AN INTELLIGENT NEURAL NETWORK BASED GAS DETECTION SYSTEM USING METAL OXIDE GAS SENSOR
Silpi Sarkar1a, Aritra Dasgupta2b, Sunipa Roy 3c
1Department of Electronics and Communication Engineering, Netaji Subhash Engineering College, Kolkata, India
2Department of Electronics and Instrumentation Engineering, Netaji Subhash Engineering College, Kolkata, India
3Department of Electronics and Communication Engineering, Gurunanak Institute of Technology, Kolkata, India
This is an open access article distributed under the Creative Commons Attribution License CC BY 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited
Probabilistic Neural Network (PNN) has been used to ensure the reliable evaluation of responses from Zinc Oxide (ZnO) based sensors comprising of as deposited ZnO nanoflakes. Nanoflakes were deposited on a SiO2 coated p-Si substrate by a low cost chemical deposition technique. One type of sensor structure, to investigate the effect of catalytic metal alloy electrode (Pd-Ag) was fabricated in a standard laboratory. This paper reports the development of an artificial neural network based model and a special types of neural network i.e. PNN is used for successfully recognizing different concentrations of methane with two different metal contacts. The data obtained from the sensors have been analyzed using MATLAB. PNN is based on Radial Basis function. PNN classifier has been able to detect the toxic gas with 95.2 % sensitivity.
Zinc Oxide; gas sensor; probabilistic neural network; radial basis function; MATLAB