Activity Recognition Using Wearable Physiological Measurements: Selection of Features from a Comprehensive Literature Study

The detection of emotions is fundamental in many areas related to health and well-being. This paper presents the identification of the level of arousal in older people by monitoring their electrodermal activity (EDA) through a commercial device. The objective was to recognize arousal changes to create future therapies that help them to improve their mood, contributing to reduce possible situations of depression and anxiety. To this end, some elderly people in the region of Murcia were exposed to listening to various musical genres (flamenco, Spanish folklore, Cuban genre and rock/jazz) that they heard in their youth. Using methods based on the process of deconvolution of the EDA signal, two different studies were carried out. The first, of a purely statistical nature, was based on the search for statistically significant differences for a series of temporal, morphological, statistical and frequency features of the processed signals. It was found that Flamenco and Spanish Folklore presented the highest number of statistically significant parameters. In the second study, a wide range of classifiers was used to analyze the possible correlations between the detection of the EDA-based arousal level compared to the participants’ responses to the level of arousal subjectively felt. In this case, it was obtained that the best classifiers are support vector machines, with 87% accuracy for flamenco and 83.1% for Spanish Folklore, followed by K-nearest neighbors with 81.4% and 81.5% for Flamenco and Spanish Folklore again. These results reinforce the notion of familiarity with a musical genre on emotional induction.

Section: Self-assessment Manikinsmentioning

confidence: 99%

Arousal Detection in Elderly People from Electrodermal Activity Using Musical Stimuli

Bartolomé-Tomás

Sánchez-Reolid

Fernández-Sotos³

et al. 2020

“…The database is described in detail in [31] and it can be downloaded from https://www.mdpi. com/1424-8220/19/24/5524 associated with [34]. A brief description of the database can be found in Appendix A.…”

Section: Database Descriptionmentioning

confidence: 99%

“…The description of the database in detail can be found in [31] and https://www.mdpi.com/1424-8220/19/24/5524 associated with [34]. The database consists of the ECG and TEB signals recorded from 40 subjects (students and climbers) aged between 20 and 49 years, of which 12 were females and 28 males.…”

Section: Conflicts Of Interestmentioning

confidence: 99%

A Wrapper Feature Selection Algorithm: An Emotional Assessment Using Physiological Recordings from Wearable Sensors

Mohíno-Herranz

Gil-Pita

García-Gómez

et al. 2020

Self Cite

Assessing emotional state is an emerging application field boosting research activities on the topic of analysis of non-invasive biosignals to find effective markers to accurately determine the emotional state in real-time. Nowadays using wearable sensors, electrocardiogram and thoracic impedance measurements can be recorded, facilitating analyzing cardiac and respiratory functions directly and autonomic nervous system function indirectly. Such analysis allows distinguishing between different emotional states: neutral, sadness, and disgust. This work was specifically focused on the proposal of a k-fold approach for selecting features while training the classifier that reduces the loss of generalization. The performance of the proposed algorithm used as the selection criterion was compared to the commonly used standard error function. The proposed k-fold approach outperforms the conventional method with 4% hit success rate improvement, reaching an accuracy near to 78%. Moreover, the proposed selection criterion method allows the classifier to produce the best performance using a lower number of features at lower computational cost. A reduced number of features reduces the risk of overfitting while a lower computational cost contributes to implementing real-time systems using wearable electronics.

“…Recent advances in technical development such as wearable biomedical sensing through smart clothing and smart mobile devices make physiological measurements of high technical quality including recordings of the electrocardiogram (ECG) available to scientific and medical staff and non-professionals alike [ 1 , 2 ]. Short-term ECG measurements and the segmental analysis of long-term ECG recordings provide information about two distinct but overlapping processes: (1) the complex and dynamic relationship between the sympathetic and parasympathetic branches of the autonomic nervous system and (2) regulatory mechanisms that control the heart rate [ 3 ].…”

Section: Introductionmentioning

confidence: 99%

How to Use Heart Rate Variability: Quantification of Vagal Activity in Toddlers and Adults in Long-Term ECG

Lackner

Eglmaier

Hackl-Wimmer

et al. 2020

Recent developments in noninvasive electrocardiogram (ECG) monitoring with small, wearable sensors open the opportunity to record high-quality ECG over many hours in an easy and non-burdening way. However, while their recording has been tremendously simplified, the interpretation of heart rate variability (HRV) data is a more delicate matter. The aim of this paper is to supply detailed methodological discussion and new data material in order to provide a helpful notice of HRV monitoring issues depending on recording conditions and study populations. Special consideration is given to the monitoring over long periods, across periods with different levels of activity, and in adults versus children. Specifically, the paper aims at making users aware of neglected methodological limitations and at providing substantiated recommendations for the selection of appropriate HRV variables and their interpretation. To this end, 30-h HRV data of 48 healthy adults (18–40 years) and 47 healthy toddlers (16–37 months) were analyzed in detail. Time-domain, frequency-domain, and nonlinear HRV variables were calculated after strict signal preprocessing, using six different high-frequency band definitions including frequency bands dynamically adjusted for the individual respiration rate. The major conclusion of the in-depth analyses is that for most applications that implicate long-term monitoring across varying circumstances and activity levels in healthy individuals, the time-domain variables are adequate to gain an impression of an individual’s HRV and, thus, the dynamic adaptation of an organism’s behavior in response to the ever-changing demands of daily life. The sound selection and interpretation of frequency-domain variables requires considerably more consideration of physiological and mathematical principles. For those who prefer using frequency-domain variables, the paper provides detailed guidance and recommendations for the definition of appropriate frequency bands in compliance with their specific recording conditions and study populations.