马尔可夫预测的移动群智感知网络日志信息收集  

Mobile group intelligence aware network log information collection based on Markov prediction

作　　者：蔡波 CAI Bo(School of Electronic Information and Electrical Engineering,Shangluo University,Shangluo 726000,Shaanxi,China)

机构地区：[1]商洛学院电子信息与电气工程学院,陕西商洛726000

出　　处：《西安工程大学学报》2022年第1期115-120,共6页Journal of Xi’an Polytechnic University

基　　金：国家自然科学基金项目(19BTJ017);陕西省教育科学研究所项目(13syk025)。

摘　　要：针对传统信息收集方法存在收集任务完成率低和剩余比例大的问题,采用多感知位置的马尔可夫预测模型,对移动群智感知网络日志实时信息进行动态收集。采用轨迹序列的生成算法,提取移动用户轨迹的序列。利用多感知的互补控制方法,得到学习转移概率矩阵。采用改进方法可有效提高任务完成比例。通过对问题进行描述,引入多感知位置的马尔可夫预测模型,给出详细的预测步骤,并进行信息动态收集。结果表明,文中改进方法的任务完成率约为93.24%,剩余比例最高为96.84%。Aiming at the problems of low completion rate and large remaining proportion of collection tasks in traditional information collection methods,the Markov prediction model of multi sensing location is used to dynamically collect the real-time information of mobile group intelligence sensing network logs.The trajectory sequence generation algorithm was used to extract the trajectory sequence of mobile users.Using the multi perception complementary control method,the learning transition probability matrix was obtained.Adopting improved methods could effectively improve the proportion of task completion.By describing the problem,the Markov prediction model of multi sensing location was introduced,the detailed prediction steps were given,and the information was collected dynamically.The experimental results show that the task completion rate of the improved method in this paper is about 93.24%,and the highest remaining proportion is 96.84%.

关 键 词：马尔可夫预测模型 移动群智感知网络 日志信息 信息收集 多感知位置 

分 类 号：TP319[自动化与计算机技术—计算机软件与理论]