Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ÄÄÇ»ÅÍ ¹× Åë½Å½Ã½ºÅÛ
ÇѱÛÁ¦¸ñ(Korean Title) |
Áú°¨ ºÐ¼®°ú CNNÀ» ÀÌ¿ëÇÑ ÀâÀ½¿¡ °ÀÎÇÑ µÅÁö È£Èí±â Áúº´ ½Äº° |
¿µ¹®Á¦¸ñ(English Title) |
Noise-Robust Porcine Respiratory Diseases Classification Using Texture Analysis and CNN |
ÀúÀÚ(Author) |
ÃÖ¿ëÁÖ
ÀÌÁ¾¿í
¹Ú´ëÈñ
Á¤¿ëÈ
Yongju Choi
Jonguk Lee
Daihee Park
Yongwha Chung
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 07 NO. 03 PP. 0091 ~ 0098 (2018. 03) |
Çѱ۳»¿ë (Korean Abstract) |
Áý´ÜÀ¸·Î »çÀ°µÇ´Â µÅÁö ³óÀå¿¡¼ µÅÁö ¼Ò¸ð¼º ÁúȯÀÇ ÀÚµ¿ ŽÁö´Â ¸Å¿ì Áß¿äÇÑ ¹®Á¦ÀÌ´Ù. ƯÈ÷, ¹ÐÁýµÈ µ·»ç¿¡¼ »çÀ°µÇ´Â µÅÁöµéÀÇ È£Èí±â ÁúȯÀº Ãà»ê ³ó°¡ÀÇ ¸·´ëÇÑ °æÁ¦Àû ¼Õ½ÇÀ» ¾ß±âÇÏ´Â ´ëÇ¥Àû Áúº´µé Áß ÇϳªÀÌ´Ù. º» ³í¹®¿¡¼´Â ¼Ò¸® ½ÅÈ£ Çؼ®¿¡ ±â¹ÝÇÏ¿© µÅÁöÀÇ È£Èí±â ÁúȯÀ» Á¶±â ŽÁö ¹× ½Äº°ÇÏ´Â ÀâÀ½¿¡µµ °ÀÎÇÑ ½Ã½ºÅÛÀ» Á¦¾ÈÇÑ´Ù. Á¦¾ÈÇÏ´Â ½Ã½ºÅÛÀº, ¸ÕÀú 1Â÷¿øÀÇ ¼Ò¸® ½ÅÈ£¸¦ 2Â÷¿øÀÇ È¸»öÁ¶ ¿µ»óÀ¸·Î º¯È¯ÇÑ ÈÄ, DNS±â¹ýÀ¸·Î Áú°¨ Ư¡ Á¤º¸¸¦ °®´Â À̹ÌÁö¸¦ »ý¼ºÇÑ´Ù. ¸¶Áö¸·À¸·Î, À̸¦ CNN¿¡ ÀÔ·ÂÇÔÀ¸·Î½á ÀâÀ½¿¡µµ °ÀÎÇÑ µÅÁö È£Èí±â Áúº´ ŽÁö ¹× ½Äº° ½Ã½ºÅÛÀ» ±¸ÇöÇÏ°íÀÚ ÇÑ´Ù. ½ÇÁ¦ ±¹³» µ·»ç¿¡¼ ÃëµæÇÑ µÅÁöÀÇ ¹ß¼ºÀ½À» ÀÌ¿ëÇÏ¿© Á¦¾ÈÇÏ´Â ½Ã½ºÅÛÀÇ ¼º´ÉÀ» ½ÇÇèÀûÀ¸·Î °ËÁõÇѹÙ, Á¦¾ÈµÈ ½Ã½ºÅÛÀº °æÁ¦ÀûÀÎ ºñ¿ë(Àú°¡ÀÇ ¼Ò¸® ¼¾¼)°ú ½Ã½ºÅÛ Á¤È®µµ(96.0% Á¤È®µµ)·Î ´Ù¾çÇÑ ÀâÀ½ ȯ°æ¿¡¼µµ µÅÁöÀÇ È£Èí±â Áúº´µéÀ» ŽÁöÇÒ ¼ö ÀÖÀ½À» ½ÇÇèÀûÀ¸·Î È®ÀÎÇÏ¿´´Ù. Á¦¾ÈµÈ ½Ã½ºÅÛÀº µ¶ÀÚÀûÀΠȤÀº ±âÁ¸ ¹æ¹ýµéÀÇ º¸¿ÏÃ¥À¸·Î »ç¿ëµÉ ¼ö ÀÖ´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
Automatic detection of pig wasting diseases is an important issue in the management of group-housed pigs. In particular, porcine respiratory diseases are one of the main causes of mortality among pigs and loss of productivity in intensive pig farming. In this paper, we propose a noise-robust system for the early detection and recognition of pig wasting diseases using sound data. In this method, first we convert one-dimensional sound signals to two-dimensional gray-level images by normalization, and extract texture images by means of dominant neighborhood structure technique. Lastly, the texture features are then used as inputs of convolutional neural networks as an early anomaly detector and a respiratory disease classifier. Our experimental results show that this new method can be used to detect pig wasting diseases both economically (low-cost sound sensor) and accurately (over 96% accuracy) even under noise-environmental conditions, either as a standalone solution or to complement known methods to obtain a more accurate solution.
|
Å°¿öµå(Keyword) |
µÅÁö È£Èí±â Áúº´
ÀâÀ½ °Àμº
¼Ò¸® ºÐ¼®
DNS
CNN
Porcine Respiratory Diseases
Noise Robustness
Sound Analysis
Dominant Neighborhood Structure
Convolutional Neural Network
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|