Machine Learning Paradigm for Internet of Things Applications

Index

• Accuracy, 113, 115–117, 124–125, 130, 137, 139–141, 143
• Adherent, 79
• ADIS model, 31
• AHH-VBF, 251, 254, 257
• Akaike information criterion (AIC), 30
• AlexNet, 267–268
• Amazon, 114, 128, 142
• ANACONDA, 61
• Anomaly detection, 8
• Anonymity, 54–55, 57
• AODV, 251, 253, 257
• Applied Sciences (journal), 267
• Architecture of IoUT, 232
• Area under the curve (AUC), 117, 119
• ARIMA, 30
• ARM, 152
• ARP, 251, 254, 257
• Artificial intelligence (AI), 67, 68, 97
• Artificial neural networks, 6
• Autonomous underwater vehicles (AUVs), 230, 233, 237, 240, 247

• Bayesian information criterion (BIC), 30
• Binary classification, 181
• Business model, 13, 14

• Chest x-ray for pneumonia detection,
  • background, 267–268
  • introduction, 266–267
  • research methodology, 268–271
  • results and discussion, 271–272
• Churn, 122, 124
• Classification, 5
• Cloud, 70, 72, 73
• Cloud computing, 15
• Clustering, 124, 131, 135, 172, 174, 177
• CNN, 98–103, 109, 153, 154
• Collaborative data publishing model with privacy preservation,
  • introduction, 54–56
  • literature survey, 56–58
  • proposed model, 58–61
  • results, 61, 64
• Collaborative filtering (CF), 114
• Computers & Electrical Engineering (journal), 267
• Confusion matrix, 198–201, 267, 272
• Content-based filtering (CBF), 114
• Convolutional neural network (CNN), 191, 267
• Correlation, 79
• Cosine similarity, 203
• Coverage, 122, 123, 138–141
• Crowding, 82

• Data mining, 54, 57, 58
• Data noise, 11
• Data perturbation–based techniques, 58
• Data pre-processing, 129
• Data publisher, 54
• Dataset augmentation, 267