- Adha questionnaires dataset collection, 26, 31
- Adult Adha self-report scale, 28
- Advantage of AI implementation in farming, 237–238
- intelligent agriculture cloud
- platform, 238–239
- consultation of remote experts, 238
- remote control and administration in real time, 238
- Agent-oriented software engineering, 249
- Agriculture, 83–91, 93–98
- chatbot, 91
- farmers, 83–84, 86–96, 98
- harvesting, 86, 89, 93, 95, 96
- robots, 83, 86, 89, 93, 97
- sensor, 83, 87, 88, 96
- Agriculture, application of AI, 11
- Alexa, 16, 20
- Algorithms, defined, 24
- Alpha-Go, 16
- Amazon, 20–21, 27
- Amyotrophic lateral sclerosis (ALS), 209
- Anxiety, 26
- AnyWare, 32
- Applications of artificial intelligence in agriculture, 231–234
- AI farming bots, 233
- AI-based irrigation system, 234
- AI-based monitoring systems, 233
- crop and soil quality surveillance, 231
- forecasting weather details, 231
- pesticide use reduction, 233
- Artificial intelligence (AI), 16–17, 69, 83–94, 96–98, 171–172, 174
- AI in agriculture, 83, 93, 96, 97
- AI startups in agriculture, 88
- applications of AI, 8, 10–12, 83, 93
- branches of, 18–21
- deep learning, 19–20
- expert systems, 21
- fuzzy logic, 21
- machine learning, 19, 20
- NLP, 20–21
- robotics, 21
- categories, 17–18
- limited memory AI, 17–18
- reactive machine AI, 17
- self-aware AI, 18
- theory of mind AI, 18
- components of artificial intelligence, 86
- defined, 8
- domains of, 28
- elements of intelligence, 12–14
- learning, 13–14
- linguistic intelligence, 14
- perception, 14
- problem solving, 14
- reasoning, 12, 13
-
explosive growth of, 15
- future in 2035, 15
- history of, 8–10
- humanoid robot and, 15
- in innovative engineering,
- defined, 2
- guiding principles for, 4–7
- overview, 2–3
- process flow for, 3–4
- learning, types, 16–17
- need for, 8
- overview, 7–15
- scope of artificial intelligence in agriculture, 91
- tools, 14
- WSN privacy through. see Wireless sensor network (WSN) privacy through AI technique
- Artificial intelligence effect on farming, 229–231
- agriculture lifecycle, 229–230
- problems with traditional methods of farming, 232–233
- Artificial intelligence in healthcare,
- advancements, 117–118
- benefits, 117
- discussion, 118–119
- expert systems, 106–107
- future challenges, 118
- fuzzy logic, 108–109
- in medicine, 115–116
- in rehabilitation, 116–117
- in surgery, 116
- introduction, 102
- machine learning, 103–104
- natural language processing, 109–110
- neural interface for sensors, intrusion devices in artificial intelligence, 113–115
- neural networks, 105
- robots, 107–108
- sensor network technology, 110–112
- sensory devices in healthcare, implantable devices, 112–113 wearable devices, 112
- Artificial narrow intelligence (ANI), 16
- Artificial neural networks (ANNs), 164, 174–175, 216, 248
- Artificial super intelligence (ASI), 17
- Assembly robotics, 9
- Astronomy, application of AI, 8
- Auditory learning, 13
- Augmented reality (AR), 210–212
- Auto regression integrated moving average (ARIMA), 183
- Autoencoders, 26
- Automotive fabrication, application of AI, 11
- Bagging, 29
- Base station, 157
- BDI model, 252, 253
- Berkeley Motes, 246
- Best matching unit (BMU), 25
- Biological intelligence, 15
- Blue River Technology, 88, 94
- Boosting, 29
- Bootstrap aggregating, 29
- BTnode, 246
- Capturing agent, 253
- Cellular networks, 156
- Challenges in AI adoption, 89
- Classification accuracy, 30
- Cleansing of data, 31–33
- CLEF eRisk, 27
- Climate change, 83–84, 86, 88, 93, 94
- Cluster algorithm, 104
- Clustering,
- K-means clustering, 71, 72
- Clustering algorithms, 164
- Competitive edge, 33
- Condition-based maintenance (CBM), 246
-
ConvNets, 25
- Convolutional neural networks (CNNs), 25, 27, 41, 45, 47, 48, 52, 53, 62, 215–216
- Coordinator agent (CoA), 253
- COVID, 189
- Data,
- cleansing of, 31–33
- collection, 33–37
- extraction, 34
- scrubbing, 31, 32
- Data security, application of AI, 11
- Dataset,
- data collection from, 34–37
- data extraction from, 31
- pre-processing, 27–28
- Decision making, improved, 32
- Decision tree, 29, 189, 192, 199, 200, 202, 205
- Decision tree algorithm, 26, 27
- Deductive reasoning, 13
- Deep belief networks (DBNs), 25, 41, 47–49
- Deep Blue Chess Program, 10
- Deep learning, 19–20, 41–44, 47, 48, 52, 53, 57, 61, 62, 172, 174–176, 215, 217
- Deep learning algorithms for stress prediction,
- dataset pre-processing, 27–28
- literature review, 26–27
- machine learning techniques used, 28–29
- bagging, 29
- boosting, 29
- decision tree, 29
- KNN classifier, 29
- logistic regression, 29
- random forest classifier, 29
- overview, 24–26
- performance parameter, 30
- proposed methodology, 31–34
- result and experiment, 34–37
- types of algorithms, 25
- Deep mind, 17
- Deep neural network, 41–44, 48, 50, 52, 61
- Deliberative agent (DA), 253
- Depression, 23, 26, 27
- Distributed AI, 247, 248
- Distributed independent reinforcement learning, 248
- Domino’s Pizza, 32
- Drones, 83, 86, 90, 93–95, 97
- Drones for agriculture, 236
- E-commerce, application of AI, 11
- Education, application of AI, 11
- Effect, 70, 74
- Eigen value decomposition, 164
- Elements of intelligence, 12–14
- learning, 13–14
- auditory, 13
- episodic, 13
- motor, 13
- observational, 13
- perceptual, 13
- relational, 13–14
- spatial, 14 stimulus response, 14
- linguistic intelligence, 14
- perception, 14
- problem solving, 14
- reasoning, 12, 13
- Elements of neural networks, 43
- Elephant intrusion detection system (EIDS), 133
- challenges, 134
- existing approaches, 133–134
- ELIZA, 9
- Emotional intelligence, 18
- Endoskeleton, 117
- Entertainment sector, application of AI, 11
- Environment, 189–191, 203–204, 206–207
-
Environmental stress, 24
- Episodic learning, 13
- Exoskeleton, 117
- Experimental results,
- dataset preparation, 144–146
- performance analysis of DL algorithms, 146–151
- Expert systems, 106–107
- AI, branch of, 21
- application of AI, 10
- External stress, 24
- Extraction, data, 34
- Eye accessing cues (EAC), 209, 211
- F – measure, 30
- Face verification algorithmic program, 20
- Facebook, 20
- Facebook prophet model, 183
- False positive, 30, 34
- Farm bot, 88
- Feature, 191, 199
- Feature engineering, 174
- Feed forward neural networks, 164
- Feedback loop, in reinforcement learning, 167
- Feed-forward ANN, 115
- Finance, application of AI, 10
- Freddy, 9
- F-score, 30, 34
- Fundamental architecture of GAN, 57
- discriminative-network, 57
- generative-network, 57
- Fuzzy logic, 21, 108–109, 248
- Gaming, application of AI, 10
- Generative adversarial networks (GANs), 25
- Genetic algorithms intrusion devices, 115
- Gmail, 27
- G-node, 246
- Google drive, 27
- Google refine, 32
- Google survey form, 27–28
- Gradient adversarial network (GAN), 41, 48–50, 57, 62
- Handwriting recognition, application of AI, 11
- Hanson artificial intelligence, 15
- Hardware specifications,
- GSM module, 142
- night vision OV5647 camera module, 141–142
- PIR sensor, 142
- raspberry-Pi 3 model B, 141
- Hawking, Leslie Stephen, Sir, 18
- Hawking, Stephen William, 16
- Healthcare industries, application of AI, 10
- Heuristic classifications, application of AI, 12
- Hidden layer, 43, 48–51, 59
- Hidden Markov model (HMM), 27
- Hog algorithm, 209–210, 213–217, 220
- Human visual system, 41, 60
- Humanoid robot and AI, 15
- Hybrid intelligent system, 116
- IBM chess program, 17
- Image processing, 209–211, 217
- Implantable devices, 112–113
- Inductive reasoning, 13
- Innovative engineering,
- defined, 2
- guiding principles for, 4–7
- agile increments, 6
- breaking proposed system, 5
- downside risk, reducing, 6
- effectuation principals, 5
- insight in technical story, 5–6
- keeping design simple, 6
-
measurable objectives, 6
- minimal viable system architecture, 6
- scaling phase, 5
- story, start with, 4–5
- support ecosystem, creating, 7
- user’s viewpoint first, 5
- overview, 2–3
- process flow for, 3–4
- Innovative engineering with AI applications,
- AI and multi-agent systems, 246–247
- introduction, 244–245
- model plan,
- application layer, 253
- hardware layer, 251
- middle layer, 252–253
- multi-agent constructed simulation, 248–249
- multi-agent model plan, 249–250
- simulation models on behalf of wireless sensor network, 250
- wireless sensor network (WSNs), 245–246
- Intelligence,
- defined, 7
- elements of, 12–14
- learning, 13–14
- linguistic intelligence, 14
- perception, 14
- problem solving, 14
- reasoning, 12, 13
- Intelligent robots, application of AI, 11–12
- Intrusion devices in artificial intelligence, 113–115
- Keras, 41, 42, 44–47, 54, 62
- functional API model, 45
- sequential API model, 44
- Kismet, 10
- K-nearest neighbor (KNN) classifier, 29
- KNN, 189
- Labelled training set, 163
- Learning, 13–14
- auditory, 13
- episodic, 13
- motor, 13
- observational, 13
- perceptual, 13
- relational, 13–14
- spatial, 14
- stimulus response, 14
- types, 16–17
- Limited memory AI, 17–18
- Linear regression, 189–193, 199–200, 202, 204
- Linguistic intelligence, 14
- LISP programming language, 9
- Logistic regression, 29
- Long short term memory networks (LSTMs), 25
- Low tech demo, 3, 4
- Machine learning, 19, 20, 84, 89, 91, 93, 94, 96, 103–104, 177–181, 195–196, 209–211, 223
- Machine learning (ML), in WSN, 156, 160–168
- algorithms, types, 161
- applications, 157, 158
- reinforcement learning, 166–168
- supervised learning, 161–164 process of, 162–164
- topology formation, 161
- unsupervised learning, 164–166
-
Machine learning technique(s),
- types, 26
- used, 28–29
- bagging, 29
- boosting, 29
- decision tree, 29
- KNN classifier, 29
- logistic regression, 29
- random forest classifier, 29
- Manager capital (MA), 252
- MANET, 160
- Matthews’s correlation coefficient (MCC), 30, 34
- Mechanical Turk (MTurk), 27
- Mental illness, 23
- Meteorological, 189, 192–193
- Mica Mote, 246
- Minimum viable product (MVP), 6
- MIT manus, 117
- MNIST, 41, 47, 49, 51, 53, 57
- Mobile agents, 250
- Mobile applications, 117–118
- Motor learning, 13
- Multiagent, 41, 62
- Multiagent networks, 244–245
- Multi-hop routing algorithms, 245
- Multilayer perceptrons (MLPs), 25
- Natural language processing (NLP), 109–110, 116, 180
- AI, branch of, 20–21
- application of AI, 10
- NCR, 189, 202–203
- Neural interface for sensors,
- intrusion devices in artificial intelligence, 113–115
- Neural network model, 24–27
- Neural networks (NNs), 19, 105, 163–164, 172, 174–175, 189–193, 195, 198–199, 203–204
- Neuro-fuzzy, 248
- NO2, 192, 194, 196, 198
- Nomad, 10
- North India, 189
- NS2, 160
- Observational learning, 13
- OpenRefine, 32
- OutWit Hub, 34
- OWL-S, 72–73
- PAPNET, 116
- Particle, 189, 193
- PDDL, 73–75
- Perceived stress scale (PSS), 26, 28, 31
- Perception, 14
- Perceptual learning, 13
- Phonology, 109
- Physical robots, 107
- Physical stress, 24
- Physical vapor deposition technique, 113
- Physiological stressor, 24
- Piezo nano-wires, 113
- Planning,
- PM, 189–192, 194, 196, 198, 200, 204
- Pollution, 189–193, 197–199, 203–206
- Post traumatic stress disorder (PTSD), 27
- Precision, 30, 34
- Precondition, 70, 74
- Pre-processing, 193, 198, 203
- Pre-processing, dataset, 27–28
- Preserving land, 168
- Principal component analysis (PCA), 164, 166
- Problem solving, 14
- Python, 42, 46, 47, 62
- Radial basis function networks (RBFNs), 25
- Random forest, 189
- Random forest classifier, 27, 29
- Rational agents, 246–247
- Reactive machine AI, 17
- Reasoning,
- categories, 12, 13
- deductive, 13
- inductive, 13
- Recall, 30, 34
- Recommender systems, 104
- Recurrent neural networks (RNNs), 25, 41, 45, 47, 48, 50, 51, 62
- Regression, 183
- Reinforcement learning, 166–168, 178–179
- Relational learning, 13–14
- Research perspective of deep learning, 61
- argumentation, 61
- phenotyping, 61
- visualization, 61
- Restricted Boltzmann machines (RBMs), 26, 48
- Robotics, 21, 84, 87–88, 93–96
- Robots, 9, 10, 107–108
- Robots in agriculture, 235
- Rossum’s universal robots (RUR), 9
- Saliency mapping, 44, 62
- See and spray model, 90, 91
- Self-aware AI, 18
- Self-awareness, 93
- Self-calibration, 248
- Self-driving cars, 16, 18, 20
- Self-organizing function map, 168
- Self-organizing maps (SOMs), 25, 168
- Self-supervised deep learning model, 26
- Semi-supervised deep learning model, 26
- Sensitivity, 30
- Sensor network technology, 110–112
- Sensor nodes, 245
- Sensors, 156–157, 159, 161
- Sensory devices in healthcare,
- implantable devices, 112–113
- wearable devices, 112
- Shakey, 9
- Sink, 157
- Siri, 16, 20
- SO2, 192, 196
- Social media, application of AI, 11
- Social robots, 107
- Social stress, 24
- Sophia, 15, 16, 21
- Spatial learning, 14
- Specificity, 30
- Speech recognition, application of AI, 11
- Stanford cart, 9
- Stimulus response learning, 14
- Stress, 23, 26
- Stressors, kinds of, 24
- Strong AI, 16–17
- Stunning discoveries of AI, 89
- Suicide, 27
- Sun spot, 246
- Supervised learning, 161–164, 178–179
- Supervised learning algorithm, 29
- Support ecosystem, creating, 7
- Support vector, 189–190, 192, 203
- Support vector machine (SVM), 27, 210
-
Tasks agent (TA), 253
- Teaching professionals, stress prediction in. see Deep learning algorithms for stress prediction
- TensorFlow, 41, 42, 44, 46, 47, 62
- Tesla, 5
- Theoretical framework,
- deep learning models for EIDS, 134
- fast RCNN, 135
- faster RCNN, 135–136
- anchors, 136
- loss function, 136
- region proposal network (RPN), 136–137
- single-shot multibox detector (SSD), 137–138
- architecture, 138
- non-maximum suppression (NMS), 139
- you only look once (YOLO), 139 bounding box predictions, 140–141
- Theory of mind AI, 18
- TIP sequence mote, 246
- Tmote sky, 246
- Transport, application of AI, 11
- Travel domain, 66–67, 71, 76–80
- True positive rate, 30, 34
- Trusted third parties (TTPs), 159
- Turing testing, 9
- Twitter, 20, 27
- Unsupervised learning, 178–180
- Unsupervised learning algorithm, 164–166
- Visible layer, 48, 49
- Vision systems, application of AI, 10–11
- Waspmote, 246
- Weak AI, 16
- Wearable devices, 112
- Web service, 65–66
- Web service composition, 65–67, 71
- Weka, 28
- Wireless intelligent sensors, 248
- Wireless sensor network (WSN) privacy through AI technique,
- architecture of, 157, 158
- ML in, 162–168
- reinforcement learning, 166–168
- supervised learning, 164–164
- unsupervised learning, 164–166
- overview, 156–158
- review of literature, 159–160
- scheme of, 157, 158
- WSN. see Wireless sensor network (WSN) privacy through AI technique
- Zinc oxygen single wire generator, 113
..................Content has been hidden....................
You can't read the all page of ebook, please click
here login for view all page.