2019³â ÄÄÇ»ÅÍÁ¾ÇÕÇмú´ëȸ
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
µö·¯´×À» È°¿ëÇÑ ½Ã°è¿ ÀÚ·áÀÇ ÀÌ»óÄ¡ ŽÁö ¸ðµ¨¿¡ ´ëÇÑ Á¶»ç |
¿µ¹®Á¦¸ñ(English Title) |
A Survey on Deep Learning-based Anomaly Detection Models for Time Series Data |
ÀúÀÚ(Author) |
¿ì¿ä
°ÁØÇõ
ÀÌÀç±æ
Yu Yao
Junhyeok Kang
Jae-Gil Lee
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 46 NO. 01 PP. 0919 ~ 0921 (2019. 06) |
Çѱ۳»¿ë (Korean Abstract) |
|
¿µ¹®³»¿ë (English Abstract) |
Anomaly detection for time series data has been of great interest to diverse research and application domains for decades. However, analysis of time series data is still challenging due to its high-dimensionality, non-station arity characteristics. In recent years, deep learning has shown its capability of dealing with high-dimensional and complex data. Since that, deep learning-based anomaly detection approaches have become increasingly popular. In this survey, we briefly introduce several kinds of deep anomaly detection models: prediction-based, reconstruc tion-based, hybrid and generative model, which provides an insight into the current work in anomaly detection for time series data. |
Å°¿öµå(Keyword) |
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|