General Electric Company

USA As Represented by Secretary of the Navy

Ronald Eugene Shaffer

Radislav Alexandrovich Potyrailo

Patrick Joseph McCloskey

John Patrick Lemmon

William Guy Morris

Ronald James Wroczynski

Sean J Hart

Susan L Rose-Pehrsson

Mark H Hammond

Ralph Joseph May

Daniel T Gottuk

A multi-criteria fire detection system, comprising a plurality of sensors, wherein each sensor is capable of detecting a signature characteristic of a presence of a fire and providing an output indicating the same. A processor for receiving each output of the plurality of sensors is also employed. The processor includes a probabilistic neural network for processing the sensor outputs. The probabilistic neural network comprises a nonlinear, nor-parametric pattern recognition algorithm that operates by defining a probability density function for a plurality of data sets that are each based on a training set data and an optimized kernel width parameter. The plurality of data sets includes a baseline, non-fire, fist data set; a second, fire data set, and a third, nuisance data set. The algorithm provides a decisional output indicative of the presence of a fire based on recognizing and discrimination between said data sets, and whether the outputs suffice to substantially indicate the presence of a fire, as opposed to a non-fire or nuisance situation.

Identification of fire signatures for shipboard multi-criteria fire detection systems

The present invention provides methods and an apparatus for the rapid analysis of data from imaging, spectroscopic, scanning probe, or sensor methods. By application of mathematical transform analysis such as wavelet transform algorithms to one or multi-order data sets obtained from individual samples or sample arrays, the analytical features of the data are preserved while undesired noise is removed, thereby reducing the integration time by more than 10-fold in subsequent measurements. The reduction in integration time enables the high-throughput measurement of combinatorial libraries and rapid dynamic processes, while still providing a signal-to-noise level suitable for a reliable measurement.

Method for enhancement in screening throughput

Systems and methods for analyzing a viscoelastic property of a combinatorial library of materials including a plurality of full bridge devices operable for measuring a temperature-modulated elongation property of each of a plurality of combinatorial materials, wherein each of the plurality of full bridge devices comprises a plurality of strain gauges operable for measuring a temperature-modulated elongation property of each of the plurality of combinatorial materials, and wherein each of the plurality of combinatorial materials is disposed on a surface of the plurality of full bridge devices. The systems and methods also including an algorithm disposed within a computer, the algorithm operable for equating the temperature-modulated elongation property of the combinatorial materials with a thermal property of the combinatorial materials.

Systems and methods for analyzing viscoelastic properties of combinatorial libraries of materials

The present invention provides a method for monitoring a reaction mixture using Raman spectroscopy. In a preferred embodiment, the invention provides a method for monitoring bulk and thin film melt polycarbonate polymerization reactions. In this method, the relative and absolute concentrations of the starting materials diphenylcarbonate (DPC) and bisphenol-A (BPA) are determined. Monitoring and maintenance of optimum stoichiometry in such a reaction is critical to ensuring desired polycarbonate product quality.

Situ determination of DPC and BPA in polycarbonate by Raman spectroscopy

The present invention is directed to a method for the rapid screening of potential reactants, catalysts, and associated process conditions. In an embodiment, the invention comprises a method for evaluating catalyst efficacy in polymerization reactions by the determination of product molecular weight and Fries products.

Method for high-throughput fluorescent screening of polymerization reactions

A device and method for a pattern recognition system using a self-training neural network classifier with automated outlier detection for use in chemical sensor array systems. The pattern recognition system uses a Probabilistic Neural Network (PNN) training computer system to develop automated classification algorithms for field-portable chemical sensor array systems. The PNN training computer system uses a pattern extraction unit to determine pattern vectors for chemical analytes. These pattern vectors form the initial hidden layer of the PNN. The hidden layer of the PNN is reduced in size by a learning vector quantization (LVQ) classifier unit. The hidden layer neurons are further reduced in number by checking them against the pattern vectors and further eliminating dead neurons using a dead neuron elimination device. Using the remaining neurons in the hidden layer of the PNN, a global, &sgr; value is calculated and a threshold rejection value is determined. The hidden layer, &sgr; value and the threshold value are then downloaded into a PNN module for use in a chemical sensor field unit. Based on the threshold value, outliers seen in the real world environment may be rejected and a predicted chemical analyte identification with a measure of uncertainty will be provided to the user.

Growing community of inventors

Clifton Park, NY, United States of America

Ronald Eugene Shaffer