Sleep posture monitoring method and system based on wireless signals

Abstract

The invention discloses a sleep posture monitoring method and system based on a wireless signal. The method comprises the following steps: transmitting a low-power radio signal, receiving reflected signals of a human body and a surrounding environment, and extracting an RF snapshot; performing motion event identification on the RF snapshot, defining an interval between motion events as a stable time period, and conducting calculating to obtain multipath distribution of a stable time period according to relative signal power; performing breathing filtering on the multipath characteristics of the surrounding environment, and retaining reflected signals from the human body; inputting multipath characteristic files obtained after breathing filtering into a full-connection neural network, training the neural network, and predicting a sleep posture corresponding to each multipath characteristic file; and inferring a sleep posture of a target user by using a small number of calibration points of the target user based on learning of training data of source users. The sleep posture monitoring method has the advantages that accurate sleep posture monitoring can be provided under the condition that user privacy and sleep comfort are not affected.

Description

technical field [0001] The invention relates to the field of medical equipment and physiological signal detection, in particular to a method and system for monitoring sleep posture based on wireless signals. Background technique [0002] Clinical studies have shown that sleeping posture is an important marker of disease progression and has a significant impact on human health. For example, fewer turns over at night may mean worsening in patients with Parkinson's disease, infrequent turning may lead to bedsores in patients after surgery, and inappropriate sleeping positions may even increase the risk of sudden death in patients with epilepsy. These examples all show us the importance of continuous, fully automated sleep posture monitoring. [0003] The two main monitoring methods in the past: installing a camera in the bedroom and using bed sensors such as accelerometers and pressure sensors are not suitable methods. The camera violates the privacy of the user, and the perfo...

AI Technical Summary

Problems solved by technology

[0003] The two main monitoring methods in the past: installing a camera in the bedroom and using bed sensors such as accelerometers and pressure sensors are not suitable methods. The camera violates the privacy of the user, and the performance will be affected at night when the light is poor. ; and the use of various sensors affects the user's sleeping comfort

Images