Can you smell my stress? Influence of stress chemosignals on empathy and emotion recognition in depressed individuals and healthy controls.

Human body odors contain chemical signals that play a key role in our non-verbal communication regarding health, genetic identity, immune system, fitness, and emotional state. Studies on human chemosignaling in individuals with psychiatric diseases are scarce but indicate altered smell perception and emotion recognition in depressed individuals. In the present project, we aimed to investigate the influence of chemosensory substances in social stress sweat on emotion recognition, perspective taking, affective responsiveness as well as stress level in healthy and depressed individuals. Therefore, chemosensory stimuli (sweat samples from Trier social stress test (TSST) and friendly-TSST (fTSST)) were obtained from 39 healthy participants (19 females). In a next step, chemosensory stimuli and an odor-free blank (cotton pad) were used to stimulate another group of 40 healthy participants (20 females) and 37 individuals with depression (24 females). Those stimuli were examined regarding their influence on subjective feelings of stress, emotion perception and empathic reactions using an empathy test. Furthermore, physiological data (breathing, heart rate, skin conductance response, stress hormones) of the participants were collected during chemosensory stimulation. Depressed individuals improved their ability of perspective taking and affective responsiveness for the emotion grief when presented with stress chemosignals compared to no chemosignals. Healthy individuals remained unaffected regarding perspective taking and affective responsiveness. Both depressed and healthy individuals showed no increased stress hormone cortisol and α-amylase values during the social stress chemosignals condition, but reduced values for fTSST condition compared to no chemosignals respectively. The results imply that stress chemosignals do not trigger a stress reaction, but for depressed individuals they lead to a better emotion assessment for grief. This research contributes to a deeper understanding of the effects of social stress chemosignals on healthy and depressed individuals. Knowing the impact of human chemosignals on emotional processing is crucial for a better understanding of non-verbal human interaction.

xLength: Predicting Expected Ski Jump Length Shortly after Take-Off Using Deep Learning.

With tracking systems becoming more widespread in sports research and regular training and competitions, more data are available for sports analytics and performance prediction. We analyzed 2523 ski jumps from 205 athletes on five venues. For every jump, the dataset includes the 3D trajectory, 3D velocity, skis' orientation, and metadata such as wind, starting gate, and ski jumping hill data. Using this dataset, we aimed to predict the expected jump length (xLength) inspired by the expected goals metric in soccer (xG). We evaluate the performance of a fully connected neural network, a convolutional neural network (CNN), a long short-term memory (LSTM), and a ResNet architecture to estimate the xLength. For the prediction of the jump length one second after take-off, we achieve a mean absolute error (MAE) of 5.3 m for the generalization to new athletes and an MAE of 5.9 m for the generalization to new ski jumping hills using ResNet architectures. Additionally, we investigated the influence of the input time after the take-off on the predictions' accuracy. As expected, the MAE becomes smaller with longer inputs. Due to the real-time transmission of the sensor's data, xLength can be updated during the flight phase and used in live TV broadcasting. xLength could also be used as an analysis tool for experts to quantify the quality of the take-off and flight phases.