TAOS is an experimental technique which collects the intensity pattern of LASER light scattered by a single, air-borne material particle, ≈1μm in size. An algorithm based on feature extraction and linear classification has been developed and implemented in two stages. In stage one the classifier is trained and validated by different sets of patterns from reference materials. In stage two the trained classifier is applied to patterns from bacterial spores and environmental sampling: pattern recognition occurs by information fusion. A large data set (>5,000 patterns) has been analysed. Bacillus subtilis patterns are discriminated from those of other materials. Progress will be reported in the classification of patterns from outdoor sampling and from confounder materials.
Crosta, G., Pan, Y., Videen, G., Aptowicz, K., Chang, R. (2013). Classification and Recognition of Light Scattering Patterns from Airborne Particles. In Proceedings. Society for industrial and applied mathematics.
Classification and Recognition of Light Scattering Patterns from Airborne Particles
CROSTA, GIOVANNI FRANCO FILIPPO;
2013
Abstract
TAOS is an experimental technique which collects the intensity pattern of LASER light scattered by a single, air-borne material particle, ≈1μm in size. An algorithm based on feature extraction and linear classification has been developed and implemented in two stages. In stage one the classifier is trained and validated by different sets of patterns from reference materials. In stage two the trained classifier is applied to patterns from bacterial spores and environmental sampling: pattern recognition occurs by information fusion. A large data set (>5,000 patterns) has been analysed. Bacillus subtilis patterns are discriminated from those of other materials. Progress will be reported in the classification of patterns from outdoor sampling and from confounder materials.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
