[Place of publication not identified] : River Publishers, 2023
Table of Contents:
“…Preface xvii Acknowledgement xxi List of Figures xxiii List of Tables xxvii List of Contributors xxix List of Abbreviations xxxiii 1 Artificial Intelligence in the Digital Chemical Industry, Its Application and Sustainability 1 1.1 Introduction 2 1.2 AI in the Chemical Industry and Applications 3 1.2.1 AI in chemical science 5 1.2.2 AI in research and development 6 1.2.3 AI in catalyst design spaces 7 1.3 Sustainability of AI Applications 9 1.3.1 Environmental aspect 9 1.3.2 Energy aspect 10 1.3.3 Economic aspect 11 1.3.4 Time aspect 12 1.3.5 Safety and human factor aspect 12 1.4 Digital Transformation of the Chemical Industry 13 1.4.1 State of digital transformation 14 1.4.2 Key trends in digitalization 14 1.4.3 Optimizing production 14 1.4.4 Supporting remote operations 15 1.4.5 Reducing waste 15 1.4.6 Unlocking new growth opportunities 16 1.4.7 Increasing supply chain visibility 16 1.4.8 Safety, compliance, and sustainability 16 1.5 Digital Chemical Industry
4.0 17 1.6 Challenges of AI in the Chemical Industry 19 1.7 Industry
4.0 Impact Technologies 20 1.8 Conclusion 22 2 Managing Transition Toward Industry
4.0: A Study on the Implementation of Digital Manufacturing Processes 31 2.1 Introduction 32 2.2 Main Text 34 2.2.1 Problem formulation 34 2.2.2 Purpose and question 34 2.2.3 Related research 34 2.2.4 Industry
4.0 34 2.2.5 Strategic guidance for IIoT 36 2.2.6 Strategy 36 2.2.7 Resources and competencies 37 2.2.8 IT maturity 38 2.2.9 Smart manufacturing
40 2.2.10 Method 41 2.2.11 Delimitation 41 2.2.12 Method selection 42 2.2.13 Data collection 43 2.2.14 Literature review 43 2.2.15 Interview 44 2.2.16 Selection and respondents 46 2.2.17 Ethics 46 2.2.18 Data analysis 47 2.2.19 Transcription 47 2.2.20 Coding 47 2.2.21 Method discussion 48 2.3 Outcomes of the Study 50 2.3.1 Industry
4.0 50 2.3.2 Strategy 51 2.3.3 Resources and competencies 53 2.3.4 IT maturity 54 2.3.5 Smart manufacturing 55 2.4 Conclusion 55 3 Container as a Service in Cloud: An Approach to Secure Hybrid Virtualization 59 3.1 Introduction 60 3.2 Virtualization in Cloud Computing 62 3.2.1 System level virtualization 63 3.2.2 OS level virtualization 64 3.2.3 Container vs. virtual machine 64 3.2.4 Architectural difference between VM and container 66 3.3 Container as a Service Model 68 3.3.1 CaaS architecture 68 3.4 Containerization Techniques 69 3.4.1 Docker 70 3.4.2 Singularity 70 3.4.3 uDocker 70 3.5 Research Challenges 71 3.6 Conclusion 73 4 Automated Framework for Detecting Unknown Activity in a Vehicular ad hoc Network 77 4.1 Introduction 78 4.1.1 VANET deployment challenges 79 4.1.2 VANET applications 81 4.1.3 Possible attacks on vehicular network 83 4.1.4 ML for vehicular networking 85 4.1.5 Current challenges and opportunities 85 4.1.5.1 Tests for vehicular networks 85 4.1.6 Research gap 86 4.1.7 Problem statement 87 4.1.8 Motivation 88 4.2 Literature Work 88 4.2.1 An overview 89 4.2.2 Mobility-based routing in VANET with security 89 4.2.3 Encryption and authentication 91 4.3 Proposed Approach 92 4.3.1 Methodology 94 4.3.2 Improve hybrid cooperative malicious node detection approach (IHCMNDA) 95 4.4 Result and Discussion 97 4.4.1 Simulation 97 4.4.2 Improved cooperative bait detection (ICBDS) 103 4.4.3 Improve hybrid cooperative malicious node detection approach (IHCMNDA) 108 4.5 Conclusion and Future Work 110 5 Control of Mobile Manipulator with Object Detection for EOD Applications 117 5.1 Introduction 118 5.1.1 Explosive ordnance disposal robots 119 5.2 Object Detection 121 5.2.1 Computer-aided design of the proposed design 122 5.2.2 System architecture 122 5.3 Hardware Architecture 122 5.3.1 Robot-arm contol and actuation 124 5.4 Object Detection 124 5.4.1 TensorFlow 124 5.4.2 TensorFlow object detection API 125 5.4.2.1 Object detection API using tensorFlow 2.0 125 5.5 Results and Discussion 127 5.5.1 Hardware implementation 127 5.5.2 Robotic arm simulation using MATLAB GUI 129 5.5.3 Simulation in gazebo using ROS 129 5.6 Conclusion 131 6 Smart Agriculture: Emerging and Future Farming Technologies 135 6.1 Introduction 136 6.2 Role of Smart Agriculture in Yield Enhancement 139 6.2.1 Soil samples and its mapping 140 6.2.2 Smart irrigation systems 142 6.2.3 Smart fertilizer system 143 6.2.4 Smart disease control and pest management 144 6.2.5 Smart monitoring of crop yields and climatic conditions 145 6.3 Technologies Involved in Precision Agriculture 146 6.3.1 Wireless sensing technology in agriculture 147 6.3.1.1 Soil monitoring sensors 149 6.3.1.2 Yield monitoring sensors 149 6.3.1.3 Weeds, pest, and disease monitoring sensors 150 6.3.1.4 Field monitoring sensors 151 6.3.2 Communication methods and latest technologies in smart agriculture 154 6.3.2.1 Mobile communication systems 154 6.3.2.2 ZigBee wireless technology 155 6.3.2.3 Bluetooth wireless technology 155 6.3.2.4 LoRa and sigFox technology 155 6.3.2.5 Smartphones-based communication 156 6.3.2.6 Cloud computing 156 6.3.2.7 Fog/edge computing 157 6.3.3 Latest technologies for large data processing 157 6.3.3.1 Big data 157 6.3.3.2 Artificial intelligence 160 6.3.3.3 Deep learning 160 6.4 Autonomous Vehicles in Smart Agriculture 163 6.4.1 IoT-based tractors 163 6.4.2 Harvesting robots 164 6.4.3 UAVs in agriculture 165 6.5 Challenges in Smart Agriculture 167 6.6 Conclusions and Future Directions 168 7 Plant Feature Extraction for Disease Classification 183 7.1 Introduction 184 7.2 Literature Review 186 7.3 Features Representation and Characteristics 187 7.4 Texture Features 187 7.4.1 Statistical methods for texture classification 188 7.4.1.1 Advantages and limitations 189 7.4.2 Gray-level run-length matrix 189 7.4.3 Advantages and limitations 190 7.4.4 Histogram of gradient magnitudes 190 7.4.4.1 Advantages and limitations 190 7.5 Color Features Extraction 191 7.5.1 Advantage and disadvantages 191 7.5.2 Color co-occurrence matrix (CCM) 192 7.5.2.1 Advantage and disadvantages 193 7.6 Shape-based Feature Extraction 194 7.6.1 Advantage and disadvantages 196 7.7 Conclusion and Future Scope 197 8 Development Methodologies for Internet of Things: For all Commercial and Industrial Needs 203 8.1 Introduction 204 8.2 Research Questions 204 8.3 Development Methodologies 205 8.3.1 Development methodologies for IoT-based smart cities 205 8.3.1.1 Spatial (Geographical) IoT 206 8.3.1.2 Smart campus surveillance 207 8.3.2 Development methodologies for IoT-based automatic driving 211 8.3.3 Development methodologies for IoT-based agriculture field monitoring 213 8.3.4 Development methodologies for IoT-based railway monitoring 215 8.3.5 Development methodologies for IoT-based forest monitoring 217 8.4 Conclusion 219 9 Bio-inspired Multilevel ICHB-HEED Clustering Protocol for Heterogeneous WSNs 225 9.1 Introduction 226 9.2 Review of Literature 227 9.3 Proposed Work 229 9.3.1 Network model for multilevel energy heterogeneity 229 9.3.2 MLICHBHEED protocol 231 9.3.2.1 Clustering and CH election process 232 9.3.2.2 ICHB algorithm 232 9.3.2.3 Process of data transmission and collection 233 9.3.2.4 Energy depletion model for MLICHBHEED protocol 233 9.4 Results and Discussions 234 9.4.1 Network lifetime 236 9.4.2 Total energy consumption 238 9.4.3 Number of packets sent to the base station 242 9.5 Conclusion 242 10 IoT Enabled by Edge Computing for Telecomm and Industry 247 10.1 Introduction to IoT and Edge Computing 248 10.1.1 IoT and edge-computing scenarios 250 10.1.2 IoT versus edge computing 253 10.1.3 Industry
4.0 254 10.1.4 Cloud computing and edge computing 256 10.1.5 Cloud computing and edge computing: use cases 257 10.2 IoT and Edge Computing Framework 261 10.2.1 IoT and edge computing integrated framework 263 10.2.2 Pros and cons 264 10.2.3 Opportunities and challenges 264 10.3 Edge Computing Devices 265 10.4 Telcos and Edge Computing 266 10.4.1 Telco network modernizations challenges 268 10.4.2 Multi-access edge computing 268 10.4.2.1 Advantages of MEC 270 10.5 Task Scheduling in Edge Computing 271 10.5.1 Scheduler-based edge computing 271 10.5.2 Computing task analysis 272 10.5.2.1 Local execution 272 10.5.2.2 Full offloading 273 10.5.2.3 Partial offloading 273 10.5.3 Computing task scheduling scheme 273 10.5.3.1 Task scheduling algorithm 274 10.5.3.2 Bidding-model optimization and adaptive algorithm 275 10.6 Security and Privacy Issues of Edge Computing 276 10.6.1 Attacks classification 277 10.7 Conclusion 279 11 Low-energy Network Protocols 283 11.1 Introduction 284 11.2 IIoT 286 11.2.1 Network architecture 286 11.2.2 Protocols 287 11.2.3 Testbed 288 11.2.4 Criteria for implementation 289 11.3 Low-energy Technologies 290 11.4 Self-powered Network 292 11.4.1 Comparison between energy harvesting WSNs and battery-operated WSNs 292 11.4.2 Energy-harvesting sources for sensors 293 11.4.3 Energy stored by a supercapacitor 294 11.4.4 Proposed circuit 295 11.4.5 BLE-RSL10 from ON Semiconductor 295 11.4.6 Key features of BLE-RSL10 295 11.4.7 Lifetime improvement of WSN 298 11.4.8 Energy model for WSN 299 11.4.9 Lifetime optimization in a mobile WSN with solar energy harvesting 300 11.4.10 Time-slotted approach 300 11.4.11 Optimization algorithm 300 11.5 Simulation of WSN Network and Results 301 11.5.1 Simulation parameters 301 11.5.2 Simulation results 302 11.6 Future Scope 305 11.7 Conclusion 305 12 Consensus Algorithms in Blockchain for Efficient and Secure Network 309 12.1 Introduction 310 12.1.1 Motivation 311 12.2 Literature Review 311 12.3 Emergence of Cryptocurrencies 315 12.4 Role of Consensus Algorithms 317 12.4.1 Proof of work 318 12.4.2 Proof of stake 320 12.4.3 Delegated proof of stake (DPoS) 322 12.4.4 Byzantine fault tolerance (BFT) 322 12.4.5 Proof of burn (PoB) 322 12.4.6 Proof of capacity (PoC) 323 12.4.7 Proof of elapsed time (PoET) 323 12.5 Limitation of Consensus Algorithms 324 12.5 ...…”
Call Number:
Loading…
Located:
Loading…
Format:
Electronic
eBook
Full text (WIT users only)