• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹ÀÎÅͳÝÁ¤º¸ÇÐȸ ³í¹®Áö

Çѱ¹ÀÎÅͳÝÁ¤º¸ÇÐȸ ³í¹®Áö

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ÄÁº¼·ç¼Ç ½Å°æ¸Á(CNN)À» ÀÌ¿ëÇÑ Æø¹ß¹° ¼ººÐ ¿ë·®º° ºÐ·ù ¼º´ÉÆò°¡¿¡ °üÇÑ ¿¬±¸
¿µ¹®Á¦¸ñ(English Title) A Study on the Evaluation of Classification Performance by Capacity of Explosive Components using Convolution Neural Network (CNN)
ÀúÀÚ(Author) ¹ÚÅÂÁØ   ¹®Á¾¼·   Tae-jun Park   Jongsub Moon   ÀÌâÇö   Á¶¼ºÀ±   ±Ç±â¿ø   ÀÓÅÂÈ£   Chang-Hyeon Lee   Sung-Yoon Cho   Tae-Ho Im   Ki-Won Kwon  
¿ø¹®¼ö·Ïó(Citation) VOL 23 NO. 04 PP. 0011 ~ 0019 (2022. 08)
Çѱ۳»¿ë
(Korean Abstract)
º» ³í¹®Àº ÄÁº¼·ç¼Ç ½Å°æ¸Á(CNN)À» ÀÌ¿ëÇÏ¿© Æø¹ß¹° ¼ººÐÀÇ ¿ë·®º°·Î ºÐ·ùÇÒ ¶§ÀÇ ¼º´ÉÀ» Æò°¡ÇÏ´Â ¿¬±¸ÀÌ´Ù. ±âÁ¸ÀÇ Æø¹ß¹° ºÐ·ù ¹æ½Ä Áß¿¡ IMS Áõ±â ŽÁö±â ¹æ½ÄÀº Æø¹ß¹°ÀÇ ³óµµ°¡ »ç¿ëÀÚ°¡ Àåºñ¿¡¼­ ¼³Á¤ÇÑ ÀÓ°èÄ¡¸¦ ³Ñ¾î¾ß¸¸ Æø¹ß¹°ÀÇ Á¸Àç ¿©ºÎ¸¦ ÆÇ´ÜÇÑ´Ù. IMS Áõ±â ŽÁö±â´Â Æø¹ß¹°ÀÌ Á¸ÀçÇÏ´õ¶óµµ ÀÓ°èÄ¡¸¦ ³ÑÁö ¾Ê´Â ¾çÀ̸é Æø¹ß¹°ÀÌ Á¸ÀçÇÏÁö ¾Ê´Â´Ù°í ÆÇ´ÜÇÏ´Â ¹®Á¦°¡ ÀÖ´Ù. µû¶ó¼­ Æø¹ß¹° ¼ººÐÀÇ ³óµµ°¡ ÀÓ°èÄ¡¸¦ ³ÑÁö ¾Ê´Â ¾çÀÏ ¶§¿¡µµ Æø¹ß¹° ¼ººÐÀ» °ËÃâÇÏ´Â ¹æ¾ÈÀÌ ÇÊ¿äÇÏ´Ù. ÀÌ¿¡ µû¶ó º» ³í¹®¿¡¼­´Â Æø¹ß¹° ½Ã°è¿­ µ¥ÀÌÅ͸¦ Gramian Angular Field(GAF) ¾Ë°í¸®ÁòÀ¸·Î À̹ÌÁöÈ­¸¦ ÁøÇàÇÑ ÈÄ À̹ÌÁö¿Í ¿µ»ó󸮻Ӹ¸ ¾Æ´Ï¶ó ½Ã°è¿­ µ¥ÀÌÅÍ Ã³¸®¿¡µµ ¶Ù¾î³­ ¼º´ÉÀ» º¸ÀÌ´Â µö·¯´× ¸ðµ¨ÀÎ ÄÁº¼·ç¼Ç ½Å°æ¸Á(CNN)À¸·Î Á÷Á¢ labelÀ» ¼³Á¤Çؼ­ ÁöµµÇнÀÀ» ÁøÇàÇÑ °á°ú Æø¹ß¹° ¼ººÐÀÇ ³óµµ°¡ ÀÓ°èÄ¡¸¦ ³ÑÁö ¾Ê´Â ¾çÀÏ ¶§¿¡µµ Æø¹ß¹° ¼ººÐÀÌ Á¸ÀçÇÑ´Ù°í ÆÇ´ÜÇÔ°ú µ¿½Ã¿¡ Æø¹ß¹° ¼ººÐÀÇ Á¾·ù¿Í Æø¹ß¹° ¼ººÐÀÇ ³óµµÀÇ ¾çÀ» °°ÀÌ ÆÇ´ÜÇÒ ¼ö ÀÖ´ÂÁö ¼º´ÉÆò°¡¸¦ ÁøÇàÇß´Ù.
¿µ¹®³»¿ë
(English Abstract)
This paper is a study to evaluate the performance when classifying explosive components by capacity using a convolutional neural network (CNN). Among the existing explosive classification methods, the IMS steam detector method determines the presence or absence of an explosive only when the explosive concentration exceeds the threshold set by the user. The IMS steam detector has a problem of determining that even if an explosive exists, the explosive does not exist in an amount that does not exceed the threshold. Therefore, it is necessary to detect the explosive component even when the concentration of the explosive component does not exceed the threshold. Accordingly, in this paper, after imaging explosive time series data with the Gramian Angular Field (GAF) algorithm, it is possible to determine whether there are explosive components and the amount of explosive components even when the concentration of explosive components does not exceed a threshold.
Å°¿öµå(Keyword) µ¹ÇɾîÅà  ½º¸¶Æ® ½ºÇÇÄ¿   À½¼º ¸í·É   È­ÀÚ ÀÎÁõ   DolphinAttack   Smart speaker   Voice Controllable System   Speaker recognition   µö·¯´×   Æø¹ß¹° ºÐ·ù   ÀÌ»ó °¨Áö ½Ã½ºÅÛ   Deep learning   explosive classification   abnormality detection system  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå