基于模糊神经网络的人体摔倒特征参数算法研究

Research on Fusion Algorithms of Human Fall Characteristic Parameters Based on Fuzzy Neural Network

提出基于模糊神经网络的人体摔倒检测方案,以运动数据、脉搏信号和温度作为特征参量,设计采用三种传感器提供不同的人体信息信号,将模糊算法与神经网络算法融合,计算摔倒报警概率。实验结果表明,该系统能够提高摔倒检测的准确率,降低误报率。

A scheme of human fall detection based on fuzzy neural network is proposed.Motion data,pulse signal and temperature are taken as characteristic parameters.Three kinds of sensors are designed to provide different human body information signals.Fuzzy algorithm and neural network algorithm are combined to calculate the fall alarm probability.The experimental results show that the sys⁃tem can improve the accuracy of fall detection and reduce the false alarm rate.