Use of Ensemble Learning Technique for Detection/Identification ofChemical Plumes

摘要

An ensemble learning approach using a number of weak classifiers, each classifier conducting learning based on arandom subset of spectral features (bands) of the training sample, is used to detect/identify a specific chemical plume.The support vector machine (SVM) is used as the weak classifier. The detection results of the multiple SVMs arecombined to generate a final decision on a pixel's class membership. Due to the multiple learning processes conducted inthe randomly selected spectral subspaces, the proposed ensemble learning can improve solution generality. This workuses a two-class approach, using samples taken from hyper-spectral image (HSI) cubes collected during a release of thetest chemical. Performance results in the form of receiver operator characteristic curves, show similar performance whencompared to a single SVM using the full spectrum. Initial results were obtained by training with samples taken from asingle HSI cube. These results are compared to results that are more recent from training with sample data from 28 HSIcubes. Performance of algorithms trained with high concentration spectra show very strong responses when scored onlyon high concentration data. However, performance drops substantially when low concentration pixels are scored as well.Training with the low concentration pixels along with the high concentration pixels can improve over all solutiongenerality and shows the strength of the ensemble approach. However, it appears that careful selection of the trainingdata and the number of examples can have a significant impact on performance.