Emotion indexing using hidden Markov expert rule model (HMER) for autism children

Hidden Markov Models (HHMs) have been applied successfully in the field of applied sciences and engineering. The potential applications in manufacturing industries have not yet been fully exploited. In this paper, we propose a Hidden Markov Expert Rule Model (HMER) to index emotion as part of the assistive technology (AT). We propose to index 4 emotions: neutral, happy, sad and surprise. Numerical examples are given to illustrate the effectiveness of the proposed models. HMER is a part of AT that can be used to increase, maintain, or improve functional capabilities of individuals with difficulties in recognizing emotions. It promotes greater independence for this group of people by enabling them to perform task that they were formerly unable to accomplish. Children with autism spectrum disordered (ASD) have difficulty recognizing emotions in themselves and others. This work presents a fast cognitive assistive Hidden Markov-based emotional indexer which can help children with ASD to read and respond to the facial expressions of people they interacting with. The result of emotion indexer is very encouraging; it achieves accuracy of about 70% and the respond time is around 2 frames per seconds.