Research on Negative Learning Emotion Recognition in English Classroom using Cross Space based Convolutional Neural Network

In English classroom the teaching behavior, changes according to the student’s facial emotions which are observed by facial expressions and behavioral phases in the class. Nonetheless, in the English classroom, behavior of the students during learning is changeable and complex to understand by teacher’s and it also difficult for understanding the negative emotions such as bored, stressed and not interested in the English classroom. To overcome these limitations, a Cross-Space based Convolutional Neural Network (CS-CNN) model is proposed to recognize the which is observed from students. The proposed method learns multiscale information such as subtle differences between various emotions and complex negative emotion pattern efficiently by cross-space feature fusion. This helps to enhance the recognition performance to assist the teachers to change their teaching strategies to make the students more focused and improve learning environment of students. For extracting significant features from the facial images are preprocessed by histogram equalization and extracted using DeepNet architecture. The experimental results of the proposed CS-CNN method achieved accuracy of 94.33% which is higher when compared to existing recognition approaches such as Support Vector Machine (SVM) and Yolo-V3.