Machine olfaction
Encyclopedia
Machine olfaction is the automated simulation of the sense of smell. It is an emerging requirement of modern robotics where robots or other automated systems are needed to measure the existence of a particular chemical concentration in air. This technology is still in the early stages of development, but it promises many applications, such as:
Machine olfaction incorporates the design of a pattern analysis system. This system requires the consideration of various issues involved in processing multivariate data: signal-preprocessing, feature extraction, feature selection, classification, regression, clustering, and validation.
They generally comprise; an array of sensors of some type; the electronics to interrogate those sensors and produce the digital signals, and finally; the data processing and user interface software.
The entire system being a means of converting complex sensor responses into an output that is a qualitative profile of the odour, volatile or complex mixture of chemical volatiles that make up a smell.
Conventional electronic noses are not analytical instruments in the classical sense and very few claim to be able to quantify an odour. These instruments are first ‘trained’ with the target odour and then used to ‘recognise’ smells so that future samples can be identified as ‘good’ or ‘bad’ smells.
Electronic noses have been demonstrated to discriminate between odours and volatiles from a wide range of sources. The list below shows just some of the typical applications for electronic nose technology – many are backed by research studies and published technical papers.
- quality control in food processing
- detection and diagnosis in medicine
- detection of drugs, explosives and dangerous or illegal substances
Machine olfaction incorporates the design of a pattern analysis system. This system requires the consideration of various issues involved in processing multivariate data: signal-preprocessing, feature extraction, feature selection, classification, regression, clustering, and validation.
Detection
There are three basic detection techniques using:- Conductive-polymer odour sensors (polypyrrole)
- Tin-oxide gas sensors
- Quartz-crystal micro-balance sensor
They generally comprise; an array of sensors of some type; the electronics to interrogate those sensors and produce the digital signals, and finally; the data processing and user interface software.
The entire system being a means of converting complex sensor responses into an output that is a qualitative profile of the odour, volatile or complex mixture of chemical volatiles that make up a smell.
Conventional electronic noses are not analytical instruments in the classical sense and very few claim to be able to quantify an odour. These instruments are first ‘trained’ with the target odour and then used to ‘recognise’ smells so that future samples can be identified as ‘good’ or ‘bad’ smells.
Electronic noses have been demonstrated to discriminate between odours and volatiles from a wide range of sources. The list below shows just some of the typical applications for electronic nose technology – many are backed by research studies and published technical papers.
External links
- Electronic Nose Technologies from Scensive Technologies Ltd, UK
- T. C. Pearce, S. S. Schiffman, H. T. Nagle, J. W. Gardner (editors), Handbook of Machine Olfaction: Electronic Nose Technology, Wiley-VCH, Weinheim, 2002. In PDF at: http://www.le.ac.uk/eg/tcp1/book/content.htm
- Network on artificial Olfactory Sensing (NOSE) Archive
- Artificial noses -- picture the smell, nature.com