摘要：【中文】本发明提供了一种基于BP神经网络的老年人摔倒检测方法及系统。采用三层BP反向神经网络，并在网络训练过程中对神经元权值和学习率进行调整，使算法计算速度大大提升，便于硬件实现，并具有更高的摔倒检测准确率。实现该方法的系统包括电源模块、数据采集模块、数据处理模块和GSM短信通信模块，可及时进行摔倒报警；同时，系统整体体积较小，便于佩戴，耗电低，续航时间长。 【EN】The invention provides a BP neural network-based old people tumbling detection method and system. The three-layer BP reverse neural network is adopted, and the weight and the learning rate of the neurons are adjusted in the network training process, so that the algorithm calculation speed is greatly improved, the hardware implementation is facilitated, and the falling detection accuracy rate is higher. The system for realizing the method comprises a power supply module, a data acquisition module, a data processing module and a GSM short message communication module, and can alarm tumbling in time; meanwhile, the whole system is small in size, convenient to wear, low in power consumption and long in endurance time.