基于贝叶斯分析的阶段性自主体育锻炼行为预测

为了提高阶段性自主体育锻炼行为分析和判断能力，提出基于贝叶斯分析的阶段性自主体育锻炼行为预测方法。构建阶段性自主体育锻炼行为预测的统计时间序列分析模型，采用大数据特征检测方法进行体育锻炼行为大数据挖掘和特征提取，基于贝叶斯分析预测思想进行行为统计特征序列的有序聚类，结合模糊C均值聚类分析方法进行体育锻炼行为预测过程中的信息聚类和属性归并，提取统计时间序列的关联规则特征量，在加权马尔可夫链中实现对阶段性自主体育锻炼行为量的准确预测。仿真结果表明，采用该方法进行阶段性自主体育锻炼行为预测的准确性较高，提高了自主体育锻炼行为的量化分析能力。

Prediction of Phased Autonomous Physical Exercise Behavior Based on Bayesian Analysis

In order to improve the ability of analyzing and evaluating the behavior of phased independent physical exercise, this paper puts forward a prediction method based on Bayesian analysis. It constructs the statistical time sequence analysis model of phased independent physical exercise behavior prediction with the big data feature detection method to explore and extract the big data of physical exercise behavior. Based on the Bayesian analysis and prediction idea, orderly clustering of the behavior statistical feature sequence is carried out, and the information clustering and categorizing in the process of physical exercise behavior prediction are combined with fuzzy C-means clustering analysis method in this paper.Characteristic quantity of associated rule for the statistical time sequence is extracted, and the phased independent physical exercise behavior is accurately predicted in the weighted Markov chain. The simulation results show that the accuracy of this method is high, and the ability of quantitative analysis of autonomous physical exercisehas been improved.