• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹Á¤º¸°úÇÐȸ ³í¹®Áö > Á¤º¸°úÇÐȸ ÄÄÇ»ÆÃÀÇ ½ÇÁ¦ ³í¹®Áö (KIISE Transactions on Computing Practices)

Á¤º¸°úÇÐȸ ÄÄÇ»ÆÃÀÇ ½ÇÁ¦ ³í¹®Áö (KIISE Transactions on Computing Practices)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) DARNN ±â¹Ý ¼­¿ï½Ã ÇàÁ¤±¸¿ªº° COVID-19 È®»ê ¿¹Ãø ¸ðµ¨
¿µ¹®Á¦¸ñ(English Title) DARNN-Based Prediction Model for COVID-19 Diffusion for Each Administrative District in Seoul
ÀúÀÚ(Author) ¹Ú¿¬Àç   Àü¿µÇ¥   ÀÌÈ«·¡   Á¶¿µ·¡   Yeonjae Park   Young Pyo Jun   Hongrae Lee   Young-Rae Cho  
¿ø¹®¼ö·Ïó(Citation) VOL 27 NO. 11 PP. 0510 ~ 0518 (2021. 11)
Çѱ۳»¿ë
(Korean Abstract)
2020³â ÇÑÇص¿¾È ¼­¿ï½Ã¿¡´Â Äڷγª¹ÙÀÌ·¯½º È®ÁøÀÚ°¡ Áö¼ÓÀûÀ¸·Î ¹ß»ýÇÏ¿´´Ù. ¼­¿ï½Ã °¢ ÇàÁ¤ ±¸¿ª¸¶´Ù Äڷγª¹ÙÀÌ·¯½º È®ÁøÀÚÀÇ ÁÖ ¹ß»ý ¿øÀÎÀÌ ´Ù¸¦ ¼ö ÀÖÁö¸¸, °øÅëÀûÀÎ ¿äÀεµ Á¸ÀçÇÑ´Ù. ÀÌ ¹ß»ý ¿øÀÎÀº ¼Ò±Ô¸ð °¨¿° ¿äÀΰú Áý´Ü °¨¿° ¿äÀÎÀ¸·Î ±¸ºÐµÈ´Ù. º» ¿¬±¸¿¡¼­´Â ´Ù¾çÇÑ °¨¿° ¿äÀο¡ ´ëÇÑ º¯¼öµéÀ» ÃÖÀûÈ­ÇÏ´Â DARNN (Dual-Stage Attention-Based Recurrent Neural Network) ±â¹ýÀ» »ç¿ëÇÏ¿© COVID-19 È®»ê ¿¹Ãø ¸ðµ¨À» Á¦½ÃÇÑ´Ù. 2020³â ¼­¿ï½ÃÀÇ °¢ ÇàÁ¤±¸¿ªº° Äڷγª¹ÙÀÌ·¯½º È®ÁøÀÚ ¼ö¿¡ ´ëÇÑ ½Ã°è¿­ µ¥ÀÌÅÍ¿Í È®ÁøÀÚ ¹ß»ý ÆÐÅÏ¿¡ ´ëÇÑ ÇàÁ¤±¸¿ªµé »çÀÌÀÇ »ó°ü°ü°è, °¢ ÇàÁ¤±¸¿ªº° À¯µ¿Àα¸ µîÀÇ Á¤º¸¸¦ È°¿ëÇÑ ½ÇÇè¿¡¼­, Á¦¾ÈµÈ DARNN ¸ðµ¨Àº ±âÁ¸¿¡ ³Î¸® È°¿ëµÇ´Â LSTM (Long Short-Term Memory) ¸ðµ¨°ú ºñ±³ÇÏ¿© ¿ì¼öÇÑ ¿¹Ãø Á¤È®µµ¸¦ º¸¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
In 2020, several coronavirus confirmed cases had been reported in Seoul. Although each administrative district in Seoul might have distinct causes of coronavirus infection, there also exist common causes between administrative districts. The cause of this occurrence can be divided into small-scale infection and mass infection. In this study, we propose a model for predicting COVID-19 diffusion using the DARNN (Dual-Stage Attention-Based Recurrent Neural Network) technique that optimizes the variables related to various causes of infection. In the experiment using the time-series data of the number of confirmed cases, the correlations between administrative districts in respect to the confirmation patterns, and the floating populations in each administrative district, the proposed DARNN model outperformed the widely used LSTM (Long Short-Term Memory) model in terms of prediction accuracy.
Å°¿öµå(Keyword) COVID-19   Äڷγª ¹ÙÀÌ·¯½º   È®»ê ¿¹Ãø ¸ðµ¨   DARNN   µö·¯´×   »ó°ü°ü°è ºÐ¼®   COVID-19   coronavirus   diffusion prediction model   DARNN   deep learning   correlation analysis  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå