메뉴 건너뛰기
소속 기관 / 학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
고객센터 ENG
주제분류

논문 기본 정보

저자정보
(Kumoh National Institute of Technology) (Kumoh National Institute of Technology) (Kumoh National Institute of Technology)
저널정보
대한전자공학회 대한전자공학회 학술대회 2018년도 대한전자공학회 정기총회 및 추계학술대회
오류 신고하기

피인용 0

검색

    초록·키워드

    Pyroelectric Infra-red (PIR) sensor is one of the corner stones of many Smart Home applications. However, PIR sensor is not capable of disregarding motion caused by house pets, eliminating false alarms. Therefore, we propose to address this problem using two analog PIR sensors in order to recognize human and pet. In this paper, we suggest a new motion classification system based on analog PIR sensors. A new approach is developed to use PIR sensors by modifying the sensor circuitry. Basically, the analog PIR sensor emits an output based on various voltage scales within a certain area rather than producing discrete outputs using a threshold value. Furthermore, an analog signal is extracted from the couple PIR sensors and it is sampled. Moreover, its frequency feature is extracted using a Fast Fourier Transform. The extracted features are used as the input of Artificial Neural Networks and obtained classification accuracy of 90.4 %. The result shows that accuracy is satisfactory and thus proved that PIR nodes can be used at home for energy saving.

    최근 본 자료 전체보기