An Enhanced Framework To Secure Big Data Based on Hybrid Machine Learning Technique: ANN-PSO
Salim Raza Qureshi
Assoc. Prof. Salim Raza Qureshi, Department of Computer Science and Engineering, Model Institute of Engineering and Technology, Jammu, India.
Manuscript received on February 11, 2021. | Revised Manuscript received on February 20, 2021. | Manuscript published on March 30, 2021. | PP: 76-84 | Volume-9 Issue-6, March 2021. | Retrieval Number: 100.1/ijrte.F5385039621 | DOI: 10.35940/ijrte.F5385.039621
Open Access | Ethics and Policies | Cite | Mendeley
© 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: With the advancement of smart devices and cloud computing, more and more public health data can be collected from various sources and analyzed in unprecedented ways. The enormous social and academic impact of this development has led to a global buzz for bigdata. Moreover, due to the massive data source, the security of big data in the cloud is becoming an important issue. In these days, various issues have arisen in the field of big data security, such as Infrastructure security, data confidentiality, data management and data integrity. In this paper, we propose a novel technique based on Artificial Neural Network-and Particle Swarm Optimization Algorithm (ANN-PSO) for enabling a highly secured framework. The ANN-PSO method was created to predict health status from a database and its functions were selected from these data sets. The particle swarm optimization algorithm matches the ANN for better results by reducing errors. The results show the potential of the ANN-PSO-based methodology for satisfactory health prediction results. This proposed approach will be tested using large medical data in a Hadoop environment. The proposed work will be carried out in the JAVA work phase.
Keywords: ANN-PSO, Accuracy, Classifier, Error, GOA, Health condition.