• 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¸Åë½ÅÇÐȸ ³í¹®Áö (Journal of the Korea Institute of Information and Communication Engineering)

Çѱ¹Á¤º¸Åë½ÅÇÐȸ ³í¹®Áö (Journal of the Korea Institute of Information and Communication Engineering)

Current Result Document : 36 / 91 ÀÌÀü°Ç ÀÌÀü°Ç   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) ·¹ÀÌºí ¸èÁýÇÕ ºÐ·ù¿Í ´ÙÁßŬ·¡½º È®·üÃßÁ¤À» »ç¿ëÇÑ ´Ü¹éÁú ¼¼Æ÷³» À§Ä¡ ¿¹Ãø
¿µ¹®Á¦¸ñ(English Title) Prediction of Protein Subcellular Localization using Label Power-set Classification and Multi-class Probability Estimates
ÀúÀÚ(Author) Áö»ó¹®   Sang-mun Chi  
¿ø¹®¼ö·Ïó(Citation) VOL 18 NO. 10 PP. 2562 ~ 2570 (2014. 10)
Çѱ۳»¿ë
(Korean Abstract)
´Ü¹éÁúÀÇ ±â´ÉÀ» À¯ÃßÇÒ ¼ö ÀÖ´Â Áß¿äÇÑ Á¤º¸ÁßÀÇ Çϳª´Â ´Ü¹éÁúÀÌ Á¸ÀçÇÏ´Â ¼¼Æ÷³» À§Ä¡ÀÌ´Ù. ÃÖ±Ù¿¡´Â ÇϳªÀÇ ´Ü¹éÁúÀÌ µ¿½Ã¿¡ Á¸ÀçÇÏ´Â ¿©·¯ ¼¼Æ÷³» À§Ä¡¸¦ ¿¹ÃøÇÏ´Â ¿¬±¸°¡ È°¹ßÇÏ´Ù. º» ³í¹®¿¡¼­´Â ´Ü¹éÁúÀÌ Á¸ÀçÇÏ´Â ¼¼Æ÷³»ÀÇ ´ÙÁßÀ§Ä¡¸¦ ¿¹ÃøÇϱâ À§Çؼ­ ·¹ÀÌºí ¸èÁýÇÕ ¹æ¹ýÀ» °³¼±ÇÑ´Ù. ·¹ÀÌºí ¸èÁýÇÕ ¹æ¹ýÀ¸·Î ºÐ·ùÇÑ ´ÙÁßÀ§Ä¡µéÀ» ¿¹Ãø È®·ü¿¡ µû¶ó °áÇÕÇÏ¿© ÃÖÁ¾ÀûÀÎ ´ÙÁß·¹À̺í·Î ºÐ·ùÇÑ´Ù. °¢ ´ÙÁßÀ§Ä¡¿¡ ´ëÇÑ Á¤È®ÇÑ È®·üÀû ±â¿©¸¦ ±¸Çϱâ À§ÇÏ¿© ½Öº° ºñ±³¿Í ¿À·ùÁ¤Á¤ Ãâ·ÂÄڵ带 »ç¿ëÇÑ ´ÙÁßŬ·¡½º È®·üÃßÁ¤ ¹æ¹ýÀ» Àû¿ëÇÏ¿´´Ù. ´Ü¹éÁú ¼¼Æ÷³» À§Ä¡ ¿¹Ãø ½ÇÇè¿¡ Á¦¾ÈÇÑ ¹æ¹ýÀ» Àû¿ëÇÏ¿© ¼º´ÉÀÌ Çâ»óµÊÀ» º¸¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
One of the important hints for inferring the function of unknown proteins is the knowledge about protein subcellular localization. Recently, there are considerable researches on the prediction of subcellular localization of proteins which simultaneously exist at multiple subcellular localization. In this paper, label power-set classification is improved for the accurate prediction of multiple subcellular localization. The predicted multi-labels from the label power-set classifier are combined with their prediction probability to give the final result. To find the accurate probability estimates of multi-classes, this paper employs pair-wise comparison and error-correcting output codes frameworks. Prediction experiments on protein subcellular localization show significant performance improvement.
Å°¿öµå(Keyword) ´Ü¹éÁú ¼¼Æ÷³» À§Ä¡   ·¹ÀÌºí ¸èÁýÇÕ ºÐ·ù   ´ÙÁßŬ·¡½º È®·üÃßÁ¤   ½Öº° ºñ±³   ¿À·ùÁ¤Á¤ Ãâ·ÂÄڵ堠 Protein subcellular localization   label power-set classification   multi-class probability estimates   pair-wise comparison   error-correcting output codes  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå