaboration and innovation in scientific research.

 

Group Head

Group Members

Alumni

 

Students

If you are interested in writing a Bachelor’s or Master’s thesis in our group, please check the lab’s Student Theses and Jobs.

 

Julia Jorkowitz

Bachelor's Thesis

Systematic Benchmarking of Pre-Ejection Period Extraction Algorithms

Robert Schröter

Master's Thesis

Improving the CARWatch Framework for Objective Cortisol Awakening Response Assessment

Simon Meske

Master's Thesis

Improving the Robustness of Heart Rate Estimation from Continuous-Wave Radar Data using a Wavelet-based Approach and Deep Learning

Past Students

  • Annika Mücke
  • Benjamin Zenke
    stress+ – Development and Evaluation of a Web Application for Remote, Internet-based Induction of Acute Psychosocial Stress
  • Clark Bäker
    Improving the robustness of radar-based heart sound detection
  • Daniel Krauß
    Benchmarking of Sleep/Wake Detection Algorithms using Wearable Sensors and Machine Learning
  • Friederike Popp
    Towards frailty assessment in older adults: Investigation of sit-to-stand transfer detection using ear-worn sensors in real-world activities
  • Jana Reinwald
    Triggering an endocrine stress response in the Virtual Reality Stroop Room through social-evaluative stress
  • Leon Schmid
    Analyzing Acute Psychosocial Stress Responses: A Video-Based Motion Analysis Approach
  • Liv Herzer
  • Luca Abel
    Machine Learning-Based Detection of Acute Psychosocial Stress from Dynamic Movements
  • Paula Kaiser
    Influence of Social-Evaluative Stress in the Virtual Reality Stroop Room
  • Philipp Dörfler
    Comparison of Algorithms for Respiratory Information Extraction from Wearable Sensors
  • Sebastian Stühler
    Investigation of the Pre-Ejection Period as a Marker for Sympathetic Activity during Acute Psychosocial Stress
  • Tobias Gessler
    OpenTSST – An Open Web Platform for Large-Scale, Video-Based Motion Analysis During Acute Psychosocial Stress
  • Ulla Sternemann
    Extraction of Pre-Ejection Period as Marker for Acute Psychosocial Stress from Wearable Sensors and Interferometry Radar
  • Veronika Koch
    Influence of Acute Psychosocial Stress on Body Posture and Movement
  • Victoria Müller
    Machine Learning-Based Detection of Acute Psychosocial Stress from Digital Biomarkers

 

Projects

Completed Projects

Publications

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015