Research On Methods Of Human Sleep Data Acquisition And Analysis

With the rapid development of wearable smart devices, more and more people are concerned about the health of the individual. Most of the human time is in sleep, and we have a good sleep, not only can make people energetic, physical strength, but also to prevent disease. Therefore, the use of wearable devices for sleep monitoring is very necessary. Sleep data obtained through the device to identify the stage of sleep, and to assess the quality of sleep, and then improve sleep. Sometimes sleep is good or bad, it determines the movement of the situation, to further explore the relationship between sleep and exercise. In this paper, we study the data acquisition and feature extraction and classification methods in the process of sleep recognition. The main research contents are:1. Aiming at the problem of data acquisition and feature selection in the process of human sleep recognition, and using smart phones collect sound and body moving data, and these data are preprocessed, and the combination of feature extraction and feature selection is proposed, which is called TSFS method. Only using a method to select features, there will be some drawbacks. The method is a combination of two methods of feature extraction and feature selection, and not only can be screened out the characteristics of the actual situation, but also improve the accuracy of classification.2. For the classification of human sleep recognition process, a fusion method of Multi-SVM sleep classifier based on improved binary tree is proposed. Only using one classification method, the classification accuracy is difficult to be improved. The method is combining multiple SVM classifiers into a single branch of the shape of binary tree, and each node of the tree is classified by a SVM. Not only the accumulation of classification error is reduced, but also the classification accuracy is improved.3. To study the relationship between human sleep and movement, and a sleep and motion prediction model based on Aprior is proposed. Sleep and exercise data are acquired by intelligent equipment, and their features are extracted and classified. The long-term statistics of sleep and exercise explore the relationship between sleep and exercise by Aprior association rule mining method. A large number of experiments have proved that sleep quality affects the intensity of motion to a certain extent.