基于基因表达式编程的多数据流压缩并行算法  

A Parallel Compression Algorithm for Multi-Streams Based on Gene Expression Programming

作　　者：杨文[1] 李文敬[1] 罗锦坤[1] 

机构地区：[1]广西师范学院计算机与信息工程学院,广西南宁530023

出　　处：《微电子学与计算机》2011年第8期94-96,101,共4页Microelectronics & Computer

基　　金：广西自然科学基金项目(0991105);2009年度广西教育厅科研项目(200911MS144)

摘　　要：针对大规模数据流需要巨量存储空间,以及串行处理速度瓶颈,着力于解决处理后的精确度及数据压缩.在并行平台下,利用阈值滑动窗口技术将数据流分段送入各处理器,并使用基因表达式编程(Gene Expression Programming,GEP)的函数发现算法实现对数据模型的函数挖掘,提出了基于基因表达式编程的多数据流压缩并行函数替代算法PFR-GEP(Parallel Function Replace-GEP).在PC机群上的实验结果表明:该算法有效提高了压缩比例与运算速度,且具有线性加速比.As considering the limitation both in huge amount memory space and the speed serial processing of the large-scale flow of data,this paper aims at dealing with the accuracy and data compression after the process.In parallel platform,by taking advantage of threshold sliding window technology,the flow of data is led into each processor in sections.In addition,function mining of the data model comes true under the help of function found algorithm of the Gene Expression Programming（GEP）.As mentioned above,proposing the multiple data compression algorithm based on Gene expression programming for Parallel Function Replace algorithm PFR-GEP（Parallel Function Replace-GEP）.The results on PC cluster shows that the algorithm effectively improve the compression ratio and computational speed,and has a linear speedup.

关 键 词：并行算法 阈值滑动窗口 基因表达式编程 函数发现 多数据流 压缩算法 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]