Research on Efficiency Optimization Method for High Dimensional Big Data Mining Based on Improved SALS Algorithm
In response to the problems of low number of successful tasks and long execution time in the application of traditional methods for efficiency optimization in high-dimensional big data mining,the efficiency optimization effect is not ideal.Therefore,a research on high-dimensional big data mining efficiency optimization method based on improved SALS algorithm is proposed.This paper builds a high-dimensional big data mining model,describes the state of high-dimensional big data mining,uses local smooth-ing processing algorithm to determine the progress of high-dimensional big data mining,judges whether the efficiency of high-dimensional big data mining is low,and uses the improved SALS algorithm to optimize the task queue,schedule idle nodes,and dy-namically schedule tasks under low efficiency conditions to achieve efficiency optimization.Experimental results have shown that the application of design methods has effectively increased the number of successful data mining tasks,has shortened the execution time of tasks,and has achieved good efficiency optimization effects.
improving SALS algorithmhigh dimensional big dataexcavateefficiency optimizationlocal smoothing processing algorithm
NETL
NSTL
万方数据
