Machine learning algorithms and applications / edited by Mettu Srinivas, G. Sucharitha, Anjanna Matta.

Format:

Book

Contributor:

Srinivas, Mettu, editor.

Sucharitha, G., editor.

Matta, Anjanna, editor.

Wiley InterScience (Online service)

Anne and Joseph Trachtman Memorial Book Fund.

Language:

English

Subjects (All):

Machine learning.

Computer algorithms.

Physical Description:

1 online resource (1 volume.)

polychrome

Place of Publication:

Hoboken : Wiley : Scrivener Publishing, 2021.

System Details:

text file

Contents:

Part 1 Machine Learning for Industrial Applications p. 1

1 A Learning-Based Visualization Application for Air Quality Evaluation During COVID-19 Pandemic in Open Data Centric Services p. 3 / Priyank Jain and Gagandeep Kaur

1.1.1 Open Government Data Initiative p. 4

1.1.2 Air Quality p. 4

1.1.3 Impact of Lockdown on Air Quality p. 5

1.2 Literature Survey p. 5

1.3 Implementation Details p. 6

1.3.1 Proposed Methodology p. 7

1.3.2 System Specifications p. 8

1.3.3 Algorithms p. 8

1.3.4 Control Flow p. 10

1.4 Results and Discussions p. 11

2 Automatic Counting and Classification of Silkworm Eggs Using Deep Learning p. 23 / Shreedhar Rangappa and Ajay A. and G. S. Rajanna

2.2 Conventional Silkworm Egg Detection Approaches p. 24

2.3 Proposed Method p. 25

2.3.1 Model Architecture p. 26

2.3.2 Foreground-Background Segmentation p. 28

2.3.3 Egg Location Predictor p. 30

2.3.4 Predicting Egg Class p. 31

2.4 Dataset Generation p. 35

3 A Wind Speed Prediction System Using Deep Neural Networks p. 41 / Jaseena K. U. and Binsu C. Kovoor

3.2.1 Deep Neural Networks p. 45

3.2.2 The Proposed Method p. 47

3.2.2.1 Data Acquisition p. 47

3.2.2.2 Data Pre-Processing p. 48

3.2.2.3 Model Selection and Training p. 50

3.2.2.4 Performance Evaluation p. 51

3.2.2.5 Visualization p. 51

3.3 Results and Discussions p. 52

3.3.1 Selection of Parameters p. 52

3.3.2 Comparison of Models p. 53

4 Res-SE-Net: Boosting Performance of ResNets by Enhancing Bridge Connections p. 61 / Varshaneya V. and S. Balasubramanian and Darshan Gera

4.3.1 ResNet p. 63

4.3.2 Squeeze-and-Excitation Block p. 64

4.4 Proposed Model p. 66

4.4.1 Effect of Bridge Connections in ResNet p. 66

4.4.2 Res-SE-Net: Proposed Architecture p. 67

4.5.1 Datasets p. 68

4.5.2 Experimental Setup p. 68

5 Hitting the Success Notes of Deep Learning p. 77 / Sakshi Aggarwal and Navjot Singh and K.K. Mishra

5.1 Genesis p. 78

5.2 The Big Picture: Artificial Neural Network p. 79

5.3 Delineating the Cornerstones p. 80

5.3.1 Artificial Neural Network vs. Machine Learning p. 80

5.3.2 Machine Learning vs. Deep Learning p. 81

5.3.3 Artificial Neural Network vs. Deep Learning p. 81

5.4 Deep Learning Architectures p. 82

5.4.1 Unsupervised Pre-Trained Networks p. 82

5.4.2 Convolutional Neural Networks p. 83

5.4.3 Recurrent Neural Networks p. 84

5.4.4 Recursive Neural Network p. 85

5.5 Why is CNN Preferred for Computer Vision Applications? p. 85

5.5.1 Convolutional Layer p. 86

5.5.2 Nonlinear Layer p. 86

5.5.3 Pooling Layer p. 87

5.5.4 Fully Connected Layer p. 87

5.6 Unravel Deep Learning in Medical Diagnostic Systems p. 89

5.7 Challenges and Future Expectations p. 94

6 Two-Stage Credit Scoring Model Based on Evolutionary Feature Selection and Ensemble Neural Networks p. 99 / Diwakar Tripathi and Damodar Reddy Edla and Annushree Bablani and Venkatanareshbabu Kuppili

16.2 Literature Survey p. 101

6.3 Proposed Model for Credit Scoring p. 103

6.3.1 Stage-1: Feature Selection p. 104

6.3.2 Proposed Criteria Function p. 105

6.3.3 Stage-2: Ensemble Classifier p. 106

6.4.1 Experimental Datasets and Performance Measures p. 107

6.4.2 Classification Results With Feature Selection p. 108

7 Enhanced Block-Based Feature Agglomeration Clustering for Video Summarization p. 117 / Sreeja M. U. and Binsu C. Kovoor

7.3 Feature Agglomeration Clustering p. 122

7.4 Proposed Methodology p. 122

7.4.1 Pre-Processing p. 123

7.4.2 Modified Block Clustering Using Feature Agglomeration Technique p. 125

7.4.3 Post-Processing and Summary Generation p. 127

7.5 Results and Analysis p. 129

7.5.1 Experimental Setup and Data Sets Used p. 129

7.5.2 Evaluation Metrics p. 130

Part 2 Machine Learning for Healthcare Systems p. 141

8 Cardiac Arrhythmia Detection and Classification From ECG Signals Using XGBoost Classifier p. 143 / Saroj Kumar Pandeyz and Rekh Ram Janghel and Vaibhav Gupta

8.2 Materials and Methods p. 145

8.2.1 MIT-BIH Arrhythmia Database p. 146

8.2.2 Signal Pre-Processing p. 147

8.2.3 Feature Extraction p. 147

8.2.4 Classification p. 148

8.2.4.1 XGBoost Classifier p. 148

8.2.4.2 AdaBoost Classifier p. 149

9 GSA-Based Approach for Gene Selection from Microarray Gene Expression Data p. 159 / Pintu Kumar Ram and Pratyay Kuila

9.3 An Overview of Gravitational Search Algorithm p. 162

9.4 Proposed Model p. 163

9.4.1 Pre-Processing p. 163

9.4.2 Proposed GSA-Based Feature Selection p. 164

9.5 Simulation Results p. 166

9.5.1 Biological Analysis p. 168

Part 3 Machine Learning for Security Systems p. 175

10 On Fusion of NIR and VW Information for Cross-Spectral Iris Matching p. 177 / Ritesh Vyas and Tirupathiraju Kanumuri and Gyanendra Sheoran and Pawan Dubey

10.2 Preliminary Details p. 179

10.2.1 Fusion p. 181

10.3 Experiments and Results p. 182

10.3.1 Databases p. 182

10.3.2.1 Same Spectral Matchings p. 183

10.3.2.2 Cross Spectral Matchings p. 184

10.3.3 Feature-Level Fusion p. 186

10.3.4 Score-Level Fusion p. 189

11 Fake Social Media Profile Detection p. 193 / Umita Deepak Joshi and Vanshika and Ajay Pratap Singh and Tushar Rajesh Pahuja and Smita Naval and Gaurav Singal

11.3.1 Dataset p. 197

11.3.2 Pre-Processing p. 198

11.3.3 Artificial Neural Network p. 199

11.3.4 Random Forest p. 202

11.3.5 Extreme Gradient Boost p. 202

11.3.6 Long Short-Term Memory p. 204

12 Extraction of the Features of Fingerprints Using Conventional Methods and Convolutional Neural Networks p. 211 / E. M. V. Naga Karthik and Madan Gopal

12.3 Methods and Materials p. 215

12.3.1 Feature Extraction Using SURF p. 215

12.3.2 Feature Extraction Using Conventional Methods p. 216

12.3.2.1 Local Orientation Estimation p. 216

12.3.2.2 Singular Region Detection p. 218

12.3.3 Proposed CNN Architecture p. 219

12.3.4 Dataset p. 221

12.3.5 Computational Environment p. 221

12.4.1 Feature Extraction and Visualization p. 223

13 Facial Expression Recognition Using Fusion of Deep Learning and Multiple Features p. 229 / M. Srinivas and Sanjeev Saurav and Akshay Nayak and Murukessan A. P.

13.3 Proposed Method p. 235

13.3.1 Convolutional Neural Network p. 236

13.3.1.1 Convolution Layer p. 236

13.3.1.2 Pooling Layer p. 237

13.3.1.3 ReLU Layer p. 238

13.3.1.4 Fully Connected Layer p. 238

13.3.2 Histogram of Gradient p. 239

13.3.3 Facial Landmark Detection p. 240

13.3.4 Support Vector Machine p. 241

13.3.5 Model Merging and Learning p. 242

13.4.1 Datasets p. 242

Part 4 Machine Learning for Classification and Information Retrieval Systems p. 247

14 AnimNet: An Animal Classification Network using Deep Learning p. 249 / Kanak Manjari and Kriti Singhal and Madhushi Verma and Gaurav Singal

14.1.1 Feature Extraction p. 250

14.1.2 Artificial Neural Network p. 250

14.1.3 Transfer Learning p. 251

14.3 Proposed Methodology p. 254

14.3.1 Dataset Preparation p. 254

14.3.2 Training the Model p. 254

14.4.1 Using Pre-Trained Networks p. 259

14.4.2 Using AnimNet p. 259

14.4.3 Test Analysis p. 260

15 A Hybrid Approach for Feature Extraction From Reviews to Perform Sentiment Analysis p. 267 / Alok Kumar and Renu Jain

15.3 The Proposed System p. 271

15.3.1 Feedback Collector p. 272

15.3.2 Feedback Pre-Processor p. 272

15.3.3 Feature Selector p. 272

15.3.4 Feature Validator p. 274

15.3.4.1 Removal of Terms From Tentative List of Features on the Basis of Syntactic Knowledge p. 274

15.3.4.2 Removal of Least Significant Terms on the Basis of Contextual Knowledge p. 276

15.3.4.3 Removal of Less Significant Terms on the Basis of Association With Sentiment Words p. 277

15.3.4.4 Removal of Terms Having Similar Sense p. 278

15.3.4.5 Removal of Terms Having Same Root p.

279

15.3.4.6 Identification of Multi-Term Features p. 279

15.3.4.7 Identification of Less Frequent Feature p. 279

15.3.5 Feature Concluder p. 281

15.4 Result Analysis p. 282

16 Spark-Enhanced Deep Neural Network Framework for Medical Phrase Embedding p. 289 / Amol P. Bhopale and Ashish Tiwari

16.3 Proposed Approach p. 292

16.3.1 Phrase Extraction p. 292

16.3.2 Corpus Annotation p. 294

16.3.3 Phrase Embedding p. 294

16.4 Experimental Setup p. 297

16.4.1 Dataset Preparation p. 297

16.4.2 Parameter Setting p. 297

16.5.1 Phrase Extraction p. 298

16.5.2 Phrase Embedding p. 298

17 Image Anonymization Using Deep Convolutional Generative Adversarial Network p. 305 / Ashish Undirwade and Sujit Das

17.2.1 Black Box and White Box Attacks p. 310

17.2.2 Model Inversion Attack p. 311

17.2.3 Differential Privacy p. 312

17.2.4 Generative Adversarial Network p. 313

17.2.5 Earth-Mover (EM) Distance/Wasserstein Metric p. 316

17.2.6 Wasserstein GAN p. 317

17.2.7 Improved Wasserstein GAN (WGAN-GP) p. 317

17.2.8 KL Divergence and JS Divergence p. 318

17.2.9 DCGAN p. 319

17.3 Image Anonymization to Prevent Model Inversion Attack p. 319

17.3.1 Algorithm p. 321

17.3.2 Training p. 322

17.3.3 Noise Amplifier p. 323

17.3.4 Dataset p. 324

17.3.5 Model Architecture p. 324

17.3.6 Working p. 325

17.3.7 Privacy Gain p. 325

17.4 Results and Analysis p. 326.

Notes:

Electronic reproduction. Hoboken, N.J. Available via World Wide Web.

Print version record.

Local Notes:

Acquired for the Penn Libraries with assistance from the Anne and Joseph Trachtman Memorial Book Fund.

Other Format:

Print version: Machine learning algorithms and applications.

ISBN:

9781119769262

1119769264

9781119769248

Publisher Number:

40031075525

Access Restriction:

Restricted for use by site license.