The conventional falling detections are hard to seek the optimal thresholding values, if new types of the falls or dailylife activities are added to the algorithms.
In this paper, we propose a new algorithm based on the back propagation neural
network to recognize the patterns of the falls and the other
activities. The advantages of the proposed algorithm is that the
neural network can easily learn the patterns of the new falls or
activities. The paper is organized as follows. In section 2, the
basic theories of back propagation neural network are given. In
section 3, the hardware architecture is implied. In section 4, the
proposed algorithm is described. In section 5, the experiments
are shown. Finally, the conclusion is discussed.