|
|
Çѱ¹¼öÀÚ¿øÇÐȸ / v.43, no.1, 2010³â, pp.81-94
|
»óÈ£Á¤º¸·® ±â¹ýÀ» Àû¿ëÇÑ Àΰø½Å°æ¸Á ÀÔ·ÂÀÚ·áÀÇ ¼±Á¤
( Input Variables Selection of Artificial Neural Network Using Mutual Information ) |
Çѱ¤Èñ;·ù¿ëÁØ;±èżø;ÇãÁØÇà; ¿¬¼¼´ëÇб³ ´ëÇпø Åä¸ñ°øÇаú;¿¬¼¼´ëÇб³ ´ëÇпø Åä¸ñ°øÇаú;¿¬¼¼´ëÇб³ ´ëÇпø Åä¸ñ°øÇаú »çȸȯ°æ½Ã½ºÅÛ°øÇкÎ;¿¬¼¼´ëÇб³ »çȸȯ°æ½Ã½ºÅÛ°øÇкΠÅä¸ñȯ°æ°øÇаú;
|
|
|
 |
|
|
ÃÊ ·Ï |
º» ¿¬±¸´Â Àΰø½Å°æ¸ÁÀÇ ¼º´ÉÀ» Çâ»ó½Ã۱â À§ÇÑ ¿©·¯ °¡Áö ¹æ¹ýµé ÁßÀÇ ÇϳªÀÎ ÀԷº¯¼ö ¼±Á¤±â¹ý¿¡ °üÇÑ ¿¬±¸·Î¼, ÀϹÝÀûÀ¸·Î ³Î¸® »ç¿ëµÇ°í ÀÖ´Â »ó°ü°è¼ö¸¦ ÀÌ¿ëÇÑ ÀԷº¯¼ö ¼±Á¤±â¹ý ¿Ü¿¡ »óÈ£Á¤º¸·®À» Ȱ¿ëÇÑ ¹æ¹ýÀ» Àû¿ëÇÏ¿© Àΰø½Å°æ¸ÁÀÇ ¼º´ÉÀ» Çâ»ó½Ã۰íÀÚ ÇÏ¿´´Ù. ´ë»óÀÚ·á´Â ±â»óû¿¡¼ Á¦°øÇÏ´Â RDAPSÀÚ·áÀÇ 152°³ Ãâ·Â°ªÀ¸·Î Áö»ó°¿ì·®ÀÇ ¿¹Ãø°ªÀÎ APCP¸¦ Æ÷ÇÔÇϰí ÀÖÀ¸¸ç, °¿ì°üÃø°ª°£ÀÇ »óÈ£Á¤º¸·®À» ±¸ÇØ °¡Àå ¿µÇâ·ÂÀÌ Å« º¯¼ö¸¦ ÀԷº¯¼ö·Î »ç¿ëÇÏ¿´´Ù. ±âÁ¸¿¬±¸°á°ú, ±×¸®°í »ó°ü°è¼ö¸¸À» ÀÌ¿ëÇØ¼ ÀԷº¯¼ö¸¦ ¼±Á¤ÇÑ °á°ú¿Í ºñ±³Çغ¼ ¶§, »óÈ£Á¤º¸·®À» Àû¿ëÇÑ °æ¿ì ÀԷº¯¼ö´Â ÁÖ·Î ¹Ù¶÷°ú °ü·ÃµÈ º¯¼öµéÀÌ ¼±Á¤µÇ¾úÀ¸¸ç, Æò±ÕÁ¦°ö±Ù¿ÀÂ÷, Æò±ÕÁ¦°ö±Ù»ó´ë¿ÀÂ÷, ±×·ìº°·Î ±¸ºÐÇÑ °æ¿ìÀÇ Àý´ë¿ÀÂ÷, ±×¸®°í ±¸°£º°·Î ±¸ºÐÇÑ °æ¿ìÀÇ »ó´ë¿ÀÂ÷¸¦ ºñ±³ÇÑ °æ°ú »óÈ£Á¤º¸·®À» ÀÌ¿ëÇÑ ÀԷº¯¼ö ¼±Á¤¹æ¹ýÀÇ Á¤È®µµ°¡ Àü¹ÝÀûÀ¸·Î ³ôÀº °ÍÀ¸·Î ³ªÅ¸³µÀ¸¸ç, ƯÈ÷ °¿ì·®ÀÌ »ó´ëÀûÀ¸·Î Å« °æ¿ìÀÇ ¿ÀÂ÷¸¦ ¸¹ÀÌ °¨¼Ò½Ãų ¼ö ÀÖ´Â °ÍÀ¸·Î ³ªÅ¸³µ´Ù. |
|
Input variable selection is one of the various techniques for improving the performance of artificial neural network. In this study, mutual information is applied for input variable selection technique instead of correlation coefficient that is widely used. Among 152 variables of RDAPS (Regional Data Assimilation and Prediction System) output results, input variables for artificial neural network are chosen by computing mutual information between rainfall records and RDAPS' variables. At first the rainfall forecast variable of RDAPS result, namely APCP, is included as input variable and the other input variables are selected according to the rank of mutual information and correlation coefficient. The input variables using mutual information are usually those variables about wind velocity such as D300, U925, etc. Several statistical error estimates show that the result from mutual information is generally more accurate than those from the previous research and correlation coefficient. In addition, the artificial neural network using input variables computed by mutual information can effectively reduce the relative errors corresponding to the high rainfall events. |
|
Ű¿öµå |
»óÈ£ Á¤º¸·®;Àΰø½Å°æ¸Á;ÀԷº¯¼ö¼±Á¤±â¹ý;mutual information;artificial neural network;input variable selection;RDAPS; |
|
|
|
 |
|
Çѱ¹¼öÀÚ¿øÇÐȸ³í¹®Áý / v.43, no.1, 2010³â, pp.81-94
Çѱ¹¼öÀÚ¿øÇÐȸ
ISSN : 1226-6280
UCI : G100:I100-KOI(KISTI1.1003/JNL.JAKO201005364710398)
¾ð¾î : Çѱ¹¾î |
|
³í¹® Á¦°ø : KISTI Çѱ¹°úÇбâ¼úÁ¤º¸¿¬±¸¿ø |
|
|
|
|
|