"Scientists have endowed computers with eyes to see, thanks to digital cameras, and ears to hear, via microphones and sophisticated recognition software. Now they're taking computers further into the realm of the senses with the development of an artificial nose." - Scientists sniff out useful applications for robotic nose. From CNN.

E-noses Could Make Diseases Something to Sniff at - Diagnosing illnesses could be as easy as breathing. By Emily Anthes. Scientific American News (January 11, 2008). "Ancient medical practitioners plied their trade by trusting their noses. They knew that diabetes could make a patient's breath smell sweet and that a wound emitting a foul odor was infected. These early doctors, lacking today's sophisticated technology, often relied on their sense of smell to diagnose illness. Technology is now turning this ancient art into a modern science. Engineers are developing electronic versions of the human nose that will allow doctors, ever in search of less-invasive techniques, to tap into what the nose knows about the human body. ... Enter the electronic nose, an emerging technology that can distinguish these subtle differences. There are a variety of electronic e-nose models, all of which consist of an array of olfactory sensors that are activated in unique patterns when exposed to different aromas; software identifies each odor and its source by analyzing the patterns. (The human brain uses this same pattern-recognition process to identify smells.) ... Combine these feats with the fact that artificial noses are faster, cheaper and less invasive than many other diagnostic tests, and it is easy to understand why physicians find the technology appealing."

Electronic Noses Sniff Success - E-noses will soon be ubiquitous, thanks to printed organic semiconductors. By Josphine B. Chang and Vivek Subramian. IEEE Spectrum Online (March 2008). "Several hundred years ago, village doctors in rural China diagnosed diabetes by the characteristically sweet smell of a patient's breath. Today hospitals use a battery of blood tests and laboratory analyses to make that same diagnosis, but doctors may soon be sniffing their patients' breath again. This time the doctors will have electronic noses small and cheap enough to carry in their pockets. This e-nose will be the culmination of decades of work at countless laboratories, where researchers have sought to create a tiny, cheap, automatic sniffer that would let wine bottles monitor the aging of their contents, allow meat packages to flag spoilage, and enable mailboxes to check for bombs. Imagine barroom coasters that double as Breathalyzers, bumper stickers that monitor car emissions. Until now, it's been just so much sci-fi. ... To identify specific odors requires the signal processor to analyze the array response with pattern-recognition algorithms; in today's expensive electronic noses, a microprocessor uses a large set of stored algorithms to sort through patterns. In the future, however, single-purpose noses looking for a simple change -- food gone bad, for example -- could use application-specific integrated circuits for analysis. ... In training a nose, it is not necessary to fully understand the chemical differences between good wine and bad wine or between two pies; it is enough that the nose knows. So to teach a nose, a developer simply presents, say, 10 samples of wine gone bad and 10 samples of good wine and asks the system to find a pattern that represents the difference and to use that to distinguish good from bad in the future."

Synthetic snot boosts robot nose. BBC News (May 2, 2007). "A layer of artificial mucus has been found to improve the ability of an 'electronic nose' to precisely sniff out aromas in foods and perfumes. ... Smells consist of a number of molecules, each of which has a specific size and shape. The human nose contains more than 100 million receptors which are able to dock with these molecules. A layer of mucus dissolves the arriving scents and separates out different odour molecules so that they arrive at the receptors at different speeds and times. The brain is able to interpret this pattern to distinguish a diverse range of smells. In contrast, an artificial nose consists of a much smaller array of chemical sensors, typically between six and 12, connected to a computer or neural network capable of recognising patterns of molecules. A neural network is a collection of computer processors that function in a similar way to a simple animal brain."

Electronic noses sniff out new markets -- Initially developed as laboratory instruments, electronic noses that mimic the human sense of smell are moving into food, beverage, medical, and environmental applications. By Jennifer Ouellette. The Industrial Physicist (February/March 1999; Volume 5, Number 1). "Researchers and manufacturers alike have long envisioned creating devices that can 'smell' odors in many different applications. Thanks to recent advances in organic chemistry, sensor technology, electronics, and artificial intelligence, the measurement and characterization of aromas by electronic noses (or e-noses) is on the verge of becoming a commercial reality."

E-nose to sniff out hospital superbugs. By Paul Marks. New Scientist (September 24, 2005; Issue 2518: page 30). "E-noses analyse gas samples by passing the gas over an array of electrodes coated with different conducting polymers. Each electrode reacts to particular substances by changing its electrical resistance in a characteristic way. Combining the signals from all the electrodes gives a 'smell-print' of the chemicals in the mixture that neural network software built into the e-nose can learn to recognise. ... David Morgan, a surgeon at the hospital, says the idea of sniffing out superbugs came to him one day in the operating theatre. 'I was operating on neck abscesses on two different patients and noticed their infections had slightly different smells, so I wondered if a machine could work out what the bacterial infections were from the smell alone.'"

Breakthrough on TB. this is Gloucestershire & The Citizen (October 18, 2006). "The lives of more than one million people could be saved, thanks to the pioneering work of a Gloucester-shire scientist.Professor Hugh Barr, who works at Gloucestershire Royal Hospital, has found a way of diagnosing TB by smelling breath. And he estimates the electronic nose will save 60 per cent of the two million people in the world who die from the disease every year. ... The machine, which costs between 5,000 and 10,000 and which is being tested in Latvia and India, uses artificial intelligence to identify the TB smell. A readout gives a probability of whether a patient has the disease."

• Also see: Electronic nose sniffs out TB. The BBC. (August 15, 2001) "The scientists at Cranfield took ideas used by makers of food flavourings, among others, to create sensors that can recognise smells. The sensors use artificial intelligence to identify bacteria in TB cases, as well as other respiratory diseases. The technique analyses sputum - saliva and mucus - converted into gas form."

The 'Nose' Knows A Sweet Smell Of Success. SpaceDaily (August 17, 2004). "What about detecting chemical leaks in enclosed spaces, like the International Space Station or Space Shuttle? NASA built 'E-Nose' to come to the rescue. The Agency's Jet Propulsion Laboratory in California and the California Institute of Technology jointly developed a method for a machine to 'smell.' ... E-Nose technology has the ability to send a signal to an environmental control system where a central computer decides how to handle the problem, without human interaction. The device also can be 'trained' in one session to detect many specific contaminants. ... Commercial companies were quick to see E-Nose's potential. In March 1997, JPL licensed the technology to Cyrano Sciences, of Pasadena, Calif. The company renamed the device 'Cyranose 320' and put it to work in the food industry, testing for spoilage. The technology is also being tested to detect toxic materials, water pollutants and chemical leaks."

• Also see: Electronic NoseNASA researchers are developing an exquisitely sensitive artificial nose for space exploration. Science@NASA Headline News (October 6, 2004).
• For more information visit the Electronic Nose project at NASA/JPL.
• Also from NASA:
  • Let's Get Nosy!, the E-Nose Smell-a-thon project from NASA's Space Place: "E-Nose uses 32 tiny sensors, which together are about the size of the nose on your face. They are connected to a small computer that takes the information from the sensors and figures out just what the smell is, similar to how your brain, through experience, learns to identify what your nose is smelling."
  • Enose is Enose is Enose, a classroom activity from the Teacher's Corner.

'Sniffer-bot' algorithm helps robots seek scents. By Mason Inman. NewScientist.com news (January 24, 2007). "Massimo Vergassola at the Pasteur Institute in Paris, France, and colleagues created an algorithm that tells a robot how to move in order to gather as much olfactory information as possible. This allows it to home in on even the faintest of scents."

Applications of electronic noses and tongues in food analysis. By Anil K. Deisingh, David C. Stone, and Michael Thompson, Department of Chemistry, University of Toronto. International Journal of Food Science & Technology (June 2004; Volume 39, Number 6). "This review examines the applications of electronic noses and tongues in food analysis. A brief history of the development of sensors is included and this is illustrated by descriptions of the different types of sensors utilized in these devices. As pattern recognition techniques are widely used to analyse the data obtained from these multisensor arrays, a discussion of principal components analysis and artificial neural networks is essential."

Wine-tasting robot to spot fraudulent bottles. By Paul Marks, NewScientist.com news (July 28, 2006). "A robotic wine taster, capable of distinguishing between 30 different varieties or blends of grape, has been developed by engineers in Japan.The idea is to automate wine analysis so that retailers and customs officials can easily check that a wine is indeed what its label declares.The wine-bot was developed by scientists from NEC's System Technologies laboratory and Mie University, both in Japan."

• Also see: Development of a Personal Robot with a Sense of Taste. NEC System Technologies, Ltd. press release (June 9, 2005). "Using its sensor, the robot is capable of examining the taste of food and giving the name of the food as well as its ingredients. Furthermore, it can give advice on the food and on health issues based on the information gathered. The robot is called 'Health and Food Advice Robot,' the world's first partner robot with a sense of taste. ... The achievement was made possible by combining NEC System Technologies' robot technology and pattern recognition technology with the analytical techniques of the infrared spectroscopic technology of the BIFE Laboratory."

Mind Over Matter. By Kurt Loft. The Tampa Tribune (July 26, 2004). "Sometime in the not-too-distant future, the worlds of people and robots will merge. Humans already are heading in artificial directions. We have false teeth and hair, plastic limbs, intraocular lenses, mechanical organs and drug- dispensing implants. Robots are becoming more like us in facial expression, voice recognition, and ability to walk, talk and make decisions. ... The future of this technology, Perkowitz says, 'is the formation of direct connections between living organic systems and nonliving ones at the neural and brain levels.'' Highly developed humanoid robots aren't far behind. At the Massachusetts Institute of Technology, researchers have dedicated laboratories to Cog and Kismet, two groundbreaking projects in which the robots mimic human actions and reactions. Another innovative project, Cyrano 320, is an electronic nose that can smell a spectrum of odors."

The Humanoid Race - Machines are getting more and more like the rest of us. A piece-by-piece guide to the globe's most advanced bots. By Robert Capps and Xeni Jardin. Wired Magazine (July 2004; Issue 12.07). "RAT: The Reactive Autonomous Testbed, a creation of Aussie researcher Andy Russell at Monash University, is a 'smellbot' that can successfully follow odorous trails through a maze. Human noses are still about a million times more sensitive to scents than the 4-inch-long Rat, and dog snouts can beat it by a factor of around 100 million. But this sniffing machine can be programmed to follow specific chemicals - and never gets stuffed up."

• Visit Andy Russell's homepage to learn more about "robot chemical sensing" and don't miss the video clip of a robot following a chemical trail.

Sniffing Robot -- Robotic Odor Perception. By Silvio Tresoldi. Circuit Cellar Magazine (Issue 108; July 1999). "Until now, one of the human senses not yet implemented in a robot was the sense of smell. This article presents a possible application of odor sensing in mobile robots. The robot estimates the maximum gas concentration point and moves toward it or can also follow a smelling path on the ground."

Clearing the air - New device sniffs offices. By Peter Healy. The Advocate (February 18, 2003). "Pro Services calls the $25,000 device the IAQ 4000 system. The acronym stands for indoor air quality. The company that makes it, Aircuity Inc. of Newton, Mass., refers to that equipment as the Aircuity Building Performance and Indoor Air Evaluation System, said spokesman Robert Skinner. The system consists of a portable air sampling device, a Web-based data collection and reporting tool and an artificial intelligence-based diagnostic program. It monitors and analyzes temperature, relative humidity, carbon dioxide, carbon monoxide, airborne particles, total volatile organic compounds, mold and pollen, ozone and radon. While the news is replete with stories about building security these days, the Aircuity system would be ineffective against a major act of sabotage or terrorism, Skinner said. 'The portable technology is not designed to detect biological agents,' he said. 'However, Aircuity is developing technology to address biological detection.'"

Robo Lobster to Sniff Out Mines. By Louise Knapp. Wired News (January 2, 2002). "Teams of sniffer robots may someday scour land and sea, using their artificial snouts to root out mines in places and situations humans would rather avoid."

E-Nose Sniffs Out Nasty Bugs. By Louise Knapp. Wired News (October 6, 2001). "Scientists are working on an electronic nose that sniffs out nasty bacteria in blood samples. The e-nose could halve the time for blood work and may one day be used in smart fridges that warn you when food has gone bad."

• Here's one of the many related papers available at the PNNL site: Electronic Noses and Their Applications. By P.E. Keller, L.J. Kangas, L.H. Liden, S. Hashem, R.T. Kouzes. World Congress on Neural Networks (WCNN'96), San Diego, California, USA, 15-18 September 1996; Proceedings of the WCNN'96, pp. 928-931, (1996). [Scroll down this PNNL page to find more papers.]

Scientists sniff out useful applications for robotic nose. Dick Wilson, contributor. CNN (April 17, 1997). "Scientists have endowed computers with eyes to see, thanks to digital cameras, and ears to hear, via microphones and sophisticated recognition software. Now they're taking computers further into the realm of the senses with the development of an artificial nose. ... 'We have tested 40 distinct materials, some of which are complex mixtures, things like cologne,' said David Walt, a professor at Tufts University near Boston. And the man-made nose is right about 97 percent of the time, he said. ... Developers of the nose say its real-world applications might include medical diagnostics and monitoring for household fumes or environmental contamination."

• Visit the Walt Group's Artificial Nose project page.

Related AI Topics Pages

• Hazards & Disasters (see the articles about landmines)
• Medicine
• Neural Networks
• Pattern Recognition