• 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¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) µµ½ÉÁö ±³ÅëÈ帧 ¹× ¹Ì¼¼¸ÕÁö ¿¹ÃøÀ» À§ÇÑ µö·¯´× LSTM ÇÁ·¹ÀÓ¿öÅ©
¿µ¹®Á¦¸ñ(English Title) A Deep Learning LSTM Framework for Urban Traffic Flow and Fine Dust Prediction
ÀúÀÚ(Author) ÀÌÈ«¼®   ºÎÀÌ Ä¬ ³²   ¼±Ãæ³ç   Hongsuk Yi   Khac-Hoai Nam Bui   Choong-Nyoung Seon  
¿ø¹®¼ö·Ïó(Citation) VOL 47 NO. 03 PP. 0292 ~ 0297 (2020. 03)
Çѱ۳»¿ë
(Korean Abstract)
Á¤È®ÇÏ°í ½Ã±â ÀûÀýÇÑ ¿¹ÃøÀº ½º¸¶Æ®½ÃƼÀÇ ¼º°øÀûÀÎ ÃßÁøÀ» À§ÇÑ Áß¿äÇÑ ´Ü°èÀÌ´Ù. ¸ÅÀÏ ¼öÁýµÇ´Â ±³Åë µ¥ÀÌÅÍÀÇ ±Þ°ÝÇÑ ¼ºÀåÀ¸·Î, µµ½ÉÁö¿¡¼­ ´Ü±â ±³Åë ¿¹ÃøÀ» À§ÇÑ ÃÖ±Ù ¿¬±¸´Â Àå´Ü±â¸Þ¸ð¸® LSTM(Long-Short Term Memory) ±â¹ÝÀÇ µö·¯´×À¸·Î ÁýÁߵǰí ÀÖ´Ù. ÇÏÁö¸¸ ´Ü±â (5ºÐ) LSTM ¸ðµ¨Àº ½Ç½Ã°£ ºñ¼±Çü ±³ÅëÈ帧 ¿¹Ãø¿¡´Â ÇÑ°è°¡ ÀÖ´Ù. ´õ¿íÀÌ, ±³Åë µ¥ÀÌÅÍ¿¡ ±â¹ÝÇÑ ¹Ì¼¼¸ÕÁö ¿¹ÃøÀº ¶ÇÇÑ ¸Å¿ì ½Ã±ÞÇÑ ¿¬±¸ ºÐ¾ßÀÌ´Ù. µû¶ó¼­ º» ³í¹®¿¡¼­´Â, Áß±â/Àå±â ¿¹ÃøÀ» Áö¿øÇϱâ À§ÇÑ ¸ÖƼ Ãþ LSTM ÇÁ·¹ÀÓ¿öÅ©¸¦ ¼³°èÇÏ¿´´Ù. ¶ÇÇÑ ±³Åëµ¥ÀÌÅÍ ±â¹Ý ¹Ì¼¼¸ÕÁö È帧À» ¿¹ÃøÇϱâÀ§ÇÑ ÄÁº¼·ç¼Ç ConvLSTM (Convolutional LSTM) ¸ðµ¨À» °³¹ßÇÏ¿´´Ù. ±³ÅëÈ帧 ¿¹ÃøÀ» À§ÇÏ¿© ´ëÀü½Ã Á߽ɵµ·ÎÀÇ Â÷·®°ËÁö±â VDS (Vehicle Detection System) µ¥ÀÌÅ͸¦ È°¿ëÇÏ¿´´Ù. ½ÇÇè °á°ú º» ³í¹®¿¡¼­ Á¦¾ÈÇÑ ¸ðµ¨Àº ¿ì¼öÇÑ ¿¹Ãø ¼º´ÉÀ» º¸¿©ÁÖ¾ú´Ù.
¿µ¹®³»¿ë
(English Abstract)
Accurate and timely forecasting is an essential step for the successful deployment of smart cities. With the rapid growth of traffic data collected daily, recent studies have focused on deep learning based on long-term short term memory (LSTM) for short-term traffic prediction, especially in urban areas. However, the short-term (five minutes) LSTM model is limited in the real-time nonlinear traffic flow prediction. Moreover, the fine dust prediction based on traffic data is also an emerging issue in this research area. Thus, this paper designs the multiple traffic data-based multi-input/output LSTM framework for supporting medium and long-term prediction. Additionally, a convolutional LSTM (ConvLSTM) model is developed for predicting fine dust flow based on traffic data. Regarding the experiment, we analyzed data from the Vehicle Detection System (VDS) located on major roads in Daejeon City for the evaluation. The experiment indicates promising results for the proposed approach.
Å°¿öµå(Keyword) µµ½ÉÁö ¹Ì¼¼¸ÕÁö ¿¹Ãø   deep learning   µö·¯´×   Àå´Ü±â ¸Þ¸ð¸®   ±³ÅëÈ帧 ¿¹Ãø   long short term memory   traffic flow prediction   fine dust prediction  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå