Research On Optimization Of Apriori Algorithm Based On Cloud Computing And Medical Data

With the continuous development of medical industry, the scale of medical data become much bigger, and the value become much higher, the concept of medical big data has become the study goal of lots of experts and scholars. In the face of huge data size of medical high data, traditional storage structure can not meet the demand, and the appearance of cloud computing provides medical big data a perfect solution for storage and usage. The value of potential information in medical big data is infinite, how to dig out the potential information is the focus of study. The technology of data mining and association rule mining is an important technique to show the value of medical big data, but the traditional mining algorithms cannot satisfy the medical big data and cloud computing requirements, the improvement and optimization of the algorithm, which applies to medical cloud platform, will be an important direction for future research.This paper firstly proposes a architecture scheme of medical cloud platform based on the concept of medical big data and cloud computing, including data acquisition layer, data storage layer, data mining layer, enterprise-level database, and application layer.Then this paper analyzes the association rule algorithm in medical data mining technology, on the premise of association-rule-based classical Apriori algorithm, interest measure threshold is introduced to improve the algorithm. At the same time, with the usage of cloud computing and cloud platform Hadoop, a new association rule algorithm of medical data mining, based on MapReduce and interest measure, is put forward.At the end of this paper, a simulation experiment is carried out based on Hadoop, the algorithm is programmed by JAVA. By mining the training data set, the result shows that the improved algorithm has lower space complexity and changes linearly with the growth of data, which proves the superiority of the improved algorithm.