基于随机Dropout深度信念网络的移动用户行为识别方法

针对移动用户行为识别模型中存在过度拟合导致泛化性差的问题，提出一种基于随机Dropout深度信念网络DBN(Deep Belief Network)的移动用户行为识别方法，该方法通过随机更改Dropout算法中的概率参数，减少隐层单元的网络节点数，优化每次训练的网络权值，以提高行为识别的准确率和样本较少时的泛化能力。实验结果表明，加入随机Dropout的网络对静止、散步、跑步、上楼及下楼五种行为的平均识别准确率可达94.23%，相对于传统的DBN识别方法，准确率提高了4.57%。

Human activity recognition method based on random Dropout deep belief networks

For the problem of mobile user activity model over-fitting which leads to the generalization of the problem, an improved mobile user activity recognition method of Dropout DBN (deep belief network) is put forward. The method is through randomly changing the probability parameters in algorithms of Dropout, reducing the number of hidden units of network nodes, optimizing the network weight in each training, this method improves the accuracy of recognition and generalization when the number of sample decreases. Experimental results show that the average recognition accuracy rate for five activities walking, running, upstairs and downstairs reaches 94.23% by using random Dropout network,, recognition accuracy improves 4.57%.