Seismic classification-based method for recognizing epicenter-neighboring orbits

From the point of view of the Fourth Paradigm, this paper attempts to find a recognizing method based on DEMETER (Detection of Electro-Magnetic Emissions Transmitted from Earthquake Regions) satellite data for epicenter-neighboring orbits during strong shocks. Detection points or small regions are used as research objects in numerous studies on seismic activities recognition. Due to the infrequency of strong shocks, the number of non-seismic data is far larger than the abnormal one, which results in the underfitting during the training of recognition model. Additionally, data located along the edge of seismic regions can hardly be classified into abnormal dataset or non-seismic one. A sloppy classification can badly reduce the accuracy of model. Hence, it is desired to put forward a more suitable approach to make better use of original data. In this paper, a seismic classification-based method for recognizing epicenter-neighboring orbit is proposed to address these problems. Unlike the existing approaches, our method regards the satellite orbits as the analyzing objects, which avoids the underfitting performance caused by the unbalanced data distribution. Moreover, error correcting output coding (ECOC) strategy is utilized to transform the recognizing problem into a series of binary classifications. By means of safe semi-supervised support vector machines (S4VMs) with kernel combination, the unlabeled orbits help obtain a better classification performance. Finally, three groups of comprehensive experiments are applied to validate the effectiveness of the method.