• 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¸Ã³¸®ÇÐȸ ³í¹®Áö > Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ´Ü¹éÁú ±â´É ¿¹Ãø ¸ðµ¨ÀÇ ÁÖ¿ä µö·¯´× ¸ðµ¨ ºñ±³ ½ÇÇè
¿µ¹®Á¦¸ñ(English Title) Comparison of Deep Learning Models Using Protein Sequence Data
ÀúÀÚ(Author) È«´Ù¿µ   ±è°¡¿µ   ±èÇöÈñ   Da Young Hong   Ga Yeong Kim   Hyon Hee Kim   ÀÌÁ¤¹Î   ÀÌÇö   Jeung Min Lee   Hyun Lee  
¿ø¹®¼ö·Ïó(Citation) VOL 11 NO. 06 PP. 0245 ~ 0254 (2022. 06)
Çѱ۳»¿ë
(Korean Abstract)
´Ü¹éÁúÀº ¸ðµç »ý¸í È°µ¿ÀÇ ±âº» ´ÜÀ§À̸ç, À̸¦ ÀÌÇØÇÏ´Â °ÍÀº »ý¸í Çö»óÀ» ¿¬±¸ÇÏ´Â µ¥ ÇʼöÀûÀÌ´Ù. Àΰø½Å°æ¸ÁÀ» ÀÌ¿ëÇÑ ±â°èÇнÀ ¹æ¹ý·ÐÀÌ ´ëµÎµÈ ÀÌÈÄ·Î ¸¹Àº ¿¬±¸ÀÚµéÀÌ ´Ü¹éÁú ¼­¿­¸¸À» »ç¿ëÇÏ¿© ´Ü¹éÁúÀÇ ±â´ÉÀ» ¿¹ÃøÇÏ°íÀÚ ÇÏ¿´´Ù. ¸¹Àº Á¶ÇÕÀÇ µö·¯´× ¸ðµ¨ÀÌ Çа迡 º¸°íµÇ¾úÀ¸³ª ±× ¹æ¹ýÀº Á¦°¢°¢À̸ç Á¤ÇüÈ­µÈ ¹æ¹ý·ÐÀÌ ¾ø°í, °¢±â ´Ù¸¥ µ¥ÀÌÅÍ¿¡ ¸ÂÃçÁ®ÀÖ¾î ¾î¶² ¾Ë°í¸®ÁòÀÌ ´õ ´Ü¹éÁú µ¥ÀÌÅ͸¦ ´Ù·ç´Â µ¥ ÀûÇÕÇÑÁö Á÷Á¢ ºñ±³ºÐ¼® µÈ ÀûÀÌ ¾ø´Ù. º» ³í¹®¿¡¼­´Â ´Ü¹éÁúÀÇ ±â´ÉÀ» ¿¹ÃøÇÏ´Â À¶ÇÕ ºÐ¾ß¿¡¼­ °¡Àå ¸¹ÀÌ »ç¿ëµÇ´Â ´ëÇ¥ ¾Ë°í¸®ÁòÀÎ CNN, LSTM, GRU ¸ðµ¨°ú À̸¦ ÀÌ¿ëÇÑ µÎ°¡Áö °áÇÕ ¸ðµ¨¿¡ µ¿ÀÏ µ¥ÀÌÅ͸¦ Àû¿ëÇÏ¿© °¢ ¾Ë°í¸®ÁòÀÇ ´ÜÀÏ ¸ðµ¨ ¼º´É°ú °áÇÕ ¸ðµ¨ÀÇ ¼º´ÉÀ» Á¤È®µµ¿Í ¼Óµµ¸¦ ±âÁØÀ¸·Î ºñ±³ Æò°¡ÇÏ¿´À¸¸ç ÃÖÁ¾ Æò°¡ ôµµ¸¦ ¸¶ÀÌÅ©·Î Á¤¹Ðµµ, ÀçÇöÀ², F1 Á¡¼ö·Î ³ªÅ¸³»¾ú´Ù. º» ¿¬±¸¸¦ ÅëÇØ ´Ü¼ø ºÐ·ù ¹®Á¦¿¡¼­ ´ÜÀÏ ¸ðµ¨·Î LSTMÀÇ ¼º´ÉÀÌ ÁؼöÇÏ°í, º¹ÀâÇÑ ºÐ·ù ¹®Á¦¿¡¼­´Â ´ÜÀÏ ¸ðµ¨·Î Áßø CNNÀÌ ´õ ÀûÇÕÇϸç, °áÇÕ ¸ðµ¨·Î CNN-LSTMÀÇ ¿¬°è ¸ðµ¨ÀÌ »ó´ëÀûÀ¸·Î ´õ ¿ì¼öÇÔÀ» È®ÀÎÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
Proteins are the basic unit of all life activities, and understanding them is essential for studying life phenomena. Since the emergence of the machine learning methodology using artificial neural networks, many researchers have tried to predict the function of proteins using only protein sequences. Many combinations of deep learning models have been reported to academia, but the methods are different and there is no formal methodology, and they are tailored to different data, so there has never been a direct comparative analysis of which algorithms are more suitable for handling protein data. In this paper, the single model performance of each algorithm was compared and evaluated based on accuracy and speed by applying the same data to CNN, LSTM, and GRU models, which are the most frequently used representative algorithms in the convergence research field of predicting protein functions, and the final evaluation scale is presented as Micro Precision, Recall, and F1-score. The combined models CNN-LSTM and CNN-GRU models also were evaluated in the same way. Through this study, it was confirmed that the performance of LSTM as a single model is good in simple classification problems, overlapping CNN was suitable as a single model in complex classification problems, and the CNN-LSTM was relatively better as a combination model.
Å°¿öµå(Keyword) ¿Â¶óÀÎ Çൿ Á¤º¸   ±¸¸Å ±â·Ï Á¤º¸   VAE ±â¹Ý Ãßõ   ÀáÀç ¿äÀÎ ÃßÃâ   Online Behavior Log   Purchase History   VAE-based Recommendation   Extracting Latent Space   CNN   LSTM   GRU   °áÇÕ ¸ðµ¨   ´Ü¹éÁú ¼­¿­   Combined Model   Protein Sequence  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå