Bed-exit prediction based on convolutional neural networks

In this paper, we propose a deep convolutional neural network model for in-bed behavior recognition and bed-exit prediction. This model extracts features for training from depth images taken by depth cameras in two categories: in-bed images taken several time intervals before a patient gets out of bed, and usual in-bed activity images. The depth camera-based model features grayscale and low-resolution images, and excels at discarding unnecessary details such as background information beyond the target's contour. The proposed model was proven to be computationally efficient, which is crucial for analyzing and predicting the category of new images in real time.