توجه: محتویات این صفحه به صورت خودکار پردازش شده و مقاله‌های نویسندگانی با تشابه اسمی، همگی در بخش یکسان نمایش داده می‌شوند.
۱SPM: A Fast and Scalable Model for Predicting Snow\No–Snow
نویسنده(ها): ، ،
اطلاعات انتشار: World Applied Sciences Journal، سي و دوم،شماره۸، ۲۰۱۴، سال
تعداد صفحات: ۱۰
From several decades, weather prediction is a vital application in meteorology and has been one of the most scientifically and technologically challenging problem across the globe. Therefore, it is important to have an accurate model for predicting the snow\no–snow occurrence across various regions. In this paper, we present a novel and robust Snow Prediction Model (SPM) for the prediction over twenty one international locations across the world. The proposed model evaluates various performance measures such as accuracy, precision, sensitivity, dice and specificity and the results are compared with various decision tree and nondecision tree algorithms such as Decision Stump, Random Tree, LAD Tree, SLIQ decision tree and Naive Bayes. With this analysis, the proposed methodology gives an outstanding result when compared with the existing models. The SPM provides an average accuracy of 87.14 % in the prediction of snow\no snow.
نمایش نتایج ۱ تا ۱ از میان ۱ نتیجه