TSN’s Emotionally Immersive Technology (EIT) measures the audience's willingness to participate in the listening and learning process (behavioral engagement) and his/her emotional attitude towards participation (emotional engagement). First, EIT captures the audience via video and tracks each face through the video frames. Then novel computer vision and machine learning approaches are used to identify the attentiveness level.
Through computer vision and machine learning EIT provides emotional analytics in any video or image formats. Our novel Deep Region Learning-based architecture extracts facial micro-expressions accurately.
Our innovative deep region learning-based technology allows us to extract emotions accurately from images. Employing this technology in our daily devices creates emotionally intelligent devices that can understand how our audience feels. From screen mounted cameras we collect video recordings of subjects in a mostly unstructured setting and gather annotations from a panel of humans for assessing student engagement levels. Next we present the predicted results of different representations of engagement, both with subject-independent and individual-specific models, and quantify the performance gap between the generalized and personalized models for engagement prediction. While the subject-independent performance is challenged by data sparsity, results show that the individual-specific models can predict engagement well even with very few labeled examples.
Our EIT serves as the crucial component of our core application used in online learning and content-centric instructional systems. While participation in on-line training and education has been rapidly adopted universally in an attempt to reduce education costs, in the world of education, existing online systems for lectures, are yet to be effective or considered equal in value to traditional classroom teaching. The purpose and commercial potential of this EIT technology is to significantly transform on-line education making it more effective than in the past.