Abstract
Various theories have been proposed since in last century to predict the first sighting of a new crescent moon. None of them uses the concept of machine and deep learning to process, interpret and simulate patterns hidden in databases. Many of these theories use interpolation and extrapolation techniques to identify sighting regions through such data. In this study, a pattern recognizer artificial neural network was trained to distinguish between visibility regions. Essential parameters of crescent moon sighting were collected from moon sight datasets and used to build an intelligent system of pattern recognition to predict the crescent sight conditions. The proposed ANN learned the datasets with an accuracy of more than 72% in comparison to the actual observational results. ANN simulation gives a clear insight into three crescent moon visibility regions: invisible (I), probably visible (P), and certainly visible (V). The proposed ANN is suitable for building lunar calendars, so it was used to build a four-year calendar on the horizon of Baghdad. The built calendar was compared with the official Hijri calendar in Iraq.
Subject
Applied Mathematics,Modeling and Simulation,General Computer Science,Theoretical Computer Science
Reference31 articles.
1. The Danjon Limit of First Visibility of the Lunar Crescent;Fatoohi;Observatory,1998
2. The Length of the Lunar Month
3. Lunar crescent visibility Criterion and Islamic Calendar;Ilyas;Q. J. R. Astr. Soc.,1994
4. The first visibility of the lunar crescent
5. Records for Young Moon Sighting;Schaefer;Q. J. R. Astr. Soc.,1993
Cited by
5 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献