Scientists from the University of Cambridge in the UK have developed a comfortable and washable smart nightgown. This nightgown can help users monitor six sleep conditions, including breathing pauses, at home by detecting small movements in the skin. The relevant paper was published in the latest issue of the Proceedings of the National Academy of Sciences in the United States. According to the research team, this smart nightgown can recognize different sleep conditions with 98.6% accuracy, while ignoring normal sleep movements such as tossing and turning. Moreover, the smart pajamas have undergone special sizing treatment, which not only improves durability but also allows them to be cleaned in regular washing machines. In order to develop this smart nightgown, the team designed a graphene based sensor that can accurately analyze the user's breathing during sleep. The sensitivity of the sensor is extremely high, and as long as it comes into contact with the skin, it will provide highly accurate readings. In addition, they have developed a machine learning model called SleepNet, which can identify six sleep conditions based on signals captured by sensors: nasal breathing, oral breathing, snoring, grinding teeth, central sleep apnea, and obstructive sleep apnea. SleepNet is a "lightweight" model that greatly reduces computational complexity and can run on portable devices without the need to connect to a computer or server. Poor sleep can have a significant negative impact on a person's physical and mental health, therefore, proper sleep monitoring is crucial. However, the current gold standard technology for sleep monitoring, polysomnography, is expensive and complex, and is not suitable for long-term use at home. Some simpler household devices typically can only monitor one type of sleep condition and are bulky in size. In contrast, the new smart pajamas are not only convenient to use, but also have high accuracy. (New Society)