TY - GEN

T1 - Simulated annealing for pattern detection and seismic analysis

AU - Huang, Kou Jen

AU - Huang, Kou-Yuan

AU - Wang, Luke K.

AU - Chou, Ying Liang

AU - Hsieh, Yueh Hsun

AU - Hsieh, Shan Chih

PY - 2009/11/18

Y1 - 2009/11/18

N2 -
Simulated annealing (SA) is adopted to detect the parameters of line, circle, ellipse, and hyperbola. The equation of pattern is defined under translation and rotation. The distance from all points to all patterns is defined as the system error. Also we use the minimum error to determine the number of patterns. The parameters of the pattern are learned with probability in SA. The proposed SA parameter detection system can search a set of parameter vectors for the global minimal error. In the seismic experiments, the system can well detect line of direct wave and hyperbola of reflection wave in the real seismic data. In the seismic data processing, the reflection curves on common depth reflection point (CDP) gathers are hyperbolic patterns. So using SA, the parameters of each hyperbolic pattern can be detected. The parameters are used to calculate the root-mean-squared velocity V
rms
. The V
rms
is used to the normal-moveout (NMO) correction and stacking to reconstruct the image of the subsurface. Using the result of SA hyperbolic parameter detection, it is a novel method in the seismic velocity analysis.

AB -
Simulated annealing (SA) is adopted to detect the parameters of line, circle, ellipse, and hyperbola. The equation of pattern is defined under translation and rotation. The distance from all points to all patterns is defined as the system error. Also we use the minimum error to determine the number of patterns. The parameters of the pattern are learned with probability in SA. The proposed SA parameter detection system can search a set of parameter vectors for the global minimal error. In the seismic experiments, the system can well detect line of direct wave and hyperbola of reflection wave in the real seismic data. In the seismic data processing, the reflection curves on common depth reflection point (CDP) gathers are hyperbolic patterns. So using SA, the parameters of each hyperbolic pattern can be detected. The parameters are used to calculate the root-mean-squared velocity V
rms
. The V
rms
is used to the normal-moveout (NMO) correction and stacking to reconstruct the image of the subsurface. Using the result of SA hyperbolic parameter detection, it is a novel method in the seismic velocity analysis.

UR - http://www.scopus.com/inward/record.url?scp=70449448497&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2009.5179090

DO - 10.1109/IJCNN.2009.5179090

M3 - Conference contribution

AN - SCOPUS:70449448497

SN - 9781424435531

T3 - Proceedings of the International Joint Conference on Neural Networks

SP - 1278

EP - 1285

BT - 2009 International Joint Conference on Neural Networks, IJCNN 2009

Y2 - 14 June 2009 through 19 June 2009

ER -