Face Detection and Classification of Sleep State of Humans by Deep Learning Mechanisms

Abstract

1/3 of lifetime of a person is spent on the sleep, and thus there is no doubt that sleep is one of the most important things for every person. However, due to various causes like working overtime or pressure or life, modern people tend to be in short of sleep but unaware of this fact. This project will try to solve this problem with the CNN model based on deep learning mechanism. The project focuses on the classification of sleep state, and the sleep state can be classified as adequate sleep, not adequate sleep and badly need sleep. The person who badly need sleep is required to go to bed at once in case that he or she slips into a coma suddenly with risk of losing life. To test the dataset, this paper requires the help from others who are willing to fill in the form of questionnaire and their personal pictures. This project get inspiration from previous framework and explore the factors that influence the accuracy of classification, including known factors and new factors. The goal of the project is to provide a more convenient way for people to do the classification of sleep state in their daily life.