Real-Time IoT Data Analytics Architecture

IoTRLab Internet of Things Research Laboratory

Sakarya University

Project Title: A New Real-Time IoT Data Analytics Architecture

Team: Celal ÇEKEN,Ph.D Mohammed Al-Hubaishi,Ph.D. Candidate Nur Banu OĞUR, Ph.D. Candidate

Sponsors: Sakarya University

Start Date: 2018

Project Overview

The importance of big data analytics has become apparent with the increasing volume of data on the Internet. The amount of data will increase even more with the widespread use of Internet of Things (IoT). One of the most important application areas of the IoT is healthcare. This study introduces new real-time data analytics architecture for an IoT-based smart healthcare system, which consists of a wireless sensor network and a radio-frequency identification tech- nology in a vertical domain. The proposed platform also includes high- performance data analytics tools, such as Kafka, Spark, MongoDB, and NodeJS, in a horizontal domain.

Project Video

Publications

Nur Banu Oğur, Mohammed Al-Hubaishi, Celal Çeken "IoT Data Analytics Architecture for Smart Healthcare Using RFID and WSN", ETRI Journal, 44.1, 135-146, 2022, DOI: 10.4218/etrij.2020-0036
Oğur, N., Çeken, C., "Real Time Data Analytics Architecture for ECG", UBMK'18, Sarajevo, Bosnia-Herzegovina, 2018
Celal Çeken, Mohammed Al-Hubaishi "Integrating SDN-Enabled Wireless Sensor Networks Into the Internet", The 10th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications, Metz, France, 2019, pp. 1090-1094. DOI: 10.1109/IDAACS.2019.8924258

In this project, a new real-time data analytics testbed is proposed for IoT-based systems. In the vertical domain, the proposed platform includes a Wireless Sensor Network (WSN) which was modeled and simulated using Riverbed Modeler. Additionally, the horizontal domain of the testbed has i) a Kafka messaging system that distributes incoming data to different points ii) a web application to visualize the temperature values, in real-time, iii) a Spark platform for real-time data analytics, and v) a NoSQL database that stores incoming data. The study reveals that the vertical domain of any IoT system can be modeled and simulated using Riverbed Modeler. In other words, the proposed architecture combines real data analytics sub-system with a simulation environment and, consequently, can be used as a time- saving experimental environment for IoT-based big data analytics.

Simulation Results

In order to investigate the performance of the system developed, the diagnosis of Wolf Parkinson White (WPW) syndrome by logistic regression is discussed as a case study. The results show that the proposed IoT data analytics system can process health data in real-time, successfully, and is capable of handling large volumes of data easily owing to the scalable technologies deployed in it.