Towards the development of an electronic nose.
MetadataShow full item record
Electronic noses are targeted at determining odour character in a fashion that emulates conscious odour perception in mammals. The intention of this study was to develop an organisational framework for electronic noses and deploy a sample cheese odour discriminator within this framework. Biological olfactory systems are reviewed with the purpose of extracting the organisational principles that result in successful olfaction. Principles of gas handling, chemoreception, and neural processing are considered in the formulation of an organisational framework. An electronic nose is then developed in accordance with the biologically inspired framework. Gas sensing is implemented by an array of six commercially available (tin oxide) semiconductor sensors. These popular gas sensors are known to lack stability thus necessitating hardware and signal processing measures to limit or compensate for instability. An odorant auto-sampler was developed to deliver measured amounts of odorant to the sensors in a synthetic air medium. Each measurement event encodes a simulated sniff, and is captured across six sensor channels over a period of 256 seconds at a sampling rate of 1Hz. The simulated sniff captures sensor base references and responses to odorant introduction and removal. A technique is presented for representation and processing of sensor-array data as a two-dimensional (2D) image where one dimension encodes time, and the other encodes multi-channel sensory outputs. The near optimal, computationally efficient 2D Discrete Cosine Transform (DCT) is used to represent the 2D signal in a decorrelated frequency domain. Several coefficient selection strategies are proposed and tested. A heuristic technique is developed for the selection of transform domain coefficients as inputs to a non-linear neural network based classifier. The benefits of using the selection heuristic as compared to standard variance-based selection are evident in the results. Benefits include: significant dimensionality reduction with concomitant reduction in classifier size and training time, improved generalisation by the neural network and improved classification performance. The electronic nose produced a 99.1% classification rate across a set of seven different cheeses.