지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술대회자료
- 저자정보
- 저널정보
- 한국정보통신학회 INTERNATIONAL CONFERENCE ON FUTURE INFORMATION & COMMUNICATION ENGINEERING 2014 INTERNATIONAL CONFERENCE ON FUTURE INFORMATION & COMMUNICATION ENGINEERING Vo.6 No.1
- 발행연도
- 2014.6
- 수록면
- 423 - 426 (4page)
이용수
초록· 키워드
오류제보하기
Smartphones with built-in sensors promise a convenient, objective way to evaluate everyday movements and recognize those movements into activities. Using accelerometer as a low level sensor data we estimate the following daily activities performed by the user: walking, jogging, walking up stairs, walking down stairs, sitting and standing. Among five common machines learning algorithms: Decision Tree (J48), Naïve Bayes (NB), Support Vector Machines (SVM), Neural Network (NN), and Logistic Regression. NN classifier was found to be the best choice with classification accuracy of more than 95%. It is shown that this method is appropriate and that the phone’s orientation information is not needed.
목차
Abstract
I. INTRODUCTION
II. DEVICE AND DATA COLLECTION
III. RESULTS AND DISCUSSION
IV. CONCLUSIONS
REFERENCES
참고문헌 (0)
참고문헌 신청이 논문의 저자 정보
이 논문과 함께 이용한 논문
최근 본 자료
댓글(0)
0
UCI(KEPA) : I410-ECN-0101-2018-004-000962884