2.9 Flow of the TT contract.Figure 2.10 Flow of the UOT contract.Figure 2.11 System overview.Figure 2.12 Working flowchart of the solution.Figure 2.13 Upon executing gradlew.bat deployNodes.Figure 2.14 Upon executing build\nodes\runnodes.bat.Figure 2.15 The ‘Client’ node.Figure 2.16 The ‘MainContractor’ node.Figure 2.17 The ‘SubContractor’ node.Figure 2.18 The ‘Notary’ node.Figure 2.19 The ‘Client’ node.Figure 2.20 The ‘MainContractor’ node.Figure 2.21 The ‘SubContractor’ node.Figure 2.22 The output on the MainContractor’s node.Figure 2.23 The output on all the nodes.2 Chapter 3Figure 3.1 Actors of an IoT system.Figure 3.2 IoT Cloud system architecture.Figure 3.3 Blockchain empowered IoT Cloud.Figure 3.4 Proposed model of blockchain-based IoT Cloud for IAM.
3 Chapter 4Figure 4.1 Examples from GTSRB.Figure 4.2 Accuracy graph of FFNN.Figure 4.3 Loss graph of FFNN.Figure 4.4 Normalized confusion matrix of FFNN.Figure 4.5 Accuracy curve of RNN.Figure 4.6 Loss graphs of RNN.Figure 4.7 Normalized confusion matrix of RNN.Figure 4.8 Accuracy graph of CNN.Figure 4.9 Loss graph of CNN.Figure 4.10 Normalized confusion matrix of CNN.Figure 4.11 Accuracy graph of improved CNN.Figure 4.12 Loss graph of improved CNN.Figure 4.13 Confusion matrix of improved CNN.
4 Chapter 5Figure 5.1 Honeypot network.Figure 5.2 Honeypot architecture.
5 Chapter 6Figure 6.1 Basic model of IoT frames.Figure 6.2 IoT application.Figure 6.3 Attack difficulties in IoT environment.Figure 6.4 (a), (b), (c) Security works on IIoT.Figure 6.5 Applications of IIoT.Figure 6.6 IoT security areas.Figure 6.7 Advantages of several techniques.Figure 6.8 No. of research work in year wise.
6 Chapter 7Figure 7.1 Classification for robot navigation planning.Figure 7.2 Taxonomy of approaches.Figure 7.3 Illustration of navigation path of a robot with waypoints.Figure 7.4 Illustration for navigation planning of robot for path smoothness.Figure 7.5 The structure of Pioneer P3dx mobile robot in different views.Figure 7.6 Model of the environment with two robots and eight static obstacles.Figure 7.7 MRN employing Jaya-DE.Figure 7.8 MRN employing basic Jaya.Figure 7.9 MRN employing DE.Figure 7.10 AUGD versus number of iteration employing Jaya-DE, basic Jaya algori...Figure 7.11 Model of the environment with eight robots and 11 static obstacles.Figure 7.12 MRN employing Jaya-DE with eight robots and 11 obstacles.Figure 7.13 MRN planning employing IGWO [26].Figure 7.14 AUGD versus number of iteration employing Jaya-DE and IGWO [26].Figure 7.15 Relative performance of Jaya-DE and IGWO [26] in terms of ANPT and A...
7 Chapter 8Figure 8.1 Comparison between two techniques: (a) traditional machine learning, ...Figure 8.2 Architecture of CNN.Figure 8.3 Logistic regression confusion matrix.Figure 8.4 KNN confusion matrix.Figure 8.5 SVM confusion matrix.Figure 8.6 SVM kernel method confusion matrix.Figure 8.7 Naïve bayes confusion matrix.Figure 8.8 Decision tree confusion matrix.Figure 8.9 Random forest confusion matrix.Figure 8.10 ANN confusion matrix.Figure 8.11 Performance evaluation.
8 Chapter 9Figure 9.1 System model.Figure 9.2 Superframe structure.Figure 9.3 DSME multi-superframe structure.Figure 9.4 DSME CAP-reduction.Figure 9.5 Illustrative example of TSCH slotframes.Figure 9.6 Simulation topology.Figure 9.7 Throughput comparison.Figure 9.8 Latency comparison.Figure 9.9 Energy consumption comparison.Figure 9.10 Channel utilization comparison.
9 Chapter 10Figure 10.1 Flow chart of methodology applied.Figure 10.2 Basic information about the DataFrame.Figure 10.3 Conversion data type of the columns.Figure 10.4 Converted data type into int64 format from object format.Figure 10.5 Pair plot of all columns in our dataset with respective to label col...Figure 10.6 Correlation values of every pair of columns.Figure 10.7 Splitting our dataset.Figure 10.8 Data before converting the data type.Figure 10.9 Data after changing the data type.Figure 10.10 Building Gaussian model.Figure 10.11 Result of Gaussian Naïve Bayes model.Figure 10.12 Basic structure of a tree.Figure 10.13 Decision tree model.Figure 10.14 Tuning of hyper-parameter for decision tree model.Figure 10.15 Plotting accuracy values of decision tree model at different depth ...Figure 10.16 Brief idea of working of KNN.Figure 10.17 Building the KNN model.Figure 10.18 Obtaining KNN algorithm accuracies changing the n_neighbor values.Figure 10.19 Accuracies of KNN model by changing the n_neighbor values.Figure 10.20 Neural network set up.Figure 10.21 Accuracy test by changing the number of layers.Figure 10.22 Accuracy vs layers plot for neural network classifier.Figure 10.23 Producing a confusion matrix.Figure 10.24 Confusion matrix representation for Gaussian Naïve Bayes model.Figure 10.25 Confusion matrix representation for tuned decision tree model.Figure 10.26 Confusion matrix representation for KNN model.Figure 10.27 Confusion matrix representation for neural networks.
10 Chapter 11Figure 11.1 An overview of the relationship between artificial intelligence (AI)...Figure 11.2 Big data analytics and visualization. Source: [8].Figure 11.3 App Store Preview. Source: [14].Figure 11.4 An image of deep fake and impersonating examples of Barak Obama. Sou...Figure 11.5 AI bring Mona Lisa’s looks from different angle. Source: [17].Figure 11.6 Social media bot uses. Source: [20].Figure 11.7 Social Media Bots Signature Behaviors. Source: [20].Figure 11.8 Visualization of the spread through social media of an article false...
11 Chapter 12Figure 12.1 SDN infrastructure and abstraction.Figure 12.2 Software defined network architecture.Figure 12.3 SR based on software defined network.Figure 12.4 Delay for the communication using six different path.Figure 12.5 Path loss rate for the communication using six different path.Figure 12.6 Energy consumption corresponding to the packet error rate during the...Figure 12.7 Load balancing with different network size.Figure 12.8 Maximum utilization with different network size.Figure 12.9 Average throughput in bps with different network size.Figure 12.10 Average hop-count in bps with different network size.Figure 12.11 Average link utilization (%) with different network size.
12 Chapter 13Figure 13.1 Timeline of COVID-19 pandemic in India.Figure 13.2 Primary symptoms of COVID-19.Figure 13.3 Precautionary measures for spreading of COVID-19.Figure 13.4 Different ways of spreading the coronavirus.Figure 13.5 COVID 19 timeline for top five countries in the world.Figure 13.6 Number of active COVID 19 cases in top 10 cities in India.Figure 13.7 State wise number of active, recovered and death cases in India.Figure 13.8 Number of recovered cases in India.Figure 13.9 Number of death cases in India.
13 Chapter 14Figure 14.1 Graphical model of model 1.Figure 14.2 Graphical model of model 2.Figure 14.3 Graphical model of ResNet50.Figure 14.4 Graph showing change of accuracy with respect to various parameters.Figure 14.5 Bar graph showing accuracy of different models.Figure 14.6 ROC curve for model 1.Figure 14.7 ROC curve for model 2.Figure 14.8 ROC curve for model 3 (ResNet50).Figure 14.9 MSE curve showing mean square error during training of model 1.Figure 14.10 MSE curve showing mean square error during training of model 2.Figure 14.11 MSE curve showing mean square error during training of model 3 (Res...
14 Chapter 15Figure 15.1 Path generation
