Cloud-Based Facial Emotion Recognition for RealTime Emotions


Authors : Sneha P Peddarpeth, Geetha G P

Volume/Issue : Volume 2 - 2017, Issue 5 - May

Google Scholar : https://goo.gl/vTYx7g

Scribd : https://goo.gl/jybjHJ

Thomson Reuters ResearcherID : https://goo.gl/3bkzwv

Business Intelligence is an important aspect of any organized education. With the growing competition and global outlook of the training, metric driven insight has become extremely important for the corporations to analyze, understand and plan their training modules in better ways. Understanding participant’s behavior and their sentiments has been an active area of research over a long time. However, due to practical challenges associated with such adaptations, there hasn’t been significant work towards participant behavior and sentiment tracking in physical classrooms. In this work, we have addressed this significant challenge of the education sector and proposed EMOMETRIC, which is an intelligent system for class that can track participant’s emotion and provide a participant behavioral insight through IOT integrated data intelligence running on Apache Spark Cluster. The proposed system uses model based face and emotion tracking under real use case conditions Results shows that the proposed technique has an overall accuracy of 95% in comparison to the current state of art. The proposed technique also adapts QOS enabled secure MQTT protocol to collect the data by the big data No-SQL storage system. It is also observed that the proposed technique is not only fast and accurate but also illumination and pose invariant. This work can be used as a framework to offer emotion as a service through SAAS platform.

Keywords : Business Intelligence, Participant Behaviour, Emotion, Apache Spark, MQTT Protocol, No-SQL, Big Data.

CALL FOR PAPERS


Paper Submission Last Date
31 - December - 2021

Paper Review Notification
In 1-2 Days

Paper Publishing
In 2-3 Days

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.
Subscribe
OR

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.
Subscribe