13 Chapter 13Figure 13.1 The architecture crack detection system.Figure 13.2 (a) Thermal image. (b) Digital image. (c) Thermal image. (d) Digital...Figure 13.3 CNN layers in learning process.
14 Chapter 14Figure 14.1 Raw images (Band 2 and Band 5, respectively).Figure 14.2 Band combination 3-4-6 and 3-2-1, respectively.Figure 14.3 Spectral signatures after atmospheric correction.Figure 14.4 Pictorial representation of Euclidean and Manhattan distances.Figure 14.5 Discriminant functions.Figure 14.6 Result of ML classifier.Figure 14.7 Result of k-NN classifier.
15 Chapter 15Figure 15.1 Digital medical images: (a) X-ray of chest, (b) MRI imaging of brain...Figure 15.2 Scheme of image processing [12].Figure 15.3 Anatomy-wise breakdown of papers in each year (2016–2020).Figure 15.4 Year-wise breakdown of papers (2016–2020) based on the task.
16 Chapter 16Figure 16.1 Prototype 1:16 scale car.Figure 16.2 Image processing pipeline.Figure 16.3 Original Image.Figure 16.4 Canny edge output.Figure 16.5 Hough lines overlaid on original image.Figure 16.6 CNN model architecture.Figure 16.7 Experimental track used for training and testing.Figure 16.8 Accuracy vs. training time (hours) plot of Model 1 that uses classif...Figure 16.9 Loss vs. training time (hours) plot of Model 1 that uses classificat...Figure 16.10 MSE vs. steps plot of Model 2 that uses classification method with ...Figure 16.11 MSE vs. steps plot of Model 8 that uses classification method with ...Figure 16.12 Accuracy vs. steps plot of Model 5 that uses classification method ...Figure 16.13 Loss vs. steps plot of Model 5 that uses classification method with...Figure 16.14 Input image given to CNN.Figure 16.15 Feature map at second convolutional layer.Figure 16.16 Feature map at the fifth convolutional layer.
17 Chapter 17Figure 17.1 An architecture of simple obstacle detection and avoidance framework...Figure 17.2 A prototype of a wearable system with image to tactile rendering fro...Figure 17.3 DG5-V hand glove developed for Arabic sign language recognition [40]...
18 Chapter 18Figure 18.1 Land cover classification using CNN.Figure 18.2 Remote sensing image classifier using stacked denoising autoencoder.Figure 18.3 Gaussian-Bernoulli RBM for hyperspectral image classification.Figure 18.4 GAN for pan-sharpening with multispectral and panchromatic images.Figure 18.5 Change detection on multi-temporal images using RNN.
List of Tables
1 Chapter 3Table 3.1 Calculation and derived value from the predicted and actual values.Table 3.2 Predicted probability value from model and actual value.Table 3.3 Predicting class value using the threshold.Table 3.4 Document information and cosine similarity.Table 3.5 Metric derived from confusion metric.Table 3.6 Metric usage.Table 3.7 Metric pros and cons.
2 Chapter 4Table 4.1 Model summary.Table 4.2 Predicted data.
3 Chapter 7Table 7.1 Literature survey of Diabetic Retinopathy.Table 7.2 Retinopathy grades in the Kaggle dataset.Table 7.3 Accuracy for binary classification using machine learning techniques.Table 7.4 Accuracy for multiclass classification using machine learning techniqu...
4 Chapter 8Table 8.1 Description of each feature in the dataset.Table 8.2 Sample dataset.Table 8.3 Experiments description.Table 8.4 Accuracy scores (in %) of all classifiers on different data size.Table 8.5 Accuracy scores (in %) of all classifiers on different data size.Table 8.6 Accuracy scores (in %) of all classifiers on different data size.Table 8.7 Logit model statistical test.Table 8.8 Chi-square test.
5 Chapter 9Table 9.1 Characteristics of the NASA data sets.Table 9.2 Attribute information of the 21 features of PROMISE repository [13].Table 9.3 Performance comparison for the data set KC1.Table 9.4 Performance comparison for the data set KC3.Table 9.5 Performance comparison for the data set PC1.Table 9.6 Performance comparison for the data set PC2.Table 9.7 Confusion matrix analysis for the KC1, KC3, PC1, and PC2 data sets (TP...
6 Chapter 10Table 10.1 Classifiers vs. classification accuracy.Table 10.2 Performance metrics of the recommended classifier.Table 10.3 Confusion matrix.
7 Chapter 11Table 11.1 Dataset description.Table 11.2 Architecture of proposed convolutional neural network.Table 11.3 Classification accuracy (%) with two proposed models on two different...
8 Chapter 12Table 12.1 Description of ULB credit card transaction dataset.Table 12.2 Confusion matrix [7].Table 12.3 Result summary for all the implemented models.Table 12.4 Confusion matrix results for all the implemented models.
9 Chapter 13Table 13.1 Activation functions.Table 13.2 Optimizers.Table 13.3 Performance: optimizer vs. activation functions.
10 Chapter 14Table 14.1 General confusion matrix for two class problems.Table 14.2 Confusion matrix for a ML classifier.Table 14.3 Confusion matrix for a k-NN classifier.Table 14.4 Average precision, recall, F1-score, and accuracy.
11 Chapter 15Table 15.1 Summary of datasets used in the survey.Table 15.2 Summary of papers in brain tumor classification using DL.Table 15.3 Paper summary—cancer detection in lung nodule by DL.Table 15.4 Paper summary—classification of breast cancer by DL.Table 15.5 Paper summary on heart disease prediction using DL.Table 15.6 COVID-19 prediction paper summary.
12 Chapter 16Table 16.1 CNN architecture.Table 16.2 Model definition.Table 16.3 Model results.
13 Chapter 17Table 17.1 Comparison of sensors for obstacle detection in ETA inspired from [16...Table 17.2 A comparison between few wearables.Table 17.3 Sensor based methods from literature.Table 17.4 Vision based approaches.
14 Chapter 18Table 18.1 Hybrid deep architectures for remote sensing.
Pages
1 v
2 ii
3 iii
4 iv
5 xix
6 xx
7 1
8 2
9 3
10 4
11 5
12 6
13 7
14 8
15 9
16 10
17 11
18 12
19 13