As based on the adsorption of the gas

As environmental
regulation become more stringent, the need to develop highly sensitive gas
sensor grows. To meet the demand of low level gas detection, gas sensors should
be upgraded in sensitivity ,selectivity, and speed of response 1.At the same
time they should be cost effective and reliable over long term2.Metal oxide
semiconductor sensors based on electric conductivity measurement have been used
extensively for gas detection .SnO2 is most widely used material
among semi-conductor oxide for making sensors due to its low cost, long life
and good reproducibility 3,4 ,thick film SnO2 device are most
studies and most candidate due to their high level of sensitivity ,simple
design, low weight and cost effectiveness. SnO2 is an n –type ,wide
–band gap (3.6 Ev) semiconductor 5.Its electrical conductivity id due to the
non-stoichiometric compositions as a result of oxygen deficiency 6.The
sensing properties of the thick film gas sensor are based on the adsorption of
the gas molecules on it surface which produce changes in their conductivity
7. When exposed to air, freshly prepared tin-oxide particles adsorbed on the
particle adsorb oxygen atoms on the surface 8. These oxygen atoms pick up the
e-s  from the conduction band
of tin oxide and are adsorbed on the particle surface as O- ions.
Each tin oxide particle is covered with negativity charged O-  ions on the surface. On the other hand
,due to depletion e-s ,there exits a layer of positively charged
donor atoms just below the particle surface. The  O- 
adsorbents react with the gases and release the  e-s   to the conduction band at higher temperature,
when reducing gases came in contact with sensor. Consequently, the depth of the space –charge layer decreases,
which result’s in a decrease in the height of the potential barrier
for  the electronic conduction at  the grain boundaries.

The concept of ANN
analysis have been discovered nearly 50 years ago, but in handing the practical
problem it is used only from last 2 –decades9.ANN are collections of small
individually interconnected processing 
units. Information is passed between these units along interconnections.
An incoming connection has two value associated with it, an input value and a
weight. The output of the unit is a function of the summed value. Once an ANN
is trained for a prescribed data it may be ready to be used then for the
prediction or classification ANNs can automatically learn to recognize pattern
in the data real system or from physical models, or other sources. An ANN can
handle many input and produce answer that are in a from suitable for designers 10.

Artificial Neural Network
(ANN) model may be used as alternative method for technological analysis and
matlab based calculation. Artificial Neural Networks have two main components-
the processing element called neurons and the connection between them, each
connection have their own weights.The neurons are the information processors
and the connection functions are the information storage. Each processing
element first calculates a weighted sum of the input signals and then applies
the transfer functions .The term ‘Feed Propagation’ comes due to the training
method used during the training process-back propagation of error. A Gradient
Descent Backpropagation with adaptive learning rate algorithm is used to adjust
the weights in the hidden and output layer nodes. The result is a network that
produces the mapping between the input values and output values with help of
the neurons. In this model perception, Feed-Forward Propagation is one of
suitable method of artificial neural network, designed for the testing and
training of data. Three training methodologies based upon forward propagation
was used. Purelin, logsin and tansin network transfer function for all the
neurons, which reflects the relationship between concentration as input and
sensitivity for different concentration as output of SnO2 based 1%
Pd-doped thick film gas sensor. Sensitivity is tested by artificial neural
network. In neural network architecture one layer acts as input layer, ten
neurons acts as the hidden layer and other layer output layer. In this model
input is concentration of methanol and output is the sensitivity of sensor.
Though in present work single sensor is exposed to single gas or vapor at a
time and ANN is utilized to confirm it with experiments so that the data
collected can be used to train the network when sensor is replaced by sensor
array and single gas is replaced by group of gases or vapors to achieve high
selectivity. This model was trained to generate a mapping between the input
concentration of the methanol and output as the sensitivity of the
methanol.Sensitivity is dimension less quantity which is obvious from its
expression In the present work for reorganization of the sensitivity of the 1 %
Pd-doped SnO2 sensor feed forward network has been used. A Feed
Forward network can be used for the reorganization the pattern of the system.
Feed Forward network uses the Gaussian activation function. The importance of
such function is that it is non negative for all value of x.