Abstract
An artificial neural network is described for classification of meteor trails into the distinct overdense, intermediate and underdense trail categories. The neural network was trained and on model data obtained using the “KAMET” program and tested on real data. The best result of classification success rate of 95% without according to the heights of the formation of meteor trails. Results of classification with according to the heights of the formation of meteor trails are 82% - 91%.
References
Fraser, D.D., Khan, Z., Levy D.C., 1992, Proceedings ICANN-92 (September 1992, Brighton, United Kingdom), 1155-1158.10.1016/B978-0-444-89488-5.50069-5Search in Google Scholar
Melville, S., Sutcliffe, G., Fraser, D.D., 1996, Proceedings of the 4th Pacific Rim International Conference on Artificial Intelligence (26-30 August 1996, Cairns, Australia), 423-434.Search in Google Scholar
Karpov, A.V. 1995, Radiophysics, 38, 767-773.Search in Google Scholar
Sulimov, A.I., Karpov, A.V., Lapshina, I.R., Khuzyashev, R.G., 2017, IEEE Transactions on Antennas and Propagation, 65, 2009-2019.10.1109/TAP.2017.2669730Search in Google Scholar
Haykin, S., 2009, Neural Networks and Learning Machines, 3rd ed., New Jersey, USA: Pearson Education.Search in Google Scholar
Kartashova, A.P., Danilov, M.V., Karpov, A.V., 2017, Proceedings ACM 2017 (10-14 April 2017, Montevideo, Uruguay), 421.Search in Google Scholar
Desourdis, R.J., Sidorov, V.V., Karpov, A.V., Huziashev, R.G., Epiktetov, L.A., Brown D.W., 1993, IEEE MILCOM 1993 Conference Proceedings, 32-36.Search in Google Scholar
Sulimov, A.I., 2017, Proceedings RSEMW-2017, (26-30 June 2017, Gelendzhik, Russia), 1-4.Search in Google Scholar
© by Mikhail Danilov, Arkadi Karpov, published by De Gruyter
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.
