• 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¸°úÇÐȸ ÄÄÇ»ÆÃÀÇ ½ÇÁ¦ ³í¹®Áö (KIISE Transactions on Computing Practices)

Á¤º¸°úÇÐȸ ÄÄÇ»ÆÃÀÇ ½ÇÁ¦ ³í¹®Áö (KIISE Transactions on Computing Practices)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ¼Ò°í±â À°Áú µî±Þ ¿¹ÃøÀ» À§ÇÑ ºÐ·ù ¾Ë°í¸®ÁòÀÇ ¼º´É ¿¬±¸
¿µ¹®Á¦¸ñ(English Title) Performance Study of Classification Algorithms for the Prediction of Beef Quality Grade
ÀúÀÚ(Author) ±è½ÂÈñ   ¹®Ã¶ÇÑ   ÃÖ¼ºÁØ   ¹ÎÁر⠠ Seung-Hee Kim   Cheolhan Moon   Sungjun Choe   Jun-Ki Min  
¿ø¹®¼ö·Ïó(Citation) VOL 26 NO. 06 PP. 0261 ~ 0267 (2020. 06)
Çѱ۳»¿ë
(Korean Abstract)
Ãà»ê¹° µî±ÞÁ¦¿¡µµ ºÒ±¸ÇÏ°í Ãà»ê¹° Ç°Áú °øÁ¤ Æò°¡ÀÇ Çʿ伺°ú ¸íÈ®¼º Á¦°í°¡ Áö¼ÓÀûÀ¸·Î ´ëµÎµÇ°í ÀÖ´Ù. º» ³í¹®¿¡¼­´Â ¼Ò°¡ µµÃàµÇ±â ÀüÀÇ ÀÌ·Â Á¤º¸¸¦ ÀÌ¿ëÇÑ ´Ù¾çÇÑ ±â°è ÇнÀ ¾Ë°í¸®Áò¿¡ Àû¿ëÇÏ¿© ¼Ò°í±âÀÇ À°Áú µî±ÞÀ» ¿¹ÃøÇÏ¿´´Ù. À̸¦ À§ÇÏ¿©, ÇǾ »ó°ü°è¼ö¸¦ ÀÌ¿ëÇÏ¿© ¼ÒÀÇ ÀÌ·ÂÁ¤º¸·ÎºÎÅÍ °¡Àå °ü·Ã ³ôÀº ¼Ó¼ºµéÀ» ÃßÃâÇÏ¿´À¸¸ç ³ªÀÌºê º£ÀÌÁî, Àΰø ½Å°æ¸Á, ·£´ý Æ÷·¹½ºÆ®, ·ÎÁö½ºÆ½ ȸ±Í, ÀÇ»ç°áÁ¤³ª¹«, kNN, SVM ±â¹ýÀ» Àû¿ëÇÏ¿´´Ù. ¿¹Ãø °á°ú¸¦ ºñ±³ÇÏ°í ÃøÁ¤ÀÇ Á¤È®µµ¸¦ °ËÁõÇÑ °á°ú kNN ±â¹ý¿¡¼­ 97.2%ÀÇ °¡Àå ¿ì¼öÇÑ ¿¹Ãø °á°ú°¡ µµÃâµÇ¾ú´Ù. ±âÁ¸ÀÇ ¿¬±¸°¡ ÃÊÀ½ÆÄ È­»ó À̹ÌÁö¿¡ SFTA ¹× AdaBoost¸¦ »ç¿ëÇÏ´Â ¿¹Ãø ¹æ¹ý µîÀ» »ç¿ëÇÑ °Í°ú ´Þ¸® º» ¿¬±¸´Â µµÃàÇϱâ Àü ¼ÒÀÇ ÀÌ·Â Á¤º¸¸¸À» È°¿ëÇÏ¿© À°Áú µî±ÞÀ» ¿¹ÃøÇÏ¿´´Ù´Âµ¥ Å« Àǹ̰¡ ÀÖ´Ù.
¿µ¹®³»¿ë
(English Abstract)
Despite the grading system used for livestock, the need for a livestock quality process assessment and increased clarity has continually been raised. In this paper, we predict beef quality grades by applying machine learning algorithms with the history information of the individual cows before slaughter. To do so, we first selected the most related features from the individual cows¡¯ historical information by using the Pearson correlation and next applied Naïve Bayes, artificial neural networks, random forests, logistic regression, decision trees, kNN, and SVM methods. As the result of their accuracy by comparison with prediction results, the kNN method was demonstrated to have the highest accuracy at 97.2%. Unlike previous studies that used SFTA and AdaBoost on ultrasound imaging, this study has major significance in predicting meat grades using the historical information of cows only before slaughter.
Å°¿öµå(Keyword) ±â°è ÇнÀ   ºÐ·ù±â¹ý   À°Áú µî±Þ ¿¹Ãø   Ãà»ê¹° µî±Þ   machine learning   classification   beef quality prediction   livestock quality grade  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå