Heart rate (HR) signal analysis is widely used in the medicine and medical research area. Physical activities (PA) are commonly recognized to greatly affect the changes of heart rate. However, the direct relationship between heart rate and physical activities is hard to describe. In this paper, a model using feedforward neural network with the function of HR prediction is designed. This model reflects the effect how PA affect HR. Experiments was conducted based on the reallife signals from a healthy male. The mean absolute error of the predicted heart rate was relatively small. The result shows the potential of the proposed method.