caa a22 4500 606159509 CHVBK 20210128100625.0 cr unu---uuuuu 210128e20150401xx s 000 0 eng 10.1007/s00521-014-1746-2 doi (NATIONALLICENCE)springer-10.1007/s00521-014-1746-2 A study of visual behavior of multidimensional scaling for kernel perceptron algorithm [Elektronische Daten] [Che-Chang Hsu, Kuo-Shong Wang, Hung-Yuan Chung, Shih-Hsing Chang] The class imbalance problem occurs when the classifier is to detect a rare but important class. The purpose of this paper is to study whether possible sources of error are not only the imbalance but also other factors in combination, which lead to these misclassifications. The theoretical difficulties in purely predictive settings arise from the lack of visualization. Therefore, for kernel classifiers we propose the link with a kernel version of multidimensional scaling in high-dimensional feature space. The transformed version of the features specifically discloses the intrinsic structure of Hilbert space and is then used as inputs into a learning system: in the example, this prediction method is based on the SVMs-rebalance methodology. The graphical representations indicate the effects of masking, skewed, and multimodal distribution, which are also responsible for the poor performance. By studying the properties of the misclassifications, we can further develop ways to improve them. The Natural Computing Applications Forum, 2014 Class imbalance problem nationallicence Sources of error nationallicence Multidimensional scaling nationallicence SVMs-rebalance nationallicence Graphical representations nationallicence Hsu Che-Chang Department of Mechanical Engineering, National Central University, No. 300, Jhongda Rd., Jhongli City, Taoyuan County, Taiwan, ROC aut Wang Kuo-Shong Department of Mechanical Engineering, National Central University, No. 300, Jhongda Rd., Jhongli City, Taoyuan County, Taiwan, ROC aut Chung Hung-Yuan Department of Electrical Engineering, National Central University, No. 300, Jhongda Rd., Jhongli City, Taoyuan County, Taiwan, ROC aut Chang Shih-Hsing Institute of Business and Management, Vanung University, No. 1 Van-Nung Rd., 320614, Jhongli City, Taoyuan County, Taiwan, ROC aut Neural Computing and Applications Springer London 26/3(2015-04-01), 679-691 0941-0643 26:3<679 2015 26 521 https://doi.org/10.1007/s00521-014-1746-2 text/html Onlinezugriff via DOI BK010053 XK010053 XK010000 Metadata rights reserved Springer special CC-BY-NC licence nationallicence 1 research-article jats NATIONALLICENCE NATIONALLICENCE NL-springer NATIONALLICENCE 856 40 https://doi.org/10.1007/s00521-014-1746-2 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Hsu Che-Chang Department of Mechanical Engineering, National Central University, No. 300, Jhongda Rd., Jhongli City, Taoyuan County, Taiwan, ROC aut NATIONALLICENCE 700 1- Wang Kuo-Shong Department of Mechanical Engineering, National Central University, No. 300, Jhongda Rd., Jhongli City, Taoyuan County, Taiwan, ROC aut NATIONALLICENCE 700 1- Chung Hung-Yuan Department of Electrical Engineering, National Central University, No. 300, Jhongda Rd., Jhongli City, Taoyuan County, Taiwan, ROC aut NATIONALLICENCE 700 1- Chang Shih-Hsing Institute of Business and Management, Vanung University, No. 1 Van-Nung Rd., 320614, Jhongli City, Taoyuan County, Taiwan, ROC aut NATIONALLICENCE 773 0- Neural Computing and Applications Springer London 26/3(2015-04-01), 679-691 0941-0643 26:3<679 2015 26 521