| 摘要 |
Since a change in a heart beat is dominated by the autonomic nerve which originates in the brain stem, it is difficult for an object person to control the heart beat at his or her own will. Therefore, frequency analysis, such as fine fluctuation analysis, is needed in order to estimate the body motion of the object person and is not suitable for instant processing. In contrast, according to this embodiment, an arithmetic unit 30 of a sleep state estimation device 1 estimates the state of the object person on the basis of the identity of each cycle of a breathing waveform of an object person M as the feature amount of the breathing waveform. The object person M can control a change in breathing at his or her own will. Therefore, when the state of the object person M is estimated on the basis of the identity of each cycle of the breathing waveform of the object person M, it is possible to easily classify the body motions of the object person M in detail and easily improve the accuracy of estimating the state of the object person M, such as the depth of sleep or the body motion. |
