2019년도 인터넷정보학회 춘계학술발표대회
Current Result Document :
| 한글제목(Korean Title) |
무선 센서 네트워크에서의 트렌드 기반 이상 탐지 |
| 영문제목(English Title) |
A Novel Trend-based Anomaly Detection In Wireless Sensor Network |
| 저자(Author) |
Dang Thien Binh
Manh-Hung Tran
염상길
추현승
Dang Thien Binh
Manh-Hung Tran
Sanggil Yeom
Hyunseung Choo
|
| 원문수록처(Citation) |
VOL 20 NO. 01 PP. 0111 ~ 0112 (2019. 04) |
한글내용
(Korean Abstract) |
|
영문내용
(English Abstract) |
A wide range of WSN applications use information collected from networks of sensors for monitoring and controlling purposes. However, the frequent appearance of anomalous data makes it difficult to extract correct information, thereby making wrong commands to actuators that can threaten human privacy and safety. For this reason, it is necessary to have a mechanism to detect anomalous data collected from sensors. In this paper, we present a trend-based principal component analysis (Trend-based PCA) model for anomalous data detection which is based on conventional PCA. Experimental results on a real dataset show the higher effectiveness of the proposed model comparing to conventional PCA model in anomalous data detection.
|
| 키워드(Keyword) |
|
| 파일첨부 |
PDF 다운로드
|
