Adaptive affective response identification for hearing threshold detection.

Area of Science:

• Neuroscience
• Bioengineering
• Psychology

Background:

• Emotional arousal can be measured using bioelectric signals like electroencephalography (EEG).
• Hearing impairment can lead to speech intelligibility issues, triggering automatic emotional responses.
• Understanding these emotional responses is crucial for audiology and mental health.

Purpose of the Study:

• To investigate the use of EEG signals to detect emotional arousal in individuals with hearing impairment.
• To develop and evaluate an adaptive support vector machine (SVM) model for identifying affective patterns.
• To assess the efficacy of the SVM model using audiogram hearing test data.

Main Methods:

• Utilizing electroencephalographic potentials from the human scalp to monitor affective patterns.
• Training an adaptive support vector machine (SVM) classifier.
• Using audiogram hearing test results to inform the SVM model training.
• Analyzing initial SVM classification data to demonstrate model efficacy.

Main Results:

• The adaptive SVM model demonstrated efficacy in identifying unique affective responses.
• Initial classification data showed promising results in distinguishing emotional patterns.
• The model's ability to link audiogram data to affective responses was validated.

Conclusions:

• EEG-based affective pattern detection is a viable method for assessing emotional responses.
• The developed adaptive SVM model shows potential for personalized audiology applications.
• Further research can explore broader applications in mental health and human-computer interaction.