7 August 2017 Customizing FP-growth algorithm to parallel mining with Charm++ library
Author Affiliations +
Proceedings Volume 10445, Photonics Applications in Astronomy, Communications, Industry, and High Energy Physics Experiments 2017; 104452L (2017) https://doi.org/10.1117/12.2281037
Event: Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2017, 2017, Wilga, Poland
Abstract
This paper presents a frequent item mining algorithm that was customized to handle growing data repositories. The proposed solution applies Master Slave scheme to frequent pattern growth technique. Efficient utilization of available computation units is achieved by dynamic reallocation of tasks. Conditional frequent trees are assigned to parallel workers basing on their workload. Proposed enhancements have been successfully implemented using Charm++ library. This paper discusses results of the performance of parallelized FP-growth algorithm against different datasets. The approach has been illustrated with many experiments and measurements performed using multiprocessor and multithreaded computer.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Marek Puścian, Marek Puścian, } "Customizing FP-growth algorithm to parallel mining with Charm++ library", Proc. SPIE 10445, Photonics Applications in Astronomy, Communications, Industry, and High Energy Physics Experiments 2017, 104452L (7 August 2017); doi: 10.1117/12.2281037; https://doi.org/10.1117/12.2281037
PROCEEDINGS
8 PAGES


SHARE
Back to Top