Review
Engineering, Electrical & Electronic
Rawin Assabumrungrat, Soravitt Sangnark, Thananya Charoenpattarawut, Wipamas Polpakdee, Thapanun Sudhawiyangkul, Ekkarat Boonchieng, Theerawit Wilaiprasitporn
Summary: This review investigates research on affective computing using electrocardiogram (ECG) and electrodermal activity (EDA). It summarizes common trends in this field and covers the fundamental pipeline of affective computing research. Future research directions and potential applications are also discussed.
IEEE SENSORS JOURNAL
(2022)
Article
Engineering, Biomedical
Claudia Marzi, Alberto Greco, Enzo Pasquale Scilingo, Nicola Vanello
Summary: This paper explores the possibility of building a model of subject arousal by analyzing speech and electrodermal activity (EDA), finding that significant information on subject arousal can be obtained through EDA analysis during affective word pronunciation. The study also establishes a significant relation between EDA features and self-reported arousal scores, suggesting that concurrent acquisition of EDA and speech features may offer a valid approach for predicting subject arousal during speech production.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Review
Behavioral Sciences
Iti Arora, Alessio Bellato, Danielle Ropar, Chris Hollis, Madeleine J. Groom
Summary: The findings suggest that differences in autonomic arousal during resting-state exist in autistic individuals, with 60.8% of studies finding evidence of group differences between neurotypical and autistic participants. While hyperarousal was more common, hypo-arousal and autonomic dysregulation were also consistently present.
NEUROSCIENCE AND BIOBEHAVIORAL REVIEWS
(2021)
Article
Agriculture, Dairy & Animal Science
Kia Golzari, Youngsun Kong, Sarah A. Reed, Hugo F. Posada-Quintero
Summary: Continuous monitoring of stress in horses is important for improving their quality of life. Current methods rely on behavior observation, which is not continuous. Monitoring the heart rate and electrodermal activity (EDA) can provide a continuous and automatic way to detect stress and pain in horses. EDA is a more sensitive measure of sympathetic arousal and shows promise for non-invasive continuous monitoring.
Article
Chemistry, Analytical
Krzysztof Kutt, Dominika Drazyk, Szymon Bobek, Grzegorz J. Nalepa
Summary: This article proposes using personality assessment to adapt affective intelligent systems and verifies the potential of this adaptation mechanism through experiments linking personality traits to psychophysiological signals and reactions to complex stimulus environments.
Article
Psychology, Biological
Helio Clemente Jose Cuve, Joseph Harper, Caroline Catmur, Geoffrey Bird
Summary: A central tenet of many theories of emotion is that emotional states are accompanied by distinct patterns of autonomic activity. However, experimental studies of coherence between subjective and autonomic responses during emotional states provide little evidence of coherence. The current study addressed this question using a multivariate dimensional approach to build a common autonomic-subjective affective space incorporating subjective responses and three different autonomic signals, and provides a framework for future multimodal emotion research, enabling both hypothesis- and data-driven testing.
Article
Mathematical & Computational Biology
Laurent Sparrow, Hugo Six, Lauren Varona, Olivier Janin
Summary: The study utilizes physiological signals and a created database to provide a range of emotional and cognitive indicators for the Affect-tag solution. Through experimental design and participants' physiological responses, all indicators achieved statistical significance in their respective tasks, with a combined accuracy rate of 89%.
FRONTIERS IN NEUROINFORMATICS
(2021)
Article
Medicine, General & Internal
Jessica Van Oosterwijck, Uros Marusic, Inge De Wandele, Mira Meeus, Lorna Paul, Luc Lambrecht, Greta Moorkens, Lieven Danneels, Jo Nijs
Summary: Although ANS dysfunction has been proposed in ME/CFS, conflicting evidence makes it difficult to draw firm conclusions about ANS activity at rest in ME/CFS patients. This study found that ME/CFS patients showed normal autonomic function at rest in the time-domain, but possible decreased (para)sympathetic activation in the frequency-domain. Additionally, reduced parasympathetic reactivation during recovery from exercise was observed in ME/CFS.
JOURNAL OF CLINICAL MEDICINE
(2021)
Article
Medicine, General & Internal
Lisa Goudman, Nieke Vets, Julie Jansen, Ann De Smedt, Maxime Billot, Philippe Rigoard, Ann Cordenier, Sebastiaan Engelborghs, Aldo Scafoglieri, Maarten Moens
Summary: This study found that in patients with FBSS, spinal cord stimulation (SCS) does not affect the sympathetic nervous system, as measured by skin conductance levels. Despite the effectiveness of SCS in reducing pain intensity, the functioning of the sympathetic nervous system in patients was not normalized.
JOURNAL OF CLINICAL MEDICINE
(2021)
Article
Multidisciplinary Sciences
Roberto Cittadini, Christian Tamantini, Francesco Scotto di Luzio, Clemente Lauretti, Loredana Zollo, Francesca Cordella
Summary: This paper aims to define a reliable and efficient approach for real-time affective state estimation. It identifies 13 optimal physiological features using ReliefF feature selection algorithm and compares the effectiveness of machine learning algorithms, such as KNN, in estimating affective states. The experimental results show that the KNN algorithm, adopted with the 13 identified optimal features, is the most effective approach for real-time affective state estimation.
SCIENTIFIC REPORTS
(2023)
Article
Computer Science, Information Systems
Fei Luo, Salabat Khan, Yandao Huang, Kaishun Wu
Summary: A wide range of sensors is used in human activity recognition, generating large amounts of data during monitoring. Server-based and cloud-based computing require uploading all sensor data, leading to increased costs and latency. However, the development of edge computing addresses this problem by moving computation and data storage closer to the sensors instead of relying on central servers/clouds.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2023)
Review
Psychology, Multidisciplinary
Maciej Behnke, Sylvia D. Kreibig, Lukasz D. Kaczmarek, Mark Assink, James J. Gross
Summary: This meta-analytic review examines the association between positive emotional states and autonomic nervous system (ANS) reactivity. The results suggest that positive emotions have minimal and highly variable effects on ANS activity. However, the limitations of the existing research indicate a need for further investigation.
Review
Chemistry, Analytical
Roberto Sanchez-Reolid, Francisco Lopez de la Rosa, Daniel Sanchez-Reolid, Maria T. Lopez, Antonio Fernandez-Caballero
Summary: This article presents a systematic review on arousal classification using EDA and ML. The review analyzed the different steps involved in processing EDA signals and examined the ML techniques used for arousal classification. It found that support vector machines and artificial neural networks performed well in supervised learning, while unsupervised learning was not effective for arousal detection using EDA.
Review
Hospitality, Leisure, Sport & Tourism
Shanshi Li, Billy Sung, Yuxia Lin, Ondrej Mitas
Summary: This paper reviews 25 articles in the field of tourism and hospitality that use electrodermal activity measurement. It highlights key methodological issues and provides guidelines for researchers using this measurement as a data collection tool for emotions.
ANNALS OF TOURISM RESEARCH
(2022)
Article
Engineering, Electrical & Electronic
Abdullah Ahmed, Jayroop Ramesh, Sandipan Ganguly, Raafat Aburukba, Assim Sagahyroon, Fadi Aloul
Summary: With the increasing use of wearable devices with embedded sensors, there is potential for modeling individual emotional and mental state variations. While there have been studies exploring digital behavior differences between groups with and without mental disorders, the interaction between physiological states and affective states within a predominantly depressive population remains to be studied. This study proposes models that leverage multiple raw signal-to-image transformations to predict depression severity and affective state, and evaluates them using a dataset.
IEEE SENSORS JOURNAL
(2023)