A Framework for an Artificial-Neural-Network-Based Electronic Nose

A Framework for an Artificial-Neural-Network-Based Electronic Nose

Mudassir Ismail (University of Bahrain, Bahrain), Ahmed Abdul Majeed (University of Bahrain, Bahrain) and Yousif Albastaki (University of Bahrain, Bahrain)
Copyright: © 2018 |Pages: 24
DOI: 10.4018/978-1-5225-3862-2.ch001

Abstract

Machine odor detection has developed into an important aspect of our lives with various applications of it. From detecting food spoilage to diagnosis of diseases, it has been developed and tested in various fields and industries for specific purposes. This project, artificial-neural-network-based electronic nose (ANNeNose), is a machine-learning-based e-nose system that has been developed for detection of various types of odors for a general purpose. The system can be trained on any odor using various e-nose sensor types. It uses artificial neural network as its machine learning algorithm along with an OMX-GR semiconductor gas sensor for collecting odor data. The system was trained and tested with five different types of odors collected through a standard data collection method and then purified, which in turn had a result varying from 93% to 100% accuracy.
Chapter Preview
Top

Objectives Of The Research Work

As humans, our sense of smell is very important, and we rely on it for various tasks and functions some of which are daily activities and others which can be more important. Despite the importance of this sense, our sense of smell is usually limited both in its capabilities and can be influenced by external factors such as flu, our surroundings and other factors. Our human sense of smell can also only detect a limited number of gases due to which must be facilitated by adding compounds to different gases for humans to be able to detect it (Lee, et al., 2012).

These limitations of human olfactory system make it difficult to rely on humans for the job of odor detection in Industries. Moreover, the odor detection of dangerous gases, even though possible by humans, may be fatal. An alternate approach is to train and utilize dog for odor sensing. This too has limitations as it is expensive to train dogs, and their life span is short and limited. These limitations have led to the development of electronic noses which try to mimic the human olfactory system. Electronic noses have proved their significance in various fields of health and industries and have been used as sensors for detection of food spoilage and in diagnosis of various diseases and much more (Gurney, 1997). Despite advances in the hardware of electronic noses, there hasn't been much attention paid to the software side of electronic noses.

This research aims to develop a general purpose Artificial Neural Network that can be used in various kinds of application from differentiating between markers, detecting food spoilage and diagnosing diseases.

As discussed in the previous section, the research and development on the software side of Odor sensing systems has been relatively less compared to its hardware. Moreover, these developments have been for very specific purposes and uses.

This chapter aims on developing an Odor sensing system using Electronic nose as a hardware and Artificial Neural Network as software for general odor sensing and identifying different odors as shown in Figure 1.

Complete Chapter List

Search this Book:
Reset