Abstract: The present invention relates to novel fragments of apolipoprotein E (ApoE). These ApoE fragments have a variety of uses including as components of vaccine compositions, particularly vaccines for the prevention or treatment of neurological disorders such as Alzheimer's disease. The ApoE fragments may also be used in screening methods and methods of detection.

Abstract: A non-human animal in which a gene coding for the N-type calcium channel is disrupted to lack functional N-type calcium channel, and a method for screening for a substance having a pharmacological action on blood pressure control, transmission of pain, blood sugar level control and so forth by using the animal.

Abstract: A pattern searching method using neural networks and correlation. This method combines the quickness and adaptiveness of neural networks with the accuracy of the mathematical correlation approach. Images are divided into small sub-images which are presented to the trained neural network. Sub-images that may contain the pattern or partial pattern are selected by the neural network. The neural network also provides the approximate location of the pattern, therefore the selected sub-images can be adjusted to contain the complete pattern. Desired patterns can be located by measuring the new sub-images' correlation values against the reference models in a small area. Experiments show that this superior method is able to find the desired patterns. Moreover, this method is much faster than traditional pattern searching methods which use only correlation.

Abstract: A neural network designed to recognize a particular character is supplied with initial tap weights for a first hidden node which are an image of the character to be recognized. The additive inverse of this set of weights is used as the tap weights for a second hidden node. A third node, if used, is initialized with random noise. The network is then trained with back propagation.

Abstract: A neural network is used to recognize characters from a character set. Based upon the character recognized, a smaller neural network is used for verification of the character recognized. The smaller neural network is trained to recognize only a single character of the set and provides a "yes" or "no" type verification of correct identification of the character.

Abstract: A pattern searching method using neural networks and correlation. This method combines the quickness and adaptiveness of neural networks with the accuracy of the mathematical correlation approach. Images are divided into small sub-images which are presented to the trained neural network. Sub-images that may contain the pattern or partial pattern are selected by the neural network. The neural network also provides the approximate location of the pattern, therefore the selected sub-images can be adjusted to contain the complete pattern. Desired patterns can be located by measuring the new sub-images' correlation values against the reference models in a small area. Experiments show that this superior method is able to find the desired patterns. Moreover, this method is much faster than traditional pattern searching methods which use only correlation.

Abstract: In a machine vision system, a pixel-discrimination threshold level, for determining whether pixels are to be assigned one or the other of two values, is established according to parameters obtained in an initialization procedure. During initialization, a test set of items is assembled and data is entered representing indicia appearing on each item of the test set. It is then determined, for each of a range of possible threshold levels, whether the machine vision system correctly recognizes the indicia on the respective test items. Based on the thresholds which permitted correct recognition, threshold parameters are calculated for each test item and average parameters are calculated from the test item parameters. The average parameters are used to set pixel-discrimination thresholds for subsequent recognition operations.

Abstract: A process for converting characters arranged circularly, as for example about the center hole of a compact disk, into a linear arrangement. Points are assigned to locations on the circular arrangement. These points are mapped to a linear arrangement. The number of points is selected to be greater than those of the original image to enhance the resolution of the resulting image. The location of the points is stored in an address array. The values of the pixels in the original image are then copied to a target array. The pixel values are then converted to binary values serving as input to a recognition neural network and a verification neural network.