Optimizing Back-Propagation Gradient for Classification by an Artificial Neural Network
								
									
										
											
											
												Said El Yamani,
											
										
											
											
												Samir Zeriouh,
											
										
											
											
												Mustapha Boutahri,
											
										
											
											
												Ahmed Roukhe
											
										
									
								 
								
									
										Issue:
										Volume 2, Issue 4, July 2014
									
									
										Pages:
										88-94
									
								 
								
									Received:
										13 July 2014
									
									Accepted:
										28 July 2014
									
									Published:
										10 August 2014
									
								 
								
								
								
									
									
										Abstract: In a complex and changing a remote sensing system, which requires taking quick and informed decisions environment, connectionist methods have shown their great contribution in particular the reduction and classification of spectral data. In this context, this paper proposes to study the parameters that optimize the results of an artificial neural network ANN multilayer perceptron based, for classification of chemical agents on multi-spectral images. The mean squared error cost function remains one of the major parameters of the network convergence at its learning phase and a challenge that will face our approach to improve the gradient descent by the conjugate gradient method that seems fast and efficient.
										Abstract: In a complex and changing a remote sensing system, which requires taking quick and informed decisions environment, connectionist methods have shown their great contribution in particular the reduction and classification of spectral data. In this context, this paper proposes to study the parameters that optimize the results of an artificial neural n...
										Show More
									
								
								
							
							
								
								54 Xe and 36Kr Gas Filled Proportional Counters and Characteristic X-Rays Detection
								
									
										
											
											
												Hemn,
											
										
											
											
												Muhammad Salh,
											
										
											
											
												Ari,
											
										
											
											
												Maghdid Hamad
											
										
									
								 
								
									
										Issue:
										Volume 2, Issue 4, July 2014
									
									
										Pages:
										95-103
									
								 
								
									Received:
										26 July 2014
									
									Accepted:
										18 August 2014
									
									Published:
										30 August 2014
									
								 
								
								
								
									
									
										Abstract: This study examines several important features of characteristic X-rays, including their production, spectroscopy and interactions with materials. Characteristic X-rays for different elements (29Cu, 42Mo, 47Ag, 56Ba and 65Tb) were obtained from a variable energy X-ray source by using gamma rays around 60 keV from 241Am. It was found that the energy and intensity of generated characteristic X-ray photons are proportional to the atomic number of the targets within the variable energy X-ray source. In addition, X-ray spectroscopy for such targets was investigated by using two gas- filled (54 Xe and 36Kr) proportional counters. Furthermore, it was discovered that the probability of photoelectric absorption of (54 Xe) gas-filled proportional counter is almost 1.5 times higher than the probability of photoelectric absorption of (36 Kr) gas-filled proportional counter.
										Abstract: This study examines several important features of characteristic X-rays, including their production, spectroscopy and interactions with materials. Characteristic X-rays for different elements (29Cu, 42Mo, 47Ag, 56Ba and 65Tb) were obtained from a variable energy X-ray source by using gamma rays around 60 keV from 241Am. It was found that the energy...
										Show More