Fuel spill identification using solid-phase extraction and solid-phase microextraction. 1. Aviation turbine fuels.

The water-soluble fraction of aviation jet fuels is examined using solid-phase extraction and solid-phase microextraction. Gas chromatographic profiles of solid-phase extracts and solid-phase microextracts of the water-soluble fraction of kerosene- and nonkerosene-based jet fuels reveal that each jet fuel possesses a unique profile. Pattern recognition analysis reveals fingerprint patterns within the data characteristic of fuel type. By using a novel genetic algorithm (GA) that emulates human pattern recognition through machine learning, it is possible to identify features characteristic of the chromatographic profile of each fuel class. The pattern recognition GA identifies a set of features that optimize the separation of the fuel classes in a plot of the two largest principal components of the data. Because principal components maximize variance, the bulk of the information encoded by the selected features is primarily about the differences between the fuel classes.

Source identification of underground fuel spills by solid-phase microextraction/high-resolution gas chromatography/genetic algorithms.

Solid-phase microextraction (SPME), capillary column gas chromatography, and pattern recognition methods were used to develop a potential method for typing jet fuels so a spill sample in the environment can be traced to its source. The test data consisted of gas chromatograms from 180 neat jet fuel samples representing common aviation turbine fuels found in the United States (JP-4, Jet-A, JP-7, JPTS, JP-5, JP-8). SPME sampling of the fuel's headspace afforded well-resolved reproducible profiles, which were standardized using special peak-matching software. The peak-matching procedure yielded 84 standardized retention time windows, though not all peaks were present in all gas chromatograms. A genetic algorithm (GA) was employed to identify features (in the standardized chromatograms of the neat jet fuels) suitable for pattern recognition analysis. The GA selected peaks, whose two largest principal components showed clustering of the chromatograms on the basis of fuel type. The principal component analysis routine in the fitness function of the GA acted as an information filter, significantly reducing the size of the search space, since it restricted the search to feature subsets whose variance is primarily about differences between the various fuel types in the training set. In addition, the GA focused on those classes and/or samples that were difficult to classify as it trained using a form of boosting. Samples that consistently classify correctly were not as heavily weighted as samples that were difficult to classify. Over time, the GA learned its optimal parameters in a manner similar to a perceptron. The pattern recognition GA integrated aspects of strong and weak learning to yield a "smart" one-pass procedure for feature selection.

Fuel identification by neural network analysis of the response of vapor-sensitive sensor arrays.

Neural network analysis of the response of an array of vapor-sensitive detectors has been used to identify six different types of aviation fuel. The data set included 96 samples of JP-4, JP-5, JP-7, JP-8, JetA, and aviation gasoline (AvGas). A sample of each neat fuel was injected into a continuous stream of breathing air through an injection port from a gas chromatograph. The aspirated sample was then swept from the injection port to the chamber without separation. In the chamber, the sample was exposed to an array of eight vapor-sensitive detectors. The analog output of each detector was digitized and stored while the sample was swept into and through the chamber. The response of each detector was then averaged and stored as the final response or pattern of each sample. It was clear from a visual inspection of each of the radar plots that there was a characteristic pattern in the response of the array to five of the six different fuel types. This was confirmed using neural network analysis to study the entire data set. A two-step procedure was developed to separate the patterns of all six fuel tyes into their respective classes. In the first step, fuels were separated into one of five groups: JP-4, JP-5, JP-7, AvGas, or a combined JP-8/JetA group. In the second step, the fuels in the combined group were separated into either JP-8 or JetA groups.

Use of computerized pattern recognition in the study of the cuticular hydrocarbons of imported fire ants. I. Introduction and characterization of the cuticular hydrocarbon patterns of Solenopsis invicta and S. richteri.

A method is described in which gas chromatographic (GC) data obtained from cuticular hydrocarbons are treated by methods of pattern recognition. Based on a recently described sample preparation procedure, GC data are normalized to eliminate slight variations in chromatographic conditions and converted into the proper format for discriminant analysis by computer. The results of several methods of data treatment and display are discussed, based upon the chemometric system package, ARTHUR. The approach has the advantage of largely removing operator bias.

Use of computerized pattern recognition in the study of the cuticular hydrocarbons of imported fire ants. II. Comparison of the cuticular hydrocarbon patterns between different colonies of Solenopsis richteri.

Gas chromatography (GC) data obtained from the cuticular hydrocarbons of the black imported fire ants are treated by methods of pattern recognition. Based on a recently described sample preparation procedure, GC data are normalized to eliminate slight variations in chromatographic conditions, and converted to the proper format for discriminant analysis by computer. The results of several methods of data treatment and display are discussed, based on the chemometrics system package, ARTHUR.