基于卷积神经网络的智能医疗护理研究

Research on Intelligent Medical Care Based on Convolution Neural Network

为了提高智能医疗护理水平,减少护理工作量,节约医院成本。提出一种基于卷积神经网络的病人体态行为特征提取算法,该算法采用双网络模型设计,包括病人检测网络模型和病人体态行为特征提取模型,应用该算法到病人体态行为检测系统中,从而实现对病人的识别监控,提高智能医疗护理水平。最后,通过开源框架平台,对病人行为检测系统进行测试,实验结果表明,测试数据集合越大,病人体态行为特征提取精度越高,对病人体态行为类别的平均识别率97.6%,从而验证了系统的有效性和正确性。

In order to improve the level of intelligent medical care, reduce the workload of nursing, saving hospital costs. This paper presents a neural network based on convolution patients posture behavior feature extraction algorithm, this algorithm adopts double network model is designed, including the posture detection network model and patients behavior feature extraction model, applied the algorithm to the patients posture behavior detection system, so as to realize the recognition of patient monitor and improve the intelligent level of medical care. Finally, the open source framework platform is used to test the patient behavior detection system. The experimental results show that the larger the test data set is, the higher the accuracy of the extraction of patients’ posture behavior characteristics is. The average recognition rate of patients’ posture behavior categories is 97.6%, which verifies the effectiveness and correctness of the system.