首页> 外文期刊>Arabian Journal for Science and Engineering. Section A, Sciences >Spark-Based Parallel Method for Prediction of Events
【24h】

Spark-Based Parallel Method for Prediction of Events

机译:基于Spark的事件并行预测方法

获取原文
获取原文并翻译 | 示例
           

摘要

Prediction of events is imperative in many areas of social network (SN) applications. These events influence the temporalevolutionary characteristic of social networks. A study of these events can give better insights to understand the evolutionarypatterns (communities) in social networks. One of the major challenges in such implementation is the processing and structuringof large datasets to suitMLmodels. This paper proposes a Spark-based parallelmethod for detection, mining, and prediction ofthese events that influence the evolution of communities in a temporal SN. The proposed framework processes large temporaldata (taken from the DBLP dataset), uses parallel algorithms to detect the structural changes, and applies ML techniquesto predict the future structural changes (events). The proposed methodology uses ensemble ML methods in the Spark MLpipeline to achieve the desired performance and accuracy. The experimental results justify that the proposed framework canpredict future events with an accuracy of 82% and saves 99% of computational time.
机译:在社交网络(SN)应用程序的许多领域中,事件的预测势在必行。这些事件影响着社交网络的时间演化特征。对这些事件的研究可以为理解社交网络中的进化模式(社区)提供更好的见解。这种实现的主要挑战之一是处理和构造适合于ML模型的大型数据集。本文提出了一种基于Spark的并行方法,用于检测,挖掘和预测这些事件,这些事件会影响时态SN中的社区演化。提出的框架处理大量的时间数据(来自DBLP数据集),使用并行算法检测结构变化,并应用ML技术来预测未来的结构变化(事件)。所提出的方法在Spark MLpipeline中使用集成ML方法来实现所需的性能和准确性。实验结果证明,提出的框架可以以82%的精度预测未来事件,并节省99%的计算时间。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号