Research Of Quality Optimal Control Method Of Big Data For Remote Health Care Monitoring

Big data-based remote health care monitoring technology is an effective health care services technology.With the improvement of living standards,the demand for remote health care services is increasing.However,telemonitoring technology is not very perfect.Through the study of the Big data quality optimization control method of remote health monitoring,the data quality in the remote health monitoring system is solved,so as to realize the assistant decision of health condition,and solve the problem of unaverage distribution of medical resources.This paper studies the research on the quality optimization control method of remote health monitoring data,including the abnormal data recognition algorithm,the missing data filling algorithm and the repeated data detection algorithm.Finally,based on remote health monitoring data,simulation and analysis are carried out.Specific work is described as follows:1.Proposed the overall design of large data quality optimization control scheme for remote health surveillance.Through the health data processing scheme,the data quality is optimized and controlled,and the key technologies such as abnormal data recognition,missing data filling and repeated data detection.2.Proposed an anomaly data recognition algorithm based on improved Grubbs test.By analyzing the shortage of Grubbs test method and the actual situation of health data,an abnormal data recognition algorithm based on improved Grubbs test method is proposed in this basic principle.Simulation results show that the algorithm can solve the problem of abnormal values of health data well.3.Proposed a missing data filling algorithm based on improved K-means algorithm and expectation maximization method.The K-means algorithm is optimized based on the artificial fish swarm algorithm,and then the missing data is filled based on the optimized K-means algorithm.The simulation results show that the classification accuracy of the optimized K-means algorithm is improved,and the missing data filling algorithm based on the optimized K-means has shorter time to fill the missing data.4.Proposed a repeated data detection algorithm based on particle swarm optimization and basic neighbor sorting algorithm to detect repeated health data.By coding the parameters of the basic nearest neighbor sorting algorithm as a whole parameter,the optimal particle group individual is decoded after the optimization of particle swarm optimization,and the optimal parameters of the basi c nearest neighbor sorting algorithm are obtained.The simulation results show that the detection precision of the optimized basic nearest neighbor algorithm is improved,and the repeated data detection algorithm based on the optimized basic nearest neighb or sorting algorithm has a shorter time to detect repeated data.