Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ
Current Result Document : 1 / 4
´ÙÀ½°Ç
ÇѱÛÁ¦¸ñ(Korean Title) |
µ¥ÀÌÅÍ ºÒ±ÕÇü°ú ÃøÁ¤ ¿ÀÂ÷¸¦ °í·ÁÇÑ »ýºÐÇؼº ¼¶À¯ ÀÎÀå °½Åµµ ¿¹Ãø ¸ðµ¨ °³¹ß |
¿µ¹®Á¦¸ñ(English Title) |
The Development of Biodegradable Fiber Tensile Tenacity and Elongation Prediction Model Considering Data Imbalance and Measurement Error |
ÀúÀÚ(Author) |
ÇÑ¿µÁø
Á¶ÀÎÈÖ
Young-Jin Han
In-Whee Joe
¾çÀ¯Áø
Àå°æ¹è
±èÇöÁö
¼Û°æÁÖ
ÀÓ¼¼Áø
¼ÈÁ¤
Yang Yu Jin
Jang Kyung Bae
Kim Hyun Ji
Song Gyung Ju
Lim Se Jin
Seo Hwa Jeong
¹ÚÁøÈ¿
±è¼ºÈñ
À±ÁÖ»ó
Park Jin Hyo
Kim Sung-Hee
Youn Joosang
¹Ú¼¼Âù
±è´ö¿±
¼°º¹
ÀÌ¿ìÁø
Se-Chan Park
Deok-Yeop Kim
Kang-Bok Seo
Woo-Jin Lee
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 11 NO. 12 PP. 0489 ~ 0498 (2022. 12) |
Çѱ۳»¿ë (Korean Abstract) |
ÃÖ±Ù ³ëµ¿ Áý¾àÀûÀÎ ¼º°ÝÀÇ ¼¶À¯ »ê¾÷¿¡¼´Â ÀΰøÁö´ÉÀ» ÅëÇØ ¼¶À¯ ¹æ»ç °øÁ¤¿¡ µé¾î°¡´Â ºñ¿ëÀ» ÁÙÀÌ°í Ç°ÁúÀ» ÃÖÀûÈÇÏ·Á°í ½Ãµµ ÇÏ°í ÀÖ´Ù. ±×·¯³ª ¼¶À¯ ¹æ»ç °øÁ¤Àº µ¥ÀÌÅÍ ¼öÁý¿¡ ÇÊ¿äÇÑ ºñ¿ëÀÌ Å©°í ü°èÀûÀÎ µ¥ÀÌÅÍ ¼öÁý ¹× ó¸® ½Ã½ºÅÛÀÌ ºÎÁ·ÇÏ¿© ÃàÀûµÈ µ¥ÀÌÅ;çÀÌ Àû´Ù. ¶Ç ¹æ»ç ¸ñÀû¿¡ µû¶ó ƯÁ¤ÇÑ º¯¼ö¿¡¸¸ º¯È¸¦ ÁØ µ¥ÀÌÅ͸¸À» ¿ì¼±À¸·Î ¼öÁýÇÏ¿© µ¥ÀÌÅÍ ºÒ±ÕÇüÀÌ ¹ß»ýÇϸç, ¹°¼º ÃøÁ¤ ȯ°æÀÇ Â÷ÀÌ·Î ÀÎÇØ µ¿ÀÏ ¹æ»ç Á¶°Ç¿¡¼ ¼öÁýµÈ »ùÇà °£¿¡µµ ¿ÀÂ÷°¡ Á¸ÀçÇÑ´Ù. ÀÌ·¯ÇÑ µ¥ÀÌÅÍ Æ¯¼ºµéÀ» °í·ÁÇÏÁö ¾Ê°í ÀΰøÁö´É ¸ðµ¨¿¡ È°¿ëÇÒ °æ¿ì °úÀûÇÕ°ú ¼º´É ÀúÇÏ µîÀÇ ¹®Á¦°¡ ¹ß»ýÇÒ ¼ö ÀÖ´Ù. µû¶ó¼ º» ³í¹®¿¡¼´Â ¹æ»ç °øÁ¤ µ¥ÀÌÅÍ Æ¯¼ºÀ» °í·ÁÇÑ ÀÌ»óÄ¡ ó¸® ±â¹ý°ú µ¥ÀÌÅÍ Áõ° ±â¹ýÀ» Á¦¾ÈÇÑ´Ù. ±×¸®°í À̸¦ ±âÁ¸ ÀÌ»óÄ¡ ó¸® ±â¹ý ¹× µ¥ÀÌÅÍ Áõ° ±â¹ý°ú ºñ±³ÇÏ¿© Á¦¾ÈÇÑ ±â¹ýÀÌ ¹æ»ç °øÁ¤ µ¥ÀÌÅÍ¿¡ ´õ ÀûÇÕÇÔÀ» º¸ÀδÙ. ¶Ç ¿øº» µ¥ÀÌÅÍ¿Í Á¦¾ÈÇÑ ±â¹ýµé·Î ó¸®µÈ µ¥ÀÌÅ͸¦ ´Ù¾çÇÑ ¸ðµ¨¿¡ Àû¿ëÇÏ¿© ºñ±³ÇÔÀ» ÅëÇØ Á¦¾ÈÇÑ ±â¹ýµéÀ» »ç¿ëÇÑ ¸ðµ¨µéÀÌ ±×·¸Áö ¾ÊÀº ¸ðµ¨µé¿¡ ºñÇØ ÀÎÀå °½Åµµ ¿¹Ãø ¸ðµ¨ÀÇ ¼º´ÉÀÌ °³¼±µÊÀ» º¸ÀδÙ. |
¿µ¹®³»¿ë (English Abstract) |
Recently, the textile industry, which is labor-intensive, is attempting to reduce process costs and optimize quality through artificial intelligence. However, the fiber spinning process has a high cost for data collection and lacks a systematic data collection and processing system, so the amount of accumulated data is small. In addition, data imbalance occurs by preferentially collecting only data with changes in specific variables according to the purpose of fiber spinning, and there is an error even between samples collected under the same fiber spinning conditions due to difference in the measurement environment of physical properties. If these data characteristics are not taken into account and used for AI models, problems such as overfitting and performance degradation may occur. Therefore, in this paper, we propose an outlier handling technique and data augmentation technique considering the characteristics of the spinning process data. And, by comparing it with the existing outlier handling technique and data augmentation technique, it is shown that the proposed technique is more suitable for spinning process data. In addition, by comparing the original data and the data processed with the proposed method to various models, it is shown that the performance of the tensile tenacity and elongation prediction model is improved in the models using the proposed methods compared to the models not using the proposed methods. |
Å°¿öµå(Keyword) |
±â°èÇнÀ
½ºÄÉÀϸµ
SMOTE
¶óÀÌÆ® GBM
ºÒ±ÕÇü ºÐ·ù
Machine Learning
Scaling
SMOTE
Light GBM
Imbalanced Classification
¾çÀÚ ÄÄÇ»ÅÍ
°æ·® ºí·Ï ¾ÏÈ£
SPARKLE
Grover Search Algorithm
Quantum Computer
Lightweight Block Cipher
SPARKLE
Grover Search Algorithm
¸ÞŸµ¥ÀÌÅÍ
FAIR¿øÄ¢
µ¥ÀÌÅÍ °ü¸®
Metadata
FAIR Principle
Data Managements
µ¥ÀÌÅÍ ºÒ±ÕÇü
ÀÌ»óÄ¡ ó¸®
µ¥ÀÌÅÍ Áõ°
ÀÎÀå °½Åµµ
»ýºÐÇؼº ¼¶À¯(PLA)
Data Imbalance
Outlier Handling
Data Augmentation
Tensile Tenacity and Tensile Elongation
Biodegradable Fiber(PLA)
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|