An Efficient Deep Learning with Optimization Algorithm for Emotion Recognition in Social Networks

Emotion recognition, or computers' ability to interpret people's emotional states, is a rapidly expanding topic with many life-improving applications. However, most image-based emotion recognition algorithms have flaws since people can disguise their emotions by changing facial expressions. As result, brain signals are being used detect human increased precision. proposed systems could do better because electroencephalogram (EEG) challenging classify using typical machine learning and deep methods. Human-computer interaction, recommendation systems, online learning, data mining all benefit from in photos. there challenges removing irrelevant text aspects during extraction. consequence, prediction inaccurate. This paper proposes Radial Basis Function Networks (RBFN) Blue Monkey Optimization address such (BMO). The RBFN-BMO detects faces on large-scale images before analyzing face landmarks predict expressions for acknowledgment. Patch cropping neural networks comprise the two stages of RBFN-BMO. Pre-processing, feature extraction, rating, organizing four categories model. In ranking stage, appropriate features extracted pre-processed information, then classed, accurate output obtained classification phase. study compares results algorithm previous state-of-the-art publicly available datasets derived Furthermore, we demonstrated efficacy our framework comparison works. show that projected method progress rate various sizes.