We develop a two-stage, modular neural network classifier and apply it to an automatic target recognition problem. The data are features extracted from infrared and TV images. We discuss the problem of robust classification in terms of a family of decision surfaces, the members of which are functions of a set of global variables. The global variables characterize how the feature space changes from one image to the next. We obtain rapid training times and robust classification with this modular neural network approach.
Comparison of interface positive charge generated in metaloxidesilicon devices by highfield electron injection and xray irradiation Appl. Phys. Lett. 51, 1643Lett. 51, (1987; 10.1063/1.98582Interface trap behavior in irradiated metaloxidesilicon structures
A linear 500×1 charge-coupled device (CCD) surface channel imager is thinned to less than 30 μm, with the thinned back surface accumulated to reduce the surface recombination velocity. Photoresponsivity is measured to be 90 mA/W of incident wide-band power from a 2854-K blackbody light source. This sensitivity is a factor of 3 higher than previously reported values. Spectral responsivity reaches a peak of 90% quantum efficiency at 7000-Å wavelength, and over 50% quantum efficiency for the spectral range from 5000 to 9000 Å. A 32% square wave amplitude response at the Nyquist limit is obtained at a location 150 resolution elements from the output diode. Optical imager resolution obtained by using the backside-illuminated device is illustrated.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.