BI-MODEL EMOTION RECOGNITION SYSTEM FOR DIFFERENT AGE GROUPS STUDENTS ON ZOOM PLATFORM USING FUZZY AND DEEP LEARNING

Abstract

Modality is the word that refers to different modes of recognition. In early researches it has been seen that single modality more over taken into considerations for emotion recognition which always not give better results due to insufficient information. Multi-model functionality helps in overall recognition process for increasing reliability. Fusing multiple feature sets and classifiers into one system will produce a comparably more accurate system. This research works includes combination of speech and facial expressions, as this hybrid mode will help in evaluating results perfectly and as per desire. The proposed methodology used here consists of two main parts; first is Facial Expression Recognizer (FER) and Speech Emotion Recognition (SER) is second part and for the final result hybrid mode will work that consider output of both FER and SER. This is multi-sensory and multi-model emotion recognition system. The research work used MLP classifier for classification of emotions from speech/audio for speech emotion recognition with the use of MFCC for feature extraction that gives accuracy of about 81% and Convolutional Neural Network classifier is used for video/images that gives accuracy of 98.68%. As a hybrid system, outputs found better than that of individual systems. Age groups like kindergarten, primary, adults, senior citizens are compared for finding emotions based on the models. Such applications may be used at schools, colleges, universities, training centers etc.

Keywords

• convolutional
• emotions
• facial expressions
• fuzzy logic
• e-learning
• speech recognition