When people have problem in sleep, they turned to medical assistance for help. Several approaches/devices were applied to measure patient's vital signs in medical, such as, electroencephalogram (EEG), and polysomnography (PSG). This paper we propose a scheme to analyze sensing data measured by high-sensitive pressure sensor, and then recognize statuses on bed and measure vital signs. Three statuses of activities on bed are recognized, including, lying on bed, flipping, and nobody. Two types of vital signs are measured, namely, breathing rate and heart rhythm. Furthermore, the proposed scheme is capable of identifying either living person or inanimate. The experiment results demonstrate that our scheme has high performance to extract useful features when people lie on bed.