Enhanced Crisis Management: Predictive Strategy for Human Blood Group and Organ Demand using Polynomial Random Forest Algorithm
Karthik Elangovan1, Sethukarasi.T2
1Karthik Elangovan, Assistant Professor, Department of Computer Science and Engineering, S.A. Engineering College, Thiruverkadu (Tamil Nadu), India.
2Dr. Sethukarasi.T, Professor and Head, Department of Computer Science and Engineering, R.M.K Engineering College, Gummidipoondi (Tamil Nadu), India.
Manuscript received on 29 May 2019 | Revised Manuscript received on 11 June 2019 | Manuscript Published on 22 June 2019 | PP: 647-650 | Volume-8 Issue-3S, February 2019 | Retrieval Number: C11380283S19/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Prediction is one of the important tasks in the Machine learning. It is the emerging trend in the Data mining as an era of internet the data has evolved into big data in the concern of volume, velocity, veracity and verity. There is a tremendous growth in the prediction techniques thereby a huge volume of data has been used and processing speed has increased through In-memory analytics. Prediction attempts to identify a new pattern that helps to predict the future events. Structured data are being collected from the various resources such as web content, social networks, sensors and made available across different domain. This paper focuses on predicting the events which make crisis in future, as of to whether they may happen or not. Proposed algorithm is Polynomial Random Forest Prediction which finds out the expected probability for the event to happen in terms of percentage. This algorithm takes a cluster of attributes as input from a data source that may depict the present condition along with an interrogative attributes that the user may want to know by the predictive capability of the algorithm. The percentage is further calculated using polynomial equations, data mining, and random forest. Hence empirically we could calculate the probability of occurrence of the event in future. This predictive model can be used for various applications amongst which we focus on human blood group and organ demands.
Keywords: Data Mining, Machine Learning, Percentage, Probability, Prediction, Random forest.
Scope of the Article: Algorithm Engineering