Björn Friedrich

Björn Friedrich, Jürgen Bauer, Andreas Hein

Proper nutrition is very important for the well-being and independence of elderly people. A significant loss of body weight or a decrease of the Body Mass Index respectively is an indicator for malnutrition. A continuous monitoring of the BMI enables doctors and nutritionists to intervene on impending malnutrition. However, continuous monitoring of the BMI by professionals is not applicable and self-monitoring not reliable. In this article a method for monitoring the trend of the BMI based on ambient sensors is introduced. The ambient sensors are used to measure the time a person spends for preparing meals at home. When the trend of the average time for 4 weeks changes, so does the trend of the BMI for those 4 weeks. Both values show a very strong correlation. Thus, the average time for preparing a meal is a suitable indicator for doctors and nutritionists to examine the patient further, become aware of an impending malnutrition, and intervene at an early stage of malnutrition. The method has been tested on a real-world dataset collected during a 10-month field study with 20 participants of an age of about 85 years.

Christian Lins, Björn Friedrich, Andreas Hein et al.

Cardiopulmonary resuscitation (CPR) is one of the most critical emergency interventions for sudden cardiac arrest. In this paper, a robust sinusoidal model-fitting method based on a Evolution Strategy inspired algorithm for CPR quality parameters -- naming chest compression frequency and depth -- as measured by an inertial measurement unit (IMU) attached to the wrist is presented. The proposed approach will allow bystanders to improve CPR as part of a continuous closed-loop support system once integrated into a smartphone or smartwatch application. By evaluating the model's precision with data recorded by a training mannequin as reference standard, a variance for the compression frequency of $\pm 2.22$ compressions per minute (cpm) has been found for the IMU attached to the wrist. It was found that this previously unconsidered position and thus, the use of smartwatches is a suitable alternative to the typical placement of phones in hand for CPR training.

Björn Friedrich, Benjamin Cauchy, Andreas Hein et al.

This article introduces the architecture of a Long-Short-Term Memory network for classifying transportation-modes via Smartphone data and evaluates its accuracy. By using a Long-Short-Term-Memory Network with common preprocessing steps such as normalisation for classification tasks a F1-Score accuracy of 63.68\% was achieved with an internal test dataset. We participated as Team 'GanbareAM' in the 'SHL recognition challenge'.