Data Science: From Research to Application

Preface......Page 6
Acknowledgement......Page 8
Contents......Page 10
 1 Introduction......Page 13
 2 Related Works......Page 14
 3 Proposed Algorithm......Page 16
 4 Simulation......Page 19
  4.1 The Default Values and Assumptions......Page 20
 5 Evaluation and Data Analysis......Page 21
 References......Page 23
 1 Introduction......Page 25
 2 Some Common Metrics......Page 26
  3.1 Fingerprint Matching [16]......Page 29
  3.2 Robot Pose Estimation......Page 30
  3.3 Polar Diagram Matching......Page 31
 4 Metrics’ Properties......Page 32
 References......Page 34
 1 Introduction......Page 36
 2 Previous Work......Page 38
 3 Proposed Method......Page 39
 4 File Selection......Page 41
 6 Feature Extraction, Similarity Measure, and Classification......Page 42
 8 Implementation and Results......Page 43
 References......Page 46
 1 Introduction......Page 48
 2 Related Work......Page 49
 3 Proposed Method (RSS-RAID)......Page 50
  3.3 Recovery Algorithm......Page 52
  4.1 Scalability and Fault Tolerance of RSS-RAID......Page 53
 5 Conclusion and Future Work......Page 54
 References......Page 55
 1 Introduction......Page 56
 2 Background of Ensemble Methods......Page 57
  2.2 AdaBoosting......Page 58
  2.3 Random Forest......Page 59
 3 Proposed Model Based on Distributed Systems......Page 60
  3.1 Phase I......Page 61
  3.2 Phase II......Page 63
  3.4 Modifications......Page 64
 4 Experimental Results......Page 65
 References......Page 69
 1 Introduction......Page 71
  2.2 Test-Case Generation......Page 73
 3 Mutation Testing......Page 74
  4.1 Evolutionary Algorithms (EAs)......Page 77
  4.2 Fitness Functions......Page 81
  5.1 Experimental Setup......Page 82
  5.2 Simulation Results......Page 83
 References......Page 85
 1 Introduction......Page 88
  2.1 The Stochastic Model......Page 90
  2.3 Maximum Entropy Fuzzy Clustering......Page 91
 3 Fuzzy Density Data Association......Page 93
 4 Results and Discussion......Page 95
  4.1 Case 1: Linear Parallel Targets......Page 96
  4.2 Case 2: Linear Crossing Targets......Page 97
 References......Page 99
 1 Introduction......Page 101
  2.1 Principal Component Analysis Family......Page 103
  2.3 Independent Component Analysis Family......Page 104
  3.1 Local Methods of Manifold Learning......Page 105
  3.3 Hybrid Methods of Manifold Learning......Page 106
 4 Shallow Representation Learning Approaches......Page 107
  4.1 Restricted Boltzmann Machines......Page 108
  4.2 Autoencoders......Page 109
 5 Deep Representation Learning Approaches......Page 110
  5.2 Convolutional Neural Networks......Page 111
  5.4 Deep Autoencoders......Page 112
 6 Discussion and Conclusion......Page 113
 References......Page 114
 1 Introduction......Page 117
  2.1 Phase I: Seeding......Page 120
  3.1 Networks......Page 122
  3.2 Performance Metrics......Page 124
  3.3 Comparison Methods......Page 125
  3.5 Experiment Process and Results......Page 126
 References......Page 130
 1 Introduction......Page 133
 2 Background and Related Work......Page 134
  3.1 Problem Formulation to Define and Fit LSTM......Page 135
  4.1 Petrochemical Plant Case Study......Page 136
  4.2 Experimental Results......Page 137
 5 Conclusions and Future Work......Page 139
 References......Page 140
 1 Introduction......Page 142
  2.1 Formal Approach......Page 144
  3.1 False-Positive Rate......Page 146
  3.2 Pathways Ranking on Real Datasets......Page 147
 4 Conclusion......Page 151
 References......Page 152
 1 Introduction......Page 154
 2 Materials and Methods......Page 156
  2.1 Dataset Description......Page 157
  2.2 Data Pre-processing......Page 158
 3 Experimental Study......Page 161
  3.1 Classification Models in Survival Prediction......Page 162
  3.2 Performance Metrics......Page 164
  4.1 Role of Attributes and Survival Prediction......Page 165
  4.2 Performance Evaluation......Page 166
  4.3 Discussion......Page 168
 5 Conclusions......Page 169
 References......Page 170
 1 Introduction......Page 173
 2 Related Work......Page 175
  3.1 Heat-Transport......Page 176
  3.2 Data Generation......Page 177
  3.3 Deep Learning......Page 180
  4.1 Analyzing Deep Learning Results......Page 182
  4.2 Comparison with ANSYS......Page 183
 References......Page 185
 1 Introduction......Page 187
 2 Related Works......Page 190
 3 Cluster Based Authentication......Page 191
  3.1 Both Members are Unregistered......Page 194
  3.3 Both Members are Registered......Page 195
 4 Performance Evaluation......Page 196
  4.2 Ensures Minimum Cost of Power and Memory Space......Page 197
 5 Conclusions......Page 198
 References......Page 199
 1 Introduction......Page 200
  2.2 Time Series Clustering......Page 201
  2.3 Time Series Forecasting......Page 203
 3 Proposed Methodology......Page 204
  3.3 Modelling......Page 205
  4.1 Input Data......Page 207
  4.3 Modelling......Page 208
  4.4 Evaluation......Page 209
 5 Conclusion......Page 211
 References......Page 212
 1 Introduction......Page 214
 2 Related Works......Page 216
 3 Google Play and Dataset......Page 217
 4 Classification Algorithms......Page 218
 5 Feature Engineering......Page 220
  6.2 Results and Discussions......Page 221
  6.3 Practical Usage......Page 225
 7 Conclusion......Page 226
 References......Page 227
 1 Introduction......Page 229
 2 Literature Review......Page 230
  2.4 Extreme Learning Machine......Page 231
  3.2 UCT-Based Classifier......Page 232
  4.3 Results and Discussion......Page 233
 References......Page 236
 1 Introduction......Page 238
 3 Related Work......Page 239
 4 Proposed Algorithm......Page 242
 5 Experiments......Page 244
 References......Page 248
 1 Introduction......Page 250
  2.1 Model......Page 251
  2.2 Optic Flow Integration......Page 252
  2.3 Model Training......Page 253
  3.1 Model Architecture......Page 255
  3.3 Results......Page 256
 References......Page 258
 1 Introduction......Page 260
 2 Background......Page 262
 4 Proposed Approach......Page 264
 5 Experimental Results......Page 266
 References......Page 268
 1 Introduction......Page 270
 2 Related Work......Page 272
  3.2 Moremorph: The Add-On for SMOR......Page 273
  3.3 Morphy......Page 275
 4 Two Lexical Databases with Morphological Information......Page 276
  4.1 CELEX......Page 277
  4.2 GermaNet......Page 278
  4.3 Building and Merging Morphological Trees of the Databases......Page 279
 5 Combining Morphological Databases with Segmenters......Page 280
 7 Results......Page 281
 References......Page 282
 1 Introduction......Page 286
  3.1 Computing the GNG Graph......Page 288
  3.2 Extracting the Outer Boundary of the GNG Graph......Page 289
  3.3 Bulges......Page 290
  3.4 Extracting Bulges......Page 291
 4 American Sign Language (ASL)......Page 293
  4.1 Topological Features......Page 294
  4.2 The Result of Experimental Study on SBU-1......Page 297
  4.4 Analysis Properties of Our Method......Page 298
 References......Page 300
 1 Introduction......Page 302
 2 Related Work......Page 303
  3.1 CRF and Pairwise CRF......Page 304
  3.2 Parameter Estimation and Optimization Problem......Page 305
  4.2 Data Set and Assessment Results......Page 307
 References......Page 309
 1 Introduction......Page 311
 3 Overview of Generative Adversarial Nets......Page 313
 4 Proposed Approach......Page 314
 6 Model Evaluation Measures......Page 315
 7 Experiments......Page 316
 8 Results......Page 318
 References......Page 320
 1 Introduction......Page 323
  2.1 IoT Security and Privacy......Page 324
  2.2 Blockchain......Page 325
  2.4 Search Process......Page 326
  3.1 RQ1: Use Cases Related to Smart City......Page 327
  3.3 RQ3: Use Cases Related to Smart Health......Page 329
  3.4 RQ4: Use Cases Related to Smart Economy......Page 330
 4 Conclusion......Page 331
 References......Page 332
An Intelligent Safety System for Human-Centered Semi-autonomous Vehicles......Page 334
 1 Introduction......Page 335
 2 Background......Page 337
  3.1 Driving Scene Perception......Page 338
  3.2 Driver State Detection......Page 341
  3.3 In-Vehicle Communication Device......Page 343
 4 Implementation Details......Page 344
 5 Conclusions and Future Work......Page 346
 References......Page 347
Author Index......Page 349