Abstract: An method and apparatus for extracting an interpretable, meaningful, and concise rule set from neural networks is presented. The method involves adjustment of gain parameter, &lgr; and the threshold, Tj for the sigmoid activation function of the interactive-or operator used in the extraction/development of a rule set from an artificial neural network. A multi-stage procedure involving coarse and fine adjustment is used in order to constrain the range of the antecedents of the extracted rules to the range of values of the inputs to the artificial neural network. Furthermore, the consequents of the extracted rules are provided based on degree of membership such that they are easily understandable by human beings. The method disclosed may be applied to any pattern recognition task, and is particularly useful in applications such as vehicle occupant sensing and recognition, object recognition, gesture recognition, and facial pattern recognition, among others.

Abstract: A vehicle-mounted sensing method and apparatus capable of monitoring the relative speed, distance, and closure rate between a sensor-equipped host vehicle and a sensed target object. The sensor uses an electronic camera to passively collect information and to provide the information to a system that identifies objects of interest using visual clues such as color, shape, and symmetry. The object's proximity may be determined, to a first approximation, by taking advantage of symmetrical relationships inherent in the vehicle of interest. The method and apparatus are particularly well-suited vehicular safety systems to provide for optimal risk assessment and deployment of multiple safety systems.