초록 ▼

The present invention provides a method of quickly identifying bioaerosols by class, even if the subject bioaerosol has not been previously encountered. The method begins by collecting laser ablation mass spectra from known particles. The spectra are correlated with the known particles, including th

The present invention provides a method of quickly identifying bioaerosols by class, even if the subject bioaerosol has not been previously encountered. The method begins by collecting laser ablation mass spectra from known particles. The spectra are correlated with the known particles, including the species of particle and the classification (e.g., bacteria). The spectra can then be used to train a neural network, for example using genetic algorithm-based training, to recognize each spectra and to recognize characteristics of the classifications. The spectra can also be used in a multivariate patch algorithm. Laser ablation mass specta from unknown particles can be presented as inputs to the trained neural net for identification as to classification. The description below first describes suitable intelligent algorithms and multivariate patch algorithms, then presents an example of the present invention including results.

대표청구항 ▼

1. A method of identifying an unknown particle as to class, where each class comprises more than one species, comprising: a) generating a trained neural network by: i) generating a laser ablation mass spectrum for each of a plurality of particles of known class and species; ii) correlating eac

1. A method of identifying an unknown particle as to class, where each class comprises more than one species, comprising: a) generating a trained neural network by: i) generating a laser ablation mass spectrum for each of a plurality of particles of known class and species; ii) correlating each spectrum with the species of the known particle and the identity of a class to which the species belongs; iii) training a neural network with the spectrum, species and class information to distinguish among the classes; b) generating a laser ablation mass spectrum for an unknown particle; c) using the trained neural network to determine whether the spectrum of the unknown particle correlates with any class identified in the training, even if the species of the unknown particle was not used to train the neural network. 2. The method of claim 1, further comprising the step of determining whether the unknown particle correlates with any species using the neural network. 3. The method of claim 1, wherein the step of training a neural network with the spectrum, species, and class information comprises using genetic algorithms to train a population of neural networks. 4. The method of claim 1, wherein the neural network comprises a fully connected feed-forward neural network. 5. The method of claim 4, wherein the neural network comprises an input layer, a hidden layer, and an output layer. 6. The method of claim 1, further comprising the step of determining whether the unknown particle correlates with any species using a multivariate patch algorithm. 7. The method of claim 6, further comprises using a genetic algorithm to select the patch for the multivariate patch algorithm.