Schweitzer Fachinformationen
Wenn es um professionelles Wissen geht, ist Schweitzer Fachinformationen wegweisend. Kunden aus Recht und Beratung sowie Unternehmen, öffentliche Verwaltungen und Bibliotheken erhalten komplette Lösungen zum Beschaffen, Verwalten und Nutzen von digitalen und gedruckten Medien.
Innovative Engineering with AI Applications demonstrates how we can innovate in different engineering domains as well as how to make most business problems simpler by applying AI to them.
Engineering advancements combined with artificial intelligence (AI), have resulted in a hyper-connected society in which smart devices are not only used to exchange data but also have increased capabilities. These devices are becoming more context-aware and smarter by the day. This timely book shows how organizations, who want to innovate and adapt, can enter new markets using expertise in various emerging technologies (e.g. data, AI, system architecture, blockchain), and can build technology-based business models, a culture of innovation, and high-performing networks. The book specifies an approach that anyone can use to better architect, design, and more effectively build things that are technically novel, useful, and valuable, and to do so efficiently, on-time, and repeatable.
Audience
The book is essential to AI product developers, business leaders in all industries and organizational domains. Researchers, academicians, and students in the AI field will also benefit from reading this book.
Anamika Ahirwar, PhD, is an associate professor at the Compucom Institute of Information Technology & Management, Jaipur, India. She has about 20 years of experience in teaching and research and has published more than 45 research papers in reputed national/international journals and conferences, authored several books as well as five patents.
Piyush Kumar Shukla, PhD, is an associate professor in the Department of Computer Science & Engineering, University Institute of Technology, Bhopal, India. He has about 15 years of experience in teaching and research, is the author of 3 books, more than 50 articles and book chapters in international publications, as well as 15 Indian patents.
Manish Shrivastava, PhD, is the Principal of the Chameli Devi Institute of Technology & Management, Indore, India. He has published more than 100 articles in international journals and spent 7 years as a software engineer.
Priti Maheshwary, PhD, is a professor in the Department of CSE and Head of the Centre for Excellence in Internet of Things and Advance Computing Lab, Rabindranath Tagore University, Bhopal, India.
Bhupesh Gour, PhD, is a professor in the Department of Computer Science and Engineering at Lakshmi Narain College of Technology in Bhopal, India. He has 22 years of experience in academia as well as the software industry. He has published more than 50 articles in national and international journals, as well as four patents.
Preface xiii
1 Introduction of AI in Innovative Engineering 1Anamika Ahirwar
1.1 Introduction to Innovation Engineering 2
1.2 Flow for Innovation Engineering 3
1.3 Guiding Principles for Innovation Engineering 4
1.4 Introduction to Artificial Intelligence 7
1.4.1 History of Artificial Intelligence 8
1.4.2 Need for Artificial Intelligence 8
1.4.3 Applications of AI 8
1.4.4 Comprised Elements of Intelligence 12
1.4.5 AI Tools 14
1.4.6 AI Future in 2035 15
1.4.7 Humanoid Robot and AI 15
1.4.8 The Explosive Growth of AI 15
1.5 Types of Learning 16
1.6 Categories of AI 17
1.7 Branches of Artificial Intelligence 18
1.8 Conclusion 21
Bibliography 22
2 An Analytical Review of Deep Learning Algorithms for Stress Prediction in Teaching Professionals 23Ruby Bhatt
2.1 Introduction 24
2.2 Literature Review 26
2.3 Dataset and Pre-Processing 27
2.4 Machine Learning Techniques Used 28
2.5 Performance Parameter 30
2.6 Proposed Methodology 31
2.7 Result and Experiment 34
2.8 Comparison of Six Different Approaches For Stress Detection 37
2.9 Conclusions 38
2.10 Future Scope 38
References 38
3 Deep Learning: Tools and Models 41Brijesh K. Soni and Akhilesh A. Waoo
3.1 Introduction 41
3.1.1 Definition 42
3.1.2 Elements of Neural Networks 43
3.1.3 Tool: Keras 44
3.2 Deep Learning Models 47
3.2.1 Deep Belief Network [DBN] 48
3.2.1.1 Fundamental Architecture of DBN 48
3.2.1.2 Implementing DBN Using MNIST Dataset 49
3.2.2 Recurrent Neural Network [RNN] 50
3.2.2.1 Fundamental Architecture of RNN 50
3.2.2.2 Implementing RNN Using MNIST Dataset 51
3.2.3 Convolutional Neural Network [CNN] 52
3.2.3.1 Fundamental Architecture of CNN 52
3.2.3.2 Implementing CNN Using MNIST Dataset 53
3.2.4 Gradient Adversarial Network [GAN] 57
3.2.4.1 Fundamental Architecture of GAN 57
3.2.4.2 Implementing GAN Using MNIST Dataset 57
3.3 Research Perspective of Deep Learning 61
3.3.1 Multi-Agent System: Argumentation 61
3.3.2 Image Processor: Phenotyping 61
3.3.3 Saliency-Map: Visualization 61
3.4 Conclusion 61
References 62
4 Web Service Composition Using an AI Planning Technique 65Lalit Purohit and Satyendra Singh Chouhan
4.1 Introduction 66
4.2 Background 69
4.2.1 Introduction to AI 69
4.2.2 AI Planning 70
4.2.3 AI Planning for Effective Composition of Web Services 70
4.3 Proposed Methodology for AI Planning-Based Composition of Web Services 71
4.3.1 Clustering Web Services 71
4.3.2 OWL-S: Semantic Markup for Web Services(For Composition Request) 72
4.3.3 PDDL: Planning Domain Description Language 73
4.3.4 AI Planner 75
4.3.5 Flowchart of Proposed Approach 75
4.4 Implementation Details 76
4.4.1 Domain Used 76
4.4.2 Case Studies on AI Planning 77
4.4.2.1 Experiments and Results on Case 1 and Case 2 78
4.5 Conclusions and Future Directions 80
References 80
5 Artificial Intelligence in Agricultural Engineering 83Ashwini A. Waoo, Jyoti Pandey and Akhilesh A. Waoo
5.1 Introduction 84
5.2 Artificial Intelligence in Agriculture 86
5.2.1 AI Startups in Agriculture 88
5.2.2 Challenges in AI Adoption 89
5.2.3 Stunning Discoveries of AI 89
5.2.3.1 Precision Technology to Sow Seeds 89
5.2.3.2 Robots for Harvesting 89
5.2.3.3 Field Inspection Using Drones 90
5.2.3.4 "See and Spray" Model for Pest and Weed Control 90
5.3 Scope of Artificial Intelligence in Agriculture 91
5.3.1 Reactive Machines 92
5.3.2 Limited Memory 92
5.3.3 Theory of Mind 92
5.3.4 Self-Awareness 93
5.4 Applications of Artificial Intelligence in Agriculture 93
5.4.1 Agricultural Robots 93
5.4.2 Soil Analysis and Monitoring 94
5.4.3 Predictive Analysis 94
5.4.4 Agricultural Industry 94
5.4.5 Blue River Technology - Weed Control 94
5.4.6 Crop Harvesting 95
5.4.7 Plantix App 95
5.4.8 Drones 95
5.4.9 Driverless Tractors 95
5.4.10 Precise Farming 96
5.4.11 Return on Investment (RoI) 96
5.5 Advantages of AI in Agriculture 96
5.6 Disadvantages of AI in Agriculture 97
5.7 Conclusion 97
References 98
6 The Potential of Artificial Intelligence in the Healthcare System 101Meena Gupta and Ruchika Kalra
6.1 Introduction 102
6.2 Machine Learning 103
6.3 Neural Networks 105
6.4 Expert Systems 106
6.5 Robots 107
6.6 Fuzzy Logic 108
6.7 Natural Language Processing 109
6.8 Sensor Network Technology in Artificial Intelligence 110
6.9 Sensory Devices in Healthcare 112
6.9.1 Wearable Devices 112
6.9.2 Implantable Devices 112
6.10 Neural Interface for Sensors 113
6.10.1 Intrusion Devices in Artificial Intelligence 113
6.11 Artificial Intelligence in Healthcare 115
6.11.1 Role of Artificial Intelligence in Medicine 115
6.11.2 Role of Artificial Intelligence in Surgery 116
6.11.3 Role of Artificial Intelligence in Rehabilitation 116
6.12 Why Artificial Intelligence in Healthcare 117
6.13 Advancements of Artificial Intelligence in Healthcare 117
6.14 Future Challenges 118
6.15 Discussion 118
6.16 Conclusion 119
References 119
7 Improvement of Computer Vision-Based Elephant Intrusion Detection System (EIDS) with Deep Learning Models 131Jothibasu M., Sowmiya M., Harsha R., Naveen K. S. and Suriyaprakash T. B.
7.1 Introduction 132
7.2 Elephant Intrusion Detection System (EIDS) 133
7.2.1 Existing Approaches 133
7.2.2 Challenges 134
7.3 Theoretical Framework 134
7.3.1 Deep Learning Models for EIDS 134
7.3.1.1 Fast RCNN 135
7.3.1.2 Faster RCNN 135
7.3.1.3 Single-Shot Multibox Detector (SSD) 137
7.3.1.4 You Only Look Once (YOLO) 139
7.3.2 Hardware Specifications 141
7.3.2.1 Raspberry-Pi 3 Model B 141
7.3.2.2 Night Vision OV5647 Camera Module 141
7.3.2.3 PIR Sensor 142
7.3.2.4 GSM Module 142
7.3.3 Proposed Work 142
7.4 Experimental Results 144
7.4.1 Dataset Preparation 144
7.4.2 Performance Analysis of DL Algorithms 146
7.5 Conclusion 152
References 152
8 A Study of WSN Privacy Through AI Technique 155Piyush Raja
8.1 Introduction 156
8.2 Review of Literature 159
8.3 ml in WSNs 160
8.3.1 Supervised Learning 161
8.3.2 Unsupervised Learning 164
8.3.3 Reinforcement Learning 166
8.4 Conclusion 169
References 169
9 Introduction to AI Technique and Analysis of Time Series Data Using Facebook Prophet Model 171S. Sivaramakrishnan, C.R. Rathish, S. Premalatha and Niranjana C.
9.1 Introduction 172
9.2 What is AI? 172
9.2.1 Process of Thoughts - Human Approach 173
9.3 Main Frameworks of Artificial Intelligence 174
9.3.1 Feature Engineering 174
9.3.2 Artificial Neural Networks 175
9.3.3 Deep Learning 175
9.4 Techniques of AI 177
9.4.1 Machine Learning 177
9.4.1.1 Supervised Learning 179
9.4.1.2 Unsupervised Learning 179
9.4.1.3 Reinforcement Learning 179
9.4.2 Natural Language Processing (NLP) 180
9.4.3 Automation and Robotics 181
9.4.4 Machine Vision 181
9.5 Application of AI in Various Fields 182
9.6 Time Series Analysis Using Facebook Prophet Model 183
9.7 Feature Scope of AI 186
9.8 Conclusion 186
References 187
10 A Comparative Intelligent Environmental Analysis of Air-Pollution in COVID: Application of IoT and AI Using ML in a Study Conducted at the North Indian Zone 189Rohit Rastogi, Abhishek Goyal, Akshit Rajan Rastogi and Neha Gupta
10.1 Introduction 190
10.1.1 Intelligent Environment Systems 190
10.1.2 Types of Pollution 190
10.1.3 Components in Pollution Particles 191
10.1.4 Research Problem Introduction and Motivation 191
10.2 Related Previous Work 191
10.2.1 Machine Learning Models 192
10.2.2 Regression Techniques Applications 192
10.3 Methodology Adopted in Research 193
10.3.1 Data Source 193
10.3.2 Data Pre-Processing 195
10.3.3 Calculating AQI 195
10.3.4 Computing AQI 195
10.3.5 Data Pre-Processing 196
10.3.6 Feature Selection 198
10.4 Results and Discussion 199
10.4.1 Collective Analysis 199
10.4.2 Applying Various Repressors 200
10.4.3 Comparison with Existing State-of-the-Art Technologies 201
10.5 Novelties in the Work 202
10.6 Future Research Directions 203
10.7 Limitations 203
10.8 Conclusions 203
Acknowledgements 204
Key Terms and Definitions 204
Additional Readings 205
References 206
11 Eye-Based Cursor Control and Eye Coding Using Hog Algorithm and Neural Network 209S. Sivaramakrishnan, Vasuprada G., V. R. Harika, Vishnupriya P. and Supriya Castelino
11.1 Introduction 210
11.2 Related Work 210
11.3 Methodology 212
11.3.1 Eye Blink Detection 213
11.3.2 Hog Algorithm 214
11.3.3 Eye Gaze Detection 215
11.3.3.1 Deep Learning and CNN 215
11.3.3.2 Hog Algorithm for Gaze Determination 216
11.3.4 GUI Automation 216
11.4 Experimental Analysis 217
11.4.1 Eye-Based Cursor Control 217
11.4.2 Eye Coding 217
11.5 Observation and Results 220
11.6 Conclusion 223
11.7 Future Scope 224
References 224
12 Role of Artificial Intelligence in the Agricultural System 227Nilesh Kunhare, Rajeev Kumar Gupta and Yatendra Sahu
12.1 Introduction 228
12.2 Artificial Intelligence Effect on Farming 229
12.2.1 Agriculture Lifecycle 229
12.2.2 Problems with Traditional Methods of Farming 230
12.3 Applications of Artificial Intelligence in Agriculture 231
12.3.1 Forecasting Weather Details 231
12.3.2 Crop and Soil Quality Surveillance 231
12.3.3 Pesticide Use Reduction 233
12.3.4 AI Farming Bots 233
12.3.5 AI-Based Monitoring Systems 233
12.3.6 AI-Based Irrigation System 234
12.4 Robots in Agriculture 235
12.5 Drones for Agriculture 236
12.6 Advantage of AI Implementation in Farming 237
12.6.1 Intelligent Agriculture Cloud Platform 238
12.6.1.1 Remote Control and Administration in Real Time 238
12.6.1.2 Consultation of Remote Experts 238
12.7 Research, Challenges, and Scope for the Future 239
12.8 Conclusion 240
References 240
13 Improving Wireless Sensor Networks Effectiveness with Artificial Intelligence 243Piyush Raja, Santosh Kumar, Digvijay Singh and Taresh Singh
13.1 Introduction 244
13.2 Wireless Sensor Network (WSNs) 245
13.3 AI and Multi-Agent Systems 246
13.4 WSN and AI 247
13.5 Multi-Agent Constructed Simulation 248
13.6 Multi-Agent Model Plan 249
13.7 Simulation Models on Behalf of Wireless Sensor Network 250
13.8 Model Plan 251
13.8.1 Hardware Layer 251
13.8.2 Middle Layer 252
13.8.3 Application Layer 253
13.9 Conclusion 253
References 254
Index 257
Anamika Ahirwar
Compucom Institute of Information Technology and Management, Jaipur, Rajasthan, India
The widespread use of Artificial Intelligence [1] technology and its ongoing development have created new opportunities for creative engineering. Our daily lives have been completely taken over by the revolutionary realm of Artificial Intelligence (AI). It is the unique fusion of brains and therefore of machines. Artificial intelligence has been growing steadily over the last few years, establishing roots in most industries. There have been recent developments and technologies that support AI. The uses of AI don't seem to be limited to physical space; they can be found in everything from a secondary aspect to a novel development. A new society is being created by many technologies, devices, and even some brand-new inventions that have yet to be realized. Therefore, it offers a seamless route that leads to a promising future. This chapter intends to focus on an overview of innovative engineering in artificial intelligence and introduces the concepts of innovative engineering and artificial engineering with the aid of many innovation engineering guiding principles. This chapter covers the background, need for, and applications of artificial intelligence and also explains the various subfields of artificial intelligence [8]. This chapter covers the background, need for, and applications of artificial intelligence.
Keywords: Innovation Engineering, Artificial Intelligence (AI), Artificial Narrow Intelligence (ANI), Artificial General Intelligence (AGI), Artificial Super Intelligence (ASI)
Innovation Engineering is defined as a method for solving technology and business problems for organizations who want to innovate, adapt, and/or enter new markets using expertise in emerging technologies (e.g. data, AI, system architecture, blockchain), technology business models, innovation culture, and high-performing networks.
When Dave Kelly specified the IDEO process for design in 1971, he changed the predictability of design projects around the world and made each design project more likely to serve its users well. In a similar way, this Innovation Engineering process is intended to make innovation projects in engineering more successful. The process builds upon many best practices in innovation, but it also brings them into a domain of more technically sophisticated areas.
The concept of Innovation Engineering also integrates many years of observing our students who have engineered novel technologies and companies. The goal is to specify an approach that anyone can use to better architect, design, and more effectively build things that are technically novel, useful, and valuable. And further, the goal is to be able to do this efficiently, on-time, and repeatable.
At its core, Innovation Engineering is the result of using the approaches, processes, behaviors, and mindsets of entrepreneurs/innovators with the context of engineering projects. This is illustrated in the Figure 1.1.
One thing that we have observed is that innovative technical leaders employ similar behavioral patterns as entrepreneurs even in areas of engineering architecture, design, and implementation. And further, these behaviors can be amplified within a process.
Figure 1.1 Innovation engineering.
A high-level process example is shown in Figure 1.2. It simply illustrates the concept of brainstorming a problem/solution, converting the problem/ solution into a 'story' called a low-tech demo, and then using agile sprints to develop the project.
This simple process flow can be extended to include business and/or organizational context. Figure 1.2 shows a process flow for Innovation Engineering with greater detail and broader context. The flow illustrates that effective projects start always with a story or narrative. This narrative is generally based on background of the team and an observation of changes in the world (e.g. market, technical, societal, or regulatory changes). When a project does not start with a story narrative, it is typically too narrowly defined and generally goes off target in our experience. Note, the "Low Tech Demo" in the example maps to the Technical Story in the lower diagram which is used to kick-off an Agile project leading to an Implementation.
The story narrative is used to collect initial stakeholders, resources, and obtain initial validation for the project. In our experience, there is no better way to attract resources than by testing a story and/or initial prototype.
From here, the story narrative can be broken into two sub-narratives, one for the technical story and another for the broader context or business story. Each story is the starting point of a learning path, and specifically not an execution path. The technical path is an agile process that leads to an implementation starting first from the user's viewpoint. For example, in Data-X, we use the following components as part of the technical story which we call a "low tech demo".
Figure 1.2 A process flow for innovation engineering.
Low tech demo outline, an example of a technical story:
In contrast, the business learning path is intended to result in
These learning paths converge when the business model/mission and the technology are all working and integrated. Only after this step can the innovation be scaled via execution and planning. Innovation Engineering tends to focus more on the technical path as required for successful implementation, but must include the broader process as described to be successful.
While all of this is a very quick overview of the process, it does set the context for a set of important principles that are required for the process to be successful. Like with any other organizational activity, Innovation Engineering requires a set of shared beliefs and behaviors to be successful. These 'Guiding Principles' for Innovation Engineering are outlined in the section below are intended to be synergistic with the process flow explained in the Figure 1.2.
Dateiformat: ePUBKopierschutz: Adobe-DRM (Digital Rights Management)
Systemvoraussetzungen:
Das Dateiformat ePUB ist sehr gut für Romane und Sachbücher geeignet – also für „fließenden” Text ohne komplexes Layout. Bei E-Readern oder Smartphones passt sich der Zeilen- und Seitenumbruch automatisch den kleinen Displays an. Mit Adobe-DRM wird hier ein „harter” Kopierschutz verwendet. Wenn die notwendigen Voraussetzungen nicht vorliegen, können Sie das E-Book leider nicht öffnen. Daher müssen Sie bereits vor dem Download Ihre Lese-Hardware vorbereiten.Bitte beachten Sie: Wir empfehlen Ihnen unbedingt nach Installation der Lese-Software diese mit Ihrer persönlichen Adobe-ID zu autorisieren!
Weitere Informationen finden Sie in unserer E-Book Hilfe.
