Àüü
ÀüÀÚ/Àü±â
Åë½Å
ÄÄÇ»ÅÍ
·Î±×ÀÎ
ȸ¿ø°¡ÀÔ
About Us
ÀÌ¿ë¾È³»
¿¬±¸¹®Çå
±¹³» ³í¹®Áö
¿µ¹® ³í¹®Áö
±¹³» ÇÐȸÁö
Çмú´ëȸ ÇÁ·Î½Ãµù
±¹³» ÇÐÀ§ ³í¹®
³í¹®Á¤º¸
¹é¼
±³À°Á¤º¸
¿¬±¸ ù°ÉÀ½
ÇаúÁ¤º¸
°ÀÇÁ¤º¸
µ¿¿µ»óÁ¤º¸
E-Learning
¿Â¶óÀÎ Àú³Î
½ÉÈÁ¤º¸
¿¬±¸ ¹× ±â¼úµ¿Çâ
Áֿ俬±¸ÅäÇÈ
ÁÖ¿ä°úÁ¦ ¹× ±â°ü
Çؿܱâ°ü °ü·ÃÀÚ·á
¹ÙÀÌ¿À Á¤º¸±â¼ú
ÁÖ¿ä Archive Site
Æ÷Ä¿½ºiN
¿¬±¸ÀÚ Á¤º¸
¶óÀÌ¡½ºÅ¸
ÆÄ¿öiNÅͺä
¼¼ÁßÇÑ
¿¬±¸ÀÚ·á
¹®ÀÚ DB
¿ë¾î»çÀü
¾Ë¸²¸¶´ç
ºÎ½Ç ÇмúÈ°µ¿ ¿¹¹æ
³í¹®¸ðÁý
´ëȸ¾È³»
What's New
¿¬±¸ºñÁ¤º¸
±¸ÀÎÁ¤º¸
°øÁö»çÇ×
CSERIC ±¤Àå
Post-Conference
¿¬±¸ÀÚ Ä«Æä
ÀÚÀ¯°Ô½ÃÆÇ
Q&A
´Ý±â
»çÀÌÆ®¸Ê
¿¬±¸¹®Çå
±¹³» ³í¹®Áö
¿µ¹® ³í¹®Áö
±¹³» ÇÐȸÁö
Çмú´ëȸ ÇÁ·Î½Ãµù
±¹³» ÇÐÀ§ ³í¹®
³í¹®Á¤º¸
¹é¼
±³À°Á¤º¸
¿¬±¸ ù°ÉÀ½
ÇаúÁ¤º¸
°ÀÇÁ¤º¸
µ¿¿µ»óÁ¤º¸
E-Learning
¿Â¶óÀÎ Àú³Î
½ÉÈÁ¤º¸
¿¬±¸ ¹× ±â¼úµ¿Çâ
Áֿ俬±¸ÅäÇÈ
ÁÖ¿ä°úÁ¦ ¹× ±â°ü
Çؿܱâ°ü °ü·ÃÀÚ·á
¹ÙÀÌ¿À Á¤º¸±â¼ú
ÁÖ¿ä Archive Site
ÄÄÇ»ÅÍiN
¿¬±¸ÀÚ Á¤º¸
¿¬±¸ÀÚ·á
¹®ÀÚ DB
Ȧ·Î±×·¥ DB
¿ë¾î»çÀü
¾Ë¸²¸¶´ç
ºÎ½Ç ÇмúÈ°µ¿ ¿¹¹æ
³í¹®¸ðÁý
´ëȸ¾È³»
What's New
¿¬±¸ºñ Á¤º¸
±¸ÀÎÁ¤º¸
°øÁö»çÇ×
IT Daily
CSERIC ±¤Àå
Post-Conference
¿¬±¸ÀÚ Ä«Æä
ÀÚÀ¯°Ô½ÃÆÇ
Q&A
¼ºñ½º ¹Ù·Î°¡±â
¼³¹®Á¶»ç
¿¬±¸À±¸®
°ü·Ã±â°ü
Please wait....
¿¬±¸¹®Çå
±¹³» ³í¹®Áö
¿µ¹® ³í¹®Áö
±¹³» ÇÐȸÁö
Çмú´ëȸ ÇÁ·Î½Ãµù
±¹³» ÇÐÀ§ ³í¹®
³í¹®Á¤º¸
¹é¼
±¹³» ÇÐȸÁö
Ȩ > ¿¬±¸¹®Çå > ±¹³» ÇÐȸÁö >
µ¥ÀÌÅͺ£À̽º ¿¬±¸È¸Áö(SIGDB)
µ¥ÀÌÅͺ£À̽º ¿¬±¸È¸Áö(SIGDB)
Current Result Document :
8
/ 8
ÀÌÀü°Ç
ÇѱÛÁ¦¸ñ(Korean Title)
ÈÀç ¿¹ÃøÀ» À§ÇÑ ÆÛ¼ÁÆ®·Ð ±â¹Ý °¡Áß À¯Å¬¸®µð¾È °Å¸®ÇÔ¼öÀÇ ÃÖÀûÈ
¿µ¹®Á¦¸ñ(English Title)
Perceptron-based Optimization of the Weighted Euclidean Distance Function for Fire Prediction
ÀúÀÚ(Author)
ÇÏ»ó¿ø
±èÇÑÁØ
Sang-won Ha
Han-joon Kim
¿ø¹®¼ö·Ïó(Citation)
VOL 34 NO. 01 PP. 0080 ~ 0090 (2018. 04)
Çѱ۳»¿ë
(Korean Abstract)
º» ³í¹®Àº °ÇÃ๰ÀÇ °ÇÃà °ü·Ã Á¤º¸¸¦ °¡Áø °ÇÃ๰ ´ëÀå, °ÇÃ๰ÀÌ ¼ÓÇÑ Áö¿ªÀÇ ÇàÁ¤µ¥ÀÌÅÍ, °ÇÃ๰ÀÇ ¿¡³ÊÁö »ç¿ë·® µ¥ÀÌÅ͸¦ ¹ÙÅÁÀ¸·Î ÈÀç°ÇÃ๰°ú À¯»çÇÑ °ÇÃ๰À» ã´Â °Å¸®ÇÔ¼öÀÇ °¡ÁßÄ¡(Weight)¸¦ ÆÛ¼ÁÆ®·Ð (Perceptron)À» ÀÌ¿ëÇØ ÇнÀÇÏ´Â ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. ÈÀç µ¥ÀÌÅÍÀÇ °æ¿ì, ¼Ó¼ºÀÇ Á¾·ù°¡ ´Ù¾çÇÏ°í ¼Ó¼º °ªµéÀÇ ½ºÄÉÀÏ(Scale)ÀÇ Â÷ÀÌ°¡ Ä¿ ¼Ó¼ºÀÇ Áß¿äµµ¸¦ ¹Ý¿µÇÏÁö ¾ÊÀº À¯Å¬¸®µð¾È °Å¸®ÇÔ¼ö(Euclidean Distance Function)¸¦ »ç¿ëÇÏ´Â °ÍÀº ÀûÀýÇÏÁö ¾Ê´Ù. µû¶ó¼ °¡Áß À¯Å¬¸®µð¾È °Å¸®ÇÔ¼ö(Weighted Euclidean Distance Function)¸¦ »ç¿ëÇØ °Å¸®¸¦ ÃøÁ¤ÇÑ´Ù. °¡Áß À¯Å¬¸®µð¾È °Å¸®ÇÔ¼öÀÇ °¡ÁßÄ¡´Â °¢ ¼Ó¼ºÀÇ ¼Ó¼ºÁß¿äµµ(Feature Importance)¿¡ µû¶ó ºÎ¿©Çϰųª, »ç¿ëÀÚ°¡ ÀÓÀÇ·Î ºÎ¿©ÇÑ´Ù. º» ³í¹®Àº »ç¿ëÀÚÀÇ °¡ÁßÄ¡ ¼³Á¤ °úÁ¤ ¾øÀÌ ÆÛ¼ÁÆ®·Ð ÇнÀÀ¸·Î ¾ò¾îÁø °¡ÁßÄ¡¸¦ °Å¸®ÇÔ¼öÀÇ °¡ÁßÄ¡·Î »ç¿ëÇÔÀ¸·Î½á ÈÀç °Ç¹°ÀÇ Å½Áö°¡ °¡´ÉÇÔÀ» º¸ÀδÙ.
¿µ¹®³»¿ë
(English Abstract)
In this work, we propose a method of learning the weights of weighted Euclidean distance function using perceptron learning for fire prediction. In our work, the data used to fire prediction include building data, regional administration data and energy consumption data. When locating fire buildings with distance functions, it is not appropriate to adopt Euclidean distance function with no weights; this is because fire data has various types of features and large difference in scales of feature values. Thus our fire prediction method measures distances between two buildings using weighted Euclidean distance function. The weights of weighted Euclidean distance function can be given according to the feature importance, not depending upon user input. Our experimental result shows that it is possible to locate fire-risk building by using weights obtained by the perceptron learning.
Å°¿öµå(Keyword)
±â°è ÇнÀ
°Å¸®ÇÔ¼ö
°¡ÁßÄ¡ ÇнÀ
Àΰø½Å°æ¸Á
machine learning
distance function
weight learning
neural network
ÆÄÀÏ÷ºÎ
PDF ´Ù¿î·Îµå
¸ñ·Ï
Copyright(c)
Computer Science Engineering Research Information Center
. All rights reserved.