KCC 2021
Current Result Document : 1,192 / 1,192
| 한글제목(Korean Title) |
무선 센서 네트워크에서 감지 데이터에 대한 적응형 이상치 탐색방안 |
| 영문제목(English Title) |
Adaptive Anomaly Detection Scheme for Sensory Data in Wireless Sensor Networks |
| 저자(Author) |
김문성
추현승
Thien-Binh Dang
Duc-Tai Le
Moonseong Kim
Hyunseung Choo
|
| 원문수록처(Citation) |
VOL 48 NO. 01 PP. 1107 ~ 1109 (2021. 06) |
한글내용
(Korean Abstract) |
|
영문내용
(English Abstract) |
Anomaly detection has been rapidly required for the security of data collection in wireless sensor networks. The current approaches might not be applied to the general cases of anomalies, i.e., both short- and long-term anomalies, as well as not be suitable with the real-time applications such as natural disaster monitoring and early warning systems. To fill this research gap, this paper proposes a novel approach, named Adaptive Anomaly Detection (AAD), which combines Discrete Wavelet Transform (DWT) and K-Mean clustering to improve the system performance. In particular, we first utilize the DWT on the input data, and then, apply the clustering algorithm on the output of DWT process to detect anomaly. Numerical experiments based on the real dataset of Intel Berkeley Research reveal that the proposed AAD scheme not only outperforms the existing schemes in terms of accuracy and false positive rate, but also is applicable to the real-time systems. |
| 키워드(Keyword) |
|
| 파일첨부 |
PDF 다운로드
|
