id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_4iou6ghsc5hgzi7fvogqcu63pm	Mostafa Ghazizadeh Ahsaee	Shell fitting space for classification	2011	10	.pdf	application/pdf	5262	857	71	In this paper, a shell fitting space (SFS) is presented to map non-linearly separable data to linearly separable ones. A linear or quadratic transformation maps data into a new space for better classification, if a linear support vector machine (SVM) multi-class classifier is applied to classify the learn data. where / is a function that depends on distance of data to each pattern's fitted curve, hyperplane or surrounded cortex or (shell). network-based methods like adaptive neural-fuzzy inference system (ANFIS) for this purpose. support vector data description (SVDD) are examples of the boundary methods (Tax & Duin, 2004; Ypma et al., 1998). Our proposed method is applied to a data series in 2-dimensional space (two classes with two features) and the results are calculated the distance of each data in the dataset to circles fitted Curves have been fitted to data sets of two classes and the result of	./cache/work_4iou6ghsc5hgzi7fvogqcu63pm.pdf	./txt/work_4iou6ghsc5hgzi7fvogqcu63pm.txt