Title :
Fuzzy functional-link net for seismic trace editing
Author_Institution :
Inst. of Comput. & Inf. Sci., Nat. Chiao Tung Univ., Hsinchu, Taiwan
fDate :
27 Jun-2 Jul 1994
Abstract :
A higher-order neural net incorporated with fuzzy concept in learning procedure is proposed. This net is called fuzzy functional-link net. Fuzzy functional-link net is applied to the seismic trace editing to determine the good or bad recording. Perceptron with pocket learning algorithm and multilayer perceptron are also applied to the seismic trace editing. Compared with the classification results, fuzzy functional-link net has good performance in learning time and recognition rate
Keywords :
feedforward neural nets; fuzzy neural nets; geophysical prospecting; geophysical signal processing; geophysical techniques; multilayer perceptrons; seismology; explosion seismology; fuzzy functional-link net; geophysical prospecting; high-order neural net; measurement technique; multilayer perceptron; neural net; pocket learning algorithm; seismic reflection profiling; seismic trace editing; signal processing; Frequency; Fuzzy neural networks; Fuzzy set theory; Information science; Multilayer perceptrons; Nearest neighbor searches; Neural networks; Pattern recognition; Tensile stress; Vectors;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374403
