ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술대회 A Study on Distance Measure for Effective Anomaly Detection using AutoEncoder
Cited 0 time in scopus Download 6 time Share share facebook twitter linkedin kakaostory
저자
이현용, 김낙우, 이준기, 이병탁
발행일
202010
출처
International Conference on Information and Communication Technology Convergence (ICTC) 2020, pp.1348-1352
DOI
https://dx.doi.org/10.1109/ICTC49870.2020.9289177
협약과제
20PK1100, 전력 빅데이터를 활용한 신산업 BM 및 서비스 개발·검증, 이병탁
초록
Anomaly detection is a popular application in various areas. One challenging issue is to build an anomaly detection model using normal data because collecting potential abnormal data is quite difficult. In this paper, we build an anomaly detection model using just normal data based on adversarial autoencoder for acoustic data. After extracting features using the trained model, we apply a distance-based method for calculating a threshold to be used for anomaly detection. In particular, we propose a method for reflecting differences in dimensions in calculating distance. Through experiments, we show that the proposed dimension-aware distance measure improves anomaly detection accuracy by up to 7% compared to existing distance measure methods.
키워드
Anomaly detection, autoencoder, deep learning, dimension-aware, distance
KSP 제안 키워드
Acoustic data, Detection accuracy, Detection model, Distance-based, abnormal data, anomaly detection, deep learning(DL), distance measure