A new method is described for determining the distribution of resistivity of semiconductor wafer and thin conducting films without contacting the surface of inside part. It has been termed as applied ...current tomography (ACT) which uses direct current injected through electrodes equally spaced around the periphery of the wafer or region to be measured , and then the resultant potential differences will be measured, from which the distribution of resistivity is calculated. The technique offers resolution and accuracy comparable to four-point probe methods and the wafer is not contaminated.
Feature reduction is an important stage in pattern recognition. This paper deals with the feature reduction methods for a time-shift invariant feature, power spectrum, in radar automatic target ...recognition using high-resolution range profiles (HRRPs). Several existing feature reduction methods in pattern recognition are analyzed, and a weighted feature reduction method based on Fisher's discriminant ratio (FDR) is proposed. According to the characteristics of radar HRRP target recognition, the proposed weighted feature reduction method uses an iterative algorithm to search for the optimal weight vector for power spectra of HRRPs, and thus reduces feature dimensionality. Compared with the method of using the raw power spectra and some existing feature reduction methods, the weighted feature reduction method can not only reduce feature dimensionality, but also improve recognition performance with low computation complexity. In the recognition experiments based on measured data, the proposed method is robust to different test data and achieves good recognition results.
A new multicalss recognition strategy is proposed in this paper, where the self-organizing mapping (SOM) scheme with a hypercube mapped space is used to represent each category in a binary string ...format and a binary classifier is assigned to each bit in the string. Our strategy outperforms the existing approaches in the prior knowledge requirement, the number of binary classifiers, computation complexity, storage requirement, decision boundary complexity and recognition rate.