ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술지 Adaptive Gesture Tracking and Recognition Using Acceleration Sensors for a Mobile Device
Cited 2 time in scopus Download 3 time Share share facebook twitter linkedin kakaostory
저자
장민수, 김재홍, 서용호, 양현승
발행일
201501
출처
International Journal of Wireless and Mobile Computing, v.8 no.2, pp.183-193
ISSN
1741-1084
출판사
Inder Science Publishers
DOI
https://dx.doi.org/10.1504/IJWMC.2015.068624
협약과제
14PC1800, 인간 친화적 로봇 서비스 환경에서 판단 적합성 90%이상인 복합지식 기반 판단 및 의미기반 로봇 표현 기술 개발, 김재홍
초록
We present in this paper an adaptive gesture classifier for mobile devices, along with an efficient method to automatically detect endpoints of gestures. A classification model based on 1- NN with DTW-based k-means clustering is augmented by a metacognitive framework that measures the quality of the learned model and continuously updates it to improve the performance. We evaluated the model with an accelerometer signal database of 26 English alphabets. The results showed that the adaptive framework improved the recall and precision rates by 4.9% and 5.6%, respectively. Our endpoint detection method, based on energy variance and low-pass filtering, successfully detected 98.5% of gestures with an average detection delay of 176 ms.
KSP 제안 키워드
Acceleration Sensor, Accelerometer signal, Classification models, Detection Method, Detection delay, End Point Detection(EPD), Mobile devices, adaptive framework, gesture tracking, k-Means Clustering, low-pass filtering