Cumulonimbus Forecasting Based on Rough Set and Artificial Immune Algorithm
In basic weather theory, there are four families of clouds. The fourth category is clouds with extensive vertical development named Cumulonimbus clouds. Cumulonimbus clouds have extensive vertical development. Cumulonimbus clouds, commonly called thunderheads, can produce high winds, torrential rain, lightning, hail, gust fronts, waterspouts, funnel clouds and tornados (Boatman, 1998). Some small scale weather, such as thunderstorm or cumulonimbus, is a grave threat to civil aviation flight safety. Despite of a great deal of data having been accumulated these years, the civil weather departments still primarily use traditional meteorology methods, mainly by the subjective factors of forecasters, to predict weather occurrence, development and changes. The idea is to take the input from ground sensors or sounding probe and then the data is entered into a database (Kusiak, 2001). Rough set data mining offers a viable approach for extraction of decision rules from data sets. The extracted rules can be used for making predictions in the formation of a forecast. According to Wei and Fan (2010), “Because of serious imbalance phenomenon of the data and based on the rule classification, artificial immune algorithm is used to deal with the problem on data recognition, finally we present a cumulonimbus forecasting model based on rough set and artificial immune algorithm which is proved effective by experimental results” (p. 2856). This can provide additional artificial intelligence approach in predicting Cumulonimbus clouds in a given area based on currently available knowledge.
Below is a diagram of Cumulonimbus Forecasting Based on Rough Set.
Rough Outline of Report:
Table of contents
1. Cumulonimbus Clouds
2. Threat to aviation safety
3. Accumulation of data
4. Rough set data mining
5. Classification
5. Application of Artificial Immune Algorithm to forecasting of Cumulonimbus Clouds
6. Conclusion
References:
Gang, W. & Dong, Z.W. Research on Rough Set Theory Application in Data Fusion. Computer
Science and Information Processing (CSIP), 2012 International Conference, 6, 432-435,
24-26. Retrieved from IEEE on October 28, 2014.
Kusiak, A. ( 2001). Rough set theory: a data mining tool for semiconductor manufacturing.
Electronics Packaging Manufacturing, 24 (1), 44, 50. Retrieved from IEEE on October
28, 2014.
Wang, Q. & Fan, W. (2010). Cumulonimbus forecasting based on rough set and artificial
immune algorithm. Natural Computation (ICNC), 2010 Sixth International Conference,
6, 2856,2860. Retrieved from IEEE on October 30, 2014.
Wang, G. & Zhang, W. D., Research on Rough Set Theory Application in Data Fusion.
Computer Science and Information Processing (CSIP), 2012 International Conference ,
24, 432,435. Retrieved from IEEE on November 1, 2014.
Lu Hong. (2008). Artificial Immune System for Anomaly Detection. Knowledge Acquisition and
Modeling Workshop. KAM Workshop 2008. IEEE International Symposium, 12, 340,343,
21-22.
Boatman.J, Hiles.J, Mcray.G, Schoeman.D, Shockley.K, Stout.C, & Werner.A. (1998)
Instrument Commercial Manual. Englewood, CO: Jeppesen Sanderson, Inc.