排序方式: 共有13条查询结果,搜索用时 93 毫秒
11.
Alexandros A. Chatzipetros Spyros B. Pavlides Demosthenis M. Mountrakis 《Journal of Geodynamics》1998,26(2-4)
Paleoseismological research by means of trenching in the area that was affected by the Kozani-Grevena strong (Ms = 6.6) earthquake sequence, revealed evidence for past reactivations of the same seismogenic fault. Five trenches were excavated along the Palaeochori-Sarakina part of the fault, in which three surface faulting paleoevents were identified at ca. 8.97, 36.7 and 72.5 ka BP (TL dates). Recurrence interval based on these datings is about 30 ka, which is very long, verifying the ‘low seismicity’ status of the area. On this basis, the 1995 earthquake was an out of sequence event, because the elapse time since the last major event is 8.97 ka instead of 30. Assuming a constant rate of strain accumulation, this would also explain the small amount of surface displacement that was observed during the 1995 earthquake (maximum 18 cm, usually up to 10 cm) in respect to the displacements observed in the trenches (> 25 cm) for previous paleoevents. 相似文献
12.
Support vector machines in remote sensing: A review 总被引:19,自引:0,他引:19
Giorgos Mountrakis Jungho Im Caesar Ogole 《ISPRS Journal of Photogrammetry and Remote Sensing》2011,66(3):247-259
A wide range of methods for analysis of airborne- and satellite-derived imagery continues to be proposed and assessed. In this paper, we review remote sensing implementations of support vector machines (SVMs), a promising machine learning methodology. This review is timely due to the exponentially increasing number of works published in recent years. SVMs are particularly appealing in the remote sensing field due to their ability to generalize well even with limited training samples, a common limitation for remote sensing applications. However, they also suffer from parameter assignment issues that can significantly affect obtained results. A summary of empirical results is provided for various applications of over one hundred published works (as of April, 2010). It is our hope that this survey will provide guidelines for future applications of SVMs and possible areas of algorithm enhancement. 相似文献
13.