We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
Classification based on dimension transposition for high dimension data.
- Authors
Qing He; Xiurong Zhao; Zhongzhi Shi
- Abstract
Abstract Based on Jordan Curve Theorem, a universal classification method called hyper surface classification (HSC) has recently been proposed. Experimental results are exciting, which show that in three-dimensional space, this method works fairly well in both accuracy and efficiency even for large size data up to 107. However, designing a number of new classifiers is needed with the growing of feature dimension. To solve the problem, a kind of efficient dimension transposition method that is suitable for HSC and without losing any essential information is put forward in this paper. The dimension transposition method rearrange all of the numerals in the higher dimensional data to lower dimensional data without changing each numeral, but only change their position according to some orders. The experiment shows that the method can classify high dimension data with high accuracy.
- Subjects
JORDAN curves; CURVES on surfaces; NUMERALS; MATHEMATICS
- Publication
Soft Computing - A Fusion of Foundations, Methodologies & Applications, 2007, Vol 11, Issue 4, p329
- ISSN
1432-7643
- Publication type
Article