Affiliations: [a] College of Computer Science and Engineering at Yanbu, Taibahu University
| [b] Dean of the College of Computer Science and Engineering
| [c] Taibah University, College of Computer Science and Engineering in Yanbu, Madinah, Saudi Arabia
| [d] Faculty of Engineering, Department of Computers Engineering, and Control Systems, Mansoura University, Mansoura, Egypt
Correspondence:
[*]
Correspondence to: Mostafa A. Elhosseini, Taibah University, College of Computer Science and Engineering in Yanbu, Madinah, Saudi Arabia and Faculty of Engineering, Department of Computers Engineering, and Control Systems, Mansoura University, Mansoura, Egypt. E-mail: mmaoustafa@taibahu.edu.sa.
Abstract: The total number of pilgrims for the Hajj Season of 1438H reached 2,352, 122 — according to the General Authority for statistics Kingdom of Saudi Arabia. Pilgrims data analysis and prediction help concerned entities of the country in the future planning programs for the purpose of ensuring the necessary services — social, health, security, food and transportation services to name a few. Predictive analytics is the process of using data along with analysis, statistics, and machine learning techniques to create a predictive model for forecasting future events. Predictive analytics is often discussed in the context of big data as businesses apply algorithms to derive insights from large datasets using a framework like Hadoop, HDFS, and Spark. Building MATLAB-based framework for data analytics applied to Hajj dataset is the main aim of this research paper. The proposed framework is mainly relying on four main concepts; namely the cloud-based Internet of things (IoT), fog, Edge-of-Things (EoT), and predictive analytics. This proposed framework helps in reducing the amount of data sent, lowering network traffic, increasing bandwidth, and reducing power energy consumption. On top that, the framework including regression has the potential to predict how likely Hajj is susceptible to illness or even death.
Keywords: Big data, cloud, Edge-of-Things (EoT), health, Internet of Things
(IoT), pilgrim, prediction
