@article{Riki Mukhaiyar_2017, title={THE COMPARATION OF BACK PROPAGATION METHOD AND KOHONEN METHOD FOR GAS IDENTIFICATION}, volume={13}, url={https://geomatejournal.com/geomate/article/view/1451}, abstractNote={<p>The identification process of gas flavor is conducted by using the output of gas sensor system<br>to recognize a variety of gas flavor. The identification and analysis process of this system is processed by<br>using an artificial neural network approaches those are back propagation and Kohonen method. According of<br>the experiment’s result, the best parameter for back propagation network is the momentum constant (α) = 0.7,<br>the constant of the sigmoid function (β) = 4.5, constant learning (η) = 0.9, and the constant of convergence (ε)<br>= 0001, convergence is achieved more or less in the 19 500 iterations (± 16 seconds). Meanwhile, the best<br>classification for Kohonen network is for the output of 8 knots with an average of 80.7% uniformity (for a<br>maximum of 500 times iteration, approximately ± 3 seconds). Thus, the best network to classify the signal<br>pattern of gas flavor is back propagation network for the parameters (α) = 0.7, a constant sigmoid function<br>(β) = 4.5, a constant learning (η) = 0.9, and a constant convergence (ε) = 0001.<br>Keywords: Kohonen, Back Propagation, Artificial Neural Network, Supervised Algorithm, Unsupervised<br>Algorithm</p>}, number={38}, journal={GEOMATE Journal}, author={Riki Mukhaiyar}, year={2017}, month={Apr.}, pages={97–103} }