Comparison of Several Machine Learning Classifiers for Arousal Classification: A Preliminary study

Erkuş, Ekin Can; Purutçuoğlu, Vi̇lda; Arı, Fikret; Gökçay, Didem

doi:10.1109/tiptekno50054.2020.9299316

Cited by 2 publications

(1 citation statement)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The manipulation of certain elements in the current VRET was successful in reducing anxiety. Going forward, machine learning could be used to identify the best candidate indicators of arousal, such as galvanic skin response (GSR), pupil diameter, heart rate (HR), and electromyography ( 77 ). Offering participants biofeedback about such arousal from heartrate and electroencephalography could enhance response to exposure therapy for SAD ( 78 ).…”

Section: Discussionmentioning

confidence: 99%

The Effectiveness of Self-Guided Virtual-Reality Exposure Therapy for Public-Speaking Anxiety

et al. 2021

View full text Add to dashboard Cite

Objectives: Self-guided virtual-reality exposure therapy (VRET) is a psychological intervention that enables a person to increase their own exposure to perceived threat. Public-speaking anxiety (PSA) is an anxiety-provoking social situation that is characterized by fear of negative evaluation from an audience. This pilot study aimed to determine whether self-guided VRET (1) increases exposure to PSA-specific virtual social threats, and (2) reduces anxiety, arousal, heartrate and PSA over repeated exposure.Methods: Thirty-two University students (27 completers) with high self-reported public-speaking anxiety attended 2 weekly self-guided VRET sessions. Each session involved the participant delivering a 20-min speech in a virtual classroom. Participants were able to increase their exposure to virtual social threat through the audience size, audience reaction, number of speech prompts, and their own salience in the virtual classroom at 4-min intervals. Participants' heartrates and self-reported anxiety and arousal were monitored during these intervals. Participants completed psychometric assessments after each session and 1 month later.Results: Participants increased their exposure to virtual social threat during each VRET session, which coincided with a reduction in heartrate and self-reported anxiety and arousal. Improvement in PSA occurred post-treatment and 1 month later. The in-session improvement in anxiety correlated with reductions in fear of negative evaluation post-treatment and 1 month later.Conclusions: Increased self-exposure to virtual social threat from self-guided VRET relieves anxiety and shows immediate reductions in subjective and physiological arousal during application, but also yields sustained improvement in PSA.

show abstract

Section: Discussionmentioning

confidence: 99%

The Effectiveness of Self-Guided Virtual-Reality Exposure Therapy for Public-Speaking Anxiety

et al. 2021

View full text Add to dashboard Cite

show abstract

Enhanced Classification of Video-Evoked Stress Response Using Power Spectral Density Features

Anjum,

Batool,

Saher

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

The analysis of stress in response to videos using electroencephalography (EEG) has emerged as a significant field of research. In this study, we propose a methodology for classifying stress responses to videos using the Database for Emotion Analysis using Physiological Signals (DEAP). EEG signals are preprocessed with resampling and a median filter. We extracted Power Spectral Density (PSD) features from the alpha, beta, delta, and theta bands of the preprocessed EEG. Instances were labeled based on the valence and arousal values provided in the DEAP dataset in response to the presented videos. Four machine learning algorithms, namely Naïve Bayes (NB), Multilayer Perceptron (MLP), Logistic Regression (LR), and Sequential Minimal Optimization (SMO) classifiers, were employed to differentiate between stressed and relaxed states using a 10-fold cross-validation technique. The SMO classifier achieved the highest accuracy of 95.65%. Additionally, statistically significant variations in the alpha band using t-tests suggest that the DEAP dataset video clips can effectively induce stress and relaxation conditions in participants.

show abstract

Comparison of Several Machine Learning Classifiers for Arousal Classification: A Preliminary study

Cited by 2 publications

References 39 publications

The Effectiveness of Self-Guided Virtual-Reality Exposure Therapy for Public-Speaking Anxiety

The Effectiveness of Self-Guided Virtual-Reality Exposure Therapy for Public-Speaking Anxiety

Enhanced Classification of Video-Evoked Stress Response Using Power Spectral Density Features

Contact Info

Product

Resources

About