Machine Learning Technology is Used to Classify Respiratory Patterns According to EEG Signals

Abstract

Respiration is an important index reflecting human physiological health. Respiratory monitoring technology has become a research hotspot in the field of biomedical engineering. The existing respiratory monitoring technology can be divided into contact type and non-contact type according to the types of sensors. Contact breathing monitoring technology needs to contact the human body, which limits the physical movement, and is easy to cause discomfort to patients, so it cannot be monitored for a long time. Non-contact respiratory monitoring technology can overcome these limitations. Machine learning is used to classify breathing patterns according to EEG signals. Machine learning technology can create algorithms that can be used for pattern recognition, prediction and classification. In this case, the algorithm will be trained on a large number of samples (EEG signals), and then it will be able to identify similar patterns in the new data. It is not easily affected by environmental factors and has strong penetration. Compared with other non-contact monitoring technologies such as infrared and video, it is more suitable for monitoring human respiratory signals.