ANN Based Approach to Integrate Smell Sense in Multimedia Systems

ANN Based Approach to Integrate Smell Sense in Multimedia Systems

Yousif Al-Bastaki (University of Bahrain, Bahrain) and Khalid A. Al-Mutawah (University of Bahrain, Bahrain)
Copyright: © 2011 |Pages: 10
DOI: 10.4018/jtd.2011070102
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

Despite the wide usage of multimedia in several applications, research in the field of olfaction is immature in helping humans work and communicate through multi-sensory interfaces, including smell. There is no consistent method of testing user capability of smell. Therefore, smell detection and generation systems are not well integrated into today’s multimedia systems. In this paper, the authors propose an odor sensing system with the capability of the discrimination among closely similar 20 different odor patterns and propose an on-line classification method using a handheld odor meter (OMX-GR sensor) and neural network that can be used in different multimedia applications. The proposed system is integrated to enhance the functionality of an online multimedia shopping system that is capable of selling products with visual and auditory senses.
Article Preview

1. Introduction

The Multimedia systems are widely defined as Multi Sensory systems that convey information about the current state of the real world environment by congregating signals from several receptors in the ears, eyes, and other sense organs. The signals from one side of the body are sent through nerve fibers to the cerebral cortex on the opposite side of the brain, where they are perceived and interpreted in terms of our previous experiences, knowledge, and expectations. The five well known physiological systems that lie at the core of the human perceptual experience are Olfactory (smell), tactile (touch), visual (sight), auditory (sound), and perception of flavor (taste). Nonetheless, extensive research has been carried out to develop multimedia systems that can capture, store and reproduce sound and video with high quality (Paeda et al., 2008; Pfeiffer, Lienhart, & Efflsberg, 2001). However, there are the other three senses, smell, touch and taste that received less attention within the multimedia research area. These senses, in addition to sight and sound, can recreate an environment similar to the real world environment in particular the smell sense. This is because amongst the three other senses the smell is the only sense that can be perceived from a long distance.

Nonetheless, few odor-sensing tools have been proposed in limited applications. This is because of the complexity on designing olfactory system that can perceive different smells for humans with a variety of preferences. Table 1 presents some of these limited applications from the literature.

Table 1.
Limited applications from previous research
ApplicationSystem SpecificationYearAuthors
agriculturalSingle coated thermistor as the odor sensor1961(Moncrieff, 1961)
smell detectoran array of eight electrochemical sensors1964(Wilkens & Hartman, 1964)
Electronic nosepattern recognition techniques1994(Gardner & Bartlett, 1994).
polymer gas sensorsan integrated circuit based device that performs data acquisition from a miniature array of 321994(Hatfield, Neaves, Hicks, Persaud, & Travers, 1994)
An Intelligent E-noseof measuring signals from arrays of resistive and piezoelectric sensor types in the same board1997(Dyer & Gardner, 1997)
Robot head that reacts to some smellsA recognition algorithm that uses a look-up table that contains sensor outputs and their derivatives2001(Miwa, Umetsu, Takanishi, & Takanohu, 2001)
chemical industry to detect toxic gases and gases without smellThe sensor electronics is based on a scanning version of a vibrating capacitor (Kelvin probe)2002(Li & Hopfield, 1989; Mizsei & Ress, 2002)

Complete Article List

Search this Journal:
Reset
Open Access Articles
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2015)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing