An Overview of IoT Sensor Data Processing, Fusion, and Analysis Techniques.

Anand Nayyar,Basit Qureshi,Dhanalekshmi Gopinathan,Adarsh Kumar,Rajalakshmi Krishnamurthi

doi:10.3390/s20216076

Abstract

In the recent era of the Internet of Things, the dominant role of sensors and the Internet provides a solution to a wide variety of real-life problems. Such applications include smart city, smart healthcare systems, smart building, smart transport and smart environment. However, the real-time IoT sensor data include several challenges, such as a deluge of unclean sensor data and a high resource-consumption cost. As such, this paper addresses how to process IoT sensor data, fusion with other data sources, and analyses to produce knowledgeable insight into hidden data patterns for rapid decision-making. This paper addresses the data processing techniques such as data denoising, data outlier detection, missing data imputation and data aggregation. Further, it elaborates on the necessity of data fusion and various data fusion methods such as direct fusion, associated feature extraction, and identity declaration data fusion. This paper also aims to address data analysis integration with emerging technologies, such as cloud computing, fog computing and edge computing, towards various challenges in IoT sensor network and sensor data analysis. In summary, this paper is the first of its kind to present a complete overview of IoT sensor data processing, fusion and analysis techniques.

Highlights

In the coming years of the Internet of Things (IoT), context-awareness bridges the interconnection between the physical world and virtual computing entities, and involves environment sensing, network communication, and data analysis methodologies [1]
These sensors are highly vulnerable to failure, attacks, and easy breakdown, leading to losses of sensor data and inaccurate information; Real-Time Processing—The sensor network will be capable of more complex networking tasks, and can perform the transformation of raw sensor data into more valuable and insightful information in real-time; Scalability—In the physical world, the sensor network includes data sources from numerous sensors and actuators
IoT Sensor Data Processing In IoT sensor networks, wireless communication protocols are popularly used for the information exchange process

Summary

Introduction

In the coming years of the Internet of Things (IoT), context-awareness bridges the interconnection between the physical world and virtual computing entities, and involves environment sensing, network communication, and data analysis methodologies [1]. Machine learning and deep learning techniques provide a promising solution towards the analysis of IoT sensor data [14,15,16]. Incorporating these data analysis techniques results in deep insights into sensor data, and provides good knowledge related to hidden data patterns and further decision-making In this respect, this paper elaborates on various existing data analysis approaches. The interaction of these modules along with the IoT sensor network; To discuss the IoT sensor output characteristics, such as the voluminous IoT sensor data, heterogeneity, real-time processing, and scalability factors; To explain the mechanism of data processing techniques so as to address various issues in. IoT sensor data, such as data denoising, missing value imputation, data outlier detection, and data aggregation; To address the importance of deep learning and machine learning models for IoT sensor data analysis.

Basic Architecture

IoT Sensor Data Processing

Denoising

Missing Data Imputation

Data Outlier Detection

Data Aggregation

Data Fusion

Data Analysis

Findings

Conclusions