scholarly journals Non-Parametric Classifiers Based Emotion Classification Using Electrodermal Activity and Modified Hjorth Features

2021 ◽  
Author(s):  
Yedukondala Rao Veeranki ◽  
Nagarajan Ganapathy ◽  
Ramakrishnan Swaminathan
Keyword(s):  
Skin Conductance ◽  
Electrodermal Activity ◽  
Statistical Significance ◽  
Skin Conductance Level ◽  
Emotional States ◽  
Emotion Classification ◽  
K Nearest Neighbor ◽  
Rotation Forest ◽  
Valence And Arousal ◽  
Non Parametric

In this work, an attempt has been made to classify various emotional states in Electrodermal Activity (EDA) signals using modified Hjorth features and non-parametric classifiers. For this, the EDA signals are collected from a publicly available online database. The EDA is decomposed into SCL (Skin Conductance Level) and SCR (Skin Conductance Response). Five features, namely activity, mobility, complexity, chaos, and hazard, collectively known as modified Hjorth features, are extracted from SCR and SCL. Four non-parametric classifiers, namely, random forest, k-nearest neighbor, support vector machine, and rotation forest, are used for the classification. The results demonstrate that the proposed approach can classify the emotional states in EDA. Most of the features exhibit statistical significance in discriminating emotional states. It is found that the combination of modified Hjorth features and rotation forest is most accurate in classifying the emotional states. Thus, the result demonstrates that this method can recognize valence and arousal dimensions under various clinical conditions.

scholarly journals An Emotion Assessment of Stroke Patients by Using Bispectrum Features of EEG Signals

2020 ◽  
Vol 10 (10) ◽  
pp. 672 ◽  
Author(s):  
Choong Wen Yean ◽  
Wan Khairunizam Wan Ahmad ◽  
Wan Azani Mustafa ◽  
Murugappan Murugappan ◽  
Yuvaraj Rajamanickam ◽  
...  
Keyword(s):  
Brain Damage ◽  
Nearest Neighbor ◽  
Probabilistic Neural Network ◽  
Statistical Significance ◽  
Emotional States ◽  
Emotion Classification ◽  
K Nearest Neighbor ◽  
Eeg Signals ◽  
Stroke Patients ◽  
Emotion Assessment

Emotion assessment in stroke patients gives meaningful information to physiotherapists to identify the appropriate method for treatment. This study was aimed to classify the emotions of stroke patients by applying bispectrum features in electroencephalogram (EEG) signals. EEG signals from three groups of subjects, namely stroke patients with left brain damage (LBD), right brain damage (RBD), and normal control (NC), were analyzed for six different emotional states. The estimated bispectrum mapped in the contour plots show the different appearance of nonlinearity in the EEG signals for different emotional states. Bispectrum features were extracted from the alpha (8–13) Hz, beta (13–30) Hz and gamma (30–49) Hz bands, respectively. The k-nearest neighbor (KNN) and probabilistic neural network (PNN) classifiers were used to classify the six emotions in LBD, RBD and NC. The bispectrum features showed statistical significance for all three groups. The beta frequency band was the best performing EEG frequency-sub band for emotion classification. The combination of alpha to gamma bands provides the highest classification accuracy in both KNN and PNN classifiers. Sadness emotion records the highest classification, which was 65.37% in LBD, 71.48% in RBD and 75.56% in NC groups.

scholarly journals The Relationship between Different Types of Alarm Sounds and Children’s Perceived Risk Based on Their Physiological Responses

2019 ◽  
Vol 16 (24) ◽  
pp. 5091
Author(s):  
Jiaxu Zhou ◽  
Xiaohu Jia ◽  
Guoqiang Xu ◽  
Junhan Jia ◽  
Rihan Hai ◽  
...  
Keyword(s):  
Skin Conductance ◽  
Perceived Risk ◽  
Electrodermal Activity ◽  
Physiological Responses ◽  
Skin Conductance Level ◽  
Kindergarten Children ◽  
Physiological Data ◽  
Adult Males ◽  
Different Types ◽  
Alarm Sounds

Due to differences in cognitive ability and physiological development, the evacuation characteristics of children are different from those of adults. This study proposes a novel method of using wearable sensors to collect data (e.g., electrodermal activity, EDA; heart rate variability, HRV) on children’s physiological responses, and to continuously and quantitatively evaluate the effects of different types of alarm sounds during the evacuation of children. In order to determine the optimum alarm for children, an on-site experiment was conducted in a kindergarten to collect physiological data for responses to different types of alarm sounds during the evacuation of 42 children of different ages. The results showed that: (1) The alarm sounds led to changes in physiological indicators of children aged 3–6 years, and the effects of different types of alarm sounds on EDA and HRV activities were significantly different (p < 0.05). Skin conductance (SC), skin conductance tonic (SCT) and skin conductance level (SCL) can be used as the main indicators for analysing EDA of children in this experiment (p < 0.05), and the indicators of ultralow frequency (ULF) and very low frequency (VLF) for HRV were not affected by the type of alarm sounds (p > 0.05). (2) Unlike adults, kindergarten children were more susceptible to the warning siren. The combined voice and warning alarm had optimal effects in stimulating children to perceive risk. (3) For children aged 3–6 years, gender had a significant impact on children’s reception to evacuation sound signals (p < 0.05): Girls are more sensitive than boys in receiving evacuation sound signals, similar to findings of studies of risk perception of adult males and females. In addition, the higher the age, the greater the sensitivity to evacuation sound signals, which accords with results of previous studies on the evacuation dynamics of children.

scholarly journals Affective Synchrony and Autonomic Coupling during Cooperation: A Hyperscanning Study

2017 ◽  
Vol 2017 ◽  
pp. 1-9 ◽  
Author(s):  
Maria Elide Vanutelli ◽  
Laura Gatti ◽  
Laura Angioletti ◽  
Michela Balconi
Keyword(s):  
Social Interactions ◽  
Electrodermal Activity ◽  
Skin Conductance Level ◽  
Social Bond ◽  
Positive Outcomes ◽  
Emotional States ◽  
Emotional Experiences ◽  
Joint Actions ◽  
Social Dynamic ◽  
Conductance Level

Previous research highlighted that during social interactions people shape each other’s emotional states by resonance mechanisms and synchronized autonomic patterns. Starting from the idea that joint actions create shared emotional experiences, in the present study a social bond was experimentally induced by making subjects cooperate with each other. Participants’ autonomic system activity (electrodermal: skin conductance level and response: SCL, SCR; cardiovascular indices: heart rate: HR) was continuously monitored during an attentional couple game. The cooperative motivation was induced by presenting feedback which reinforced the positive outcomes of the intersubjective exchange. 24 participants coupled in 12 dyads were recruited. Intrasubject analyses revealed higher HR in the first part of the task, connoted by increased cognitive demand and arousing social dynamic, while intersubject analysis showed increased synchrony in electrodermal activity after the feedback. Such results encourage the use of hyperscanning techniques to assess emotional coupling in ecological and real-time paradigms.

Skin Conductance, Marlowe-Crowne Defensiveness, and Dental Anxiety

1994 ◽  
Vol 79 (1) ◽  
pp. 611-622 ◽  
Author(s):  
Carmen Benjamins ◽  
Albert H. B. Schuurs ◽  
Johan Hoogstraten
Keyword(s):  
Skin Conductance ◽  
Dental Care ◽  
Electrodermal Activity ◽  
Dental Anxiety ◽  
Skin Conductance Level ◽  
Dental Patients ◽  
High Anxious ◽  
Skin Conductance Levels ◽  
Dental Appointment ◽  
The Relationship

The present study assesses the relationship between self-reported dental anxiety (Dental Anxiety Inventory, Dental Anxiety Scale, and Duration of Psychophysiological Fear Reactions), electrodermal activity (skin-conductance level and frequency of spontaneous responses), and Marlowe-Crowne defensiveness. All measurements were made twice. The first session was scheduled immediately before a semi-annual dental check-up (stress condition), and baseline measurements were made two months later without the prospect of a dental appointment. Subjects were male dental patients who regularly attended a university dental clinic and a clinic for Special Dental Care. The main findings were that the low anxious-high defensive-scoring (Marlowe-Crowne Denial subscale) university patients showed significantly higher skin-conductance levels and frequency of nonspecific fluctuations than the low anxious-low defensive-scoring subjects. Besides, the conductance values of the low anxious-high defensive-scoring subjects resembled those of the high anxious-low defensive-scoring patients of the clinic for Special Dental Care, the baseline frequency of nonspecific fluctuations excepted.

scholarly journals Effects of Affctive Ambiguity on Emotion Regulation through Affect Labeling

2020 ◽  
Author(s):  
Miyu Matsuguma ◽  
Mariko Shirai ◽  
Makoto Miyatani ◽  
Takashi Nakao
Keyword(s):  
Emotion Regulation ◽  
Facial Expressions ◽  
Skin Conductance ◽  
Skin Conductance Level ◽  
Stimulus Presentation ◽  
Future Research ◽  
Emotional States ◽  
Affect Labeling ◽  
Emotion Word ◽  
Skin Conductance Responses

Putting feelings into words, called affect labeling, has been shown to attenuate emotional responses. However, labeling ambiguous emotional states may reduce the emotion regulation effect because it is difficult to categorize such feelings. Conversely, it may prove more effective by reducing feelings of uncertainty. The current study aimed to investigate how affect labeling in affective ambiguity influences emotion regulation effects on the subjective intensity of feelings, skin conductance level, and skin conductance response. Participants were asked to rate the intensity of their feelings after being presented with images of clear facial expressions for the prototypical condition and morphed facial expressions for the ambiguous condition. In addition, participants assigned to the labeling group selected the emotion word that best matched their own feelings during the stimulus presentation. As a result, affect labeling increased skin conductance responses during presentation only in the prototypical condition, suggesting the possibility of different effects according to affective ambiguity. However, both subjective and physiological responses did not decline, contrary to previous research. We discuss the consequences and the experimental characteristics, and propose a direction for future research.

scholarly journals Agents' pivotality and reward fairness modulate sense of agency in cooperative joint action

2019 ◽  
Author(s):  
Solène Le Bars ◽  
Alexandre Devaux ◽  
Tena Nevidal ◽  
Valerian Chambon ◽  
Elisabeth Pacherie
Keyword(s):  
Skin Conductance ◽  
Joint Action ◽  
Electrodermal Activity ◽  
Skin Conductance Level ◽  
Motor Task ◽  
Sense Of Agency ◽  
Skin Conductance Responses ◽  
The Individual ◽  
And Control ◽  
Individual Motor

The sense of agency (SoA) experienced in joint action is an essential subjective dimension of human cooperativeness, but we still know little about the specific factors that contribute to its emergence or alteration. In the present study, dyads of participants were instructed to coordinate their key presses to move a cursor up to a specific target (i.e., to achieve a common goal). We applied random deviations on the cursor’s trajectory to manipulate the motor fluency of the joint action, while the agents’ motor roles were either balanced (i.e., equivalent) or unbalanced (i.e., one agent contributed more than the other), making the agents more or less pivotal to the joint action. Then, the final outcomes were shared equally, fairly (i.e., reflecting individual motor contributions) or arbitrarily in an all-or none fashion, between the co-agents. Self and joint SoA were measured through self-reports about feeling of control (FoC), and electrodermal activity was recorded during the whole motor task. We observed that self and joint FoC were reduced in the case of low motor fluency, pointing out the importance of sensorimotor cues for both I- and we-modes. Moreover, while self FoC was reduced in the low pivotality condition (i.e., low motor role), joint FoC was significantly enhanced when agents’ roles and rewards were symmetrical (i.e. equal). Skin conductance responses to rewards were impacted by the way outcomes were shared between partners (i.e., fairly, equally or arbitrarily) but not by the individual gains, which demonstrates the sensitivity of low-level physiological reactions to external signs of fairness. Skin conductance level was also reduced in the fair context, where rewards were shared according to individual motor contributions, relative to the all-or-none context, which could mirror the feeling of effective responsibility and control over actions’ outcomes.

scholarly journals Acute relaxation during pregnancy leads to a reduction in maternal electrodermal activity, changes in cardiovascular activity and subjective stress levels depending on the week of gestation.

2020 ◽  
Author(s):  
Ilena Bauer ◽  
Julia Hartkopf ◽  
Anna-Karin Wikström ◽  
Nora Schaal ◽  
Hubert Preissl ◽  
...  
Keyword(s):  
Heart Rate ◽  
Skin Conductance ◽  
Maternal Stress ◽  
Physiological Stress ◽  
Electrodermal Activity ◽  
Skin Conductance Level ◽  
Self Report ◽  
Relaxation Techniques ◽  
Management Interventions ◽  
Stress Levels

Background: Prenatal maternal stress can have adverse effects on birth outcomes and fetal development. Relaxation techniques have been examined as one potential countermeasure. This study investigates different relaxation techniques and their effect on mood and physiological stress levels in pregnant women.Methods: 36 pregnant women (30 to 40 weeks of gestation) were randomly assigned to one of three groups: music, guided imagery or resting. Dependent measures included self-report questionnaires, subjective ratings of stress levels as well as physiological measures, i.e. cardiovascular and electrodermal activity.Results: All three forms of relaxation led to reduced maternal stress: decreased heart rate and decreased skin conductance levels. Based on heart rate, skin conductance level and stress ratings there were no significant differences between relaxation interventions. Subjective post-intervention stress ratings indicated that more relaxation occured after intervention in earlier gestation than in late gestation.Conclusion: Independent of relaxation technique, a 20-minute period of acute relaxation can reduce maternal stress. Notably, women earlier in pregnancy reported to be more relaxed after the intervention than women later in gestation. Hence, gestational age can influence perceived stress levels and should be considered when evaluating relaxation or stress management interventions during pregnancy.

Analysis of Fluctuation Patterns in Emotional States Using Electrodermal Activity Signals and Improved Symbolic Aggregate Approximation

2021 ◽  
Author(s):  
Yedukondala Rao Veeranki ◽  
Nagarajan Ganapathy ◽  
Ramakrishnan Swaminathan
Keyword(s):  
Support Vector Machine ◽  
Electrodermal Activity ◽  
Maximum Amplitude ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Clinical Settings ◽  
Emotional States ◽  
Rotation Forest ◽  
Symbolic Aggregate Approximation ◽  
Symbolic Sequences

Analysis of fluctuations in electrodermal activity (EDA) signals is widely preferred for emotion recognition. In this work, an attempt has been made to determine the patterns of fluctuations in EDA signals for various emotional states using improved symbolic aggregate approximation. For this, the EDA is obtained from a publicly available online database. The EDA is decomposed into phasic components and divided into equal segments. Each segment is transformed into a piecewise aggregate approximation (PAA). These approximations are discretized using 11 time-domain features to obtain symbolic sequences. Shannon entropy is extracted from each PAA-based symbolic sequence using varied symbol size [Formula: see text] and window length [Formula: see text]. Three machine-learning algorithms, namely Naive Bayes, support vector machine and rotation forest, are used for the classification. The results show that the proposed approach is able to determine the patterns of fluctuations for various emotional states in EDA signals. PAA features, namely maximum amplitude and chaos, significantly identify the subtle fluctuations in EDA and transforms them in symbolic sequences. The optimal values of [Formula: see text] and [Formula: see text] yield the highest performance. The rotation forest is accurate (F-[Formula: see text] and 60.02% for arousal and valence dimensions) in classifying various emotional states. The proposed approach can capture the patterns of fluctuations for varied-length signals. Particularly, the support vector machine yields the highest performance for a lower length of signals. Thus, it appears that the proposed method might be utilized to analyze various emotional states in both normal and clinical settings.

scholarly journals Predicting Exact Valence and Arousal Values from EEG

Sensors ◽  
2021 ◽  
Vol 21 (10) ◽  
pp. 3414
Author(s):  
Filipe Galvão ◽  
Soraia M. Alarcão ◽  
Manuel J. Fonseca
Keyword(s):  
Machine Learning ◽  
Affective Computing ◽  
Manhattan Distance ◽  
Emotional States ◽  
Emotion Classification ◽  
Learning Models ◽  
Systematic Analysis ◽  
Brain Waves ◽  
Valence And Arousal ◽  
Machine Learning Models

Recognition of emotions from physiological signals, and in particular from electroencephalography (EEG), is a field within affective computing gaining increasing relevance. Although researchers have used these signals to recognize emotions, most of them only identify a limited set of emotional states (e.g., happiness, sadness, anger, etc.) and have not attempted to predict exact values for valence and arousal, which would provide a wider range of emotional states. This paper describes our proposed model for predicting the exact values of valence and arousal in a subject-independent scenario. To create it, we studied the best features, brain waves, and machine learning models that are currently in use for emotion classification. This systematic analysis revealed that the best prediction model uses a KNN regressor (K = 1) with Manhattan distance, features from the alpha, beta and gamma bands, and the differential asymmetry from the alpha band. Results, using the DEAP, AMIGOS and DREAMER datasets, show that our model can predict valence and arousal values with a low error (MAE < 0.06, RMSE < 0.16) and a strong correlation between predicted and expected values (PCC > 0.80), and can identify four emotional classes with an accuracy of 84.4%. The findings of this work show that the features, brain waves and machine learning models, typically used in emotion classification tasks, can be used in more challenging situations, such as the prediction of exact values for valence and arousal.

Sign in / Sign up

Export Citation Format

Share Document