Читать книгу Simulation and Analysis of Mathematical Methods in Real-Time Engineering Applications - Группа авторов - Страница 4

1 Chapter 1Figure 1.1 Gartner hyper cycle.Figure 1.2 Two state Markov model.Figure 1.3 Distribution of data points and first obtained representative.Figure 1.4 SVM.Figure 1.5 Hyperplane in SVM.Figure 1.6 Exposed, infection and recovery transmission in SEIR model. (a) Any s...Figure 1.7 SIR model.

2 Chapter 2Figure 2.1 Edge network.Figure 2.2 Edge computing motivation, challenges and opportunities.Figure 2.3 Offloading in IoT nodes.Figure 2.4 Offloading schemes advantages.Figure 2.5 Computation offloading flow.Figure 2.6 Offloading techniques.Figure 2.7 Markov chain-based stochastic process.Figure 2.8 Offloading in vehicular node.

3 Chapter 3Figure 3.1 Integrating IoT and cloud.Figure 3.2 Star cubing algorithm.Figure 3.3 Dividing and recreating shares.Figure 3.4 Encryption and decryption.Figure 3.5 Encryption and decryption process.Figure 3.6 Step 1 - Generation of data using Arduino UNO board.Figure 3.7 Step 2 - Generated data displayed.Figure 3.8 Step 3 - Converting data into .csv file.Figure 3.9 Step 4 - Output of Star cubing algorithm.Figure 3.10 Step 5 - Partitioned secret shares.Figure 3.11 Step 6 - The encrypted partitioned secret shares.Figure 3.12 Step 7 - The encrypted shares stored in cloud.Figure 3.13 Step 8 - The decrypted file shares.Figure 3.14 Step 9 - The recovered original main file.

4 Chapter 4Figure 4.1 Edge computing.Figure 4.2 Pioneering edge security and privacy preservation.Figure 4.3 2-way trust management scheme.Figure 4.4 Encryption mechanisms in edge computing.Figure 4.5 Dynamic key exchange mechanism.Figure 4.6 Identity and key management security design pattern.Figure 4.7 IoT combined with edge gateways.Figure 4.8 Edge blockchain.Figure 4.9 Privacy preservation model.Figure 4.10 Beyond 5G capabilities.Figure 4.11 Anomaly based IDS.

5 Chapter 5Figure 5.1 Damage detection methods [12].Figure 5.2 (a) and (b) shows the relationship between AI, ML and DL [10].Figure 5.3 Taxonomy of ML [12].Figure 5.4 Variety of ML techniques in SHM [12].Figure 5.5 Model of shear building [13].Figure 5.6 The discrepancy matrix [13].Figure 5.7 Test structure [14].Figure 5.8 ANN performance of the beam model [15].Figure 5.9 Arrangement of sensors in beam model [16].Figure 5.10 Methodology of Machine Learning [17].Figure 5.11 CFRP sandwich structure and PZT distribution [17].Figure 5.12 Result of four test [18].Figure 5.13 Sydney Harbour bridge [19].Figure 5.14 Sensor arrangements and joints of Harbour bridge [19].Figure 5.15 Top view of bridge [20].Figure 5.16 Observations [20].Figure 5.17 Event tree [21].Figure 5.18 Proposed method [22].Figure 5.19 Data sets [23].Figure 5.20 Test setup [25].Figure 5.21 Arrangement of sensors in panels [26].Figure 5.22 Similarity between system [27].Figure 5.23 ROC curve [28].Figure 5.24 Damages in flange [28].Figure 5.25 Pictures of mouth brooding fish (a) The way of protection. (b) Left ...Figure 5.26 Variable representation in cichlids [3].Figure 5.27 Inspiration of MBF algorithm [29].Figure 5.28 Application sectors of MBF system [29].Figure 5.29 Fitness curve of IGA system [31].Figure 5.30 Optimal domains [32].Figure 5.31 OSP algorithm for DABC [33].Figure 5.32 Convergence curves [1].Figure 5.33 Reinforced concrete one-way slab [35].Figure 5.34 Convergence curves [35].Figure 5.35 Expression tree [36].Figure 5.36 Comparison based on C1 and C3 parameter.Figure 5.37 Sensor contribution and coverage.

6 Chapter 6Figure 6.1 Technical problem design.Figure 6.2 Velocity curves with several qualities of α.Figure 6.3 Variation of “Gr” on velocity.Figure 6.4 Velocity curves with several qualities of M.Figure 6.5 Velocity curves with several qualities of Ko.Figure 6.6 Impact of “Gm” on velocity.Figure 6.7 Velocity curves with several qualities of Kr.Figure 6.8 Velocity curves with several qualities of Sc.Figure 6.9 Velocity curves with several qualities of S₀.Figure 6.10 Impact of “Q” on temperature.Figure 6.11 Impact of “Pr” on temperature.Figure 6.12 Effect of “Kr” on concentration profile.Figure 6.13 Concentration curves with several qualities of Sc.Figure 6.14 Concentration curves with several qualities of So.

7 Chapter 7Figure 7.1 M₀.Figure 7.2 M₁.

8 Chapter 8Figure 8.1 Basic structure of deep learning.Figure 8.2 Process involved in digital forensics.Figure 8.3 Cybernetics loop.Figure 8.4 Cybernetics relating method oriented and science oriented services [7...Figure 8.5 Data acquisition system in biometric identity.Figure 8.6 Deep learning process involved in fingerprint recognition.Figure 8.7 Deep learning framework for forensic data analysis.Figure 8.8 Digital forensic data reduction.Figure 8.9 Deep auto encoders.Figure 8.10 Restricted Boltzmann Machine.Figure 8.11 Federated learning architecture.Figure 8.12 IoT factors influencing computer forensics.

9 Chapter 9Figure 9.1 Structure of the heart.Figure 9.2 Cardiac image segmentation activities with various imaging types.Figure 9.3 Shows 3 concentric rings, in the inner rings with a focus sapling and...Figure 9.4 Shows three algorithms Weak edge actions (a) Circular scale image wit...Figure 9.5 Memory vs Computation time.

10 Chapter 10Figure 10.1 CNN architecture [16].Figure 10.2 LSTM unit [17].Figure 10.3 CNN-LSTM model used to classify DR.Figure 10.4 Hybrid CNN-LSTM architecture.Figure 10.5 Metrics of CNN-LSTM model.

11 Chapter 11Figure 11.1 Machine learning vs. deep learning.Figure 11.2 Block diagram of auto encoder.Figure 11.3 Architecture of convolution neural network.Figure 11.4 Various applications of deep learning.Figure 11.5 Different big data parameters.Figure 11.6 Machine learning in healthcare.

12 Chapter 12Figure 12.1 Concern physical configuration [1].Figure 12.2 Velocity outline for several Nemours of β. R=0.5, γ = α π/6, Pr=0.71...Figure 12.3 Velocity outline for several Nemours of α. R=0.5, β=5, γ = π/6, Pr=0...Figure 12.4 Velocity outlines for several Nemours of γ. R=0.5, α = π/6, β=5, Sc=...Figure 12.5 Velocity outline for several Nemours of Gr. R=0.5, Pr=0.71, Ko=1, γ=...Figure 12.6 Velocity outline for several Nemours of Gm. R=0.5, M=1, Sc=0.6, Pr=0...Figure 12.7 Velocity outline for several Nemours of M. R=0.5, Sc=0.6, Pr=0.71, K...Figure 12.8 Velocity outline for several Nemours of Ko. R=0.5, M=1, Sc=0.6, Pr=0...Figure 12.9 Temperature outline for several Nemours of Q. R=0.5, M=1, Sc=0.6, Pr...Figure 12.10 Temperature outline for several Nemours of Pr. R=0.5, M=1, Sc=0.6, ...Figure 12.11 Temperature outline for several Nemours of R., Q=0.5, M=1, Sc=0.6, ...Figure 12.12 Concentration outline for several Nemours of Kr.Figure 12.13 Concentration outline for several Nemours of Sc.

13 Chapter 13Figure 13.1 Paddy disease detection framework.Figure 13.2 RGB color image of Gall midge in paddy crop.Figure 13.3 Pre-processing of Gall midge insect.Figure 13.4 Deep CNN model.Figure 13.5 Deep CNN image denoising.Figure 13.6 Gray scale orientation.Figure 13.7 Histogram of inclination.Figure 13.8 Pest spot identification.Figure 13.9 (a) Input image; (b) Filtered image; (c) Boundary detection; (d) Rem...Figure 13.10 Accuracy performance analysis.

14 Chapter 14Figure 14.1 Proposed framework using machine learning on the edge.Figure 14.2 Comparison of number of test cases.Figure 14.3 Comparison of testing time.