Children with Autism Spectrum Disorder (ASD) cannot express their emotions explicitly; this makes it difficult for the parents and caretakers associated with these children to understand the child's behavior, leading to a major setback in the child's early developmental stages. Studies have shown that a human being's physiological changes are directly related to his/her psychological reaction. In this paper we propose a wearable wristband for acquiring physiological signals and an algorithm, using a support vector machine (SVM) classifier, that will predict emotional states such as neutral, happy & involvement of children with autism. The psychological reactions (or emotions) are recognized based on the changes in the bodily parameters (physiological basis) such as the galvanic skin response (GSR) and heart rate variability (HRV). For this purpose, vital features extracted from the recorded physiological signals are classified into different emotional states using SVM, which resulted in an overall accuracy of 90 %. This will help the parents and the care takers to understand the emotional patterns of the child better.

No abstract

No abstract

No abstract

No abstract