Classification rejection by prediction
We address the problem of autonomous decision making in classification of radioastronomy spectrograms from spacecraft. It is known that the assessment of the decision process can be divided into acceptation of the classification, instant rejection of the current signal classification, or rejection of the entire classifier model. We propose to combine prediction and classification with a double architecture of Time Delay Neural Network (TDNN) to optimize a decision minimizing the false alarm risk. Results on real data from URAP experiment aboard Ulysses spacecraft show that this scheme is tractable and effective.
Keywordsspectrogram classification radioastronomy neural network classification transient signal prediction
Unable to display preview. Download preview PDF.
- 1.P. Y. Arques. Décision en Traitement du Signal. Collection Technique et Scientifique des Télécommunications. Masson, Paris, 1982.Google Scholar
- 2.H. de Lassus A. Lecacheux S. Thiria F. Badran. Neural Network Clusters and Cellular Automata for the Detection and Classification of Overlapping Transient Signals on Radio Astronomy Spectrograms from Spacecraft. In International Symposium on Time-Frequency and Time-Scale Analysis, Paris, France, june 1996. IEEE Signal Processing Society. Accepted paper.Google Scholar
- 3.K. J. Lang A. H. Waibel G. E. Hinton. A Time Delay Neural Network Architecture for Isolated Word Recognition. Neural Networks, 3:23–43, 1990.Google Scholar
- 4.Stone and al. The Unified Radio and Plasma Waves Investigation. Astron. Astrophys. Suppl. Series, 92:291–316, 1992.Google Scholar
- 5.Gm. Jenkins Dg. Watts. Spectral Analysis and its applications. Holden-Day, San Francisco, holden-day edition, 1968.Google Scholar