Allgemein
Productive and Efficient Data Science with Python
This book focuses on the Python-based tools and techniques to help you become highly productive at all aspects of typical data science stacks such as statistical analysis, visualization, model selection, and feature engineering.You’ll review the inefficiencies and bottlenecks lurking in the daily business process and solve them with practical solutions. Automation of repetitive data science tasks is a key mindset that is promoted throughout the book. You’ll learn how to extend the existing coding practice to handle larger datasets with high efficiency with the help of advanced libraries and packages that already exist in the Python ecosystem.The book focuses on topics such as how to measure the memory footprint and execution speed of machine learning models, quality test a data science pipelines, and modularizing a data science pipeline for app development. You’ll review Python libraries which come in very handy for automating and speeding up the day-to-day tasks.In the end, you’ll understand and perform data science and machine learning tasks beyond the traditional methods and utilize the full spectrum of the Python data science ecosystem to increase productivity.WHAT YOU’LL LEARN* Write fast and efficient code for data science and machine learning* Build robust and expressive data science pipelines* Measure memory and CPU profile for machine learning methods* Utilize the full potential of GPU for data science tasks * Handle large and complex data sets efficientlyWHO THIS BOOK IS FORData scientists, data analysts, machine learning engineers, Artificial intelligence practitioners, statisticians who want to take full advantage of Python ecosystem.Dr. Tirthajyoti Sarkar lives in the San Francisco Bay area works as a Data Science and Solutions Engineering Manager at Adapdix Corp., where he architects Artificial intelligence and Machine learning solutions for edge-computing based systems powering the Industry 4.0 and Smart manufacturing revolution across a wide range of industries. Before that, he spent more than a decade developing best-in-class semiconductor technologies for power electronics.He has published data science books, and regularly contributes highly cited AI/ML-related articles on top platforms such as KDNuggets and Towards Data Science. Tirthajyoti has developed multiple open-source software packages in the field of statistical modeling and data analytics. He has 5 US patents and more than thirty technical publications in international journals and conferences.He conducts regular workshops and participates in expert panels on various AI/ML topics and contributes to the broader data science community in numerous ways. Tirthajyoti holds a Ph.D. from the University of Illinois and a B.Tech degree from the Indian Institute of Technology, Kharagpur.Chapter 1: What is Productive and Efficient Data Science?Chapter Goal: To introduce the readers with the concept of doing data science tasks efficiently and more productively and illustrating potential pitfalls in their everyday work.No of pages – 10Subtopics• Typical data science pipeline• Short examples of inefficient programming in data science• Some pitfalls to avoid• Efficiency and productivity go hand in hand• Overview of tools and techniques for a productive data science pipeline• Skills and attitude for productive data scienceChapter 2: Better Programming Principles for Efficient Data ScienceChapter Goal: Help readers grasp the idea of efficient programming techniques and how they can be applied to a typical data science task flow.No of pages – 15Subtopics• The concept of time and space complexity, Big-O notation• Why complexity matters for data science• Examples of inefficient programming in data science tasks• What you can do instead• Measuring code execution timingChapter 3: How to Use Python Data Science Packages more ProductivelyChapter Goal: Illustrate handful of tricks and techniques to use the most well-known Python data science packages – Numpy, Pandas, Matplotlib, Seaborn, Scipy – more productively.No of pages – 20Subtopics• Why Numpy is faster than regular Python code and how much• Using Numpy efficiently• Using Pandas productively• Matplotlib and Seaborn code for and productive EDA• Using SciPy for common data science tasksChapter 4: Writing Machine Learning Code More ProductivelyChapter Goal: Teach the reader about writing efficient and modular machine learning code for productive data science pipeline with hands-on examples using Scikit-learn.No of pages – 15Subtopics• Why modular code for machine learning and deep learning• Scikit-learn tools and techniques• Systematic evaluation of Scikit-learn ML algorithms in automated fashion• Decision boundary visualization with custom function• Hyperparameter search in Scikit-learnChapter 5: Modular and Productive Deep Learning CodeChapter Goal: Teach the reader about mixing modular programming style in deep learning code with hands-on examples using Keras/TensorFlow.No of pages – 25Subtopics• Why modular code and object-oriented style for deep learning• Wrapper functions with Keras for faster deep learning experimentations• A single function to streamline image classification task flow• Visualize activation functions of neural networks• Custom callback functions in Keras and their utilities• Using Scikit-learn wrapper for hyperparameter search in KerasChapter 6: Build Your Own Machine Learning Estimator/PackageChapter Goal: Illustrate how to build a new Python machine learning module/package from scratch.No of pages – 15Subtopics• Why write your own ML package/module?• A simple example vs. a data scientist’s example• A good, old Linear Regression estimator — with a twist• How do you start building?• Add utility functions• Do more with object-oriented approachChapter 7: Some Cool Utility PackagesChapter Goal: Introduce the readers to the idea of executing data science tasks efficiently by going beyond traditional stack and utilizing exciting, new libraries.No of pages – 20Subtopics• The great Python data science ecosystem• Build pipeline using “pdpipe”• Check data integrity and expectations with “great_expectations”• Speed up Numpy and Pandas using Numexpr• Discover best fitted distributions using “distfit”Chapter 8: Testing the Machine Learning CodeChapter Goal: Teach the readers some basic principles of testing Python code and how to apply them to a specific case of machine learning module.No of pages – 20Subtopics• Why testing boosts productivity• Basic principles and variations of testing• Data science or machine learning testing is somewhat different• A PyTest module for a ML moduleChapter 9: Memory and Timing ProfilingChapter Goal: Illustrate how to measure and profile typical data science and machine learning code/ module.No of pages – 15Subtopics• Why profiling is important• Well-known profilers out there• cProfile• Memory_profile• ScaleneChapter 10: Scalable Data ScienceChapter Goal: Demonstrate the importance of scalability in data science tasks with hands-on examples.No of pages – 15Subtopics• Data science pipeline needs to be easily scalable• Common problems - out-of-memory and single-threading• What options are out there?• Hands-on example with Vaex• Hands-on example with ModinChapter 11: Parallelized Data ScienceChapter Goal: Demonstrate the importance of parallel processing in data science tasks with hands-on examples.No of pages – 15Subtopics• Data science pipeline should take advantage of parallel computing• Two great options – Ray and Dask• Hands-on example with Dask cluster• Hands-on example with “Ray serve” and actorsChapter 12: GPU-Based Data Science for High ProductivityChapter Goal: Illustrate how to harness the power of GPU-based hardware for common data science tasks and classical machine learning.No of pages – 20Subtopics• GPU-powered data science (not deep learning)• The RAPIDS ecosystem• CuPy vs. NumPy• CuDF vs. Pandas• CuML vs. Scikit-learnChapter 13: Other Useful Skills to MasterChapter Goal: Give an overview of other related skills to master for executing data science tasks more efficiently.No of pages – 25Subtopics• Key things to learn• Understanding the basics of web technologies• Going from local to cloud• Simple web app to showcase a data science project• GUI programming for a quick demo• Being comfortable with container technologies• Putting it all togetherChapter 14: Wrapping It UpChapter Goal: Show a summary of all the things discussed and some future projections.No of pages – 10Subtopics• Chapter-wise summary• What were not discussed in this book• Future projections• General advice for upcoming data scientists
CompTIA Linux+ Practice Tests
THE BEST TEST PREPARATION RESOURCE FOR THE COMPTIA LINUX+ CERTIFICATION EXAMIn the newly updated Third Edition of CompTIA Linux+ Practice Tests: Exam XK0-005, veteran Linux expert, Steve Suehring, delivers an instructive set of practice questions written to get you ready to ace the new XK0-005 test. Providing hundreds of domain-by-domain questions covering system management, security, scripting, containers, automation, and troubleshooting, the book helps you prepare for the exam with confidence and efficiency. You’ll be able to pinpoint those areas you’ve mastered and those which require more study, as well as get a feel for the structure of the test itself. The book also offers:* Hundreds of practice questions that reinforce your skills and knowledge* A great way for practicing and aspiring Linux network and system administrators to improve their on-the-job skills* One year of complimentary access after activation to the online Sybex test bank, where you can study and work through hundreds of questionsAn indispensable resource for anyone preparing for the CompTIA Linux+ exam, CompTIA Linux+ Practice Tests: Exam XK0-005, Third Edition, is also a must-have for new and experienced sysadmins and network administrators seeking to identify areas of strength and weakness and improve their grasp of Linux systems. ABOUT THE AUTHORSTEVE SUEHRING is a technical architect with extensive experience in technology and Linux. He is the author of several technology education books, and has worked as a systems engineer and security specialist, as well as in roles providing architectural direction to several different technology initiatives. He is an expert in JavaScript, Linux security, Windows Server certifications, Perl, and more. Introduction XIChapter 1 System Management (Domain 1.0) 1Chapter 2 System Operations and Maintenance (Domain 2.0) 49Chapter 3 Scripting, Containers, and Automation (Domain 3.0) 83Chapter 4 Troubleshooting (Domain 4.0) 113Chapter 5 Practice Exam 157Appendix Answers to the Review Questions 175Chapter 1: System Management (Domain 1.0) 176Chapter 2: System Operations and Maintenance (Domain 2.0) 197Chapter 3: Scripting, Containers, and Automation (Domain 3.0) 211Chapter 4: Troubleshooting (Domain 4.0) 224Chapter 5: Practice Exam 241Index 249
Artificial Intelligence in Industry 4.0 and 5G Technology
ARTIFICIAL INTELLIGENCE IN INDUSTRY 4.0 AND 5G TECHNOLOGYEXPLORES INNOVATIVE AND VALUE-ADDED SOLUTIONS FOR APPLICATION PROBLEMS IN THE COMMERCIAL, BUSINESS, AND INDUSTRY SECTORSAs the pace of Artificial Intelligence (AI) technology innovation continues to accelerate, identifying the appropriate AI capabilities to embed in key decision processes has never been more critical to establishing competitive advantage. New and emerging analytics tools and technologies can be configured to optimize business value, change how an organization gains insights, and significantly improve the decision-making process across the enterprise.Artificial Intelligence in Industry 4.0 and 5G Technology helps readers solve real-world technological engineering optimization problems using evolutionary and swarm intelligence, mathematical programming, multi-objective optimization, and other cutting-edge intelligent optimization methods. Contributions from leading experts in the field present original research on both the theoretical and practical aspects of implementing new AI techniques in a variety of sectors, including Big Data analytics, smart manufacturing, renewable energy, smart cities, robotics, and the Internet of Things (IoT).* Presents detailed information on meta-heuristic applications with a focus on technology and engineering sectors such as smart manufacturing, smart production, innovative cities, and 5G networks.* Offers insights into the use of metaheuristic strategies to solve optimization problems in business, economics, finance, and industry where uncertainty is a factor.* Provides guidance on implementing metaheuristics in different applications and hybrid technological systems.* Describes various AI approaches utilizing hybrid meta-heuristics optimization algorithms, including meta-search engines for innovative research and hyper-heuristics algorithms for performance measurement.Artificial Intelligence in Industry 4.0 and 5G Technology is a valuable resource for IT specialists, industry professionals, managers and executives, researchers, scientists, engineers, and advanced students an up-to-date reference to innovative computing, uncertainty management, and optimization approaches.PANDIAN VASANT is Research Associate at MERLIN Research Centre, TDTU, HCMC, Vietnam, and Editor in Chief of International Journal of Energy Optimization and Engineering (IJEOE). He holds PhD in Computational Intelligence (UNEM, Costa Rica), MSc (University Malaysia Sabah, Malaysia, Engineering Mathematics) and BSc (Hons, Second Class Upper) in Mathematics (University of Malaya, Malaysia). He has co-authored research articles in journals, conference proceedings, presentations, special issues Guest Editor, chapters and General Chair of EAI International Conference on Computer Science and Engineering in Penang, Malaysia (2016) and Bangkok, Thailand (2018).ELIAS MUNAPO, PhD, currently heads the Department of Business Statistics and Operations research at North West University-Mafikeng, South Africa. He has published 50+ articles and contributed to five chapters on industrial engineering and management texts.J. JOSHUA THOMAS is an Associate Professor at UOW Malaysia KDU Penang University College. He obtained his PhD (Intelligent Systems Techniques) from University Sains Malaysia, Penang and master’s degree from Madurai Kamaraj University, India. He is working with Deep Learning algorithms, specially targeting on Graph Convolutional Neural Networks (GCNN) and Bi-directional Recurrent Neural Networks (RNN) for drug target interaction and image tagging with embedded natural language processing. His work involves experimental research with software prototypes and mathematical modelling and design.GERHARD-WILLIAM WEBER, PhD, is Professor and Chair of Marketing and Economic Engineering at Poznan University of Technology, Poland. He is also an Adjunct Professor at Department of Industrial and Systems Engineering, College of Engineering at Istinye University, Istanbul, Turkey.List of Contributors xvPreface xixProfile of Editors xxviiAcknowledgments xxx1 DYNAMIC KEY-BASED BIOMETRIC END-USER AUTHENTICATION PROPOSAL FOR IOT IN INDUSTRY 4.0 1Subhash Mondal, Swapnoj Banerjee, Soumodipto Halder, and Diganta Sengupta1.1 Introduction 11.2 Literature Review 21.3 Proposed Framework 51.3.1 Enrolment Phase 51.3.2 Authentication Phase 71.3.2.1 Pre-processing 71.3.2.2 Minutiae Extraction and False Minutiae Removal 121.3.2.3 Key Generation from extracted Minutiae points 131.3.2.4 Encrypting the Biometric Fingerprint Image Using AES 141.4 Comparative Analysis 181.5 Conclusion 19References 192 DECISION SUPPORT METHODOLOGY FOR SCHEDULING ORDERS IN ADDITIVE MANUFACTURING 25Juan Jesús Tello Rodríguez and Lopez-I Fernando2.1 Introduction 252.2 The Additive Manufacturing Process 262.3 Some Background 282.4 Proposed Approach 302.4.1 A Mathematical Model for the Initial Printing Scheduling 322.4.1.1 Considerations 322.4.1.2 Sets 322.4.2 Parameters 332.4.2.1 Orders 332.4.2.2 Parts 332.4.2.3 Printing Machines 332.4.2.4 Process 332.4.3 Decision Variables 332.4.4 Optimization Criteria 332.4.5 Constrains 342.5 Results 352.5.1 Orders 352.6 Conclusions 39References 393 SIGNIFICANCE OF CONSUMING 5G-BUILT ARTIFICIAL INTELLIGENCE IN SMART CITIES 43Y. Bevish Jinila, Cinthia Joy, J. Joshua Thomas, and S. Prayla Shyry3.1 Introduction 433.2 Background and RelatedWork 473.3 Challenges in Smart Cities 493.3.1 Data Acquisition 493.3.2 Data Analysis 503.3.3 Data Security and Privacy 503.3.4 Data Dissemination 503.4 Need for AI and Data Analytics 503.5 Applications of AI in Smart Cities 513.5.1 Road Condition Monitoring 513.5.2 Driver Behavior Monitoring 523.5.3 AI-Enabled Automatic Parking 533.5.4 Waste Management 533.5.5 Smart Governance 533.5.6 Smart Healthcare 543.5.7 Smart Grid 543.5.8 Smart Agriculture 553.6 AI-based Modeling for Smart Cities 553.6.1 Smart Cities Deployment Model 553.6.2 AI-Based Predictive Analytics 573.6.3 Pre-processing 583.6.4 Feature Selection 583.6.5 Artificial Intelligence Model 583.7 Conclusion 60References 604 NEURAL NETWORK APPROACH TO SEGMENTATION OF ECONOMIC INFRASTRUCTURE OBJECTS ON HIGH-RESOLUTION SATELLITE IMAGES 63Vladimir A. Kozub, Alexander B. Murynin, Igor S. Litvinchev, Ivan A. Matveev, and Pandian Vasant4.1 Introduction 634.2 Methodology for Constructing a Digital Terrain Model 644.3 Image Segmentation Problem 654.4 Segmentation Quality Assessment 674.5 Existing Segmentation Methods and Algorithms 684.6 Classical Methods 694.7 Neural Network Methods 724.7.1 Semantic Segmentation of Objects in Satellite Images 744.8 Segmentation with Neural Networks 764.9 Convolutional Neural Networks 794.10 Batch Normalization 834.11 Residual Blocks 844.12 Training of Neural Networks 854.13 Loss Functions 854.14 Optimization 864.15 Numerical Experiments 884.16 Description of the Training Set 884.17 Class Analysis 904.18 Augmentation 904.19 NN Architecture 924.20 Training and Results 934.21 Conclusion 97Acknowledgments 97References 975 THE IMPACT OF DATA SECURITY ON THE INTERNET OF THINGS 101Joshua E. Chukwuere and Boitumelo Molefe5.1 Introduction 1015.2 Background of the Study 1025.3 Problem Statement 1035.4 Research Questions 1035.5 Literature Review 1035.5.1 The Data Security on IoT 1035.5.2 The Security Threats and Awareness of Data Security on IoT 1055.5.3 The DifferentWays to Assist with Keeping Your IoT Device Safer from Security Threats 1055.6 Research Methodology 1065.6.1 Population and Sampling 1065.6.2 Data Collection 1075.6.3 Reliability and Validity 1085.7 Chapter Results and Discussions 1085.7.1 The Demographic Information 1095.7.1.1 Age, Ethnic Group, and Ownership of a Smart Device 1095.7.2 Awareness of Users About Data Security of the Internet of Things 1095.7.3 The Security Threats that are Affecting the Internet of Things Devices 1115.7.3.1 The Architecture of IoT Devices 1125.7.3.2 The botnets Attack 1125.7.4 The Effects of Security Threats on IoT Devices that are Affecting Users 1125.7.4.1 The Slowness or Malfunctioning of the IoT Device 1125.7.4.2 The Trust of Users on IoT 1135.7.4.3 The Safety of Users 1135.7.4.4 The Guaranteed Duration of IoT Devices 1145.7.5 DifferentWays to Assist with Keeping IoT Smart Devices Safer from Security Threats 1145.7.5.1 The Change Default Passwords 1145.7.5.2 The Easy or Common Passwords 1145.7.5.3 On the Importance of Reading Privacy Policies 1145.7.5.4 The Bluetooth and Wi-Fi of IoT Devices 1155.7.5.5 The VPN on IoT 1155.7.5.6 The Physical Restriction 1155.7.5.7 Two-Factor Authentication 1165.7.5.8 The Biometric Authentication 1165.8 Answers to the Chapter Questions 1165.8.1 Objective 1: Awareness on Users About Data Security of Internet of Things (IoT) 1165.8.2 Objective 2: Determine the Security Threats that are Involved in the Internet of Things (IoT) 1175.8.3 Objective 3: The Effects of Security Threats on IoT Devices that are Affecting Users 1175.8.4 Objective 4: DifferentWays to Assist with Keeping IoT Devices Safer from Security Threats 1175.8.5 Other Descriptive Analysis (Mean) 1185.8.5.1 Mean 1 – Awareness on Users About Data Security on IoT 1185.8.5.2 The Effects of Security Threats on IoT Devices that are Affecting Users 1185.8.5.3 DifferentWays to Assist with Keeping an IoT Device Safer 1225.9 Chapter Recommendations 1225.10 Conclusion 122References 1246 SUSTAINABLE RENEWABLE ENERGY AND WASTE MANAGEMENT ON WEATHERING CORPORATE POLLUTION 129Choo K. Chin and Deng H. Xiang6.1 Introduction 1296.2 Literature Review 1316.2.1 Energy Efficiency 1356.2.2 Waste Minimization 1366.2.3 Water Consumption 1376.2.4 Eco-Procurement 1376.2.5 Communication 1386.2.6 Awareness 1386.2.7 Sustainable and Renewable Energy Development 1386.3 Conceptual Framework 1396.4 Conclusion 1396.4.1 Energy Efficiency 1406.4.2 Waste Minimization 1406.4.3 Water Consumption 1406.4.4 Eco-Procurement 1416.4.5 Communication 1416.4.6 Sustainable and Renewable Energy Development 141Acknowledgment 142References 1427 ADAM ADAPTIVE OPTIMIZATION METHOD FOR NEURAL NETWORK MODELS REGRESSION IN IMAGE RECOGNITION TASKS 147Denis Y. Nartsev, Alexander N. Gneushev, and Ivan A. Matveev7.1 Introduction 1477.2 Problem Statement 1497.3 Modifications of the Adam Optimization Method for Training a Regression Model 1517.4 Computational Experiments 1557.4.1 Model for Evaluating the Eye Image Blurring Degree 1557.4.2 Facial Rotation Angle Estimation Model 1587.5 Conclusion 160Acknowledgments 161References 1618 APPLICATION OF INTEGER PROGRAMMING IN ALLOCATING ENERGY RESOURCES IN RURAL AFRICA 165Elias Munapo8.1 Introduction 1658.1.1 Applications of the QAP 1658.2 Quadratic Assignment Problem Formulation 1668.2.1 Koopmans–Beckmann Formulation 1668.3 Current Linearization Technique 1678.3.1 The General Quadratic Binary Problem 1678.3.2 Linearizing the Quadratic Binary Problem 1698.3.2.1 Variable Substitution 1698.3.2.2 Justification 1698.3.3 Number of Variables and Constraints in the Linearized Model 1708.3.4 Linearized Quadratic Binary Problem 1718.3.5 Reducing the Number of Extra Constraints in the Linear Model 1718.3.6 The General Binary Linear (BLP) Model 1718.3.6.1 Convex Quadratic Programming Model 1728.3.6.2 Transforming Binary Linear Programming (BLP) Into a Convex/Concave Quadratic Programming Problem 1728.3.6.3 Equivalence 1738.4 Algorithm 1748.4.1 Making the Model Linear 1758.5 Conclusions 176References 1769 FEASIBILITY OF DRONES AS THE NEXT STEP IN INNOVATIVE SOLUTION FOR EMERGING SOCIETY 179Sadia S. Ali, Rajbir Kaur, and Haidar Abbas9.1 Introduction 1799.1.1 Technology and Business 1819.1.2 Technological Revolution of the Twenty-first Century 1819.2 An Overview of Drone Technology and Its Future Prospects in Indian Market 1829.2.1 Utilities 1839.2.1.1 Delivery 1839.2.1.2 Media/Photography 1839.2.1.3 Agriculture 1849.2.1.4 Contingency and Disaster Management Scenarios 1849.2.1.5 Civil and Military Services: Search and Rescue, Surveillance,Weather, and Traffic Monitoring, Firefighting 1859.2.2 Complexities Involved 1859.2.3 Drones in Indian Business Scenario 1869.3 Literature Review 1879.3.1 Absorption and Diffusion of New Technology 1889.3.2 Leadership for Innovation 1889.3.3 Social and Economic Environment 1899.3.4 Customer Perceptions 1909.3.5 Alliances with Other National and International Organizations 1909.3.6 Other Influencers 1919.4 Methodology 1919.5 Discussion 1939.5.1 Market Module 1959.5.2 Technology Module 1969.5.3 Commercial Module 1989.6 Conclusions 199References 20010 DESIGNING A DISTRIBUTION NETWORK FOR A SODA COMPANY: FORMULATION AND EFFICIENT SOLUTION PROCEDURE 209Isidro Soria-Arguello, Rafael Torres-Esobar, and Pandian Vasant10.1 Introduction 20910.2 New Distribution System 21110.3 The Mathematical Model to Design the Distribution Network 21410.4 Solution Technique 21610.4.1 Lagrangian Relaxation 21610.4.2 Methods for Finding the Value of Lagrange Multipliers 21610.4.3 Selecting the Solution Method 21610.4.4 Used Notation 21710.4.5 Proposed Relaxations of the Distribution Model 21810.4.5.1 Relaxation 1 21810.4.5.2 Relaxation 2 21910.4.6 Selection of the Best Lagrangian Relaxation 21910.5 Heuristic Algorithm to Restore Feasibility 22010.6 Numerical Analysis 22210.6.1 Scenario 2020 22310.6.2 Scenario 2021 22410.6.3 Scenario 2022 22510.6.4 Scenario 2023 22610.7 Conclusions 228References 22811 MACHINE LEARNING AND MCDM APPROACH TO CHARACTERIZE STUDENT ATTRITION IN HIGHER EDUCATION 231Arrieta-M Luisa F and Lopez-I Fernando11.1 Introduction 23111.1.1 Background 23211.2 Proposed Approach 23311.3 Case Study 23411.3.1 Intelligent Phase 23411.3.2 Design Phase 23511.3.3 Choice Phase 23611.4 Results 23811.5 Conclusion 240References 24012 A CONCISE REVIEW ON RECENT OPTIMIZATION AND DEEP LEARNING APPLICATIONS IN BLOCKCHAIN TECHNOLOGY 243Timothy Ganesan, Irraivan Elamvazuthi, Pandian Vasant, and J. Joshua Thomas12.1 Background 24312.2 Computational Optimization Frameworks 24612.3 Internet of Things (IoT) Systems 24812.4 Smart Grids Data Systems 25012.5 Supply Chain Management 25212.6 Healthcare Data Management Systems 25512.7 Outlook 257References 25813 INVENTORY ROUTING PROBLEM WITH FUZZY DEMAND AND DELIVERIES WITH PRIORITY 267Paulina A. Avila-Torres and Nancy M. Arratia-Martinez13.1 Introduction 26713.2 Problem Description 27013.3 Mathematical Formulation 27313.4 Computational Experiments 27513.4.1 Numerical Example 27613.4.1.1 The Inventory Routing Problem Under Certainty 27913.4.1.2 The Inventory Routing Problem Under Uncertainty in the Consumption Rate of Product 27913.5 Conclusions and FutureWork 280References 28114 COMPARISON OF DEFUZZIFICATION METHODS FOR PROJECT SELECTION 283Nancy M. Arratia-Martinez, Paulina A. Avila-Torres, and Lopez-I Fernando14.1 Introduction 28314.2 Problem Description 28614.3 Mathematical Model 28614.3.1 Sets and Parameters 28714.3.2 Decision Variables 28714.3.3 Objective Functions 28714.4 Constraints 28814.5 Methods of Defuzzification and Solution Algorithm 28914.5.1 k-Preference Method 28914.5.2 Integral Value 29114.5.3 SAUGMECON Algorithm 29114.6 Results 29214.6.1 Results of k-Preference Method 29214.6.2 Results of Integral Value Method 29514.7 Conclusions 299References 30015 RE-IDENTIFICATION-BASED MODELS FOR MULTIPLE OBJECT TRACKING 303Alexey D. Grigorev, Alexander N. Gneushev, and Igor S. Litvinchev15.1 Introduction 30315.2 Multiple Object Tracking Problem 30515.3 Decomposition of Tracking into Filtering and Assignment Tasks 30615.4 Cost Matrix Adjustment in Assignment Problem Based on Re-Identification with Pre-Filtering of Descriptors by Quality 31015.5 Computational Experiments 31315.6 Conclusion 315Acknowledgments 315References 316Index 319
Cyber-Physical Systems
CYBER-PHYSICAL SYSTEMSAcknowledgement xix1 A SYSTEMATIC LITERATURE REVIEW ON CYBER SECURITY THREATS OF INDUSTRIAL INTERNET OF THINGS 1Ravi Gedam and Surendra Rahamatkar1.1 Introduction 21.2 Background of Industrial Internet of Things 31.3 Literature Review 61.4 The Proposed Methodology 131.5 Experimental Requirements 141.6 Conclusion 15References 162 INTEGRATION OF BIG DATA ANALYTICS INTO CYBER-PHYSICAL SYSTEMS 19Nandhini R.S. and Ramanathan L.2.1 Introduction 192.2 Big Data Model for Cyber-Physical System 212.2.1 Cyber-Physical System Architecture 222.2.2 Big Data Analytics Model 222.3 Big Data and Cyber-Physical System Integration 232.3.1 Big Data Analytics and Cyber-Physical System 232.3.1.1 Integration of CPS With BDA 242.3.1.2 Control and Management of Cyber-Physical System With Big Data Analytics 242.3.2 Issues and Challenges for Big Data-Enabled Cyber-Physical System 252.4 Storage and Communication of Big Data for Cyber-Physical System 262.4.1 Big Data Storage for Cyber-Physical System 272.4.2 Big Data Communication for Cyber-Physical System 282.5 Big Data Processing in Cyber-Physical System 292.5.1 Data Processing 292.5.1.1 Data Processing in the Cloud and Multi-Cloud Computing 292.5.1.2 Clustering in Big Data 312.5.1.3 Clustering in Cyber-Physical System 322.5.2 Big Data Analytics 322.6 Applications of Big Data for Cyber-Physical System 332.6.1 Manufacturing 332.6.2 Smart Grids and Smart Cities 342.6.3 Healthcare 352.6.4 Smart Transportation 352.7 Security and Privacy 362.8 Conclusion 37References 383 MACHINE LEARNING: A KEY TOWARDS SMART CYBER-PHYSICAL SYSTEMS 43Rashmi Kapoor, Chandragiri Radhacharan and Sung-ho Hur3.1 Introduction 443.2 Different Machine Learning Algorithms 463.2.1 Performance Measures for Machine Learning Algorithms 483.2.2 Steps to Implement ML Algorithms 493.2.3 Various Platforms Available for Implementation 503.2.4 Applications of Machine Learning in Electrical Engineering 503.3 ML Use-Case in MATLAB 513.4 ML Use-Case in Python 563.4.1 ML Model Deployment 593.5 Conclusion 60References 604 PRECISE RISK ASSESSMENT AND MANAGEMENT 63Ambika N.4.1 Introduction 644.2 Need for Security 654.2.1 Confidentiality 654.2.2 Integrity 664.2.3 Availability 664.2.4 Accountability 664.2.5 Auditing 674.3 Different Kinds of Attacks 674.3.1 Malware 674.3.2 Man-in-the Middle Assault 694.3.3 Brute Force Assault 694.3.4 Distributed Denial of Service 694.4 Literature Survey 704.5 Proposed Work 754.5.1 Objective 754.5.2 Notations Used in the Contribution 764.5.3 Methodology 764.5.4 Simulation and Analysis 784.6 Conclusion 80References 805 A DETAILED REVIEW ON SECURITY ISSUES IN LAYERED ARCHITECTURES AND DISTRIBUTED DENIAL SERVICE OF ATTACKS OVER IOT ENVIRONMENT 85Rajarajan Ganesarathinam, Muthukumaran Singaravelu and K.N. Padma Pooja5.1 Introduction 865.2 IoT Components, Layered Architectures, Security Threats 895.2.1 IoT Components 895.2.2 IoT Layered Architectures 905.2.2.1 3-Layer Architecture 915.2.2.2 4-Layer Architecture 915.2.2.3 5-Layer Architecture 935.2.3 Associated Threats in the Layers 935.2.3.1 Node Capture 935.2.3.2 Playback Attack 935.2.3.3 Fake Node Augmentation 935.2.3.4 Timing Attack 945.2.3.5 Bootstrap Attack 945.2.3.6 Jamming Attack 945.2.3.7 Kill Command Attack 945.2.3.8 Denial-of-Service (DoS) Attack 945.2.3.9 Storage Attack 945.2.3.10 Exploit Attack 955.2.3.11 Man-In-The-Middle (MITM) Attack 955.2.3.12 XSS Attack 955.2.3.13 Malicious Insider Attack 955.2.3.14 Malwares 955.2.3.15 Zero-Day Attack 955.3 Taxonomy of DDoS Attacks and Its Working Mechanism in IoT 975.3.1 Taxonomy of DDoS Attacks 995.3.1.1 Architectural Model 995.3.1.2 Exploited Vulnerability 1005.3.1.3 Protocol Level 1015.3.1.4 Degree of Automation 1015.3.1.5 Scanning Techniques 1015.3.1.6 Propagation Mechanism 1025.3.1.7 Impact Over the Victim 1025.3.1.8 Rate of Attack 1035.3.1.9 Persistence of Agents 1035.3.1.10 Validity of Source Address 1035.3.1.11 Type of Victim 1035.3.1.12 Attack Traffic Distribution 1035.3.2 Working Mechanism of DDoS Attack 1045.4 Existing Solution Mechanisms Against DDoS Over IoT 1055.4.1 Detection Techniques 1055.4.2 Prevention Mechanisms 1085.5 Challenges and Research Directions 1135.6 Conclusion 115References 1156 MACHINE LEARNING AND DEEP LEARNING TECHNIQUES FOR PHISHING THREATS AND CHALLENGES 123Bhimavarapu Usharani6.1 Introduction 1246.2 Phishing Threats 1246.2.1 Internet Fraud 1246.2.1.1 Electronic-Mail Fraud 1256.2.1.2 Phishing Extortion 1266.2.1.3 Extortion Fraud 1276.2.1.4 Social Media Fraud 1276.2.1.5 Tourism Fraud 1286.2.1.6 Excise Fraud 1296.2.2 Phishing 1296.3 Deep Learning Architectures 1316.3.1 Convolution Neural Network (CNN) Models 1316.3.1.1 Recurrent Neural Network 1316.3.1.2 Long Short-Term Memory (LSTM) 1346.4 Related Work 1356.4.1 Machine Learning Approach 1356.4.2 Neural Network Approach 1366.4.3 Deep Learning Approach 1386.5 Analysis Report 1396.6 Current Challenges 1406.6.1 File-Less Malware 1406.6.2 Crypto Mining 1406.7 Conclusions 140References 1417 NOVEL DEFENDING AND PREVENTION TECHNIQUE FOR MAN-IN-THE-MIDDLE ATTACKS IN CYBER-PHYSICAL NETWORKS 147Gaurav Narula, Preeti Nagrath, Drishti Hans and Anand Nayyar7.1 Introduction 1487.2 Literature Review 1507.3 Classification of Attacks 1527.3.1 The Perception Layer Network Attacks 1527.3.2 Network Attacks on the Application Control Layer 1537.3.3 Data Transmission Layer Network Attacks 1537.3.3.1 Rogue Access Point 1547.3.3.2 ARP Spoofing 1557.3.3.3 DNS Spoofing 1577.3.3.4 mDNS Spoofing 1607.3.3.5 SSL Stripping 1617.4 Proposed Algorithm of Detection and Prevention 1627.4.1 ARP Spoofing 1627.4.2 Rogue Access Point and SSL Stripping 1687.4.3 DNS Spoofing 1697.5 Results and Discussion 1737.6 Conclusion and Future Scope 173References 1748 FOURTH ORDER INTERLEAVED BOOST CONVERTER WITH PID, TYPE II AND TYPE III CONTROLLERS FOR SMART GRID APPLICATIONS 179Saurav S. and Arnab Ghosh8.1 Introduction 1798.2 Modeling of Fourth Order Interleaved Boost Converter 1818.2.1 Introduction to the Topology 1818.2.2 Modeling of FIBC 1828.2.2.1 Mode 1 Operation (0 to d1 Ts) 1828.2.2.2 Mode 2 Operation (d1 Ts to d2 Ts) 1848.2.2.3 Mode 3 Operation (d2 Ts to d3 Ts) 1868.2.2.4 Mode 4 Operation (d3 Ts to Ts) 1888.2.3 Averaging of the Model 1908.2.4 Small Signal Analysis 1908.3 Controller Design for FIBC 1938.3.1 PID Controller 1938.3.2 Type II Controller 1948.3.3 Type III Controller 1958.4 Computational Results 1978.5 Conclusion 204References 2059 INDUSTRY 4.0 IN HEALTHCARE IOT FOR INVENTORY AND SUPPLY CHAIN MANAGEMENT 209Somya Goyal9.1 Introduction 2109.1.1 RFID and IoT for Smart Inventory Management 2109.2 Benefits and Barriers in Implementation of RFID 2129.2.1 Benefits 2139.2.1.1 Routine Automation 2139.2.1.2 Improvement in the Visibility of Assets and Quick Availability 2159.2.1.3 SCM-Business Benefits 2159.2.1.4 Automated Lost and Found 2169.2.1.5 Smart Investment on Inventory 2179.2.1.6 Automated Patient Tracking 2179.2.2 Barriers 2189.2.2.1 RFID May Interfere With Medical Activities 2189.2.2.2 Extra Maintenance for RFID Tags 2189.2.2.3 Expense Overhead 2189.2.2.4 Interoperability Issues 2189.2.2.5 Security Issues 2189.3 IoT-Based Inventory Management—Case Studies 2189.4 Proposed Model for RFID-Based Hospital Management 2209.5 Conclusion and Future Scope 225References 22610 A SYSTEMATIC STUDY OF SECURITY OF INDUSTRIAL IOT 229Ravi Gedam and Surendra Rahamatkar10.1 Introduction 23010.2 Overview of Industrial Internet of Things (Smart Manufacturing) 23110.2.1 Key Enablers in Industry 4.0 23310.2.2 OPC Unified Architecture (OPC UA) 23410.3 Industrial Reference Architecture 23610.3.1 Arrowgead 23710.3.2 FIWARE 23710.3.3 Industrial Internet Reference Architecture (IIRA) 23810.3.4 Kaa IoT Platform 23810.3.5 Open Connectivity Foundation (OCF) 23910.3.6 Reference Architecture Model Industrie 4.0 (RAMI 4.0) 23910.3.7 ThingsBoard 24010.3.8 ThingSpeak 24010.3.9 ThingWorx 24010.4 FIWARE Generic Enabler (FIWARE GE) 24110.4.1 Core Context Management GE 24110.4.2 NGSI Context Data Model 24210.4.3 IDAS IoT Agents 24410.4.3.1 IoT Agent-JSON 24610.4.3.2 IoT Agent-OPC UA 24710.4.3.3 Context Provider 24710.4.4 FIWARE for Smart Industry 24810.5 Discussion 24910.5.1 Solutions Adopting FIWARE 25010.5.2 IoT Interoperability Testing 25110.6 Conclusion 252References 25311 INVESTIGATION OF HOLISTIC APPROACHES FOR PRIVACY AWARE DESIGN OF CYBER-PHYSICAL SYSTEMS 257Manas Kumar Yogi, A.S.N. Chakravarthy and Jyotir Moy Chatterjee11.1 Introduction 25811.2 Popular Privacy Design Recommendations 25811.2.1 Dynamic Authorization 25811.2.2 End to End Security 25911.2.3 Enrollment and Authentication APIs 25911.2.4 Distributed Authorization 26011.2.5 Decentralization Authentication 26111.2.6 Interoperable Privacy Profiles 26111.3 Current Privacy Challenges in CPS 26211.4 Privacy Aware Design for CPS 26311.5 Limitations 26511.6 Converting Risks of Applying AI Into Advantages 26611.6.1 Proof of Recognition and De-Anonymization 26711.6.2 Segregation, Shamefulness, Mistakes 26711.6.3 Haziness and Bias of Profiling 26711.6.4 Abuse Arising From Information 26711.6.5 Tips for CPS Designers Including AI in the CPS Ecosystem 26811.7 Conclusion and Future Scope 269References 27012 EXPOSING SECURITY AND PRIVACY ISSUES ON CYBER-PHYSICAL SYSTEMS 273Keshav Kaushik12.1 Introduction to Cyber-Physical Systems (CPS) 27312.2 Cyber-Attacks and Security in CPS 27712.3 Privacy in CPS 28112.4 Conclusion & Future Trends in CPS Security 284References 28513 APPLICATIONS OF CYBER-PHYSICAL SYSTEMS 289Amandeep Kaur and Jyotir Moy Chatterjee13.1 Introduction 28913.2 Applications of Cyber-Physical Systems 29113.2.1 Healthcare 29113.2.1.1 Related Work 29313.2.2 Education 29513.2.2.1 Related Works 29513.2.3 Agriculture 29613.2.3.1 Related Work 29713.2.4 Energy Management 29813.2.4.1 Related Work 29913.2.5 Smart Transportation 30013.2.5.1 Related Work 30113.2.6 Smart Manufacturing 30113.2.6.1 Related Work 30313.2.7 Smart Buildings: Smart Cities and Smart Houses 30313.2.7.1 Related Work 30413.3 Conclusion 304References 305Index 311
Datenanonymisierung im Kontext von Künstlicher Intelligenz und Big Data
Die fortschreitende Digitalisierung, die immer höhere Verfügbarkeit des Internets in Echtzeit sowie die progressive Entwicklung der IT ermöglichen es Unternehmen und Organisationen, Daten in einem nie zuvor dagewesenen Umfang zu erzeugen und zu verarbeiten, wodurch sie einen enormen Stellen- und Marktwert erhalten haben. Zudem kann mithilfe der künstlichen Intelligenz (KI) das in den Daten enthaltene Wissen extrahiert werden. Oft handelt es sich dabei um gesammelte Daten von Personen, mit denen Vorhersagen über verschiedene Aspekte der Personen getroffen werden können.Das Buch befasst sich mit der Anonymisierung im Kontext der KI und Big Data. Dazu werden die wesentlichen Grundlagen dargestellt sowie pseudonymisierte und anonymisierte Daten mit Personenbezug im Rahmen der Datenschutz-Grundverordnung (DSGVO) und des Bundesdatenschutzgesetzes (BDSG) beleuchtet. Es werden Möglichkeiten zur Pseudonymisierung, zu den jeweiligen Techniken und Verfahren der Anonymisierung sowie entsprechende Risikobetrachtungen behandelt. Abschließend wird die Vorgehensweise der Anonymisierung aus rechtlicher und technischer Sicht unter Anwendung entsprechender Software behandelt.DR. HEINZ-ADALBERT KREBS ist geschäftsführender Gesellschafter der Green Excellence GmbH, welche Unternehmen der Energiewirtschaft bei Softwareimplementierungen, Geschäftsprozessoptimierungen, der Informationssicherheit und des Datenschutzes berät. Daneben lehrt er am Fachbereich Wirtschaftsinformatik der Universität Kassel die Einführung von ERP-Systemen (SAP) und ist zertifizierter Datenschutzbeauftragter sowie ISO 27001 Lead Auditor.DR. PATRICIA HAGENWEILER ist langjährige Mitarbeiterin der Green Excellence GmbH und zertifizierte Datenschutzbeauftragte.Einleitung.- Künstliche Intelligenz.- Big Data und Analysemethoden.- Personenbezogene, pseudonymisierte und anonymisierte Daten.- Techniken der Pseudonymisierung.- Anonymisierung strukturierter Daten.- Anonymisierung unstrukturierter Daten.- Risiken der Nutzung anonymisierter Daten.- Verfahren zur Durchführung der Anonymisierung.- Software zur Unterstützung der Anonymisierung.- Fazit und Ausblick.- Literatur.
If It's Smart, It's Vulnerable
REIMAGINE THE FUTURE OF THE INTERNETAll our devices and gadgets—from our refrigerators to our home security systems, vacuum cleaners, and stereos—are going online, just like our computers did. But once we’ve successfully connected our devices to the internet, do we have any hope of keeping them, and ourselves, safe from the dangers that lurk beneath the digital waters? In If It’s Smart, It’s Vulnerable, veteran cybersecurity professional Mikko Hypponen delivers an eye-opening exploration of the best—and worst—things the internet has given us. From instant connectivity between any two points on the globe to organized ransomware gangs, the net truly has been a mixed blessing. In this book, the author explores the transformative potential of the future of the internet, as well as those things that threaten its continued existence: government surveillance, censorship, organized crime, and more. Readers will also find:* Insightful discussions of how law enforcement and intelligence agencies operate on the internet* Fulsome treatments of how money became data and the impact of the widespread use of mobile supercomputing technology* Explorations of how the internet has changed the world, for better and for worse* Engaging stories from Mikko's 30-year career in infosecPerfect for anyone seeking a thought-provoking presentation of some of the most pressing issues in cybersecurity and technology, If It’s Smart, It’s Vulnerable will also earn a place in the libraries of anyone interested in the future of the internet. MIKKO HYPPONEN is a global cyber security expert with over thirty years’ experience working as a researcher and investigator. He is a sought-after lecturer, and he was profiled in Vanity Fair. His TED Talk has been viewed more than 2 million times.Foreword: Jeff Moss xiiiPreface xviiSaab 9000 Turbo xxiThe Good and the Bad of the Internet 1Prehistoric Internet 2The First Websites 5Linux Is the World’s Most Important System 7iPhone vs. Supercomputer 10Online Communities 11Money Is Data 13Codes All Around Us 14Geopolitics 17Security Tetris 21Who Are We Fighting? 24Schoolboys 24Spammer 26Professional Cybercrime Groups 28Extremists 29The Rolex 30Malware—Then, Now, and in the Near Future 33The History of Malware 34Viruses on Floppies 34Brain.A 35File Viruses 43Macro Viruses 43Email Worms 45Internet Worms 46The Virus Wars 49Web Attacks 51Mobile Phone Viruses 51Worms on Social Media 54Smartphones and Malware 55Law Enforcement Malware 57Case R2D2 58Cracking Passwords 59When a Hacker Spilled Her Coffee 60Ransomware Trojans 61The History of Ransomware Trojans 61Cryptolocker 64Honest Criminals 65Notpetya 65Case Maersk 67Wannacry 71My Week with Wannacry 72Targeted Ransomware Trojans 76Ransomware Trojans v2 77The Human Element 79The Two Problems 80The Heist 82CEO Fraud 89Touring the Headquarters 92Protecting Company Networks 95Zero Trust 100Bug Bounties 101Wi-Fi Terms of Use 110Mikko’s Tips 112Mikko’s Tips for the Startup Entrepreneur 114Boat for Sale 118What If the Network Goes Down? 121Electrical Networks 122Security in Factories 124A Search Engine for Computers 126Slammer 128Hypponen’s Law 130Dumb Devices 132Regulation 134Car Software Updates 136Online Privacy 137Life Without Google 138Murder Charges Never Expire 139Is Google Listening to You? 142Gorillas 143Startup Business Logic 145Biometrics 147Antisocial Media 149Online Influencing and Elections 151Privacy Is Dead 153Before and After Gmail 156Encryption Techniques 160Perfect Encryption 160Unbreakable Encryption 161Criminal Use of Encryption Systems 162Data Is The New Uranium 166CASE Vastaamo 168Patient Registry 169Technologies 170Vastaamo.tar 171Extortion Messages 173The Hunt for the TAR File 175Innocent Victims 177Cryptocurrencies 179The Value of Money 180Blockchains 181Blockchain Applications 182Blockchains and Money 183The Environmental Impacts of Bitcoin 185Playing the Market 187Ethereum, Monero, and Zcash 189NFT 191Bitcoin and Crime 193Border Guards vs. Bitcoin 195Technology, Espionage, and Warfare Online 199Cyberweapons 200Lunch Break at Google 201Technology and Warfare 202Under a False Flag 204Concealability of Cyberweapons 205The Fog of Cyberwar 207Case Prykarpattyaoblenergo 211Case Pyeongchang 213Governments as Malware Authors 214Russia and China 216Case Stuxnet 217Damage Coverage 226Explosion at the White House 227My Boycott of RSA, Inc 229The Future 233Artificial Intelligence 234Wolverines 237AI Will Take Our Jobs 238Smart Malware 239Metaverse 240The Technology of Warfare 241“You Are Under Arrest for a Future Murder” 242Those Who Can Adapt Will Prosper 243Tesla 245Trends in Technology 247Coda 249Index 251
Network Programming with Go Language
Dive into key topics in network architecture implemented with the Google-backed open source Go programming language. Networking topics such as data serialization, application level protocols, character sets and encodings are discussed and demonstrated in Go. This book has been updated to the Go version 1.18 which includes modules, generics, and fuzzing along with updated and additional examples.Beyond the fundamentals, Network Programming with Go, Second Edition covers key networking and security issues such as HTTP protocol changes, validation and templates, remote procedure call (RPC) and REST comparison, and more. Additionally, authors Ronald Petty and Jan Newmarch guide you in building and connecting to a complete web server based on Go. Along the way, use of a Go web toolkit (Gorilla) will be employed.This book can serve as both an essential learning guide and reference on networking concepts and implementation in Go. Free source code is available on Github for this book under Creative Commons open source license.WHAT YOU WILL LEARN* Perform network programming with Go (including JSON and RPC)* Understand Gorilla, the Golang web toolkit, and how to use it* Implement a microservice architecture with Go* Leverage Go features such as generics, fuzzing* Master syscalls and how to employ them with GoWHO THIS BOOK IS FORAnyone interested in learning networking concepts implemented in modern Go. Basic knowledge in Go is assumed, however, the content and examples in this book are approachable with modest development experience in other languages.JAN NEWMARCH, Ph.d., is Head of Higher Education (ICT), Box Hill Institute, Adjunct Senior Research Fellow, Faculty of IT, Monash University, and Adjunct Lecturer, School of Computing and Mathematics Charles Sturt University.RONALD PETTY is a Principal Consultant at RX-M LLC. His programming expertise is in open source languages like Go, Ruby and more. He currently is working on a number of Go code projects on Github.1: Architectural Layers2: Overview of the Go Language3: Socket-Level Programming4: Data Serialization5: Application-Level Protocols6: Managing Character Sets and Encodings7: Security8: HTTP9: Templates10: A Complete Web Server11: HTML12: XML13: Remote Procedure Call14: REST15: WebSockets16: Gorilla17: TestingAppendix A: FuzzingAppendix B: Generics
Accounting Fraud
Dieses Buch beschreibt, welche typischen Fälle von Bilanzmanipulationen auch im Alltag von Konzernen und KMUs vorkommen können, durch Mitarbeiter und Dienstleister. Das Bewusstsein für Accounting Fraud ist oft nicht vorhanden. In diesem Buch werden branchentypische Besonderheiten der Bilanz und GuV aufgegriffen. Die Autoren erläutern verschiedene Manipulationsarten und zeigen, wie diese aufgedeckt werden können. Zudem wird erklärt, welche Maßnahmen Unternehmen zur Früherkennung und Prävention ergreifen können, beispielsweise durch den Einsatz forensischer Datenanalyse. Dieses Buch veranschaulicht, wie wichtig es für Praktiker ist, sich dem Thema zu widmen, auch anhand von Praxisbeispielen.
Automated Deep Learning Using Neural Network Intelligence
Optimize, develop, and design PyTorch and TensorFlow models for a specific problem using the Microsoft Neural Network Intelligence (NNI) toolkit. This book includes practical examples illustrating automated deep learning approaches and provides techniques to facilitate your deep learning model development.The first chapters of this book cover the basics of NNI toolkit usage and methods for solving hyper-parameter optimization tasks. You will understand the black-box function maximization problem using NNI, and know how to prepare a TensorFlow or PyTorch model for hyper-parameter tuning, launch an experiment, and interpret the results. The book dives into optimization tuners and the search algorithms they are based on: Evolution search, Annealing search, and the Bayesian Optimization approach. The Neural Architecture Search is covered and you will learn how to develop deep learning models from scratch. Multi-trial and one-shot searching approaches of automatic neural network design are presented. The book teaches you how to construct a search space and launch an architecture search using the latest state-of-the-art exploration strategies: Efficient Neural Architecture Search (ENAS) and Differential Architectural Search (DARTS). You will learn how to automate the construction of a neural network architecture for a particular problem and dataset. The book focuses on model compression and feature engineering methods that are essential in automated deep learning. It also includes performance techniques that allow the creation of large-scale distributive training platforms using NNI.After reading this book, you will know how to use the full toolkit of automated deep learning methods. The techniques and practical examples presented in this book will allow you to bring your neural network routines to a higher level.WHAT YOU WILL LEARN* Know the basic concepts of optimization tuners, search space, and trials* Apply different hyper-parameter optimization algorithms to develop effective neural networks* Construct new deep learning models from scratch* Execute the automated Neural Architecture Search to create state-of-the-art deep learning models* Compress the model to eliminate unnecessary deep learning layersWHO THIS BOOK IS FORIntermediate to advanced data scientists and machine learning engineers involved in deep learning and practical neural network developmentIVAN GRIDIN is a machine learning expert from Moscow who has worked on distributive high-load systems and implemented different machine learning approaches in practice. One of the primary areas of his research is the design and analysis of predictive time series models. Ivan has fundamental math skills in probability theory, random process theory, time series analysis, machine learning, deep learning, and optimization. He has published books on genetic algorithms and time series analysis. Chapter 1: Introduction to Neural Network Intelligence1.1 Installation1.2 Trial, search space, experiment1.3 Finding maxima of multivariate function1.4 Interacting with NNIChapter 2:Hyper-Parameter Tuning2.1 Preparing a model for hyper-parameter tuning2.2 Running experiment2.3 Interpreting results2.4 DebuggingChapter 3: Hyper-Parameter TunersChapter 4: Neural Architecture Search: Multi-trial4.1 Constructing a search space4.2 Running architecture search4.3 Exploration strategies4.4 Comparing exploration strategiesChapter 5: Neural Architecture Search: One-shot5.1 What is one-shot NAS?5.2 ENAS5.3 DARTSChapter 6: Model Compression6.1 What is model compression?6.2 Compressing your model6.3 Pruning6.4 QuantizationChapter 7: Advanced NNI
SAP S/4 HANA-Systeme in Hyperscaler Clouds
Dieses Buch hilft Ihnen bei der Architektur, dem Setup, der Installation und dem Betrieb von SAP S/4HANA-Systemen in der Public Cloud von Amazon, Microsoft und Google. Blue-Prints, Beispielarchitekturen und konkrete Handlungsanweisungen helfen bei der Erreichung Ihres Ziels.ANDRÉ BÖGELSACK arbeitet als Principal Director bei der Firma Accenture in der Schweiz und berät Kunden aller Industrien bei der Nutzung von Hyperscaler Services für den Betrieb von SAP-Systemen. Er wurde in Informatik über das Thema SAP promoviert und ist weithin in der SAP Community und bei den Hyperscalern bekannt.ELENA WOLZ studierte Wirtschaftsinformatik an der Technischen Universität München. Als Produktverantwortliche für SAP S/4HANA am SAP University Competence Center München beschäftigt sie sich zentral mit der Bereitstellung von SAP S/4HANA-Systemen. Weiterhin begleitete sie ganzheitlich ein S/4HANA Deployment-Projekt in Hyperscaler-Cloud-Umgebung.JOHANNES RANK leitet die Basis am SAP University Competence Center in München und verantwortet seit vielen Jahren den Betrieb von SAP S/4HANA-Systemen in Cloud- und On-Premise Umgebungen.JESSICA TISCHBIEREK übernimmt seit Herbst 2021 die Rolle als SAP GTM Lead EMEA bei Google Cloud mit Standort München. Sie hat zuvor seit 2018 bei Google Cloud im Pre-Sales Umfeld als Customer Engineer Specialist for SAP on Google Cloud Kunden bei ihrer Cloud Transformation beraten. Dabei arbeitet sie mit globalen Unternehmen und Partnern zusammen.DHIRAJ KUMAR arbeitet als Manager bei Accenture in Indien und leitet mit seinem Team die Ausführung der Migrationen von sehr großen und komplexen SAP-Landschaften. Sein Fokus sind der Einsatz von neuartigen Methoden für die Bereitstellung von SAP.UTPAL CHAKRABORTY arbeitet als Manager bei der Accenture GmbH in Deutschland und hat mehrjährige Erfahrung beim Betrieb und der Migration von SAP-Systemen in die Cloud. Er arbeitet branchenübergreifend und hat bereits die SAP-Systeme einer Vielzahl von Kunden in die Cloud gehoben.Einleitung und Einführung zu Hyperscaler Clouds - SAP S/4HANA-Systeme in den Hyperscaler Clouds - Konzepte und Architekturen für SAP S/4HANA-Systeme auf Amazon Web Services – AWS - Konzepte und Architekturen für SAP S/4HANA-Systeme auf Microsoft Azure - Konzepte und Architekturen für SAP S/4HANA-Systeme auf Google Cloud - Installation und Provisionierung von SAP S/4HANA-Systemen auf den Hyperscaler Clouds - Zusammenfassung und Ausblick
Microsoft Orleans for Developers
Use a simple programming model and the .NET language of your choice to build large distributed systems. This book teaches you the Microsoft Orleans framework.Even well-versed professional software developers with expertise in C# (or another language) find themselves unequipped to meet the challenges of distributed systems as infrastructure moves to multi-core; multiple computers are being used for scale, redundancy, and cloud computing; and multi-region deployment is taking place.Orleans handles many of the concerns of distributed computing and cloud infrastructure, allowing you to concentrate on writing application logic.WHAT YOU WILL LEARN* Know the key concepts for building distributed systems* Gain a background in the origin and evolution of Orleans, and why it is important for your projects* Dive into each of the features available in Orleans by building an example application* Develop troubleshooting skills for fixing bugs and running diagnostics* Achieve performance optimization and advanced configuration* Use the Orleans Dashboard to discern valuable insight in system performanceWHO THIS BOOK IS FORExperienced C# developers who want to build a new high-scale application (perhaps for an IoT requirement) and are interested in learning the concepts and features available in OrleansRICHARD ASTBURY works at Microsoft UK, helping software teams build software systems to run in the cloud. Richard is a former Microsoft MVP for Windows Azure. He is often found developing open source software in C# and Node.js, navigating the river on his paddle board, and riding his bike. He lives in rural Suffolk, UK with his wife, three children, and golden retriever. 1. Fundamentals2. Grains and Silos3. Hello World4. Debugging an Orleans Application5. Orleans Dashboard6. Adding Persistence7. Adding ASP.NET Core8. Unit Testing9. Streams10. Timer and Reminders11. Transactions12. Event Sourced Grains13. Updating Grains14. Optimizations15. Advanced Features16. Interviews
Model-based Systems Architecting
Model-based Systems Architecting is a key tool for designing complex industrial systems. It is dedicated to the working systems architects, engineers and modelers, in order to help them master the complex integrated systems that they are dealing with in their day-to-day professional lives.It presents the CESAMES Systems Architecting Method (CESAM), a systems architecting and modeling framework which has been developed since 2003 in close interaction with many leading industrial companies, providing rigorous and unambiguous semantics for all classical systems architecture concepts. This approach is practically robust and easy-to-use: during the last decade, it was deployed in more than 2,000 real system development projects within the industry, and distributed to around 10,000 engineers around the globe. DANIEL KROB is one of the leading world experts in systems architecting and engineering. He was Institute Professor at Ecole Polytechnique, Palaiseau, France, and founder and Director of its Industrial Chair dedicated to complex systems engineering for more than 15 years. He is currently President of the Center of Excellence on Systems Architecture, Management, Economy & Strategy (CESAMES) and has been an INCOSE Fellow since 2014.Preface ixAcknowledgments xvIntroduction xviiCHAPTER 1 INTRODUCTION TO CESAM 11.1 CESAM: a mathematically sound system modeling framework 11.2 CESAM: a framework focused on complex integrated systems 81.3 CESAM: a collaboration-oriented architecting framework 121.4 CESAM: a business-oriented framework 16CHAPTER 2 WHY ARCHITECTING SYSTEMS? 192.1 Product and project systems 192.2 The complexity threshold 222.3 Addressing systems architecting becomes key 252.4 The value of systems architecting 312.5 The key role of systems architects 342.6 How to analyze a systems architect profile? 36CHAPTER 3 CESAM FRAMEWORK 393.1 Elements of systemics 393.1.1 Interface 393.1.2 Environment of a system 413.2 The three architectural visions 423.2.1 Architectural visions definition 423.2.2 Architectural visions overview 463.2.3 Relationships between the three architectural visions 523.2.4 Organization of a system model 553.3 CESAM systems architecture pyramid 573.3.1 The three key questions to ask 573.3.2 The last question that shall not be forgotten 593.4 More systems architecture dimensions 603.4.1 Descriptions versus expected properties 603.4.2 Descriptions 623.4.3 Expected properties 733.5 CESAM systems architecture matrix 78CHAPTER 4 IDENTIFYING STAKEHOLDERS: ENVIRONMENT ARCHITECTURE 834.1 Why identify stakeholders? 834.2 The key deliverables of environment architecture 854.2.1 Stakeholder hierarchy diagram 854.2.2 Environment diagram 87CHAPTER 5 UNDERSTANDING INTERACTIONS WITH STAKEHOLDERS: OPERATIONAL ARCHITECTURE 915.1 Why understand interactions with stakeholders? 915.2 The key deliverables of operational architecture 945.2.1 Need architecture diagram 945.2.2 Lifecycle diagram 955.2.3 Use case diagrams 975.2.4 Operational scenario diagrams 995.2.5 Operational flow diagram 101CHAPTER 6 DEFINING WHAT THE SYSTEM SHALL DO: FUNCTIONAL ARCHITECTURE 1036.1 Why understand what the system does? 1036.2 The key deliverables of functional architecture 1056.2.1 Functional requirement architecture diagram 1066.2.2 Functional mode diagram 1086.2.3 Functional breakdown and interaction diagrams 1096.2.4 Functional scenario diagrams 1116.2.5 Functional flow diagram 112CHAPTER 7 DECIDING HOW THE SYSTEM SHALL BE FORMED: CONSTRUCTIONAL ARCHITECTURE 1157.1 Understanding how the system is formed? 1157.2 The key deliverables of constructional architecture 1177.2.1 Constructional requirement architecture diagram 1187.2.2 Configuration diagram 1207.2.3 Constructional breakdown and interaction diagram 1217.2.4 Constructional scenario diagram 1237.2.5 Constructional flow diagram 124CHAPTER 8 TAKING INTO ACCOUNT FAILURES: DYSFUNCTIONAL ANALYSIS 1278.1 Systems do not always behave as they should 1278.2 The key deliverables of dysfunctional analysis 1348.2.1 Dysfunctional analysis from an operational perspective 1358.2.2 Dysfunctional analysis from a functional perspective 1368.2.3 Dysfunctional analysis from a constructional perspective 138CHAPTER 9 CHOOSING THE BEST ARCHITECTURE: TRADE-OFF TECHNIQUES 1419.1 Systems architecting does not usually lead to a unique solution 1419.2 Trade-off techniques 1439.2.1 General structure of a trade-off process 1439.2.2 Managing trade-offs in practice 145Conclusion 149APPENDICES 157Appendix 1 System Temporal Logic 159Appendix 2 Classical Engineering Issues 163Appendix 3 Example of System Model Managed with CESAM 177Appendix 4 Implementing CESAM through a SysML Modeling Tool 199Appendix 5 Some Good Practices in Systems Modeling 209References 211Index 219
From Logistic Networks to Social Networks
As a result of its widespread implementation in economic and social structures, the network concept appears to be a paradigm of the contemporary world. The need for various services – transport, energy, consumption of manufacturing goods, provision of care, information and communication, etc. – draws users into interwoven networks which are meshes of material and immaterial flows. In this context, the user is a consumer of goods and services from industries and administrations, or they themselves are part of the organization (digital social networks).This book examines the invariants that unify networks in their diversity, as well as the specificities that differentiate them. It provides a reading grid that distinguishes a generic level where these systems find a common interpretation, and a specific level where appropriate analytical methods are used. Three case studies from different fields are presented to illustrate the purpose of the book in detail. Jean-Paul Bourrières is Emeritus Professor at the University of Bordeaux, France.Nathalie Pinède is Associate Professor at Bordeaux Montaigne University, France.Mamadou Kaba Traoré is Professor at the University of Bordeaux, France.Gregory Zacharewicz is Professor at IMT Mines Alès, France.Foreword ixIntroduction xiPART 1. NETWORK VARIETY AND MODELING 1CHAPTER 1. NETWORK TYPOLOGY 31.1. Introduction 31.1.1. Network description levels 31.1.2. Network, graph and flow 41.1.3. Shared or dedicated infrastructure 51.1.4. User inclusion 61.2. The principal networks 61.2.1. (Human) transport networks 61.2.2. (Goods) distribution and collection networks 71.2.3. Dedicated distribution and collection networks (of fluids and energy) 81.2.4. IT networks 91.2.5. Communication networks 91.2.6. Social and digital social networks 101.3. Characterization and typology of networks 111.3.1. Key characteristics 111.3.2. Network integration 121.3.3. Typology 131.4. Engineering issues 161.5. Performance indicators, evaluation, optimization 181.5.1. Performance indicators 181.5.2. Evaluation and optimization 201.6. Conclusion 23CHAPTER 2. MODELING DISCRETE FLOW NETWORKS 252.1. Introduction 252.2. Structure 282.3. Characterization of a discrete flow 302.3.1. Statistical description 302.3.2. Probabilistic description 322.4. Activities 322.5. Control system 372.6. Resources 402.7. Fluid kinematics 412.7.1. Flow/resource/decision synchronization 422.7.2. Congestion phenomenon 482.7.3. Dissemination of information in social networks 512.8. Formalisms for modeling flows in a network 522.8.1. BPM tools 532.8.2. Timed Petri nets 532.8.3. Flow networks 542.8.4. Queuing networks 552.9. Multi-modeling 572.9.1. Multi-formalism versus mono-formalism 572.9.2. The DEVS hierarchical model 602.9.3. Multi-layer networks 622.10. Conclusion 64PART 2. NETWORK ANALYSIS METHODS AND APPLICATIONS 67CHAPTER 3. EXACT METHODS APPLIED TO THE FLOW ANALYSIS OF TOPOLOGICAL NETWORKS 693.1. Introduction 693.2. Additive flow networks – deterministic modelling by flow networks 713.2.1. Two-terminal series–parallel graph 723.2.2. General case – max-flow/min-cut 743.3. Additive flow networks – stochastic modelling by queuing networks 763.4. Synchronized flow networks – modeling by timed event graphs 813.4.1. Steady-state analysis of timed event graphs 813.4.2. Example of application: sizing a flow-shop 833.5. Conclusion 88CHAPTER 4. SIMULATION TECHNIQUES APPLIED TO THE ANALYSIS OF SOCIOLOGICAL NETWORKS 914.1. Introduction 914.2. Simulation techniques 924.2.1. Discrete event simulation (worldviews) 944.2.2. DEVS formalism 964.2.3. Coupling simulation/resolutive methods 1004.2.4. Distributed simulation 1024.2.5. Architectural solutions 1034.2.6. Time management and synchronization 1044.2.7. Pessimistic approach 1044.2.8. Optimistic approach 1054.2.9. HLA 1064.2.10. Cosimulation 1074.2.11. FMI/FMU 1084.2.12. FMI/FMU and HLA coupling 1094.3. Simulation of flows in sociological networks 1104.3.1. Behavioral simulation based on DEVS formalism 1114.3.2. Application study 1134.4. Conclusion 116PART 3. CASE STUDIES 119CHAPTER 5. SMART GRID 1215.1. Summary of the study 1225.2. Demand profile 1225.3. Solar power station, fuel station and regional import 1235.4. Hydroelectric power station and PHES 1235.5. Operational issues 1245.6. Model 1255.6.1. Decision variables 1255.6.2. Constraints 1265.6.3. Objective function 1275.7. Optimization results 128CHAPTER 6. FORESTRY LOGISTICS 1316.1. Summary of the study 1326.2. Forest timber supply problem 1326.3. Tactical planning model 1346.4. Logistics benchmarking 1366.4.1. AS IS scenario (non-collaborative logistics) 1366.4.2. TO BE scenario (collaborative logistics) 1376.4.3. Results 1386.5. Conclusion 139CHAPTER 7. MULTI-LAYERED DIGITAL SOCIAL NETWORKS 1437.1. Summary of the study 1447.2. Digital social networks 1447.3. Studying digital social networks via an interview broadcast 1457.3.1. Pre-interview social network scenario 1467.3.2. Social network audience 1487.4. Modeling and simulation 1487.4.1. Modeling the interview production and broadcast processes 1487.4.2. MSN/HLA simulation architecture 1497.5. Simulation results 1527.6. Conclusion and perspectives 154References 157Index 167
Pro Angular
Welcome to this one-stop shop for learning Angular. Pro Angular is the most concise and comprehensive guide available, giving you the knowledge you need to take full advantage of this popular framework for building your own dynamic JavaScript applications.Angular is an open-source JavaScript library maintained by Google. It has many excellent options when it comes to server-side development and is used in some of the largest and most complex web applications in the world to enhance HTML in the browser. Its cornerstone is the ability to create applications that are extendable, maintainable, testable, and standardized. Knowing Angular’s foundations and understanding its applications is an asset in any developer toolbox.The fifth edition of this popular guide explains how to get the most from Angular, presenting the range of benefits it can offer. You will begin learning how to use Angular in your projects, starting with the nuts-and-bolts concepts, and progressing to more advanced and sophisticated features. Each topic in this full-color book provides you with precisely enough learning and detail to be effective. In true Adam Freeman style, the most important features are given full-court press treatment, while also addressing common problems and how to avoid them.WHAT YOU WILL LEARN* Access accompanying online files for Angular 13 and 14 (when it is released)* Create rich and dynamic web app clients using Angular* Tap into some of the best aspects of server-side development* Know when to use Angular and when to seek an alternative* Use the ng tools to create and build an Angular project* Extend and customize Angular* Take advantage of popular component libraries* Utilize source code located at github.com/Apress/pro-angular-5edWHO THIS BOOK IS FORThis book is for web developers who want to create rich client-side applications. Foundational knowledge of HTML and JavaScript is recommended."Adam's books provide a finely tuned blend of architectural overview, technical depth, and experience-born wisdom. His clear, concise writing style, coupled with project-driven, real-world examples make me comfortable recommending his books to a broad audience, ranging from developers working with a technology for the first time to seasoned professionals who need to learn a new skill quickly."KEITH DUBLIN, STAFF ARCHITECT, Upfront Health Care“Adam’s books are the print version of a chat bot. His investment in learning how developers learn pays off in dividends, making this one of the most comprehensive resources available. Novices and experienced professionals alike will gain knowledge from the accessible and insightful material.”MARK DONILE, SOFTWARE ENGINEER, MS CSADAM FREEMAN is an experienced IT professional who has held senior positions in a range of companies, most recently serving as chief technology officer and chief operating officer of a global bank. Now retired, he spends his time writing and long-distance running.PART I – GETTING READYChapter 1. Getting ReadyChapter 2. Jumping Right InChapter 3. Primer, Part IChapter 4. Primer, Part IIChapter 5. SportsStore: A Real ApplicationChapter 6. SportsStore: Orders and CheckoutChapter 7. SportsStore:AdministrationChapter 8. SportsStore: Progressive Features and DeploymentPART II - WORKING WITH ANGULARChapter 9. Understanding Angular Projects and ToolsChapter 10. Using Data Bindings Chapter 11. Using the Built-In DirectivesChapter 12. Using Events and FormsChapter 13. Creating Attribute DirectivesChapter 14. Creating Structural DirectivesChapter 15. Understanding ComponentsChapter 16. Using and Creating PipesChapter 17. Using ServicesChapter 18. Using Service ProvidersChapter 19. Using and Creating ModulesPART III - ADVANCED ANGULAR FEATURESChapter 20. Creating the Example ProjectChapter 21. Using the Forms API, Part IChapter 22. Using the Forms API, Part IIChapter 23. Making HTTP RequestsChapter 24. Routing and Navigation, Part IChapter 25. Routing and Navigation, Part IIChapter 26. Routing and Navigation, Part IIIChapter 27. Using AnimationsChapter 28. Working with Component LibrariesChapter 29. Angular Unit Testing
Just ›A Machine for Doing Business‹?
An analysis of the informal practices and strategies surrounding the technology implementation process. How is a new intranet involved in an ongoing merger integration process? Katja Schönian analyses internal communication and branding strategies in connection with the implementation of a new company intranet. Based on qualitative data, the study contrasts managerial expectations and everyday usage of the intranet in distinct work settings. Relying on social practice theories and research in Science & Technology Studies, Katja Schönian unpacks the different logics the intranet brings together and, furthermore, interrogates the characteristics that make an (un)workable technology. The book sheds light on the informal practices and politics surrounding the technology implementation process. It provides readers with new insights into the dynamics of a merger integration process, the production of worker subjectivity, and the increasing involvement of technologies in contemporary knowledge work.
Anisotropic hp-Mesh Adaptation Methods
Mesh adaptation methods can have a profound impact on the numerical solution of partial differential equations. If devised and implemented properly, adaptation significantly reduces the size of the algebraic systems resulting from the discretization, while ensuring that applicable error tolerances are met. In this monograph, drawing from many years of experience, the authors give a comprehensive presentation of metric-based anisotropic hp-mesh adaptation methods.A large part of this monograph is devoted to the derivation of computable interpolation error estimates on simplicial meshes, which take into account the geometry of mesh elements as well as the anisotropic features of the interpolated function. These estimates are then used for the optimization of corresponding finite element spaces in a variety of settings. Both steady and time dependent problems are treated, as well as goal-oriented adaptation. Practical aspects of implementation are also explored, including several algorithms. Many numerical experiments using the discontinuous Galerkin method are presented to illustrate the performance of the adaptive techniques.This monograph is intended for scientists and researchers, including doctoral and master-level students. Portions of the text can also be used as study material for advanced university lectures concerning a posteriori error analysis and mesh adaptation. Introduction.- Metric Based Mesh Representation.- Interpolation Error Estimates for Two Dimensions.- Interpolation Error Estimates for Three Dimensions.- Anisotropic Mesh Adaptation, h-Variant.- Anisotropic Mesh Adaptation Method, hp-Variant.- Framework of the Goal-Oriented Error Estimates.- Goal-Oriented Anisotropic Mesh Adaptation.- Implementation Aspects.- Applications.
Digitalization and Control of Industrial Cyber-Physical Systems
Industrial cyber-physical systems operate simultaneously in the physical and digital worlds of business and are now a cornerstone of the fourth industrial revolution. Increasingly, these systems are becoming the way forward for academics and industrialists alike. The very essence of these systems, however, is often misunderstood or misinterpreted. This book thus sheds light on the problem areas surrounding cyber-physical systems and provides the reader with the key principles for understanding and illustrating them.Presented using a pedagogical approach, with numerous examples of applications, this book is the culmination of more than ten years of study by the Intelligent Manufacturing and Services Systems (IMS2) French research group, part of the MACS (Modeling, Analysis and Control of Dynamic Systems) research group at the CNRS. It is intended both for engineers who are interested in emerging industrial developments and for master’s level students wishing to learn about the industrial systems of the future. OLIVIER CARDIN is a lecturer in Industrial Engineering at the IUT de Nantes, Nantes University, France.WILLIAM DERIGENT is a Professor in Industrial Engineering at the University of Lorraine, France.DAMIEN TRENTESAUX is a Professor in Industrial Engineering at the Université Polytechnique Hauts-de-France, France.Foreword xiiiAndré THOMASIntroduction xviiOlivier CARDIN, William DERIGENT and Damien TRENTESAUXPART 1 CONCEPTUALIZING INDUSTRIAL CYBER-PHYSICAL SYSTEMS 1CHAPTER 1 GENERAL CONCEPTS 3Olivier CARDIN and Damien TRENTESAUX1.1 Industry at the heart of society 31.2 Industrial world in search of a new model 41.3 Cyber-physical systems 61.4 From cyber-physical systems to industrial cyber-physical systems 81.5 Perspectives on the study of industrial cyber-physical systems 111.6 References 15CHAPTER 2 MOVING TOWARDS A SUSTAINABLE MODEL: SOCIETAL, ECONOMIC AND ENVIRONMENTAL 17Patrick MARTIN, Maroua NOUIRI and Ali SIADAT2.1 Industry of the future and sustainable development 172.2 Contribution of ICPS to the social dimension 182.2.1 Background 182.2.2 Cognitive aspects 212.2.3 Health and safety aspects at work 222.3 Contribution of ICPS to the environmental dimension 282.3.1 Objectives and expectations 282.3.2 Example of application 292.4 Contribution of ICPS to the economic dimension 302.5 Conclusion 322.6 References 32PART 2 SENSING AND DISTRIBUTING INFORMATION WITHIN INDUSTRIAL CYBER-PHYSICAL SYSTEMS 37CHAPTER 3 INFORMATION FLOW IN INDUSTRIAL CYBER-PHYSICAL SYSTEMS 39Thierry BERGER and Yves SALLEZ3.1 Introduction 393.2 Information and decision loops when using an ICPS 393.3 Decision-making processes within the loops of an ICPS 413.3.1 Nature of decision-making processes 413.3.2 Nature of information 423.3.3 Approach to studying the informational loops of the cyber part of an ICPS 433.4 Elements for the implementation of loops 453.4.1 Generic architecture 453.4.2 Link to decision-making processes and the nature of the information 483.5 Illustrative examples 483.5.1 Example from rail transport 493.5.2 Example from the manufacturing sector 503.6 Conclusion 523.7 References 52CHAPTER 4 THE INTELLIGENT PRODUCT CONCEPT 55William DERIGENT4.1 The intelligent product, a leading-edge concept in industrial cyber-physical systems 554.2 Definitions of the intelligent product concept 564.3 Developments in the concept of intelligent products 594.3.1 Group 1: product-driven systems (PDS) 614.3.2 Group 2: product lifecycle information management (PLIM) 634.4 Conclusions and perspectives on the intelligent product 664.5 References 67PART 3 DIGITALIZING AT THE SERVICE OF INDUSTRIAL CYBER-PHYSICAL SYSTEMS 71CHAPTER 5 VIRTUALIZING RESOURCES, PRODUCTS AND THE INFORMATION SYSTEM 73Theodor BORANGIU, Silviu RĂILEANU and Octavian MORARIU5.1 Virtualization – the technology for industrial cyber-physical systems 735.2 Virtualization in the industrial environment 745.3 Shop floor virtualization of resource and product workloads 785.3.1 Resource and product virtualization through shop floor profiles 785.3.2 Virtualization of collaborative product and resource workloads 835.4 MES virtualization in the cloud (vMES) 895.5 Perspectives offered by virtualization to industry of the future 945.6 References 95CHAPTER 6 CYBERSECURITY OF INDUSTRIAL CYBER-PHYSICAL SYSTEMS 97Antoine GALLAIS and Youcef IMINE6.1 What are the risks involved? 986.1.1 Unavailability of systems 986.1.2 Loss of confidentiality or integrity 1016.1.3 Bypassing access and authentication controls 1046.2 What means of protection? 1056.2.1 Ensuring availability 1056.2.2 Ensuring confidentiality 1076.2.3 Implementing authentication mechanisms 1086.2.4 Controlling access, permissions and logging 1096.3 Conclusion 1126.4 References 114PART 4 CONTROLLING INDUSTRIAL CYBER-PHYSICAL SYSTEMS117CHAPTER 7 INDUSTRIAL AGENTS: FROM THE HOLONIC PARADIGM TO INDUSTRIAL CYBER-PHYSICAL SYSTEMS 119Paulo LEITÃO, Stamatis KARNOUSKOS and Armando Walter COLOMBO7.1 Overview of multi-agent systems and holonics 1207.1.1 Multi-agent systems 1207.1.2 Holonic paradigm 1227.2 Industrial agents 1247.2.1 Definition and characteristics 1247.2.2 Interfacing with physical assets 1267.3 Industrial agents for realizing industrial cyber-physical systems 1277.3.1 Supporting the development of intelligent products, machines and systems within cyber-physical systems 1277.3.2 Implementing an industrial multi-agent system as ICPS 1297.4 Discussion and future directions 1307.5 References 131CHAPTER 8 HOLONIC CONTROL ARCHITECTURES 135Olivier CARDIN, William DERIGENT and Damien TRENTESAUX8.1 Introduction 1358.2 HCA fundamentals 1368.3 HCAs in the physical part of ICPS 1378.4 Dynamic architectures, towards a reconfiguration of the physical part from the cyber part of ICPS 1408.5 HCAs and Big Data 1438.6 HCAs and digital twin: towards the digitization of architectures 1448.7 References 145PART 5 LEARNING AND INTERACTING WITH INDUSTRIAL CYBER-PHYSICAL SYSTEMS 149CHAPTER 9 BIG DATA ANALYTICS AND MACHINE LEARNING FOR INDUSTRIAL CYBER-PHYSICAL SYSTEMS 151Yasamin ESLAMI, Mario LEZOCHE and Philippe THOMAS9.1 Introduction 1519.2 Data massification in industrial cyber-physical systems 1539.3 Big Data and multi-relational data mining (MRDM) 1549.3.1 Formal concept analysis (FCA) 1549.3.2 Relational concept analysis (RCA) 1579.4 Machine learning 1609.4.1 Basics of machine learning 1609.4.2 Multilayer perceptron (MLP) 1609.5 Illustrative example 1659.6 Conclusion 1679.7 References 167CHAPTER 10 HUMAN–INDUSTRIAL CYBER-PHYSICAL SYSTEM INTEGRATION: DESIGN AND EVALUATION METHODS 171Marie-Pierre PACAUX-LEMOINE and Frank FLEMISCH10.1 Introduction 17110.2 Design methods 17510.3 Method of integrating HICPS 17610.3.1 Descending phase 17710.3.2 Ascending phase 18010.4 Summary and conclusion 18510.5 References 186PART 6 TRANSFORMING INDUSTRIES WITH INDUSTRIAL CYBER-PHYSICAL SYSTEMS 189CHAPTER 11 IMPACT OF INDUSTRIAL CYBER-PHYSICAL SYSTEMS ON RECONFIGURABLE MANUFACTURING SYSTEMS 191Catherine DA CUNHA and Nathalie KLEMENT11.1 Context 19111.1.1 Developments 19211.1.2 Issues 19311.1.3 Resources 19311.2 Reconfiguration 19411.2.1 Implementation and decision levels 19411.2.2 Information systems 19511.2.3 Adaptation in the context of CPPS/RMS 19611.2.4 Where and when to reconfigure? 19711.3 Modeling 19711.3.1 Data collection 19811.3.2 Simulation platforms 19911.4 Ergonomics/cognitive aspects 20011.5 Operation of the information system 20111.5.1 Operational level: procurement 20111.5.2 Responding to disruptions 20211.5.3 Decision support 20311.6 Illustrative example 20311.7 References 205CHAPTER 12 IMPACT OF INDUSTRIAL CYBER-PHYSICAL SYSTEMS ON GLOBAL AND INTERCONNECTED LOGISTICS 207Shenle PAN, Mariam LAFKIHI and Eric BALLOT12.1 Logistics and its challenges 20712.2 Contemporary logistics systems and organizations 20812.2.1 Intra-site logistics 20912.2.2 Intra-urban logistics 21012.2.3 Inter-site inter-city logistics 21112.3 The Physical Internet as a modern and promising logistics organization 21212.3.1 Concept and definition 21212.3.2 Topologies of networks of networks 21312.4 Perspectives of ICPS applications in interconnected logistics: the example of the Physical Internet 21512.4.1 Modeling the Physical Internet by ICPS: the example of routing 21612.4.2 Exploiting ICPS: the data-driven approach and the digital twin-driven approach 21912.5 Conclusion 22112.6 References 222CHAPTER 13 IMPACT OF INDUSTRIAL CYBER-PHYSICAL SYSTEMS ON TRANSPORTATION 225John MBULI and Damien TRENTESAUX13.1 Introduction 22513.1.1 Pull forces 22613.1.2 Complexity factors of the transportation sector 22713.1.3 Push forces 22813.2 The impact of ICPS on transportation 22913.3 Rail transportation service: an illustrative example 23113.3.1 The physical space of SUPERFLO 23313.3.2 The human fleet supervisor 23513.3.3 The cyber space of SUPERFLO 23613.3.4 Evaluation of the proposed model and industrial expectations 23613.4 Concluding remarks 23813.5 Acknowledgments 23913.6 References 239CHAPTER 14 IMPACTS OF INDUSTRIAL CYBER-PHYSICAL SYSTEMS ON THE BUILDING TRADES 243William DERIGENT and Laurent JOBLOT14.1 General introduction 24314.2 The place of BIM in Construction 4.0 24514.3 Examples of transformations in the construction sector 24714.3.1 Control: real-time site management 24814.3.2 Learning and interacting: virtual reality and machine learning 24914.3.3 Capturing and distributing: use of wireless technologies (RFID and WSN) 25114.3.4 Digitalizing: digitalizing technologies for BIM 25214.4 Example of ICPS in construction 25414.5 Achieving the digital transformation of businesses 25514.6 References 257CHAPTER 15 IMPACT OF INDUSTRIAL CYBER-PHYSICAL SYSTEMS ON THE HEALTH SYSTEM 261Franck FONTANILI and Maria DI MASCOLO15.1 Introduction 26115.1.1 The health system and its specificities 26115.1.2 The digital evolution of healthcare production and health 26315.2 HCPS in the literature 26315.2.1 HCPS for medical monitoring 26615.2.2 HCPS for well-being and prevention 26615.2.3 HCPS for organizational monitoring of patient pathways 26715.2.4 Sensors for monitoring patients and resources 26815.3 The contribution of a digital twin in an HCPS 27015.3.1 General principle of digital twins in health 27015.3.2 A proposal for an HCPS based on a digital twin of patient pathways in the hospital 27115.4 Conclusion 27415.5 References 275PART 7 ENVISIONING THE INDUSTRIAL CYBER-PHYSICAL SYSTEMS OF THE FUTURE 279CHAPTER 16 ETHICS AND RESPONSIBILITY OF INDUSTRIAL CYBER-PHYSICAL SYSTEMS 281Sylvie JONAS and Françoise LAMNABHI-LAGARRIGUE16.1 Introduction 28116.2 Ethics and ICPS 28316.2.1 Data management and protection 28416.2.2 Control in the design of algorithms 28516.3 Liability and ICPS 28816.3.1 Existing liability regimes applied to ICPS 28916.3.2 Proposals for changes in liability regimes 29116.4 References 294CHAPTER 17 TEACHING AND LEARNING ICPS: LESSONS LEARNED AND BEST PRACTICES 297Bilal AHMAD, Freeha AZMAT, Armando Walter COLOMBO and Gerrit JAN VELTINK17.1 Introduction 29717.2 University of Warwick – Bachelor-level curriculum 29917.2.1 ICPS education: Fusion of computer science and engineering 30017.2.2 Key enabling technologies in the ICPS curriculum 30117.2.3 Pedagogical principles: teaching ICPS modules 30117.3 University of Applied Sciences Emden/Leer – master’s-level curriculum 30217.3.1 ICPS education: fusion of computer science, electrical and mechatronics engineering 30317.3.2 Key enabling technologies in the ICPS curriculum 30517.3.3 Pedagogical principles: teaching ICPS modules 30717.4 Conclusion 30817.5 References 309Conclusion 313William DERIGENT, Olivier CARDIN and Damien TRENTESAUXList of Authors 317Index 321
Reinforcement Learning with Hybrid Quantum Approximation in the NISQ Context
This book explores the combination of Reinforcement Learning and Quantum Computing in the light of complex attacker-defender scenarios. Reinforcement Learning has proven its capabilities in different challenging optimization problems and is now an established method in Operations Research. However, complex attacker-defender scenarios have several characteristics that challenge Reinforcement Learning algorithms, requiring enormous computational power to obtain the optimal solution.The upcoming field of Quantum Computing is a promising path for solving computationally complex problems. Therefore, this work explores a hybrid quantum approach to policy gradient methods in Reinforcement Learning. It proposes a novel quantum REINFORCE algorithm that enhances its classical counterpart by Quantum Variational Circuits. The new algorithm is compared to classical algorithms regarding the convergence speed and memory usage on several attacker-defender scenarios with increasing complexity. In addition, to study its applicability on today's NISQ hardware, the algorithm is evaluated on IBM's quantum computers, which is accompanied by an in-depth analysis of the advantages of Quantum Reinforcement Learning.About the authorLeonhard Kunczik obtained his Dr. rer. nat. in 2021 in Quantum Reinforcement Learning from the Universität der Bundeswehr München as a member of the COMTESSA research group. Now, he continues his research as a project leader at the forefront of Quantum Machine Learning and Optimization in the context of Operations Research and Cyber Security.Motivation: Complex Attacker-Defender Scenarios - The eternal conflict., The Information Game - A special Attacker-Defender Scenario., Reinforcement Learning and Bellman’s Principle of Optimality., Quantum Reinforcement Learning - Connecting Reinforcement Learning and Quantum Computing.- Approximation in Quantum Computing.- Advanced Quantum Policy Approximation in Policy Gradient Rein-forcement Learning.- Applying Quantum REINFORCE to the Information Game.- Evaluating quantum REINFORCE on IBM’s Quantum Hardware.- Future Steps in Quantum Reinforcement Learning for Complex Scenarios.- Conclusion.
Infobody Theory and Infobody Model
This book presents a new concept: infobody.It contains four chapters:Chapter 1: Infobody OverviewThis chapter talks about the new concept—infobody and all related concepts and definitions. It also gives a summary for each following chapter and potential applications and research topics.Chapter 2: Infobody ChartingThis chapter talks about infobody charting with detailed steps and illustrations. Infobody charting is actually a visualization of the infobody model described in Chapter 3.Chapter 3: Infobody Model in Terms of Graph TheoryThis chapter talks about the infobody model in terms of graph theory. It gives detailed mathematical definitions and descriptions.Chapter 4: Chaos and Entropy in Infobody StructuresThis chapter talks about the chaos and entropy in infobody structures and gives detailed definitions and mathematical formulas.The author would like to discuss the infobody topics with anyone who is interested in it, such as university professors and students, managers and employees in any business industries and government agencies. His dedicated email address for this topic is yuhuinfobody@gmail.com.
Machines Behaving Badly
Can we build moral machines?Artificial intelligence is an essential part of our lives – for better or worse. It can be used to influence what we buy, who gets shortlisted for a job and even how we vote. Without AI, medical technology wouldn't have come so far, we'd still be getting lost in our GPS-free cars, and smartphones wouldn't be so, well, smart. But as we continue to build more intelligent and autonomous machines, what impact will this have on humanity and the planet?Professor Toby Walsh, a world-leading researcher in the field of artificial intelligence, explores the ethical considerations and unexpected consequences AI poses. Can AI be racist? Can robots have rights? What happens if a self-driving car kills someone? What limitations should we put on the use of facial recognition? Machines Behaving Badly is a thought-provoking look at the increasing human reliance on robotics and the decisions that need to be made now to ensure the future of AI is a force for good, not evil.
Medical Imaging and Health Informatics
MEDICAL IMAGING AND HEALTH INFORMATICSPROVIDES A COMPREHENSIVE REVIEW OF ARTIFICIAL INTELLIGENCE (AI) IN MEDICAL IMAGING AS WELL AS PRACTICAL RECOMMENDATIONS FOR THE USAGE OF MACHINE LEARNING (ML) AND DEEP LEARNING (DL) TECHNIQUES FOR CLINICAL APPLICATIONS.Medical imaging and health informatics is a subfield of science and engineering which applies informatics to medicine and includes the study of design, development, and application of computational innovations to improve healthcare. The health domain has a wide range of challenges that can be addressed using computational approaches; therefore, the use of AI and associated technologies is becoming more common in society and healthcare. Currently, deep learning algorithms are a promising option for automated disease detection with high accuracy. Clinical data analysis employing these deep learning algorithms allows physicians to detect diseases earlier and treat patients more efficiently. Since these technologies have the potential to transform many aspects of patient care, disease detection, disease progression and pharmaceutical organization, approaches such as deep learning algorithms, convolutional neural networks, and image processing techniques are explored in this book.This book also delves into a wide range of image segmentation, classification, registration, computer-aided analysis applications, methodologies, algorithms, platforms, and tools; and gives a holistic approach to the application of AI in healthcare through case studies and innovative applications. It also shows how image processing, machine learning and deep learning techniques can be applied for medical diagnostics in several specific health scenarios such as COVID-19, lung cancer, cardiovascular diseases, breast cancer, liver tumor, bone fractures, etc. Also highlighted are the significant issues and concerns regarding the use of AI in healthcare together with other allied areas, such as the Internet of Things (IoT) and medical informatics, to construct a global multidisciplinary forum.AUDIENCEThe core audience comprises researchers and industry engineers, scientists, radiologists, healthcare professionals, data scientists who work in health informatics, computer vision and medical image analysis.TUSHAR H. JAWARE, PHD, received his degree in Medical Image Processing and is now an assistant professor in the Department of Electronics and Telecommunication Engineering, R C Patel Institute of Technology, Shirpur, India. He has published more than 50 research articles in refereed journals and IEEE conferences, and has three international patents granted and two Indian patents published.K. SARAT KUMAR, PHD, received his degree in Electronics Engineering and is now a professor in the Department of Electronics & Communication Engineering, K L University, Andhra Pradesh, India. RAVINDRA D. BADGUJAR, PHD, received his degree in Electronics Engineering and is now an assistant professor in the Department of Electronics and Telecommunication Engineering, R C Patel Institute of Technology, Shirpur, India. He has published many research articles in refereed journals and IEEE conferences as well as one international patent granted and two Indian patents published. SVETLIN ANTONOV, PHD, received his degree in Telecommunications and is now a lecturer in the Faculty of Telecommunications, TU-Sofia, Bulgaria. He is the author of several books and more than 60 peer-reviewed articles. PREFACE XVII1 MACHINE LEARNING APPROACH FOR MEDICAL DIAGNOSIS BASED ON PREDICTION MODEL 1Hemant Kasturiwale, Rajesh Karhe and Sujata N. Kale1.1 Introduction 21.1.1 Heart System and Major Cardiac Diseases 21.1.2 ECG for Heart Rate Variability Analysis 21.1.3 HRV for Cardiac Analysis 31.2 Machine Learning Approach and Prediction 31.3 Material and Experimentation 41.3.1 Data and HRV 41.3.1.1 HRV Data Analysis via ECG Data Acquisition System 51.3.2 Methodology and Techniques 61.3.2.1 Classifiers and Performance Evaluation 71.3.3 Proposed Model With Layer Representation 81.3.4 The Model Using Fixed Set of Features and Standard Dataset 111.3.4.1 Performance of Classifiers With Feature Selection 111.4 Performance Metrics and Evaluation of Classifiers 131.4.1 Cardiac Disease Prediction Through Flexi Intra Group Selection Model 131.4.2 HRV Model With Flexi Set of Features 141.4.3 Performance of the Proposed Modified With ISM-24 151.5 Discussion and Conclusion 181.5.1 Conclusion and Future Scope 19References 202 APPLICATIONS OF MACHINE LEARNING TECHNIQUES IN DISEASE DETECTION 23M.S. Roobini, Sowmiya M., S. Jancy and L. Suji Helen2.1 Introduction 242.1.1 Overview of Machine Learning Types 242.1.2 Motivation 252.1.3 Organization the Chapter 252.2 Types of Machine Learning Techniques 252.2.1 Supervised Learning 252.2.2 Classification Algorithm 252.2.3 Regression Analysis 262.2.4 Linear Regression 272.2.4.1 Applications of Linear Regression 272.2.5 KNN Algorithm 282.2.5.1 Working of KNN 282.2.5.2 Drawbacks of KNN Algorithm 292.2.6 Decision Tree Classification Algorithm 292.2.6.1 Attribute Selection Measures 292.2.6.2 Information Gain 292.2.6.3 Gain Ratio 292.2.7 Random Forest Algorithm 292.2.7.1 How the Random Forest Algorithm Works 292.2.7.2 Advantage of Using Random Forest 302.2.7.3 Disadvantage of Using the Random Forest 312.2.8 Naive Bayes Classifier Algorithm 312.2.8.1 For What Reason is it Called Naive Bayes? 312.2.8.2 Disservices of Naive Bayes Classifier 312.2.9 Logistic Regression 312.2.9.1 Logistic Regression for Machine Learning 312.2.10 Support Vector Machine 322.2.11 Unsupervised Learning 322.2.11.1 Clustering 332.2.11.2 PCA in Machine Learning 352.2.12 Semi-Supervised Learning 382.2.12.1 What is Semi-Supervised Clustering? 382.2.12.2 How Semi-Supervised Learning Functions? 382.2.13 Reinforcement Learning 392.2.13.1 Artificial Intelligence 392.2.13.2 Deep Learning 402.2.13.3 Points of Interest of Machine Learning 412.2.13.4 Why Machine Learning is Popular 412.2.13.5 Test Utilizations of ML 422.3 Future Research Directions 432.3.1 Privacy 432.3.2 Accuracy 43References 433 DENGUE INCIDENCE RATE PREDICTION USING NONLINEAR AUTOREGRESSIVE NEURAL NETWORK TIME SERIES MODEL 47S. Dhamodharavadhani and R. Rathipriya3.1 Introduction 473.2 Related Literature Study 483.2.1 Limitations of Existing Works 503.2.2 Contributions of Proposed Methodology 503.3 Methods and Materials 503.3.1 NAR-NNTS 503.3.2 Fit/Train the Model 513.3.3 Training Algorithms 543.3.3.1 Levenberg-Marquardt (LM) Algorithm 543.3.3.2 Bayesian Regularization (BR) Algorithm 553.3.3.3 Scaled Conjugate Gradient (SCG) Algorithm 553.3.4 DIR Prediction 553.4 Result Discussions 563.4.1 Dataset Description 563.4.2 Evaluation Measure for NAR-NNTS Models 573.4.3 Analysis of Results 573.5 Conclusion and Future Work 65Acknowledgment 66References 664 EARLY DETECTION OF BREAST CANCER USING MACHINE LEARNING 69G. Lavanya and G. Thilagavathi4.1 Introduction 704.1.1 Objective 704.1.2 Anatomy of Breast 704.1.3 Breast Imaging Modalities 714.2 Methodology 714.2.1 Database 714.2.2 Image Pre-Processing 714.3 Segmentation 724.4 Feature Extraction 724.5 Classification 724.5.1 Naive Bayes Neural Network Classifier 724.5.2 Radial Basis Function Neural Network 734.5.2.1 Input 734.5.2.2 Hidden Layer 734.5.2.3 Output Nodes 744.6 Performance Evaluation Methods 744.7 Output 754.7.1 Dataset 754.7.2 Pre-Processing 754.7.3 Segmentation 754.7.4 Geometric Feature Extraction 774.8 Results and Discussion 784.8.1 Database 784.9 Conclusion and Future Scope 81References 815 MACHINE LEARNING APPROACH FOR PREDICTION OF LUNG CANCER 83Hemant Kasturiwale, Swati Bhisikar and Sandhya Save5.1 Introduction 845.1.1 Disorders in Lungs 845.1.2 Background 845.1.3 Material, Datasets, and Techniques 855.2 Feature Extraction and Lung Cancer Analysis 865.3 Methodology 875.3.1 Proposed Algorithm Steps 875.3.2 Classifiers in Concurrence With Datasets 885.4 Proposed System and Implementation 895.4.1 Interpretation via Artificial Intelligence 895.4.2 Training of Model 905.4.3 Implementation and Results 905.5 Conclusion 995.5.1 Future Scope 99References 1006 SEGMENTATION OF LIVER TUMOR USING ANN 103Hema L. K. and R. Indumathi6.1 Introduction 1036.2 Liver Tumor 1046.2.1 Overview of Liver Tumor 1046.2.2 Classification 1056.2.2.1 Benign 1056.2.2.2 Malignant 1076.3 Benefits of CT to Diagnose Liver Cancer 1086.4 Literature Review 1086.5 Interactive Liver Tumor Segmentation by Deep Learning 1096.6 Existing System 1096.7 Proposed System 1106.7.1 Pre-Processing 1106.7.2 Segmentation 1116.7.3 Feature Extraction 1126.7.4 GLCM 1126.7.5 Backpropagation Network 1136.8 Result and Discussion 1136.8.1 Processed Images 1146.8.2 Segmentation 1166.9 Future Enhancements 1176.10 Conclusion 118References 1187 DMSAN: DEEP MULTI-SCALE ATTENTION NETWORK FOR AUTOMATIC LIVER SEGMENTATION FROM ABDOMEN CT IMAGES 121Devidas T. Kushnure and Sanjay N. Talbar7.1 Introduction 1217.2 Related Work 1227.3 Methodology 1237.3.1 Proposed Architecture 1237.3.2 Multi-Scale Feature Characterization Using Res2Net Module 1257.4 Experimental Analysis 1267.4.1 Dataset Description 1267.4.2 Pre-Processing Dataset 1277.4.3 Training Strategy 1287.4.4 Loss Function 1287.4.5 Implementation Platform 1297.4.6 Data Augmentation 1297.4.7 Performance Metrics 1297.5 Results 1317.6 Result Comparison With Other Methods 1357.7 Discussion 1367.8 Conclusion 137Acknowledgement 138References 1388 AI-BASED IDENTIFICATION AND PREDICTION OF CARDIAC DISORDERS 141Rajesh Karhe, Hemant Kasturiwale and Sujata N. Kale8.1 Introduction 1428.1.1 Cardiac Electrophysiology and Electrocardiogram 1438.1.2 Heart Arrhythmia 1448.1.2.1 Types of Arrhythmias 1458.1.3 ECG Database 1478.1.3.1 Association for the Advancement of Medical Instrumentation (AAMI) Standard 1478.1.4 An Overview of ECG Signal Analysis 1488.2 Related Work 1498.3 Classifiers and Methodology 1518.3.1 Databases for Cardiac Arrhythmia Detection 1528.3.2 MIT-BIH Normal Sinus Rhythm and Arrhythmia Database 1528.3.3 Arrhythmia Detection and Classification 1538.3.4 Methodology 1538.3.4.1 Database Gathering and Pre-Processing 1538.3.4.2 QRST Wave Detection 1538.3.4.3 Features Extraction 1548.3.4.4 Neural Network 1558.3.4.5 Performance Evaluation 1568.4 Result Analysis 1568.4.1 Arrhythmia Detection and Classification 1568.4.2 Dataset 1568.4.3 Evaluations and Results 1568.4.4 Evaluating the Performance of Various Neural Network Classifiers (Arrhythmia Detection) 1578.5 Conclusions and Future Scope 1598.5.1 Arrhythmia Detection and Classification 1598.5.2 Future Scope 161References 1619 AN IMPLEMENTATION OF IMAGE PROCESSING TECHNIQUE FOR BONE FRACTURE DETECTION INCLUDING CLASSIFICATION 165Rocky Upadhyay, Prakash Singh Tanwar and Sheshang Degadwala9.1 Introduction 1659.2 Existing Technology 1669.2.1 Pre-Processing 1669.2.2 Denoise Image 1679.2.3 Histogram 1689.3 Image Processing 1699.3.1 Canny Edge 1699.4 Overview of System and Steps 1709.4.1 Workflow 1709.4.2 Classifiers 1719.4.2.1 Extra Tree Ensemble Method 1719.4.2.2 SVM 1729.4.2.3 Trained Algorithm 1739.4.3 Feature Extraction 1739.5 Results 1749.5.1 Result Analysis 1759.6 Conclusion 176References 17610 IMPROVED OTSU ALGORITHM FOR SEGMENTATION OF MALARIA PARASITE IMAGES 179Mosam K. Sangole, Sanjay T. Gandhe and Dipak P. Patil10.1 Introduction 17910.2 Literature Review 18010.3 Related Works 18210.4 Proposed Algorithm 18310.5 Experimental Results 18410.6 Conclusion 193References 19311 A RELIABLE AND FULLY AUTOMATED DIAGNOSIS OF COVID-19 BASED ON COMPUTED TOMOGRAPHY 195Bramah Hazela, Saad Bin Khalid and Pallavi Asthana11.1 Introduction 19611.2 Background 19611.3 Methodology 19911.3.1 Models Used 19911.3.2 Architecture of the Image Source Classification Model 19911.3.3 Architecture of the CT Scan Classification Model 20011.3.4 Architecture of the Ultrasound Image Classification Model 20111.3.5 Architecture of the X-Ray Classification Model 20111.3.6 Dataset 20211.3.6.1 Training 20211.4 Results 20411.5 Conclusion 206References 20712 MULTIMODALITY MEDICAL IMAGES FOR HEALTHCARE DISEASE ANALYSIS 209B. Rajalingam, R. Santhoshkumar, P. Santosh Kumar Patra, M. Narayanan, G. Govinda Rajulu and T. Poongothai12.1 Introduction 21012.1.1 Background 21012.2 Brief Survey of Earlier Works 21212.3 Medical Imaging Modalities 21312.3.1 Computed Tomography (CT) 21412.3.2 Magnetic Resonance Imaging (MRI) 21412.3.3 Positron Emission Tomography (PET) 21412.3.4 Single-Photon Emission Computed Tomography (SPECT) 21512.4 Image Fusion 21612.4.1 Different Levels of Image Fusion 21612.4.1.1 Pixel Level Fusion 21612.4.1.2 Feature Level Fusion 21712.4.1.3 Decision Level Fusion 21712.5 Clinical Relevance for Medical Image Fusion 21812.5.1 Clinical Relevance for Neurocyticercosis (NCC) 21812.5.2 Clinical Relevance for Neoplastic Disease 21812.5.2.1 Clinical Relevance for Astrocytoma 21812.5.2.2 Clinical Relevance for Anaplastic Astrocytoma 21912.5.2.3 Clinical Relevance for Metastatic Bronchogenic Carcinoma 22012.5.3 Clinical Relevance for Alzheimer’s Disease 22112.6 Data Sets and Softwares Used 22112.7 Generalized Image Fusion Scheme 22112.7.1 Input Image Modalities 22212.7.2 Image Registration 22212.7.3 Fusion Process 22312.7.4 Fusion Rule 22312.7.5 Evaluation 22412.7.5.1 Subjective Evaluation 22412.7.5.2 Objective Evaluation 22412.8 Medical Image Fusion Methods 22412.8.1 Traditional Image Fusion Techniques 22412.8.1.1 Spatial Domain Image Fusion Approach 22512.8.1.2 Transform Domain Image Fusion Approach 22512.8.1.3 Fuzzy Logic–Based Image Fusion Approach 22712.8.1.4 Filtering Technique–Based Image Fusion Approach 22712.8.1.5 Neural Network–Based Image Fusion Approach 22712.8.2 Hybrid Image Fusion Techniques 22812.8.2.1 Transforms with Fuzzy Logic–Based Medical Image Fusion 22812.8.2.2 Transforms With Guided Image Filtering–Based Medical Image Fusion 22912.8.2.3 Transforms With Neural Network–Based Image Fusion 22912.9 Conclusions 23312.9.1 Future Work 234References 23413 HEALTH DETECTION SYSTEM FOR COVID-19 PATIENTS USING IOT 237Dipak P. Patil, Kishor Badane, Amit Kumar Mishra and Vishal A. Wankhede13.1 Introduction 23713.1.1 Overview 23713.1.2 Preventions 23813.1.3 Symptoms 23813.1.4 Present Situation 23813.2 Related Works 23913.3 System Design 23913.3.1 Hardware Implementation 23913.3.1.1 NodeMCU 24013.3.1.2 DHT 11 Sensor 24013.3.1.3 MAX30100 Oxygen Sensor 24113.3.1.4 ThingSpeak Server 24213.3.1.5 Arduino IDE 24313.4 Proposed System for Detection of Corona Patients 24513.4.1 Introduction 24513.4.2 Arduino IDE 24613.4.3 Hardware Implementation 24613.5 Results and Performance Analysis 24713.5.1 Hardware Implementation 24713.5.1.1 Implementation of NodeMCU With Temperature Sensor 24713.5.2 Software Implementation 24813.5.2.1 Simulation of Temperature Sensor With Arduino on Proteus Software 24813.5.2.2 Interfacing of LCD With Arduino 25013.6 Conclusion 250References 25014 INTELLIGENT SYSTEMS IN HEALTHCARE 253Rajiv Dey and Pankaj Sahu14.1 Introduction 25314.2 Brain Computer Interface 25514.2.1 Types of Signals Used in BCI 25614.2.2 Components of BCI 25714.2.3 Applications of BCI in Health Monitoring 25814.3 Robotic Systems 25814.3.1 Advantages of Surgical Robots 25814.3.2 Centralization of the Important Information to the Surgeon 25914.3.3 Remote-Surgery, Software Development, and High SpeedConnectivity Such as 5G 26014.4 Voice Recognition Systems 26014.5 Remote Health Monitoring Systems 26014.5.1 Tele-Medicine Health Concerns 26214.6 Internet of Things–Based Intelligent Systems 26214.6.1 Ubiquitous Computing Technologies in Healthcare 26414.6.2 Patient Bio-Signals and Acquisition Methods 26514.6.3 Communication Technologies Used in Healthcare Application 26714.6.4 Communication Technologies Based on Location/Position 26914.7 Intelligent Electronic Healthcare Systems 27014.7.1 The Background of Electronic Healthcare Systems 27014.7.2 Intelligent Agents in Electronic Healthcare System 27014.7.3 Patient Data Classification Techniques 27114.8 Conclusion 271References 27215 DESIGN OF ANTENNAS FOR MICROWAVE IMAGING TECHNIQUES 275Dnyaneshwar D. Ahire, Gajanan K. Kharate and Ammar Muthana15.1 Introduction 27515.1.1 Overview 27615.2 Literature 27715.2.1 Microstrip Patch Antenna 27815.2.2 Early Detection of Breast Cancer and Microstrip Patch Antenna for Biomedical Application 27915.2.3 UWB for Microwave Imaging 27915.3 Design and Development of Wideband Antenna 28015.3.1 Overview 28015.3.2 Design of Rectangular Microstrip Patch Antenna 28115.3.3 Design of Microstrip Line Feed Rectangular Microstrip Patch Antenna 28315.3.4 Design of Microstrip Line Feed Rectangular Microstrip Patch Antenna With Partial Ground 28515.3.5 Key Shape Monopole Rectangular Microstrip Patch Antenna With Rounded Corner in Partial Ground 28615.4 Results and Inferences 29015.4.1 Overview 29015.4.2 Rectangular Microstrip Patch Antenna 29015.4.2.1 Reflection and VSWR Bandwidth 29015.4.2.2 Surface Current Distribution 29115.4.3 Microstrip Line Feed Rectangular Microstrip Patch Antenna With Partial Ground 29215.4.3.1 Reflection and VSWR Bandwidth 29215.4.3.2 Surface Current Distribution 29215.4.3.3 Inference 29315.4.4 Key Shape Monopole Rectangular Microstrip Patch Antenna with Rounded Corner in Partial Ground 29415.4.4.1 Reflection and VSWR Bandwidth 29415.4.4.2 Surface Current Distribution 29415.4.4.3 Results of the Fabricated Antenna 29515.4.4.4 Inference 29615.5 Conclusion 297References 29816 COVID-19: A GLOBAL CRISIS 303Savita Mandan and Durgeshwari Kalal16.1 Introduction 30316.1.1 Structure 30416.1.2 Classification of Corona Virus 30416.1.3 Types of Human Coronavirus 30416.1.4 Genome Organization of Corona Virus 30516.1.5 Coronavirus Replication 30516.1.6 Host Defenses 30616.2 Clinical Manifestation and Pathogenesis 30616.2.1 Symptoms 30716.2.2 Epidemiology 30716.3 Diagnosis and Control 30816.3.1 Molecular Test 30816.3.2 Serology 30816.3.3 Concerning Lab Assessments 30916.3.4 Significantly Improved D-Dimer 30916.3.5 Imaging 30916.3.6 HRCT 30916.3.7 Lung Ultrasound 31016.4 Control Measures 31016.4.1 Prevention and Patient Education 31116.5 Immunization 31216.5.1 Medications 31216.6 Conclusion 313References 31317 SMART HEALTHCARE FOR PREGNANT WOMEN IN RURAL AREAS 317D. Shanthi17.1 Introduction 31717.2 National/International Surveys Reviews 31917.2.1 National Family Health Survey Review-11 31917.2.2 National Family Health Survey Review-2.2 31917.2.3 National Family Health Survey Reviews-3 32017.3 Architecture 32017.4 Anganwadi’s Collaborative Work 32117.5 Schemes Offered by Central/State Governments 32117.5.1 AAH (Anna Amrutha Hastham) 32117.5.2 Programme Arogya Laxmi 32317.5.3 Balamrutham-Kids’ Weaning Food from 7 Months to 3 Years 32317.5.4 Nutri TASC (Tracking of Group Responsibility for Services) 32317.5.5 Akshyapatra Foundation (ISKCON) 32417.5.6 Mahila Sishu Chaitanyam 32417.5.7 Community Management of Acute Malnutrition 32517.5.8 Child Health Nutrition Committee 32517.5.9 Bharat Ratna APJ Abdul Kalam Amrut Yojna 32517.6 Smart Healthcare System 32617.7 Data Collection 32817.8 Hardware and Software Features of HCS 32817.9 Implementation 32917.9.1 Modules 32917.9.2 Modules Description 32917.9.2.1 Data Preprocessing 32917.9.2.2 Component Features Extraction 32917.9.2.3 User Sentimental Measurement 33017.9.2.4 Sentiment Evaluation 33017.10 Results and Analysis 33117.11 Conclusion 333References 33318 COMPUTER-AIDED INTERPRETATION OF ECG SIGNAL—A CHALLENGE 335Shalini Sahay and A.K. Wadhwani18.1 Introduction 33618.1.1 Electrical Activity of the Heart 33618.2 The Cardiovascular System 33818.3 Electrocardiogram Leads 34018.4 Artifacts/Noises Affecting the ECG 34218.4.1 Baseline Wander 34318.4.2 Power Line Interference 34318.4.3 Motion Artifacts 34418.4.4 Muscle Noise 34418.4.5 Instrumentation Noise 34418.4.6 Other Interferences 34518.5 The ECG Waveform 34618.5.1 Normal Sinus Rhythm 34718.6 Cardiac Arrhythmias 34718.6.1 Sinus Bradycardia 34718.6.2 Sinus Tachycardia 34818.6.3 Atrial Flutter 34818.6.4 Atrial Fibrillation 34918.6.5 Ventric ular Tachycardia 34918.6.6 AV Block 2 First Degree 35018.6.7 Asystole 35018.7 Electrocardiogram Databases 35118.8 Computer-Aided Interpretation (CAD) 35118.9 Computational Techniques 35418.10 Conclusion 356References 357Index 359
Up and Running with DAX for Power BI
Take a concise approach to learning how DAX, the function language of Power BI and PowerPivot, works. This book focuses on explaining the core concepts of DAX so that ordinary folks can gain the skills required to tackle complex data analysis problems. But make no mistake, this is in no way an introductory book on DAX. A number of the topics you will learn, such as the concepts of context transition and table expansion, are considered advanced and challenging areas of DAX.While there are numerous resources on DAX, most are written with developers in mind, making learning DAX appear an overwhelming challenge, especially for those who are coming from an Excel background or with limited coding experience. The reality is, to hit the ground running with DAX, it’s not necessary to wade through copious pages on rarified DAX functions and the technical aspects of the language. There are just a few mandatory concepts that must be fully understood before DAX can be mastered. Knowledge of everything else in DAX is built on top of these mandatory aspects.Author Alison Box has been teaching and working with DAX for over eight years, starting with DAX for PowerPivot, the Excel add-in, before moving into the Power BI platform. The guide you hold in your hands is an outcome of these years of experience explaining difficult concepts in a way that people can understand. Over the years she has refined her approach, distilling down the truth of DAX which is “you can take people through as many functions as you like, but it’s to no avail if they don’t truly understand how it all works.”You will learn to use DAX to gain powerful insights into your data by generating complex and challenging business intelligence calculations including, but not limited to:* Calculations to control the filtering of information to gain better insight into the data that matters to you* Calculations across dates such as comparing data for the same period last year or the previous period* Finding rolling averages and rolling totals* Comparing data against targets and KPIs or against average and maximum values* Using basket analysis, such as “of customers who bought product X who also bought product Y”* Using “what if” analysis and scenarios* Finding “like for like” sales* Dynamically showing TopN/BottomN percent of customers or products by sales* Finding new and returning customers or sales regions in each month or each yearWHO THIS BOOK IS FORExcel users and non-technical users of varying levels of ability or anyone who wants to learn DAX for Power BI but lacks the confidence to do soALISON BOX is Director of Burningsuit Ltd, and an IT trainer and consultant with over 30 years of experience delivering computer applications training to all skill levels, from basic users to advanced technical experts. Currently, she specializes in delivering training in Microsoft Power BI Service and Desktop, Data Modeling, DAX (Data Analysis Expressions), and Excel. Alison also works with organizations as a DAX and Data Analysis consultant. She was one of the first Excel trainers to move into delivering courses in Power Pivot and DAX, from where Power BI was born. Part of her job entails promoting Burningsuit as a knowledge base for Power BI and includes writing regular blog posts on all aspects of Power BI that are published on her website.Chapter 1: Show Me the DataChapter 2: DAX Objects, Syntax & FormattingChapter 3: Calculated Columns & MeasuresChapter 4: Evaluation ContextChapter 5: IteratorsChapter 6: The CALCULATE FunctionChapter 7: DAX Table FunctionsChapter 8: The ALL Function and All its VariationsChapter 9: Calculations on Dates: Using DAX Time IntelligenceChapter 10: Empty Values Versus ZeroChapter 11: Using Variables: Making Our Code More ReadableChapter 12: Returning Values in the Current FilterChapter 13: Controlling the Direction of Filter PropagationChapter 14: Working with Multiple Relationships Between TablesChapter 15: Understanding Context TransitionChapter 16: Leveraging Context TransitionChapter 17: Virtual Relationships: the LOOKUPVALUE and TREATAS FunctionsChapter 18: Table ExpansionChapter 19: The CALCULATETABLE Function
Electronic Governance
Noch nie sind die technologischen Entwicklungen und die Veränderungen der Märkte so rasant verlaufen wie heutzutage. Die Digitalisierung von Wirtschaft und Gesellschaft stehen dabei erst am Anfang. Viele Menschen beobachten die Entwicklungen misstrauisch. Sie können mit den in Verbindung stehenden Methoden und Begriffen kaum etwas anfangen. Dieses Buch schafft Abhilfe, in dem es umfassend und verständlich aufklärt und erklärt. Beispiele aus Theorie und Praxis veranschaulichen die Inhalte. Die Beherrschung der zugehörigen Komplexitäten ist noch nicht gelungen, wie z.B. die lange Liste gescheiterter Digitalisierungsvorhaben anschaulich belegt. Es geht darum, die Unternehmen zukunftsfest zu machen und die Beschäftigten zu befähigen. Hierfür braucht es einer Art digitaler bzw. technisierter „Leitplanken“, die mit einer „Electronic Governance“ entwickelt und spezifiziert werden. Es handelt sich um ein Steuerungs- und Regelungssystem, welches Organisationen und ihre Beschäftigten in Zeiten der Digitalisierung erfolgreich in die Zukunft führt. PROF. DR. ANDREAS SCHMID lehrt und forscht an der Hochschule Hannover. Er hat zahlreiche (IT-) Projekte und Organisationen evaluiert. Electronic Governance.- Digitalisierung.-Scheitern von Digitalisierungsprojekten.- Disruption.-(Digitale) Strategie.- (Digitales) Geschäftsmodell.-Industrie 4.0.- Robotic Process Automation.- Agilität.-Elektronische Akte.- Design Thinking.-Customer Journey.-Blockchain.-Kryptowährungen.- Künstliche Intelligenz.- Big Data inklusive Praxisbeispiel.
Echtzeit 2021
Mit seiner Tagung 2021 zum Thema „Echtzeitkommunikation“ greift der GI/GMA/ITG-Fachausschuss Echtzeitsysteme ein immer wichtiger werdendes Thema in einer mehr und mehr vernetzten Welt auf. Die präsentierten Lösungen reichen dabei von Hardware über Systementwurf bis hin zu einzelnen Applikationen.Das Buch stellt die auf der Tagung Echtzeit präsentierten Ergebnisse der Forscher auf dem diesjährigen Themengebiet der Echtzeitkommunikation dar. Diese Tagung des Fachausschusses Echtzeitsysteme der Gesellschaft für Informatik ist einzigartig im deutschem Sprachraum und fand 2021 zum 42. Mal statt.HERWIG UNGER und MARCEL SCHAIBLE sind Sprecher bzw. stellv. Sprecher des GI/GMA/ITG-Fachausschuss Echtzeitsysteme, der sich dem immer wichtiger werdenden Thema zeitkritischer Systeme von Hardware bis hin zu einzelnen Applikationen widmet.Real-Time Systems Through the Ages - Dynamische Migrationsentscheidungen in Multicore-Systemen - Ausführungszeit und Stromverbrauch von Inferenzen künstlicher neuronaler Netze auf einem Tensorprozessor - Dynamic Vision-Sensoren zur Texturklassifikation in der automatischen Sichtprüfung - Sind Bitcoin-Transaktionen sicher, echtzeitfähig und ressourcenadäquat? - Analysemethodiken zur Berechnung der WCET mit asynchroner Ein-/Ausgabeverarbeitung - Ein auf Bluetooth 5.1 und Ultrabreitband basierendes Innenraum- Positionssystem - Hardware-Beschleuniger für automobile Multicore-Mikrocontroller mit einer harten Echtzeitanforderung - Fault Tolerance in Heterogeneous Automotive Real-time Systems - Echtzeitfähige Ethernet-Kommunikation in automobilen Multicore-Systemen mit hierarchischem Speicherlayout - Zeitgesteuerte Kommunikationsschnittstellen in unterschiedlichen Anwendungskontexten - Ein Konferenzsystem mit biometrisch basierter Gesichtsvisualisierung für sehr große Teilnehmerzahlen - Machine Learning für die Temperaturermittlung eines Permanentmagnet-Synchronmotors.- Zeitoptimierungsuntersuchungen für Algorithmen des maschinellen Lernens