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
- 발행연도
- 2012.11
- 수록면
- 1,249 - 1,254 (6page)
이용수
초록· 키워드
오류제보하기
The paper suggests an algorithm for detecting driver’s high cognitive workload using driving performance and physiological data. The algorithm adopts radial basis probabilistic neural network (RBPNN) to construct estimation models. In order to train and test the models, combinations of two driving performance data including velocity and steering wheel reversal rate(SRR), and three physiological signals including inter-beat interval(IBI), skin conductance level(SCL) and skin temperature were considered as measures of cognitive workload. The training and testing data were collected from on-road driving experiments of 13 subjects who were asked to complete three levels of difficulty of a delayed digit-recall task (n-back task). As a result, The best performance was achieved from a combination of measures including SCL, skin temperature and velocity over 10 seconds time window with an average accuracy of 94.2%. It is expected that the accuracy can be improved applying more sophisticated algorithms and various window sizes and combinations.
목차
Abstract
1. 서론
2. 방법
3. 결과
4. 결론
References
참고문헌 (0)
참고문헌 신청이 논문의 저자 정보
최근 본 자료
댓글(0)
0
UCI(KEPA) : I410-ECN-0101-2014-556-000409605