Methods and systems for discriminating targets using information derived from a sensor are presented. In one embodiment, a method features receiving a plurality of observations corresponding to a target; retrieving probabilities of the observations associated with each of a plurality of states, where the states are based a statistical model associated with at least one target type; consolidating the probabilities of observations for each of the plurality of states using a weighted combination; computing the probability of each state associated with the plurality of observations; selecting a state of the target based upon the computed probability of each state; and discriminating the target based upon the selected state.

 
Web www.patentalert.com

< Data processing apparatus and data processing method

< Training convolutional neural networks on graphics processing units

> Prediction method of near field photolithography line fabrication using by the combination of taguchi method and neural network

> Method of and system for evaluating tactile sensations of car seat covers using statistical recursive and artificial neural network models

~ 00618