|
|
|
Çѱ¹¼öÀÚ¿øÇÐȸ / v.34, no.4, 2001³â, pp.303-316
|
Áß¼ÒÇÏõÀ¯¿ª¿¡¼ Hybrid Neural Networks¿¡ ÀÇÇÑ ¼ö¹®ÇÐÀû ¿¹Ãø
( Hydrological Forecasting Based on Hybrid Neural Networks in a Small Watershed ) |
| ±è¼º¿ø;À̼øÅ¹;Á¶Á¤½Ä; µ¿¾ç´ëÇб³ Åä¸ñȯ°æ°øÇаú;¿µ³²´ëÇб³ Åä¸ñµµ½Ãȯ°æ°øÇкÎ;´ë±¸´ëÇб³ °Ç¼³È¯°æ°øÇкÎ;
|
|
|
 |
|
| |
| ÃÊ ·Ï |
| º» ¿¬±¸¿¡¼´Â Áß¼ÒÇÏõ¼ö°è¿¡¼ ¼ö¹®ÇÐÀû ¿¹ÃøÀ» À§ÇÏ¿© Hybrid Neural NetworksÀÇ ÀÏÁ¾ÀÎ ¹Ý°æ±âÃÊÇÔ¼ö(RBF) ½Å°æ¸Á¸ðÇüÀÌ Àû¿ëµÇ¾ú´Ù. RBF ½Å°æ¸Á¸ðÇüÀº 4Á¾·ùÀÇ ¸Å°³º¯¼ö·Î ±¸¼ºµÇ¾î ÀÖÀ¸¸ç, ÁöÀ² ¹× ÁöµµÈƷðúÁ¤À¸·Î ÀÌ·ç¾îÁ®ÀÖ´Ù. ¹Ý°æ±âÃÊÇÔ¼ö·Î¼ °¡¿ì½ºÇÙÇÔ¼ö(GKF)°¡ ÀÌ¿ëµÇ¾úÀ¸¸ç, GKFÀÇ ¸Å°³º¯¼öÀÎ Á߽ɰú ÆøÀº K-Means ±ºÁý¾Ë°í¸®Áò¿¡ ÀÇÇØ ÃÖÀûÈ µÈ´Ù. ±×¸®°í RBF ½Å°æ¸Á¸ðÇüÀÇ ¸Å°³º¯¼öÀÎ Áß½É, Æø, ¿¬°á°µµ¿Í ÆíÂ÷º¤ÅÍ´Â ÈÆ·ÃÀ» ÅëÇÏ¿© ÃÖÀû ¸Å°³º¯¼öÀÇ °ªÀÌ °áÁ¤µÇ¸ç, ÀÌ ¸Å°³º¯¼öµéÀ» ÀÌ¿ëÇÏ¿© ¸ðÇüÀÇ °ËÁõ°úÁ¤ÀÌ ÀÌ·ç¾îÁø´Ù. RBF ½Å°æ¸Á¸ðÇüÀº Çѱ¹ÀÇ IHP ´ëÇ¥À¯¿ªÁß ÇϳªÀÎ À§ÃµÀ¯¿ª¿¡ Àû¿ëÇÏ¿´À¸¸ç, ¸ðÇüÀÇ ÈÆ·Ã°ú °ËÁõÀ» À§ÇÏ¿© 10°³ÀÇ °¿ì»ç»óÀ» ¼±ÅÃÇÏ¿´´Ù. ¶ÇÇÑ RBF ½Å°æ¸Á¸ðÇü°ú ºñ±³°ËÅäÇϱâ À§ÇÏ¿© ¿¤¸¸ ½Å°æ¸Á(ENN)¸ðÇüÀ» ÀÌ¿ëÇÏ¿´À¸¸ç, ENN ¸ðÇüÀº ÀÏ´Ü°Ô ÇÒ¼±¿ªÀüÆÄ(OSSBP) ¹× ź¼º¿ªÀüÆÄ(RBP)¾Ë°í¸®ÁòÀ¸·Î ÀÌ·ç¾îÁ® ÀÖ´Ù. ¸ðÇüÀÇ ÈÆ·Ã°ú °ËÁõ°úÁ¤À» ÅëÇÏ¿© RBF ½Å°æ¸Á¸ðÇüÀÌ ENN ¸ðÇüº¸´Ù ¾çÈ£ÇÑ °á°ú¸¦ ³ªÅ¸³»´Â °ÍÀ¸·Î ºÐ¼®µÇ¾ú´Ù. RBF ½Å°æ¸Á¸ðÇüÀº ÈÆ·Ã½Ã۴µ¥ ½Ã°£ÀÌ Àû°Ô µé°í, ÀÌ·ÐÀû ¹è°æÀÌ ºÎÁ·ÇÑ ¼ö¹®ÇÐÀڵ鵵 ½±°Ô »ç¿ëÇÒ ¼ö ÀÖ´Â ½Å°æ¸Á¸ðÇüÀÌ´Ù. |
|
| In this study, Radial Basis Function(RBF) Neural Networks Model, a kind of Hybrid Neural Networks was applied to hydrological forecasting in a small watershed. RBF Neural Networks Model has four kinds of parameters in it and consists of unsupervised and supervised training patterns. And Gaussian Kernel Function(GKF) was used among many kinds of Radial Basis Functions(RBFs). K-Means clustering algorithm was applied to optimize centers and widths which ate the parameters of GKF. The parameters of RBF Neural Networks Model such as centers, widths weights and biases were determined by the training procedures of RBF Neural Networks Model. And, with these parameters the validation procedures of RBF Neural Networks Model were carried out. RBF Neural Networks Model was applied to Wi-Stream basin which is one of the IHP Representative basins in South Korea. 10 rainfall events were selected for training and validation of RBF Neural Networks Model. The results of RBF Neural Networks Model were compared with those of Elman Neural Networks(ENN) Model. ENN Model is composed of One Step Secant BackPropagation(OSSBP) and Resilient BackPropagation(RBP) algorithms. RBF Neural Networks shows better results than ENN Model. RBF Neural Networks Model spent less time for the training of model and can be easily used by the hydrologists with little background knowledge of RBF Neural Networks Model. |
| |
| Ű¿öµå |
| ¹Ý°æ±âÃÊÇÔ¼ö;K-Means ±ºÁý¾Ë°í¸®Áò;°¡¿ì½ºÇÙÇÔ¼ö;Áß½É;Æø;¼ö¹®ÇÐÀû ¿¹Ãø; |
| |
|
|
 |
|
Çѱ¹¼öÀÚ¿øÇÐȸ³í¹®Áý / v.34, no.4, 2001³â, pp.303-316
Çѱ¹¼öÀÚ¿øÇÐȸ
ISSN : 1226-6280
UCI : G100:I100-KOI(KISTI1.1003/JNL.JAKO200111920731355)
¾ð¾î : Çѱ¹¾î |
|
| ³í¹® Á¦°ø : KISTI Çѱ¹°úÇбâ¼úÁ¤º¸¿¬±¸¿ø |
|
|
|
|
|
|