http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Feature extraction of light sleep state in polysomnogram by use of conditional probability
Hiroaki Yoshiyama,Takenao Sugi,Bei Wang,Shuichiro Shirakawa,Masatoshi Nakamura 제어로봇시스템학회 2009 제어로봇시스템학회 국제학술대회 논문집 Vol.2009 No.8
Human sleep stages during whole right are usually classified into six stages based on polysommnographic (PSG) record. Sleep state of human light sleep changes gradually and continously. In this study, automatic judgrenet of light sleep state in PSG record was developed. Parameters for characterizing the PSG were calculated from the periodogram and the discriminant funtion was constructed by using conditional probability. Estimated value of wake full level was grdually decreased according to the stage charged from W to S1. In conuast, changing the sleep state from S1 to S2 increased estimated value of sleep level accordingly.
Lanlan Chen,Junzhong Zou,Takenao Sugi,Masatoshi Nakamura,Shuichiro Shirakawa 제어·로봇·시스템학회 2010 International Journal of Control, Automation, and Vol.8 No.4
Rest breaks are very important to prevent the accumulation of mental fatigue in sustained mental work environments. In this research, an integrated design and evaluation system for fatigue and relaxation is proposed, which consists of subjective scale, performance assessment and neurological signals. A work-rest schedule containing mental calculation and rest break is designed to reflect effect of prolonged cognitive work and rest time in mental work environments. Inter-individual difference has been taken into account to extract common features. The results indicate that rest breaks in sus-tained mental work are effective to counteract mental fatigue and improve work efficiency. Rest breaks are widely recommended in practical mental work circumstance. Integrated analysis from multi-estimators is helpful to improve the validity and explore the underlying mechanisms central to mental fatigue. Electroencephalogram (EEG) signals at occipital region show high correlation with performance. Thus EEG signals can contribute to the efficient design of work-rest schedule.