2014³â Ãá°èÇмú´ëȸ
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
³ªÀÌºê º£À̽º¿¡¼ÀÇ Ä¿³Î ¹Ðµµ ÃøÁ¤°ú »óÈ£ Á¤º¸·® |
¿µ¹®Á¦¸ñ(English Title) |
Mutual Information in Naive Bayes with Kernel Density Estimation |
ÀúÀÚ(Author) |
¼§ÃÑ·®
À¯¼§·ç
°´ë±â
Zhongliang Xiang
Xiangru Yu
Dae-Ki Kang
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 18 NO. 01 PP. 0086 ~ 0088 (2014. 05) |
Çѱ۳»¿ë (Korean Abstract) |
³ªÀÌºê º£À̽º°¡ °¡Áö´Â °¡Á¤Àº ½Ç¼¼°è µ¥ÀÌÅ͸¦ ºÐ·ùÇÔ¿¡ ÀÖ¾î Çطοî È¿°ú¸¦ º¸ÀÌ°ï ÇÑ´Ù. ÀÌ·¯ÇÑ °¡Á¤À» ¿ÏÈÇϱâ À§ÇØ, ¿ì¸®´Â Naive Bayes Mutual Information Attribute Weighting with Smooth Kernel Density Estimation (NBMIKDE) Á¢±Ù ¹æ¹ýÀ» ¼Ò°³ÇÑ´Ù. NBMIKDE´Â ¾ÖÆ®¸®ºäÆ®¸¦ À§ÇÑ ½º¹«µå Ä¿³Î°ú »óÈ£ Á¤º¸·® ÃøÁ¤°ªÀ» ±â¹ÝÀ¸·Î ÇÏ´Â ¾îÆ®¸®ºäÆ® °¡ÁßÄ¡ ±â¹ýÀ» Á¶ÇÕÇÑ °ÍÀÌ´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
Naive Bayes (NB) assumption has some harmful effects in classification to the real world data. To relax this assumption, we now propose approach called Naive Bayes Mutual Information Attribute Weighting with Smooth Kernel Density Estimation (NBMIKDE) that combine the smooth kernel for attribute and attribute weighting method based on mutual information measure.
|
Å°¿öµå(Keyword) |
Naive Bayes
Attribute Weighting
Mutual Information
Kernel Density Estimation
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|