ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술대회 Power Quality Problem Classification Methods Based on Active Transfer Learning
Cited 0 time in scopus Download 2 time Share share facebook twitter linkedin kakaostory
저자
오승민, 고석갑, 김에덴, 이병탁
발행일
202010
출처
International Conference on Information and Communication Technology Convergence (ICTC) 2020, pp.1222-1224
DOI
https://dx.doi.org/10.1109/ICTC49870.2020.9289605
협약과제
20PK1100, 전력 빅데이터를 활용한 신산업 BM 및 서비스 개발·검증, 이병탁
초록
In this paper, we propose approach for classification of power quality problem using active transfer learning. Active learning is suitable for solving problems with real industrial data because even a small amount of labeled data can derive good performance. Active learning can derive performance by querying human data labelers for data the model does not learn or trained. Active transfer learning utilizes transfer learning for data sampling of the trained model. However, querying too much data can put pressure on human data labelers. Thus, we suggest the solution of this problem by limiting query in two ways. One is to limit the number of queries to 100 and the other is dynamically controlled the number of queries according to the accuracy. As a result, we derive better predictive performance with suggest method and compare the results with the traditional method.
키워드
Active Transfer Learning, Classification, Diversity Sampling, Power quality problem, Supervised Learning
KSP 제안 키워드
Active transfer learning, Classification method, Data Sampling, Human data, Labeled data, Power Quality(PQ), Predictive performance, Problem classification, Quality problem, Real industrial data, Supervised Learning