The application of rough set and fuzzy rough set based algorithm to classify incomplete meteorological data

• Published in: 2014 International Conference on Data and Software Engineering (ICODSE) pp. 1 - 6
• Main Authors: Aprianti, Winda, Mukhlash, Imam
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.11.2014
• Subjects: Approximation methods; classification; Classification algorithms; data mining; fuzzy rough set; incomplete data; Iron; Prediction algorithms; Rain; rough set; Rough sets
• ISBN: 1479981753; 9781479981755
• DOI: 10.1109/ICODSE.2014.7062674

Weather has an important role in people's lives, such as agriculture, economics, socio-economic, disaster management, and finance. So, weather prediction is very important to be considered. In the prediction process we are often faced with the problem of data incompleteness. Therefore, it needs a proper classification algorithm that able to handle incomplete attribute values in the training data. In this paper, we use two approaches to handle incomplete data, namely are rough set and fuzzy rough set based algorithms. To test the performance of the two algorithms, we use meteorological data to classify rain or dry season. Conclusion of the study showed that the rough set approach is more efficient than the fuzzy rough sets approach. The advantage of fuzzy rough set approach can predict all the conditions that may occur, which can't be done by the rough set approach.