TIIS (한국인터넷정보학회)
Current Result Document :
| 한글제목(Korean Title) |
CutPaste-Based Anomaly Detection Model using Multi Scale Feature Extraction in Time Series Streaming Data |
| 영문제목(English Title) |
CutPaste-Based Anomaly Detection Model using Multi Scale Feature Extraction in Time Series Streaming Data |
| 저자(Author) |
Byeong-Uk Jeon
Kyungyong Chung
|
| 원문수록처(Citation) |
VOL 16 NO. 8 PP. 2787 ~ 2800 (2022. 8) |
한글내용
(Korean Abstract) |
|
영문내용
(English Abstract) |
The aging society increases emergency situations of the elderly living alone and a variety of social crimes. In order to prevent them, techniques to detect emergency situations through voice are actively researched. This study proposes CutPaste-based anomaly detection model using multi-scale feature extraction in time series streaming data. In the proposed method, an audio file is converted into a spectrogram. In this way, it is possible to use an algorithm for image data, such as CNN. After that, mutli-scale feature extraction is applied. Three images drawn from Adaptive Pooling layer that has different-sized kernels are merged. In consideration of various types of anomaly, including point anomaly, contextual anomaly, and collective anomaly, the limitations of a conventional anomaly model are improved. Finally, CutPaste-based anomaly detection is conducted. Since the model is trained through self-supervised learning, it is possible to detect a diversity of emergency situations as anomaly without labeling. Therefore, the proposed model overcomes the limitations of a conventional model that classifies only labelled emergency situations. Also, the proposed model is evaluated to have better performance than a conventional anomaly detection model. |
| 키워드(Keyword) |
Anomaly Detection
Multi Scale Feature Extraction
Self-Supervised Learning
|
| 파일첨부 |
PDF 다운로드
|
