Analysis of physiological changes related to emotions during a zipline activity

Abstract

Despite the popularity of physiological wearable sensors in sport activities to provide feedback on athletes' performance, understanding the factors influencing changes in athletes' physiological rhythms remains a challenge. Changes in physiological rhythms such as heart rate, breathing rate or galvanic skin response can be due to both physical exertion and psychoemotional states. Separating the influence of physical exertion and psychoemotional states in activities that involves both is complicated. As a result, the influence of psycho-emotional states is usually underestimated. In order to identify the specific influence of psycho-emotional states in physiological rhythm changes, 28 participants were asked to participate in a zipline activity, which involve little or no physical exertion while stimulating psycho-emotional states. By using nonlinear analyses, results show that specific changes in phys-This research was supported and led by Sensum Ltd. in collaboration with Queen's University Belfast.

A Multimodal Dataset and Evaluation for Feature Estimators of Temporal Phases of Anxiety

“…It is a statistical technique that models non-linear relationships between time-varying predictors and outcome variables. It has been used in domains such as acoustic and physiological analyses [14,29,60], as it combines the strengths of flexibility (as in machine-learning techniques) and interpretability (defined as an addition of linear models). GAMMs facilitate deriving a model for a cluster of time series data by applying non-parametric smoothing functions and comparing significant differences between multiple models; therefore, suitable for testing our hypotheses.…”

Towards a Protocol for Preference Evaluation of Cosmetic Products Using Physiological Sensors

“…This limitation has been pointed by other researchers [33]. Some of them have shown that the combination of sensors signals, for example in the General Additive Mixed Model (GAMM), can provide more information of the tendency of physiological reactions [34] [33]. In Figure 4 we see an example of one GAMMs model (Fig.…”

“…Clear methods for the treatment and statistical analysis of data should be established in future research. This limitation has been pointed by other researchers [33]. Some of them have shown that the combination of sensors signals, for example in the General Additive Mixed Model (GAMM), can provide more information of the tendency of physiological reactions [34] [33].…”

Wearables and Machine Learning for Improving Runners’ Motivation from an Affective Perspective

“…Bi et al [ 19 ] also used commercial wearables but to recognise the emotional state of long-distance runners during a race in order to create affective maps that are shared with the spectators. The works of Dupre are focused on the use of wearables for modelling emotional patterns in athletes during physical activities [ 20 ] and for analysing the relationship between their emotions and their performance when performing zipline activities [ 21 ]. There are also many works that use wearables and consider athletes’ emotions to detect stress [ 22 ], pain [ 23 ] or fatigue perception [ 4 , 24 ].…”