• 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 : 4 / 8

ÇѱÛÁ¦¸ñ(Korean Title) DPESS: ÀÓº£µù °ø°£ Åë°è¸¦ ÀÌ¿ëÇÑ ÁÖ°£ À§¼º À̹ÌÁö ±â¹ÝÀÇ Àα¸ Åë°èÇÐÀû ¼Ó¼º ¿¹Ãø
¿µ¹®Á¦¸ñ(English Title) DPESS: Daytime Satellite Imagery-based Prediction of Demographic Attributes Using Embedding Spatial Statistics
ÀúÀÚ(Author) Â÷ÇöÁö   ÇѼº¿ø   ¾Èµ¿Çö   ¹Ú¼º¿ø   Â÷¹Ì¿µ   Hyunji Cha   Sungwon Han   Donghyun Ahn   Sungwon Park   Meeyoung Cha  
¿ø¹®¼ö·Ïó(Citation) VOL 47 NO. 08 PP. 0742 ~ 0747 (2020. 08)
Çѱ۳»¿ë
(Korean Abstract)
À§¼º À̹ÌÁö¸¦ ÀÌ¿ëÇÏ¿© »çȸ °æÁ¦Àû ÁöÇ¥·Î È°¿ëµÇ´Â Àα¸ Åë°è¸¦ ¿¹ÃøÇϰųª ºÐ¼®ÇÏ´Â ¿¬±¸°¡ È°¹ßÈ÷ ÁøÇàµÇ°í ÀÖ´Ù. º» ¿¬±¸¿¡¼­´Â ½ÉÃþ ½Å°æ¸Á ¸ðµ¨À» ±â¹ÝÀ¸·Î ÁÖ°£ À§¼º À̹ÌÁö¸¦ ÀÌ¿ëÇÏ¿© ƯÁ¤ Áö¿ªÀÇ Àα¸ Åë°èÇÐÀû ¼Ó¼º °ªÀ» ¿¹ÃøÇϱâ À§ÇÑ »õ·Î¿î Á¢±Ù¹ýÀ» Á¦½ÃÇÑ´Ù. ÃÑ 4´Ü°è·Î ÀÌ·ç¾îÁø DPESS ¸ðµ¨Àº Á¤º¸ÀÇ ¼Õ½Ç ¾øÀÌ ¸¹Àº ¼öÀÇ ÀÔ·Â À§¼º À̹ÌÁö¸¦ °íÁ¤ ±æÀÌÀÇ º¤ÅÍ·Î ¿ä¾àÇÑ´Ù. ÀÌ´Â ÀüÀÌ ÇнÀ ¹× ÀÓº£µù °ø°£ Åë°è¿Í °°Àº °íÀ¯ÇÑ ±â¼ú·Î ÀÎÇØ °¡´ÉÇÏ´Ù. ¿¬±¸ °á°ú, Àα¸ ¹Ðµµ(ɲÉÖ=0.94), 15-29¼¼ ±×·ì Àα¸¼ö(0.80), °íµîÇб³ Á¹¾÷ Àα¸¼ö(0.79), °¡±¸´ç ÃÑ ±¸¸Å·Â(0.80)°ú °°Àº ´Ù¾çÇÑ Àα¸ Åë°èÇÐÀû ¿ä¼Ò °ªÀ» À§¼º À̹ÌÁö¸¸À¸·Îµµ È¿°úÀûÀ¸·Î ¿¹ÃøÇÒ ¼ö ÀÖ´Ù. ÇÑÆí, º» ¿¬±¸¸¦ ´Ù¸¥ ±¹°¡¿¡ Àû¿ëÇϱâ À§Çؼ­´Â Ãß°¡ÀûÀÎ ¿¬±¸°¡ ÇÊ¿äÇÒ °ÍÀ¸·Î »ç·áµÈ´Ù.
¿µ¹®³»¿ë
(English Abstract)
Studies are being actively conducted to predict or analyze demographics used as socioeconomic factors using satellite images. We present a new approach, called DPESS, for estimating demographic attributes from daytime satellite imagery based on a deep neural network model. The four steps of the DPESS summarize any number of input images into a fixed-length embedded vector without a considerable loss of information, which is possible because of its unique structure and technique like transfer learning and embedded spatial statistics. Our extensive validation demonstrates that the DPESS model can predict various advanced demographics such as population density (ɲÉÖ =0.94), population count by age group (0.80), population count by education degree (0.79), and total purchase amount per household (0.80). We discuss future applications of this method in terms of applying our algorithm to other countries.
Å°¿öµå(Keyword) À§¼º À̹ÌÁö   À§¼º¿µ»ó   µö·¯´×   ÀÓº£µù   Àα¸Åë°è   ÁÖ¼ººÐºÐ¼®   µµ½ÃÈ­   satellite imagery   embedding   demographics   deep learning   urbanization   principle component analysis  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå