메뉴 건너뛰기

추천
검색
질문

논문 기본 정보

자료유형
학술대회자료
저자정보
(대구가톨릭대학교) (대구가톨릭대학교) (대구가톨릭대학교)
저널정보
대한전자공학회 대한전자공학회 학술대회 2025년도 대한전자공학회 추계학술대회 논문집
발행연도
수록면
568 - 571 (4page)

이용수

표지
📌
연구주제
📖
연구배경
🔬
연구방법
이 논문의 연구방법이 궁금하신가요?
🏆
연구결과
이 논문의 연구결과가 궁금하신가요?
AI에게 요청하기
추천
검색
질문

초록· 키워드

Water-meters can generally be classified into three types: mechanical, digital, and cloud server-based. Each type has its own advantages and disadvantages. Mechanical meters require manual reading by a person, digital meters may fail to charge properly if the battery is discharged, and cloud server-based meters increase communication costs due to video data transmission and require replacement of the existing billing system. To address these issues, this paper proposes a system that attaches a TinyML-based edge device equipped with a camera to a mechanical meter. The edge device automatically recognizes the meter digits and performs billing autonomously. In previous studies, to recognize the unknown state, which refers to the transitional state between digits, 10 additional classes were added for each state, resulting in a total of 20 classes. In contrast, since the proposed method operates on a low-capacity edge device where DNN efficiency is critical, only 10 standard digit classes were used. By applying data augmentation techniques, the proposed method effectively recognized the unknown states while simplifying the network structure.
상세정보 수정요청해당 페이지 내 제목·저자·목차·페이지
정보가 잘못된 경우 알려주세요!

목차

  1. Abstract
  2. I. 서론
  3. II. 본론
  4. Ⅲ. 실험 결과
  5. Ⅳ. 결론
  6. 참고문헌

참고문헌

참고문헌 신청

최근 본 자료

전체보기