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

»çÀÌÆ®¸Ê

Loading..

Please wait....

Çмú´ëȸ ÇÁ·Î½Ãµù

Ȩ Ȩ > ¿¬±¸¹®Çå > Çмú´ëȸ ÇÁ·Î½Ãµù > Çѱ¹Á¤º¸Åë½ÅÇÐȸ Çмú´ëȸ > 2018³â Ãß°èÇмú´ëȸ

2018³â Ãß°èÇмú´ëȸ

Current Result Document : 9 / 34 ÀÌÀü°Ç ÀÌÀü°Ç   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) µ¥ÀÌÅÍ ¿À¡¤°áÃø Àú°¨ Á¤Á¦ ¾Ë°í¸®Áò
¿µ¹®Á¦¸ñ(English Title) Data Cleansing Algorithm for reducing Outlier
ÀúÀÚ(Author) ÀÌÁ¾¿ø   ±èÈ£¼º   ȲöÇö   °­ÀνĠ  Á¤È¸°æ   Jongwon Lee   Hosung Kim   Chulhyun Hwang   Inshik Kang   Hoekyung Jung  
¿ø¹®¼ö·Ïó(Citation) VOL 22 NO. 02 PP. 0342 ~ 0344 (2018. 10)
Çѱ۳»¿ë
(Korean Abstract)
º» ³í¹®¿¡¼­´Â ±âÁ¸ ¿À¡¤°áÃø µ¥ÀÌÅÍ ºÐ¼® ±â¹ýÀÎ Æò±Õ ´ëü¹ý, »ó°ü°è¼ö ¼öÄ¡ºÐ¼®, ±×·¡ÇÁ »ó°ü¼º ºÐ¼® ¹× Åë°è Àü¹®°¡ ºÐ¼® µî Åë°èÀû ¹æ¹ýÀ¸·Î ´ëü °¡´É¼ºÀ» Á¶»çÇÏ¿© Á¤¼öó¸® °øÁ¤¿¡¼­ °èÃøµÇ´Â °¢Á¾ ÀÌ»ó µ¥ÀÌÅ͸¦ Á¤Á¦Çϱâ À§ÇÑ ¹æ¹ýÀ» ´Ù¾çÇÑ ºÐ¼®¿¬±¸·Î ÁøÇàÇÏ¿´´Ù. ¶ÇÇÑ ¹° Á¤º¸ µ¥ÀÌÅÍ ¿À¡¤°áÃø Àú°¨ Á¤Á¦ ¾Ë°í¸®ÁòÀÇ ½Å·Ú¼º ¹× °ËÁõ¿¡ ÀÖ¾î ºÐÀ§¼ö ÆÐÅÏ°ú µö·¯´× ±â¹ÝÀÇ LSTM ¾Ë°í¸®ÁòÀ¸·Î µ¿ÀÛÇÏ´Â ½Ã½ºÅÛÀ» ¸ðµ¨¸µÇÏ°í, Keras, Theano, Tensorflow µîÀÇ ¿ÀÇ ¼Ò½º ¶óÀ̺귯¸®·Î ±¸ÇöÇÒ ¼ö Àִ ü°è¸¦ ¿¬±¸ÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
This paper shows the possibility to substitute statistical methods such as mean imputation, correlation coefficient analysis, graph correlation analysis for the proposed algorithm, and replace statistician for processing various abnormal data measured in the water treatment process with it. In addition, this study aims to model a data-filtering system based on a recent fractile pattern and a deep learning-based LSTM algorithm in order to improve the reliability and validation of the algorithm, using the open-sourced libraries such as KERAS, THEANO, TENSORFLOW, etc.
Å°¿öµå(Keyword) Cleansing Algorithm   CNN   Deep Learning   LSTM  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå