Intelligent electronic nose (ENOSE) system technology is gaining importance in several industrial applications. These include process control and quality control in industries such as foodstuffs, beverages, tobacco, p...
详细信息
Intelligent electronic nose (ENOSE) system technology is gaining importance in several industrial applications. These include process control and quality control in industries such as foodstuffs, beverages, tobacco, perfumery and pharmaceutical. ENOSE is also crucial component in industrial safety (smoke and hazardous gas detection) as well as environmental pollution control. This paper deals with design of an intelligent ENOSE system for the identification of gas/odours using a sensor array and a neural network pattern classifier. Previous researchers have shown that the power of discrimination increases rapidly with the number of sensors in the array whose information potential is very large and the pattern recognition (PARC) method is a clever way to extract this information. The authors show in this paper with the powerful PARC technique, the need of larger array can be compensated. With this view, they design a neural classifier using two different learning approaches and train the network over the responses of surface acoustic wave (SAW) sensors exposed to hazardous vapours like diethyl sulphide (DES) and iso-octane (ISO). Dimensionality of the data set is varied from 1 to 8 by taking different number of sensors. It is found that for a backpropagation trained neural classifier, the optimum number of sensors required for satisfactory classification under noisy conditions is 4 to 5. This is a very limited range beyond which backpropagation has great difficulty in training the neural classifier even with repeated restarts and different weight initializations. To alleviate this problem, hybridization of soft computing tools like neural networks and genetic algorithms promises to provide the design of better intelligent system. The authors propose the use of a genetic algorithm based on a special MRX operator introduced by them and demonstrate very encouraging results with genetically trained neural network model even with larger as well as smaller numbers of senso
This paper reports the effect of some advanced genetic operators like two-parents multipoint restricted crossover (Double-MRX), three-parents multipoint restricted crossover (Triple-MRX), elitist selection and schedul...
详细信息
This paper reports the effect of some advanced genetic operators like two-parents multipoint restricted crossover (Double-MRX), three-parents multipoint restricted crossover (Triple-MRX), elitist selection and scheduled mutation on the adaptability of feedforward neural networks trained over complex and computationally expensive electronic nose data. The authors show that the performance of Triple-MRX is better that of Double-MRX. Upon applying elitist selection with Double-MRX and scheduled mutation with Triple-MRX, the performance of the genetic training of the neural network improves up to some extent, but Triple-MRX is still better than Double-MRX as far as quality of solution and speed of convergence are concerned. It is also shown that the performance levels of these hybrid techniques far exceeds those of the commonly used backpropagation model. The search for a good neuro-genetic hybrid computational paradigm based on advanced genetic operators is a frontier research area in the evolution of a sixth generation computing system.
暂无评论