Smell Electronically!

Smell Electronically!

This article describes the science behind electronic smelling. The e-nose described here is a combination of chemical sensors and an Artificial Neural Network (ANN). This will be a very useful application of technology in future.
Techspirited Staff
Nowadays, we see electronics making life easy. Almost mimicking human intelligence, it can work wonders in every sphere of life. In many fields, technology has outsmarted human capacities and helped achieve remarkable speeds in calculations, processing information and even decision-making. This article will give you an overview of the advancements in electronics and some information about this amazing application of smelling electronically.

It's because of our nose that we can identify and distinguish between smells of food, perfumes, etc. But there are certain limitations to the human sense of smell. Common cold, for example, hampers one's sense of smell. Also, during winters or rains, one may not be able to smell correctly. Dogs and other animals, however, have better accuracy in identifying odors. How does electronic smelling work? Well, it goes beyond human and animal capacities of smelling and overcomes limitations in olfaction. It automatically detects and recognizes odors.

The E-Nose has a chemical sensing system and a pattern recognition system. It consists of an array of chemical sensors. Each element in this array measures different properties of the sensed chemical compound. It also produces an array of measurements for each chemical. There may be a combination of both of them. Each chemical vapor has a signature or pattern characteristic. We present many different chemicals to the sensor array and create a database of signatures. Now, this database will be used to train the pattern recognition system. The aim of the training is to configure the recognition system which will give a unique classification to odors.

We need sensors at least equal to number of chemicals being monitored. We use an array of sensors and each sensor responds to a specific chemical.

Artificial Neural Networks (ANN) are mostly used for pattern recognition and for analyzing complex data. When an ANN is combined with a sensor array, the number of detectable chemicals is greater than the number of sensors. Less selective sensors can be used with this approach. Once the ANN is trained for chemical vapor recognition, the sensor data is propagated through the network. As this is simply a series of vector-matrix multiplications, unknown chemicals can be identified rapidly.


Environment Monitoring: Huge amount of hazardous waste is generated by nuclear operations. There is a need for new and developing technologies for environmental restoration and managing the waste in a cost-effective manner. This means development of portable, inexpensive systems that are capable of real-time identification of contaminants is necessary. An electronic nose serves this purpose. Other environmental applications include toxin identification, fuel mixture analysis, oil leakage detection, household odor detection, factory emission monitoring, etc.

Medicine: The sense of the smell is important to physicians. An electronic nose can be used as a diagnostic tool. An electronic nose can examine body odor and identify possible problems.

Food Industry: Currently, this is the biggest market for this kind of a device. It can be used to augment or replace human experts. Potential applications of the electronic nose in the food industry are, inspection of food quality by odor, fish inspection, fermentation control, etc.