No Detail Found!

Cognitive Computing for Multimodal Sentiment Sensing and Emotion Recognition Fusion Based onMachine Learning Techniques Implemented by Computer Interface System

Author(s)
Arun Kumar Marandi Department of Computer Science, ARKA JAIN University, Jamshedpur, Jharkhand, India.
Gordhan Jethava Department of Computer Science and Engineering, Parul Institute of Technology, Parul University, Vadodara, Gujarat, India.
A Rajesh Department of Computer Science and Engineering, Jain (Deemed-to-be University), Bangalore, India
Mr. Sachin Gupta Department of Management, Sanskriti University, Mathura, Uttar Pradesh, India.
Shrddha Sagar School of Computing Science and Engineering, Galgotias University, Greater Noida, Uttar Pradesh, India.
Mrs. Sonia Sharma Department of Computer Science Engineering, Chandigarh Engineering College, Jhanjeri, India
Abstract
In the last two decades, human emotion recognition and analysis have inspired a lot of interest, garnering a lot of research in neuroscience, psychology, cognitive science, and computer science. Multimodal emotion identification has gotten a lot of interest in field of affective computing, thanks to continued development of portable non-invasive human sensor technologies like BCI (brain-computer interfaces). This paper presents the cognitive computing based multimodal sentimental sensing and emotion recognition using machine learning architectures. Here the data has been collected based on the online review of the social media and twitter datasets. The collected dataset has been pre-processed and segmented to remove noise and unwanted numerical data. Then features have been extracted based on FFT (fast Fourier transform) based convolutional neural network (FFT-CNN) which extracts both numerical data and image data extraction. The extracted features have been classified based on transfer learning based SVM classification (TL-SVM). The experimental analysis has been carried out based on various datasets in terms of accuracy of 98%, precision of 88%, recall of 80%, F-1 score of 78% and mean square error of 45% for proposed FFT-CNN_TL-SVM
Publication Details
Page(s) 15-32
DOI DOI not available
Published Journal: International Journal of Communication Networks and Information Security, Volume: 14, Issue: 2, Year: 2022

Request the full text from PASTIC

Keywords
sentimental sensing, BCI, FFT-CNN, TL-SVM., multimodal emotion recognition
More from International Journal of Communication Networks and Information Security
0

Citations

0

Downloads

42

Views

Copyright ©  PASTIC National Center, Islamabad www.pastic.gov.pk