Intelligent Network Design Driven by Big Data Analytics, IoT, AI and Cloud Computing

Description

As enterprise access networks evolve with a larger number of mobile users, a wide range of devices and new cloud-based applications, managing user performance on an end-to-end basis has become rather challenging. Recent advances in big data network analytics combined with AI and cloud computing are being leveraged to tackle this growing problem. AI is becoming further integrated with software that manage networks, storage, and can compute. This edited book focuses on how new network analytics, IoTs and Cloud Computing platforms are being used to ingest, analyse and correlate a myriad of big data across the entire network stack in order to increase quality of service and quality of experience (QoS/QoE) and to improve network performance. From big data and AI analytical techniques for handling the huge amount of data generated by IoT devices, the authors cover cloud storage optimization, the design of next generation access protocols and internet architecture, fault tolerance and reliability in intelligent networks, and discuss a range of emerging applications. This book will be useful to researchers, scientists, engineers, professionals, advanced students and faculty members in ICTs, data science, networking, AI, machine learning and sensing. It will also be of interest to professionals in data science, AI, cloud and IoT start-up companies, as well as developers and designers. Contents About the Editors 1 Introduction to intelligent network design driven by big data analytics, IoT, AI and cloud computing Preface Chapter 2: Role of automation, Big Data, AI, ML IBN, and cloud computing in intelligent networks Chapter 3: An intelligent verification management approach for efficient VLSI computing system Chapter 4: Evaluation of machine learning algorithms on academic big dataset by using feature selection techniques Chapter 5: Accurate management and progression of Big Data analysis Chapter 6: Cram on data recovery and backup cloud computing techniques Chapter 7: An adaptive software defined networking (SDN) for load balancing in cloud computing Chapter 8: Emerging security challenges in cloud computing: An insight Chapter 9: Factors responsible and phases of speaker recognition system Chapter 10: IoT-based water quality assessment using fuzzy logic controller Chapter 11: Design and analysis of wireless sensor network for intelligent transportation and industry automation Chapter 12: A review of edge computing in healthcare Internet of Things: theories, practices, and challenges Chapter 13: Image processing for medical images on the basis of intelligence and bio computing Chapter 14: IoT-based architecture for smart health-care systems Chapter 15: IoT-based heart disease prediction system Chapter 16: DIAIF: detection of interest flooding using artificial intelligence-based framework in NDN android Chapter 17: Intelligent and cost-effective mechanism for monitoring road quality using machine learning References 2 Role of automation, Big Data, AI, ML IBN, and cloud computing in intelligent networks 2.1 Evolution of networks: everything is connected 2.1.1 Intelligent devices 2.1.2 Intelligent devices connection with networks 2.2 Huge volume of data generation by intelligent devices 2.2.1 Issues and challenges of Big Data Analytics 2.2.2 Storage of Big Data 2.3 Need of data analysis by business 2.3.1 Sources of information 2.3.2 Data visualization 2.3.3 Analyzing Big Data for effective use of business 2.3.4 Intelligent devices thinking intelligently 2.4 Artificial intelligence and machine learning in networking 2.4.1 Role of ML in networks 2.5 Intent-based networking 2.6 Role of programming 2.6.1 Basic programming using Blockly 2.6.2 Blockly games 2.7 Role of technology to design a model 2.7.1 Electronic toolkits 2.7.2 Programming resources 2.8 Relation of AI, ML, and IBN 2.9 Business challenges and opportunities 2.9.1 The evolving job market 2.10 Security 2.10.1 Challenges to secure device and networks 2.11 Summary References 3 An intelligent verification management approach for efficient VLSI computing system 3.1 Introduction 3.2 Literature study 3.3 Verification management approach: Case Study 1 3.3.1 The pseudo random number generator in a verification environment 3.3.2 Implementation of PRNG in higher abstraction language and usage of DPI 3.4 Verification management approach: Case Study 2 3.5 Challenges and research direction 3.5.1 Challenges in intelligent systems 3.6 Conclusion References 4 Evaluation of machine learning algorithms on academic big dataset by using feature selection techniques 4.1 Introduction 4.1.1 EDM 4.1.2 EDM process 4.1.3 Methods and techniques 4.1.4 Application areas of data mining 4.2 Literature survey 4.3 Materials and methods 4.3.1 Dataset description 4.3.2 Classification algorithms 4.3.3 FS algorithms 4.3.4 Data preprocessing phase 4.4 Implementation of the proposed algorithms 4.4.1 Model construction for the standard classifier 4.4.2 Implementation after attribute selection using ranker method 4.5 Result analysis and discussion 4.6 Conclusion References 5 Accurate management and progression of Big Data Analysis 5.1 Introduction 5.1.1 Examples of Big Data 5.2 Big Data Analysis 5.2.1 Life cycle of Big Data 5.2.2 Classification of the Big Data 5.2.3 Working of Big Data Analysis 5.2.4 Common flaws that undermine Big Data Analysis 5.2.5 Advantages of Big Data Analysis 5.3. Processing techniques 5.3.1 Traditional method 5.3.2 MapReduce 5.3.3 Advantages of MapReduce 5.4 Cyber crime 5.4.1 Different strategies in Big Data to help in various circumstances 5.4.2 Big Data Analytics and cybercrime 5.4.3 Security issues associated with Big Data 5.4.4 Big Data Analytics in digital forensics 5.5 Real-time edge analytics for Big Data in IoT 5.6 Conclusion References 6 Cram on data recovery and backup cloud computing techniques 6.1 Introduction 6.1.1 Origin of cloud 6.1.2 Sole features of cloud computing 6.1.3 Advantages of cloud computing 6.1.4 Disadvantages of cloud computing 6.2 Classification of data recovery and backup 6.2.1 Recovery 6.2.2 Backup 6.3 Study on data recovery and backup cloud computing techniques 6.3.1 Backup of real-time data and recovery using cloud computing 6.3.2 Data recovery and security in cloud 6.3.3 Amoeba: An autonomous backup and recovery solid-state drives for ransomware attack defense 6.3.4 A cloud-based automatic recovery and backup system for video compression 6.3.5 Efficient and reliable data recovery techniques in cloud computing 6.3.6 Cost-efficient remote backup services for enterprise cloud 6.3.7 DR-cloud: Multi-cloud-based disaster recovery service 6.4 Conclusion References 7 An adaptive software-defined networking (SDN) for load balancing in cloud computing 7.1 Introduction 7.2 Related works 7.3 Architecture overview of SDN 7.4 Load-balancing framework in SDN 7.4.1 Classification of SDN controller architectures 7.5 Problem statement 7.5.1 Selection strategy of controller head 7.5.2 Network setup 7.6 Illustration 7.7 Results and discussion 7.7.1 Comparison of throughput 7.7.2 Comparison of PTR 7.7.3 Comparison of number of packet loss 7.8 Conclusion References 8 Emerging security challenges in cloud computing: an insight 8.1 Introduction 8.1.1 An introduction to cloud computing and its security 8.2 The security issues in different cloud models and threat management techniques 8.2.1 Five most indispensable characteristics 8.2.2 The security issues in cloud service model 8.2.3 Security issues in cloud deployment models 8.2.4 Security challenges in the cloud environment 8.2.5 The threat management techniques 8.3 Review on existing proposed models 8.3.1 SeDaSC 8.3.2 The ‘SecCloud’ protocol 8.3.3 Data accountability and auditing for secure cloud data storage 8.4 Conclusion and future prospectives References 9 Factors responsible and phases of speaker recognition system 9.1 Study of related research 9.2 Phases of speaker recognition system 9.2.1 Speaker database collection 9.2.2 Feature extraction 9.2.3 Feature mapping 9.3 Basics of speech signals 9.3.1 Speech production system 9.3.2 Speech perception 9.3.3 Speech signals 9.3.4 Properties of the sinusoids 9.3.5 Windowing signals 9.3.6 Zero-crossing rate 9.3.7 Autocorrelation 9.4 Features of speech signals 9.4.1 Physical features 9.4.2 Perceptual features 9.4.3 Signal features 9.5 Localization of speaker 9.6 Conclusion References 10 IoT-based water quality assessment using fuzzy logic controller 10.1 Introduction 10.2 Experimental procedures 10.3 Working 10.4 Results and discussions 10.5 Conclusion References 11 Design and analysis of wireless sensor network for intelligent transportation and industry automation 11.1 Introduction 11.2 Wireless sensor network 11.3 WSN application 11.4 Limitations of WSN 11.5 Literature survey 11.6 Related work 11.7 Methodology 11.7.1 Throughput 11.7.2 Delay 11.7.3 Packet delivery ratio 11.7.4 Design of WiMAX-based WSN system 11.8 Related results 11.9 Conclusion 11.10 Future scope References 12 A review of edge computing in healthcare Internet of things: theories, practices and challenges 12.1 Introduction 12.2 Cloud computing in healthcare and its limitations 12.2.1 Public cloud 12.2.2 Private cloud 12.2.3 Hybrid cloud 12.2.4 Community cloud 12.3 Edge computing and its advantages over cloud computing 12.3.1 Advantages of edge/fog computing 12.3.2 Disadvantages of edge/fog computing 12.4 IoT in healthcare 12.5 Edge computing in healthcare 12.6 Machine learning in healthcare 12.7 Integrated role of IOT, ML and edge computing in healthcare 12.7.1 Patient care during surgical procedure 12.7.2 Patient care at home 12.7.3 Patient care in ambulance 12.8 Modelling and simulation tools for edge/fog computing 12.9 Edge computing in Covid-19 pandemic era 12.10 Challenges of edge computing 12.11 Conclusion References 13 Image Processing for medical images on the basis of intelligence and biocomputing 13.1 Introduction 13.1.1 What is an image? 13.2 Image processing 13.2.1 Equivalent image processing 13.2.2 Digital image processing 13.2.3 Digital image 13.2.4 Applications of color models 13.2.5 Applications of digital image processing 13.2.6 Fundamental steps in digital image processing 13.2.7 Components of an image processing system 13.3 Medical imaging 13.4 Deep learning techniques 13.4.1 Uses of image processing 13.5 Convolutional neural network 13.6 Convolution layers 13.6.1 Training phase 13.6.2 Training strategies 13.6.3 CNN performance 13.6.4 Convolutional neutral networks with AI 13.6.5 CNN layers 13.6.6 CNN image classifier 13.7 Deep learning for lung disease detection 13.7.1 Preprocessing of images 13.7.2 Training 13.7.3 Classification 13.8 Conclusion References 14 IoT-based architecture for smart health-care systems 14.1 Introduction 14.2 Literature survey 14.3 Related works 14.4 Hardware components and sensors 14.4.1 Development boards 14.4.2 Sensors 14.4.3 Other modules 14.5 Proposed work 14.5.1 Hardware components used 14.6 Implementation and results 14.7 Conclusion References 15 IoT-based heart disease prediction system 15.1 Introduction 15.1.1 Deep learning 15.2 Related work 15.3 Proposed system 15.3.1 Arduino UNO 15.3.2 Heartbeat sensor 15.3.3 Temperature sensor 15.3.4 Pressure sensor 15.3.5 Liquid crystal display (LCD) display (16 × 2) 15.4 Advantages of proposed system 15.5 Limitations of proposed system 15.6 Results and discussion 15.7 Conclusion References 16 DIAIF: Detection of Interest Flooding using Artificial Intelligence-based Framework in NDN android 16.1 Introduction 16.2 Background 16.2.1 ICN communication model 16.2.2 Generating IFA in NDN android 16.3 Proposed methodology: RD Iterative Adaptive Inverse Filtering (RD-IAIF) 16.3.1 Attack detection 16.4 Real-time deployment on emergency applications 16.4.1 Communication establishment through NFD 16.4.2 NDN application on android 16.4.3 Attack detection on NFD android using AI 16.5 Conclusion References 17 Intelligent and cost-effective mechanism for monitoring road quality using machine learning 17.1 Introduction 17.1.1 Definition of TMS 17.1.2 Issues and challenges faced in TMS 17.2 Literature review of machine learning for road condition detection 17.3 Gaps identified in the literature 17.4 Proposed methodology 17.5 Implementation 17.5.1 Flutter-based application 17.5.2 Machine learning models 17.6 Results 17.6.1 Comparison with the existing models 17.7 Conclusion and future scope References 18 Conclusion 18.1 Conclusion References Index