• 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) ¼øȯ ½Å°æ¸ÁÀ» È°¿ëÇÑ ÄÚµå º¯°æ Ãßõ ½Ã½ºÅÛÀÇ ÇнÀ ½Ã°£ ´ÜÃà ¹æ¹ý
¿µ¹®Á¦¸ñ(English Title) Reducing the Learning Time of Code Change Recommendation System Using Recurrent Neural Network
ÀúÀÚ(Author) ¹èº´ÀÏ   °­¼º¿ø   À̼±¾Æ   Byeong-il Bae   Sungwon Kang   Seonah Lee  
¿ø¹®¼ö·Ïó(Citation) VOL 47 NO. 10 PP. 0948 ~ 0957 (2020. 10)
Çѱ۳»¿ë
(Korean Abstract)
°³¹ßÀÚ¿¡°Ô ¼öÁ¤ÀÌ ÇÊ¿äÇÑ ÆÄÀÏÀ» ÃßõÇÏ´Â ½Ã½ºÅÛÀº °³¹ßÀÚÀÇ ÀÛ¾÷ ½Ã°£À» ÁÙ¿© ÁØ´Ù. ±×·¯³ª ÀÌ·± Ãßõ ½Ã½ºÅÛÀº ÀϹÝÀûÀ¸·Î ÃàÀûµÈ µ¥ÀÌÅ͸¦ ÇнÀÇÒ ¶§ ¸¹Àº ½Ã°£ÀÌ µé¸ç, ¶ÇÇÑ »õ·Î¿î µ¥ÀÌÅÍ°¡ ÃàÀûµÉ ¶§¸¶´Ù »õ·ÎÀÌ ÇнÀÇϴµ¥ ¸¹Àº ½Ã°£À» ¼Ò¸ðÇÑ´Ù. º» ¿¬±¸´Â ¼øȯ ½Å°æ¸ÁÀ» ÀÌ¿ëÇÑ ÄÚµå º¯°æ Ãßõ ½Ã½ºÅÛ(RNN-CRS)¿¡ »õ·Î¿î µ¥ÀÌÅÍ°¡ ÃàÀûµÇ¾î ÇнÀÀ» ´Ù½Ã ÇØ¾ß ÇÒ ¶§ ºÒÇÊ¿äÇÑ ÇнÀÀ» ȸÇÇÇÏ¿© ÇнÀ¿¡ µå´Â ½Ã°£À» ÁÙÀÌ´Â ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. Á¦¾È ¹æ¹ýÀÇ ½ÇÇè Æò°¡¿¡¼­ Á¦¾È ¹æ¹ýÀº µ¥ÀÌÅÍ°¡ »õ·Î ÃàÀûµÇ¾î ÇнÀ ¸ðµ¨À» ´Ù½Ã »ý¼ºÇϴµ¥ ¼Ò¿äµÇ´Â ½Ã°£À», ½ÇÇè¿¡ »ç¿ëµÈ ´Ù¼¸ °³ÀÇ Á¦Ç°µé¿¡ ´ëÇÏ¿© ½Ã°£ ´ÜÃàÀÌ Å« °æ¿ì¿¡´Â ±âÁ¸ ¿¬±¸¿¡ ºñÇØ 49.08%¢¦68.15% ´ÜÃà½ÃÄ×°í ÀÛÀº °æ¿ì¿¡´Â 10.66% ´ÜÃà½ÃÄ×´Ù.
¿µ¹®³»¿ë
(English Abstract)
Since code change recommendation systems select and recommend files that needing modifications, they help developers save time spent on software system evolution. However, these recommendation systems generally spend a significant amount of time in learning accumulated data and relearning whenever new data are accumulated. This study proposes a method to reduce the time spent on learning when using Code change Recommendation System using Recurrent Neural Network (RNN-CRS), which works by avoiding the learning that is unlikely to contribute to new knowledge. For the five products used in the experimental evaluation, our proposed method reduced the time to relearn data and re-generate a learning model by as much as 49.08%-68.15%, and by 10.66% in the least effective case, compared to the existing method.
Å°¿öµå(Keyword) µ¥ÀÌÅÍ ±â¹Ý ¼ÒÇÁÆ®¿þ¾î °øÇР  º¯°æ Ãßõ   Ãßõ ½Ã½ºÅÛ   ±â°è ÇнÀ   data-based software engineering   change recommendation   recommendation system   machine learning  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå