Big Data Analytics and Intelligent Techniques for Smart Cities

Kolla Bhanu Prakash, Janmenjoy Nayak, B Madhhav, Sanjeevikumar Padmanaban, Valentina Emilia Balas, Kolla Bhanu Prakash, Janmenjoy Nayak, B Madhhav, Sanjeevikumar Padmanaban, Valentina Emilia Balas, B tp Madhhav, Kolla Bhanu Prakash, Janmenjoy Nayak, B tp Madhhav, Sanjeevikumar Padmanaban, Valentina Emilia Balas

• Publisher: CRC Press
• Year: 2021
• Print ISBN:
  9781032034522
  9780367753559
• eBook ISBN:
  9781000413366
• Edition: 1
• Topic: Informatica
• Subtopic: Data mining

Big Data Analytics and Intelligent Techniques for Smart Cities covers fundamentals, advanced concepts, and applications of big data analytics for smart cities in a single volume.

This comprehensive reference text discusses big data theory modeling and simulation for smart cities and examines case studies in a single volume. The text discusses how to develop a smart city and state-of-the-art system design, system verification, real-time control and adaptation, Internet of Things, and testbeds. It covers applications of smart cities as they relate to smart transportation/connected vehicle (CV) and intelligent transportation systems (ITS) for improved mobility, safety, and environmental protection.

It will be useful as a reference text for graduate students in different areas including electrical engineering, computer science engineering, civil engineering, and electronics and communications engineering.

Features:

• Technologies and algorithms associated with the application of big data for smart cities
• Discussions on big data theory modeling and simulation for smart cities
• Applications of smart cities as they relate to smart transportation and intelligent transportation systems (ITS)
• Discussions on concepts including smart education, smart culture, and smart transformation management for social and societal changes

1 Big Data for Smart Education

Ayesha Naureen

University of Technology

B.V. Raju Institute of Technology

Anil Badarla

University of Technology

Ahmed A. Elngar

Beni-Suef University

CONTENTS

1. 1.1 Introduction
   1. 1.1.1 Big Data (BD)
      1. 1.1.1.1 Big Data Analytics (BDA)
   2. 1.1.2 Big Data Architecture Aimed at Learning Analytics
   3. 1.1.3 Role of Big Data in Smart Education
2. 1.2 Fruition of Smart Learning
   1. 1.2.1 Insight of Smart Learning
   2. 1.2.2 Smart Learning Environment
   3. 1.2.3 Denotation of Smart in Smart Learning
   4. 1.2.4 Smart Learner
3. 1.3 Framework of Smart Education
   1. 1.3.1 Smart Pedagogy
   2. 1.3.2 Smart Learning Environments
   3. 1.3.3 Technical Architecture of a Smart Education Environment
   4. 1.3.4 3-Tier Architecture of Smart Computing
   5. 1.3.5 Key Function of Smart Computing
4. 1.4 Big Data Subsequent Revolution in Education
   1. 1.4.1 Big Data is Making Education Smarter
5. 1.5 Technique Educators Are Improving in Learning Process
   1. 1.5.1 Measure, Monitor, and Respond
   2. 1.5.2 Epitomize Learning Experience
   3. 1.5.3 Designing New Courses
6. 1.6 Big Data Components in Smart Education
7. 1.7 Big Data Tools in Smart Education
8. 1.8 Big Data Applications for Smart Education
   1. 1.8.1 Higher Education Analysis
   2. 1.8.2 Student Engagement
   3. 1.8.3 Bookstore Effectiveness
9. 1.9 How BD and Education Could Work Together to Benefit Student Success
   1. 1.9.1 Customized Curricula Aimed at Improved Learning Outcome
   2. 1.9.2 Big Data to Expand Student’s Performance
   3. 1.9.3 New Paths of Learning Potentials
10. 1.10 Big Data Analytics Consequensces in Advanced Education
11. 1.11 Opportunities along with Challenges of Big Data in Smart Education
12. 1.12 Conclusion: Challenge of Simplifying Smart Education
13. References

1.1 INTRODUCTION

Consistent intelligent design is applied in the field of education as a result of rapid technological developments in terms of what can be instrumented. Smart education, which has recently gained prominence, will be discussed here. Smart education-focused educational programmers must conduct a global study of the current time span. Malaysia decided to take part in a smart education initiative back in 1997. As a result, Malaysia has adopted the smart school strategy. Smart schools, which are backed by the government, aim to expand educational programmers and achieve nationwide education while also ensuring that job force is prepared to face the challenges of the 21st century. Intellectual theory has also been used as a criterion in Singapore, and technology-assisted education was found to be important in 2006. As a result, both schools will place a greater emphasis on the variety of learning environments in the future (traditional as well as smart school strategies). The smart interdisciplinary student central education system was designed in collaboration with IBM in Australia. The system will connect schools and tertiary institutions, and also participate in staff training. In South Korea, the smart education project is the most important challenge for reforming the country’s educational system and improving educational infrastructure. A smart school initiative in New York emphasizes the importance of technology in the classroom. Global smart education was given focus in Finland, based on a news release from 2011, and in the UAE, from 2012 onward, and much progress has been made in this novel trend. The related research topics of smart education growth are reviewed in the following sections, and perceptions of smart education and the intangible context aimed at research are proposed, as well as research frameworks for smart education. Furthermore, smart computing is portrayed as a form of smart education in technical architecture. Universities efficient data had reached a stage of smart education, strategy, but rapid commercialization of technologies such as mass storage, cloud computing, and IoT in universities, application of Big Data (BD) has become a specific core application of a smart education system (SES). The BD applications link physical data storage systems to computation-supporting platforms for data collection and sorting, while the management framework is for data analysis and processing. Data is used to link the various sections of a SES. Large amounts of data on the current status and behavior of each component mutually together will be organized through Big Data Analytics (BDA) to existing development designs and placed into smart application [1]. In conclusion, a provocation of easing smart education is provided to stimulate researchers and educators who are interested in smart education project and expansion.

1.1.1 Big Data (BD)

Big Data is a collection of data [2] that is so large and complex that traditional systems are unable to process it. The word also refers to the methods and software used to switch “BD” and sample BD from the large amount of data exchanged on the internet on a daily basis, such as YouTube video views, Twitter feeds, and mobile data location tracking. The current data would create an environment conducive to learning.

1.1.1.1 Big Data Analytics (BDA)

BD has recently been applied to datasets that have become so large that performing tasks with a conventional database management system (DBMS) has become challenging. To collect, stockpile, actively use, and release the data at the required time, extremely large datasets necessitate the use of software resources and storage systems [3]. The size of BDs is continuously growing, ranging from a few hundred TB to several PBs of data in a single dataset. As a result, analytics, storage, discovery, data capture, data exchange, and visualization, as well as exploration of the volume of a massive, broad dataset to discover previously unknown truths, are all complications associated with BD [4].

BDA is a sophisticated analytic method that can be used for BD sets. The analytic foundation of a large data sample allows for the disclosure and exploiting of commercial variance in large datasets. In terms of control, there is an additional issue [4].

Features of BD

Data of a size, distribution, multiplicity, or otherwise timeless nature necessitates the use of newly technical architecture, analytic, and tool orderly allowing insight such as the discovery of a new source of commercial cost. BD’s main characteristics are as follows: volume, variety, and velocity, or any three V’s volume data, its scope, and how huge it is. The pace at which data changes, or how often it is produced, is defined by velocity. To sum it up, diversity encompasses a wide range of data formats, categories, and uses, as well as various types of data analysis [5]. Furthermore, BD offers the benefit of velocity, or speed, which is largely determined by the density of a data peer group or the density of data dispatch. Flowing data collected in real time from websites [4] is the most significant advantage of BD. Few researchers and organizations have considered the inclusion of a fourth V, veracity, which is concerned with data accuracy. Data inconsistency, deficiency, uncertainty, inactivity, deceit, and estimates are used to classify BD output as good, mediocre, or unspecified (Figure 1.1).

FIGURE 1.1 Big Data V’s.

1.1.2 Big Data Architecture Aimed at Learning Analytics

It is essential to plan an architecture for learning analytic framework. The aim of the system is to use a phase structure to seamlessly combine generation, addition, cleaning, and other types of preprocessing, storage, and management, as well as analytic, visual, and other alert systems. Furthermore, the optimized architecture should be generic. However, in the following sections, an additional optimized outline aimed at the real-world implementation is given in Figure 1.2.

• Data Gathering Device: The framework is made up entirely of artifacts and devices that are responsible for gathering raw data at each stage of the advanced education process. Many data collection devices have been blamed for amassing unanalyzed data, particularly at every stage of the advanced education process. Various data collection devices, such as student ID cards, communal networks, and learning management system (LMS), sense student data and can be used as data sources. Since each student is passed through Data Management Systems (DMS) for review, both structured and unstructured data are produced.
• Data Storage and Management Systems: The DS framework includes a massive DBMS as well as features such as buffering and Return Time Query Objective (RTQO). This stage is also responsible for—and focuses on—data preprocessing rather than data cleaning. Another important feature of a DS and management system is to process and change raw data using the hooked-on approach so that data can be efficiently processed by the analytic engine [7].
• Data Analytics Systems: This is the system’s nerve center. A smart processing algorithm is used in the DA framework, and it is designed to extract evocative and useful information from raw streams of otherwise static data.
• Data Visualization: An impartial data visualization framework forms the pictorial representation of an analysis outcome, allowing for a fast decision.
• Action: A learning analytics system’s goal is to provide learners, administrators, and lecturers with information through alarm and warning systems in order to direct systemic progress, course design, and participation in instruction.

FIGURE 1.2 Big Data architecture.

1.1.3 Role of Big Data in Smart Education

We may imagine that BD and education both have one or else two to learn from one another. BD systems are used by businesses to capture, store, and analyze large volumes of data as well as gain an invaluable insight into their operations. Innovation is changing the way businesses use data, improve sectors, and transform education. BD systems assist people in cramming information and improving how organizations analyze it, as well as offering opportunities to view data and use the data to make sound decisions. BD systems has assembled a team of experts who can better understand and interpret the data than ever before. Following segmentation and exploring three approaches that BD technology has that are different from the current study climate, BD technology has incredible potential aimed at the future of teaching and learning. Modified syllabi strive for higher-quality learning outcomes, and BD aids this by broadening student presentation and comprehension, thus creating a new learning pathway [8].

1.2 FRUITION OF SMART LEARNING

While smart learning is a groundbreaking academic pattern, it is built on smart devices and intellectual technology (Lee et al. [9]; Kim et al. [10]), despite the fact that technology has been implemented and manipulated within serving learners for decades. It is described as the use of technology to improve studying because technology improves learning and makes educational methods more workable. Technology may take the form of media or some other type of tool aimed at increasing educational access. Bruce and Levin [11] evaluated speech, while Dani...

Table of contents

• Cover
• Half Title
• Title Page
• Copyright Page
• Dedicated to
• Table of Contents
• Preface
• Acknowledgments
• Editors
• Contributors
• Chapter 1 Big Data for Smart Education
• Chapter 2 Big Data Analytics Using R for Offline Voltage Prediction in an Electric Power System
• Chapter 3 Intelligent Face Recognition Based on Regularized Robust Coding with Deep Learning Process
• Chapter 4 Big Data Analysis, Interpretation, and Management for Secured Smart Health Care
• Chapter 5 Big Data Handling for Smart Healthcare System: A Brief Review and Future Directions
• Chapter 6 Big Data Analysis for Smart Energy System: An Overview and Future Directions
• Chapter 7 Optimum Placement of Multiple Distributed Generators in Distribution Systems for Loss Mitigation Considering Load Growth
• Chapter 8 Big Data for Smart Energy
• Chapter 9 An Intelligent Security Framework for Cyber-Physical Systems in Smart City
• Chapter 10 Big Data and Its Application in Smart Education during the COVID-19 Pandemic Situation
• Chapter 11 Role of IoT, Machine Learning, and Big Data in Smart Building
• Chapter 12 Design of Futuristic Trolley System with Comparative Analysis of Previous Models
• Chapter 13 Big Data for Smart Health
• Index