Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ
Current Result Document : 1 / 1
ÇѱÛÁ¦¸ñ(Korean Title) |
119 ½Å°í µ¥ÀÌÅ͸¦ ÀÌ¿ëÇÑ ÀÚ¿¬¾îó¸® ±â¹Ý Àç³¾ÈÀü »óȲ ºÐ·ù ¾Ë°í¸®Áò ºÐ¼® |
¿µ¹®Á¦¸ñ(English Title) |
Analysis of Disaster Safety Situation Classification Algorithm Based on Natural Language Processing Using 119 Calls Data |
ÀúÀÚ(Author) |
±Ç¼öÁ¤
°À±Èñ
ÀÌ¿ëÇÐ
À̹ÎÈ£
¹Ú¼ºÈ£
°¸íÁÖ
Su-Jeong Kwon
Yun-Hee Kang
Yong-Hak Lee
Min-Ho Lee
Seung-Ho Park
Myung-Ju Kang
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 09 NO. 10 PP. 0317 ~ 0322 (2020. 10) |
Çѱ۳»¿ë (Korean Abstract) |
ÀΰøÁö´ÉÀÇ ¹ß´Þ·Î ÀÎÇÏ¿© Àç³ ºÐ¾ß¿¡¼´Â Àç³´ëÀÀ Áö¿ø ½Ã½ºÅÛÀ¸·Î ÀÌ¿ëµÇ°í ÀÖ´Ù. Àç³Àº ¾ðÁ¦ ¾îµð¼µçÁö ¹ß»ýÇÒ ¼ö ÀÖÀ¸¸ç, Àç³ ¹ß»ý ½Ã ¼Ò¹æû 119 ½Å°íÁ¢¼ö´ë¿¡ Á¢¼öµÇ´Â ½Å°í´Â Å©°Ô ÈÀç, ±¸Á¶, ±¸±Þ, ±âŸ ½Å°í µî 4°¡Áö·Î ±¸ºÐµÈ´Ù. 119 ½Å°í¿¡ µû¸¥ Àç³ ´ëÀÀµµ ±× Á¾·ù ¹× »óȲ¿¡ µû¶ó ´Ù¸£°Ô ´ëÀÀµÈ´Ù. º» ³í¹®¿¡¼´Â 119 ½Å°í µ¥ÀÌÅÍ 1280°³ ¹®¼¸¦ ÇнÀ µ¥ÀÌÅÍ ¼ÂÀ» ÀÌ¿ëÇÏ¿© SVM, NB, k-NN, DT, SGD, RF »óȲ ºÐ·ù ±â°èÇнÀ ¾Ë°í¸®ÁòÀ» 3 Ŭ·¡½º·Î Å×½ºÆ®ÇÑ ºÐ·ù ¼º´ÉÀº ÃÖ°í 92%, ÃÖ¼Ò 77%ÀÇ ¼º´ÉÀ» º¸¿´´Ù. ÀΰøÁö´ÉÀÇ ¹ß´Þ·Î ÀÎÇÏ¿© Àç³ ºÐ¾ß¿¡¼´Â Àç³ ´ëÀÀ Áö¿ø ½Ã½ºÅÛÀ¸·Î ÀÌ¿ëµÇ°í ÀÖ´Ù. Àç³Àº ¾ðÁ¦ ¾îµð¼µçÁö ¹ß»ýÇÒ ¼ö ÀÖÀ¸¸ç, Àç³ ¹ß»ý ½Ã ¼Ò¹æû 119 ½Å°íÁ¢¼ö´ë¿¡ Á¢¼öµÇ´Â ½Å°í´Â Å©°Ô ÈÀç, ±¸Á¶, ±¸±Þ, ±âŸ ½Å°í µî 4°¡Áö·Î ±¸ºÐµÈ´Ù. 119 ½Å°í¿¡ µû¸¥ Àç³´ëÀÀµµ ±× Á¾·ù ¹× »óȲ¿¡ µû¶ó ´Ù¸£°Ô ´ëÀÀµÈ´Ù. º» ³í¹®¿¡¼´Â 119 ½Å°í µ¥ÀÌÅÍ 1280°³ ¹®¼¸¦ ÇнÀ µ¥ÀÌÅÍ ¼ÂÀ» ÀÌ¿ëÇÏ¿© SVM, NB, k-NN, DT, SGD, RF »óȲ ºÐ·ù ¾Ë°í¸®ÁòÀ» 3 Ŭ·¡½º·Î Å×½ºÆ®ÇÑ ºÐ·ù ¼º´ÉÀº ÃÖ°í 92%, ÃÖ¼Ò 77%ÀÇ ¼º´ÉÀ» º¸¿´´Ù. ¾ÕÀ¸·Î ´Ù¾çÇÑ ºÐ¾ßÀÇ À糺° µ¥ÀÌÅÍ ¼ÂÀ» È®º¸ÇÏ¿© È¿À²ÀûÀÎ Àç³ ´ëÀÀ ¿¬±¸°¡ ÇÊ¿äÇÏ´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
Due to the development of artificial intelligence, it is used as a disaster response support system in the field of disaster. Disasters can occur anywhere, anytime. In the event of a disaster, there are four types of reports: fire, rescue, emergency, and other call. Disaster response according to the 119 call also responds differently depending on the type and situation. In this paper, 1280 data set of 119 calls were tested with 3 classes of SVM, NB, k-NN, DT, SGD, and RF situation classification algorithms using a training data set. Classification performance showed the highest performance of 92% and minimum of 77%. In the future, it is necessary to secure an effective data set by disaster in various fields to study disaster response.
|
Å°¿öµå(Keyword) |
ÀΰøÁö´É
Àç³ ´ëÀÀ
ÀÚ¿¬¾îó¸®
»óȲ ºÐ·ù
±â°èÇнÀ
Artificial Intelligence
Emergency Response
Natural Language Processing
Situation Classification
Machine Learning
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|