Title :
Self-organization of feature detectors in time sequences (SOFT)-a neural network approach to multidimensional signal analysis
Author :
Wismuller, Axel ; Jaeger, Herbert ; Ritter, Helge ; Dersch, Dominik R. ; Palm, Guünther
Author_Institution :
Inst. fur Radiol. Diagnostick, Munchen Univ., Germany
Abstract :
We present a neural network algorithm for self-organization of feature detectors in time sequences (SOFT) based on the mathematical concept of transient attractors. It evaluates local phase space volume contraction as an indicator for good short-term predictability. SOFT supports category formation and event detection in multidimensional time sequences by linking together neural function approximation and principal component analysis. Possible extensions of the algorithm including iteration and vector quantization procedures for further data analysis are discussed
Keywords :
feature extraction; function approximation; self-organising feature maps; signal processing; statistical analysis; vector quantisation; SOFT algorithm; event detection; feature detectors; function approximation; iterative method; phase space volume contraction; principal component analysis; self-organization neural nets; time sequences; transient attractors; vector quantization; Computer vision; Data analysis; Detectors; Event detection; Function approximation; Joining processes; Multidimensional systems; Neural networks; Principal component analysis; Vector quantization;
Conference_Titel :
Neural Networks Proceedings, 1998. IEEE World Congress on Computational Intelligence. The 1998 IEEE International Joint Conference on
Conference_Location :
Anchorage, AK
Print_ISBN :
0-7803-4859-1
DOI :
10.1109/IJCNN.1998.682331
