Developing an emotional-based application for human-agent societies

Abstract

The purpose of this paper is to present an emotional-based application for human-agent societies. This kind of applications are those where virtual agents and humans coexist and interact transparently into a fully integrated environment. Specifically, the paper presents an application where humans are immersed into a system that extracts and analyzes the emotional states of a human group trying to maximize the welfare of those humans by playing the most appropriate music in every moment. This system can be used not only online, calculating the emotional reaction of people in a bar to a new song, but also in simulation, to predict the people's reaction to changes in music or in the bar layout.

A Systematic Review on Facial Expression Based Emotion Recognition System for Smart Homes

“…Mano et al in two separate works [7,25], used public datasets for training of their systems and then tested the built model using their own collected dataset. Meanwhile [26,27] and [28] fully utilized public datasets for both training and testing. All seven works used discrete multiclass data.…”

“…The applications for smart homes can be broadly categorized to entertainment advisory system and assisted living. In entertainment advisory system the ERS is used for music and movies recommendation to suit the current state of emotion [24,25,27]. A magic mirror that display positive messages and choose suitable background music for mood alleviation is proposed in [23].…”