作　　者： ; ; ;

机构地区： 佛山职业技术学院

出　　处： 《计算机应用研究》 2019年第7期2065-2069,共5页

摘　　要： 带有传感器的可穿戴式医疗设备不断生成大量数据,由于数据的复杂性,难以通过处理和分析大数据来找到有价值的决策信息。为了解决这个问题,提出一种新的物联网体系结构,用于存储和处理医疗应用的可扩展传感器数据(大数据)。所提出的架构主要由Metafog重定向(MF-R)架构和AWS密钥管理机制两个子架构组成。MF-R架构使用Apache Pig和Apache HBase等大数据技术来收集和存储不同传感器设备生成的传感器数据,并利用卡尔曼滤波消除噪声;AWS密钥管理机制使用密钥管理方案,目的是保护云中的数据,防止未经授权的访问。当数据存储在云中时,所提出的系统能够使用随机梯度下降算法和逻辑回归来开发心脏病的预测模型。仿真实验表明,与其他几种算法相比,提出的算法具有更小的误差,且在吞吐量、准确度等方面具有一定的优越性。 Wearable medical devices with sensor continuously generate enormous data, due to the complexity of the data, it is difficult to process and analyze the big data for finding valuable information that can be useful in decision-making. In order to overcome this issue, this paper proposed a new architecture for the implementation of IoT to store and process scalable sensor data (big data) for health care applications. The proposed architecture consisted of two main sub architectures, namely, Meta fog-redirection (MF-R) and AWS key management mechanism. MF-R architecture used big data technologies such as Apache Pig and Apache HBase for collecting and storing the sensor data generated from different sensor devices and it also used Kalman filter for removal of noise. AWS key management mechanism used a key management scheme to protect data in the cloud and prevent unauthorized access. When data was stored in the cloud, the proposed system could use stochastic gradient descent algorithms and logistic regression to develop a predictive model of heart disease. Simulation experiments show that compared with other algorithms, the proposed algorithm has smaller error and it has certain advantages in terms of throughput and accuracy.

关 键 词： 无线传感器网络 物联网 大数据 卡尔曼滤波 云计算 密钥管理机制

领　　域： []