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

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ÇÐȸÁö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ÇÐȸÁö > µ¥ÀÌÅͺ£À̽º ¿¬±¸È¸Áö(SIGDB)

µ¥ÀÌÅͺ£À̽º ¿¬±¸È¸Áö(SIGDB)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) Attention LSTM°ú SHAPÀ» »ç¿ëÇÑ ¼³¸í °¡´ÉÇÑ COVID-19 È®ÁøÀÚ ¼ö ¿¹Ãø ±â¹ý
¿µ¹®Á¦¸ñ(English Title) Explainable COVID-19 Forecasting Scheme Using Attention LSTM and SHAP
ÀúÀÚ(Author) ³ëÀ±¾Æ   Á¤½Â¿ø   ¹®Àç¿í   ȲÀÎÁØ   Yoona Noh   Seungwon Jung   Jaeuk Moon   Eenjun Hwang  
¿ø¹®¼ö·Ïó(Citation) VOL 37 NO. 02 PP. 0037 ~ 0051 (2021. 08)
Çѱ۳»¿ë
(Korean Abstract)
COVID-19ÀÇ È®»êÀ¸·Î ÀÎÇØ ¼¼°èÀûÀ¸·Î ¸¹Àº ¼Õ½ÇÀÌ º¸°íµÇ°í ÀÖ´Ù. È¿°úÀûÀÎ È®»ê ¹æÁö ´ëÃ¥À» ¼ö¸³Çϱâ À§Çؼ­´Â COVID-19 È®»ê Á¤µµÀÇ Á¤È®ÇÑ ¿¹ÃøÀÌ ÇÊ¿äÇϸç, À̸¦ À§ÇØ È®»ê ÃʱâºÎÅÍ ±â°èÀû Á¢±Ù¹ýÀ̳ª ±â°èÇнÀ ±â¹Ý Á¢±Ù¹ý µîÀ» È°¿ëÇÑ ±â¹ýµéÀÌ Á¦¾ÈµÇ¾î¿Ô´Ù. ±×·¯³ª ÃÖ±Ù ¹é½Å µµÀÔÀ¸·Î ÀÎÇÏ¿© º¯È­µÈ È®»ê ÆÐÅÏ¿¡ ÀûÇÕÇÑ ¿¹Ãø ¸ðµ¨ÀÌ ÇÊ¿äÇϸç, ±â°èÇнÀ ±â¹Ý Á¢±Ù¹ýÀ» ÅëÇØ ¿¹Ãø Á¤È®µµ´Â ³ô¾ÆÁ³À¸³ª ¸ðµ¨ÀÇ ¼³¸í¼ºÀÌ ºÎÁ·ÇÏ¿© ÃæºÐÇÑ ½Å·Ú¸¦ ÁÖÁö ¸øÇÏ´Â ½ÇÁ¤ÀÌ´Ù. ÀÌ¿¡, º» ³í¹®¿¡¼­´Â Attention LSTM(Long Short-Term Memory) ¸ðµ¨À» »ç¿ëÇÏ¿© COVID-19 È®ÁøÀÚ ¼ö¸¦ ¿¹ÃøÇÏ°í, ±× °á°ú¸¦ SHAP(SHapley Additive exPlanations)À» ÅëÇÏ¿© ºÐ¼®ÇÏ´Â ¼³¸í °¡´ÉÇÑ COVID-19 È®ÁøÀÚ ¼ö ¿¹Ãø ±â¹ýÀ» Á¦¾ÈÇÑ´Ù. ¹é½Å Á¢Á¾ µ¥ÀÌÅ͸¦ Æ÷ÇÔÇÑ COVID-19 °ü·Ã ´Ù¾çÇÑ µ¥ÀÌÅ͸¦ ¼öÁýÇÏ°í, Attention LSTM ¸ðµ¨ÀÇ ÀÔ·Â º¯¼ö·Î »ç¿ëÇÔÀ¸·Î½á ¹é½Å µµÀÔÀ¸·Î ÀÎÇÑ º¯È­¸¦ ¹Ý¿µÇÏ¿´´Ù. ´Ù¾çÇÑ ¸ðµ¨°úÀÇ ºñ±³ ½ÇÇèÀ» ÅëÇÏ¿© Á¦¾ÈÇÑ ¸ðµ¨ÀÇ ¿ì¼öÇÑ ¿¹Ãø ¼º´ÉÀ» º¸¿´À¸¸ç, SHAPÀ» ÅëÇØ ¿¹Ãø °á°ú¿¡ ´ëÇÑ ¼³¸í °¡´É¼ºÀ» ÀÔÁõÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
Due to the spread of COVID-19, many losses are being reported worldwide. In order to establish effective countermeasures to prevent the spread of COVID-19, it is necessary to accurately predict the extent of the spread of COVID-19. However, due to the recent introduction of vaccines, a forecasting model suitable for the changed diffusion pattern is needed, and although the forecasting accuracy has been improved through a machine learning-based approach, the model does not provide sufficient confidence due to the lack of explanatory properties of the model. Therefore, in this paper, we propose an explainable forecasting scheme that forecasts the number of COVID-19 confirmed cases using an Attention LSTM(Long Short-Term Memory) model and explains the analysis results using SHAP(SHapley Additive exPlanations). Changes due to introduction of vaccines were reflected by collecting various data related to COVID-19, including vaccination data, and using it as an input variable for the Attention LSTM model. Through comparative experiments with various models, we demonstrated the excellent forecasting performance of the proposed model and the explanatory capacity of the SHAP for the results.
Å°¿öµå(Keyword) Äڷγª19 ¿¹Ãø   LSTM   ¾îÅÙ¼Ç ¸ÅÄ¿´ÏÁò   SHAP   COVID-19 Forecasting   LSTM   Attention Mechanism   SHAP  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå