In the current era, data are growing with a faster rate in terms of exponential form where these data create a major challenge for suitable classification to classify the statistical data. The relevance of this topic is extraction of data, insights, mining of information from the dataset with an efficient and faster manner has attracted attention towards the best classification strategy. This paper presents a Ranger Random forest (RRF) algorithm for high-dimensional data classification. Random Forest (RF) has been treated as a most popular ensemble technique of classification due to its measure variable importance, out-of-bag error, proximities, etc. To make the classification constraint possible, in this paper, we use three different datasets in order to accommodate the runtime and memory utilization effectively with the same efficiency as given by the traditional random forest. We also depict the improvements of Random Forest in terms of computational time and memory without affecting the efficiency of the traditional Random Forest. Experimental results show that the proposed RRF outperforms with others in terms of memory utilization and computation time.
CITATION STYLE
Rao, G. M., Ramesh, D., & Kumar, A. (2020). RRF-BD: Ranger Random Forest Algorithm for Big Data Classification. In Advances in Intelligent Systems and Computing (Vol. 990, pp. 15–25). Springer. https://doi.org/10.1007/978-981-13-8676-3_2
Mendeley helps you to discover research relevant for your work.