Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2002 · 109 citations · 0 references
ComputingComputer ScienceMeteorologyData MiningMachine LearningTime Series AnalysisClassificationFeature SelectionPattern RecognitionSupport Vector MachinesTime Series ClassificationTime Series Feature ExtractionHybrid Genetic AlgorithmsHybrid Time Series Classification ModelsSupport Vector ClassificationSupport Vector Machine ClassificationTime Series Pattern RecognitionTime-series Feature Construction
We introduce an algorithm for classifying time series data. Since our initial application is for lightning data, we call the algorithm Zeus. Zeus is a hybrid algorithm that employs evolutionary computation for feature extraction, and a support vector machine for the final backend classification. Support vector machines have a reputation for classifying in high-dimensional spaces without overfitting, so the utility of reducing dimensionality with an intermediate feature selection step has been questioned. We address this question by testing Zeus on a lightning classification task using data acquired from the Fast On-orbit Recording of Transient Events (FORTE) satellite.