Big Data Analytics for Internet of Things

Tausifa Jan Saleem, Mohammad Ahsan Chishti, Tausifa Jan Saleem, Mohammad Ahsan Chishti

• Publisher: Wiley
• Year: 2021
• ISBN:
  9781119740773
• Edition: 1
• Topic: Mathematics
• Subtopic: Probability & Statistics
• Index: Mathematics

BIG DATA ANALYTICS FOR INTERNET OF THINGS

Discover the latest developments in IoT Big Data with a new resource from established and emerging leaders in the field

Big Data Analytics for Internet of Things delivers a comprehensive overview of all aspects of big data analytics in Internet of Things (IoT) systems. The book includes discussions of the enabling technologies of IoT data analytics, types of IoT data analytics, challenges in IoT data analytics, demand for IoT data analytics, computing platforms, analytical tools, privacy, and security.

The distinguished editors have included resources that address key techniques in the analysis of IoT data. The book demonstrates how to select the appropriate techniques to unearth valuable insights from IoT data and offers novel designs for IoT systems.

With an abiding focus on practical strategies with concrete applications for data analysts and IoT professionals, Big Data Analytics for Internet of Things also offers readers:

• A thorough introduction to the Internet of Things, including IoT architectures, enabling technologies, and applications
• An exploration of the intersection between the Internet of Things and Big Data, including IoT as a source of Big Data, the unique characteristics of IoT data, etc.
• A discussion of the IoT data analytics, including the data analytical requirements of IoT data and the types of IoT analytics, including predictive, descriptive, and prescriptive analytics
• A treatment of machine learning techniques for IoT data analytics

Perfect for professionals, industry practitioners, and researchers engaged in big data analytics related to IoT systems, Big Data Analytics for Internet of Things will also earn a place in the libraries of IoT designers and manufacturers interested in facilitating the efficient implementation of data analytics strategies.

1
Big Data Analytics for the Internet of Things : An Overview

Tausifa Jan Saleem¹ and Mohammad Ahsan Chishti²

¹ Department of Computer Science and Engineering, National Institute of Technology Srinagar, India

² Department of Information Technology, Central University of Kashmir, Kashmir, India

Internet of Things (IoT) is an emerging idea that has the prospective to completely reform the outlook of businesses. The goal of the IoT is to transmute day‐to‐day objects to being smart by utilizing a broad range of sophisticated technologies, from embedded devices and communication technologies to data analytics. IoT is bound to transform the ways of our everyday working and living. The number of IoT devices is anticipated to amount to several billion in the next few years. This unpredictable growth in the number of devices connected to IoT and the exponential rise in data consumption manifest how the expansion of big data seamlessly coincides with that of IoT. The growth of big data and the IoT is swiftly accelerating and affecting all areas of technologies and businesses. The main objective of data analytics in IoT is to identify trends in the data, extract concealed information, and to dig out valuable information from the raw data generated by IoT systems. This is extremely crucial for dispensing elite services to IoT users. In this regard, investigating the technological advancements in the said area becomes indispensable. To this purpose, this book uncovers the recent trends in big data analytics for IoT applications so that novel, optimized, and efficient designs of IoT use‐cases are formulated.

This book contains high‐quality research articles discussing various aspects of IoT data analytics like enabling technologies of IoT data analytics, types of IoT data analytics, challenges in IoT data analytics, etc. This is critically important for keeping researchers up‐to‐date with the eco‐system they have to deal with. IoT is being used as a field for garnering huge business profits. It is extremely important to squeeze out the best decisions or wisdom from the data that is being fed into the systems of business organizations. The book involves discussions of ways for extracting valuable insights from Big Data. The techniques that are suitable for digging out best decisions from the humungous IoT data to gain control of IoT devices are unleashed in the book. The book discusses almost every aspect of IoT data analytics.

The following topics are explored in this book:

• Enabling technologies for IoT Big Data Analytics
• Machine Learning Techniques for IoT Data Analytics
• Types of IoT Data Analytics
• IoT Data Analytical Platforms
• Challenges in IoT Data Analytics
• Deep Learning Architectures for IoT Data Analytics
• Personalization in IoT
• How IoT makes cities smarter
• Role of IoT and Big Data in Environmental Sustainability
• Synchro‐phasor Data Management in Power Grids
• Autonomous Vehicle Identification in Smart Transportation
• Cloud‐based Water Management System
• Security and Privacy Requirements in IoT
• Mitigation of DDOS attacks
• Opportunities provided by Data Fusion
• Role of IoT and Big Data in Journalism
• Role of IoT and Big Data in Finance

The book comprises of sixteen chapters. Following provides a glimpse of their contribution:

The second chapter entitled “Data, Analytics and Interoperability between Systems (IoT) is Incongruous with the Economics of Technology: Evolution of Porous Pareto Partition (P3)” aspires to inform that tools and data related to the affluent world are not a template to be “copied” or applied to systems in the remaining (80%) parts of the world which suffer from economic constraints. The chapter suggests that we need different thinking that resists the inclination of the affluent 20% of the world to treat the rest of the world (80% of the population) as a market. The 80/20 concept evokes the Pareto theme in P3, and the implication is that ideas may float between (porous) the 80/20 domains (partition).

The third chapter entitled “Machine Learning Techniques for IoT Data Analytics” discusses the various supervised and unsupervised machine learning approaches and their highly significant role in the smart analysis of IoT data. A detailed taxonomy of various machine learning algorithms together with their strengths, challenges and shortcomings is discussed. Following this, a review of application areas and use cases for each algorithm is presented in the chapter. It is quite helpful in having a better understanding of the usage of each algorithm and helps in choosing a suitable data analytic algorithm for a particular problem. The chapter concludes that machine learning has a lot of scope in the world of IoT and is proving highly beneficial for efficient analysis of smart data.

The fourth chapter entitled “IoT Data Analytics using Cloud Computing” discusses the cloud computing framework for IoT data analytics. Moreover, the importance of machine learning in IoT data analytics is also presented in the chapter. The chapter also lists the challenges faced by IoT data analytics when cloud is used as a computing platform.

The fifth chapter entitled “Deep Learning Architectures for IoT Data Analytics” unleashes the opportunities created by Deep Learning in IoT data analytics. Deep Learning has shown phenomenal performance in diverse domains, including image recognition, speech recognition, robotics, natural language processing, human‐computer interface, etc. The chapter provides a description of the various Deep Learning architectures. The role of these Deep Learning architectures in IoT data analytics is also presented in the chapter.

The sixth chapter entitled “Adding Personal Touches to IoT: A User‐Centric IoT Architecture” focuses on the use of the concept of personalization to achieve the goal of taking the human‐computer interaction to the next level. Personalization is a powerful instrument that has the potential of shaping the quality of IoT products and services to keep pace with the constantly evolving customer needs. Use cases and real‐life examples are used to demonstrate how using users personal insights spell magic for boosting IoT systems across a variety of domains such as businesses, marketing, recommendation systems and commercial and industrial IoT systems and services. The chapter investigates how personalization is assuming an important, irreplaceable role in the development of IoT systems being deployed across multiple domains and the lives of associated varied strata of users such as the business owners, marketing professionals, business analysts, data analysts, designers and the end‐user. The work takes stock of the current scenario and establishes through use cases, and examples that personalization is already being exploited for huge benefits but the concept itself is being given a rather ad‐hoc treatment. This is evident as personalization finds no mention in the IoT architecture itself. It is left to dangle on as a last‐minute job in most of the IoT systems developed so far. Concerns regarding the usage of personalization viz. privacy and the filter bubble have also been taken into consideration to point out the future directions of work in Big Data Analytics of IoT systems.

The seventh chapter entitled “Smart Cities and the Internet of Things” investigates the development of smart cities from a perspective of the IoT. The chapter uses existing examples of smart cities to forecast what the future holds for cities seeking to utilize the IoT in optimizing their operations and resource usage.

The eighth chapter entitled “A Roadmap for Application of IoT Generated Big Data in Environmental Sustainability” describes the role of IoT generated big data in environmental sustainability. The chapter proposes a roadmap for achieving better environmental sustainability. Moreover, the obstacles that create hindrance in environmental sustainability are also discussed in the chapter.

The ninth chapter entitled “Application of High‐Performance Computing in Synchrophasor Data Management and Analysis for Power Grids” discusses the various problems associated with the big data analysis with particular reference to Phasor Measurement Unit’s (PMU) data handling and introduces the modern techniques and tools to resolve those pitfalls.

The tenth chapter entitled “Intelligent enterprise‐level big data analytics for modelling and management in smart internet of roads” proposes a method based on Fully Convolutional Neural Network for semantic segmentation of vehicle license plates in a complex and multi‐language environment. First, the license plates are detected, and then digits in the license plates are segmented. The performance of the proposed algorithm is evaluated using a dataset of real and manually generated data. The impact of various parameters in improving the accuracy of the proposed algorithm is investigated. The experimental results show that the proposed framework can detect and segment the license plates in complex scenarios, and the results can be used in smart highways and smart road applications.

The eleventh chapter entitled “Predictive analysis of intelligent sensing and cloud‐based integrated water management system” proposes a water management system with following characteristics; real‐time measurement of consumption, monitoring of leakages, ability to control the water supply if there is leakage, a completely automated platform for societies, and apartment complexes to set up their billing system. The proposed system consists of a flow sensor meter installed in the main water inlet pipe that captures information about water usage and communicates through a WiFi network to iOS and Android compatible applications.

The twelfth chapter entitled “Data Security in the Internet‐of‐Things: Challenges and Opportunities” highlights the IoT security threats and vulnerabilities. The chapter categorizes the IoT security based on context of application, architecture and communication. Furthermore, the chapter discusses the research directions in confidentiality, privacy and IoT data security.

The thirteenth entitled “DDoS Attacks: Tools, Mitigation Approaches, and Probable Impact on Private Cloud Environment” discusses the seriousness of the threats posed by DDoS attacks in the context of the cloud, particularly in the personal private cloud. The chapter discusses several prominent approaches introduced to counter DDoS attacks in private clouds. The chapter presents a generic framework to defend against DDoS attacks in an individual private cloud environment taking into account different challenges and issues.

The fourteenth chapter entitled “Securing the Defense Data for Making Better Decisions using Data Fusion” gives an idea of the problems that arise in the defense related IoT‐big data analytics with special attention to its security. Data fusion has been introduced as a probable solution to tackle these problems. The chapter guides the researchers regarding the issues of data fusion, the stages where it could be used and the mathematical techniques that could be adopted to implement it on IoT big data.

The fifteenth chapter entitled “New age Journalism and Big data (Understanding big data & its influence on Journalism)” tries to identify how big data is altering the way journalism is practiced in the twentyfirst century. For the purpose, the chapter takes the case study of award‐winning data journalism projects, which have not only used big data for their stories but also using converging big data with new media practices of interactive visualization, revolutionized the practice of journalism. The chapter not only provides a glimpse into how big data is changing journalism but also critically examines the impact, practices and methods involved to lay forward a guide for future research into this genre. The chapter concludes that both IoT and Big Data have tremendous potential to influence the economies of global markets, and at the same time change, the way content (information) is collected and produced for the audiences.

The last chapter entitled “Two decades of big data in finance: Systematic literature review and future research agenda” presents a review on IoT and big data in finance. The chapter identifies the gaps in the current body of knowledge to deliberate upon the areas of future research. The study uses a systematic literature review method on a sample of 105 articles published from 2000 to 2019. The majority of work on big data in finance is dominated by the empirical setup in financial markets, internet finance, and financial services. The chapter contains all‐inclusive publications on the big data in fin...

Table of contents

• Cover
• Table of Contents
• Title Page
• Copyright Page
• List of Contributors
• List of Abbreviations
• 1 Big Data Analytics for the Internet of Things
• 2 Data, Analytics and Interoperability Between Systems (IoT) is Incongruous with the Economics of Technology: Evolution of Porous Pareto Partition (P3)
• 3 Machine Learning Techniques for IoT Data Analytics
• 4 IoT Data Analytics Using Cloud Computing
• 5 Deep Learning Architectures for IoT Data Analytics
• 6 Adding Personal Touches to IoT
• 7 Smart Cities and the Internet of Things
• 8 A Roadmap for Application of IoT‐Generated Big Data in Environmental Sustainability
• 9 Application of High‐Performance Computing in Synchrophasor Data Management and Analysis for Power Grids
• 10 Intelligent Enterprise‐Level Big Data Analytics for Modeling and Management in Smart Internet of Roads
• 11 Predictive Analysis of Intelligent Sensing and Cloud‐Based Integrated Water Management System
• 12 Data Security in the Internet of Things
• 13 DDoS Attacks
• 14 Securing the Defense Data for Making Better Decisions Using Data Fusion
• 15 New Age Journalism and Big Data (Understanding Big Data and Its Influence on Journalism)
• 16 Two Decades of Big Data in Finance
• Index
• End User License Agreement