Energy Efficient Data Mining Scheme for Big Data Biodiversity Environment
Mohammad Abdulaziz Alwadi, Girija Chetty · University of Canberra Research Portal · 2014
In this paper, we propose a novel energy efficient data mining scheme for big data biodiversity environment. Efficient machine learning and data mining techniques provide an unprecedented opportunity to monitor and characterize big data biodiversity environments, such as forest cover type, monitored using low cost wireless sensor networks. However, given the sheer amount of data collected by the wireless sensor networks, conventional classification schemes that demand enormous storage and computation requirements make them less effective for real world real time deployments. There is a need for intelligent and energy efficient monitoring techniques for such environments, made possible by adapting the traditional data mining and classification algorithms to work for big data environments. The work reported in this paper involves an effective scheme for big data environment based on random forests and ensemble classifiers, which have an inherent capability to address the three Vs (Volume, Velocity and Variety) of big data problems.