Obsah: Applications of generative AI /

Applications of generative AI /

Uloženo v:

Podrobná bibliografie
Další autoři:	Lyu, Zhihan (Editor)
Typ dokumentu:	Kniha
Jazyk:	Angličtina
Vydáno:	Cham : Springer International Publishing AG, 2024
Témata:	umělá inteligence artificial intelligence e-knihy online e-books online
On-line přístup:	Elektronická verze přístupná pouze pro studenty a pracovníky MU
Příbuzné jednotky:	Tištěná verze:: Applications of generative AI

Přejít na ObalkyKnih.cz

Obsah:

Intro
Contents
Generative AI as a Supportive Tool for Scientific Research
1 Generative AI History and Evolution
2 How Does GAI Models Work?-Training GAI Models: Data Sources and Techniques
3 The Difference Between Conventional ML and Deep Learning (DL) Systems, Generative AI Models and Prompt Based ML (PML)
4 GAI Model Usages and Tools
4.1 Pre-writning Stage
4.2 Writing Stage
4.3 Post-writing Stage
5 Optimizing and Utilizing GAI Models Through Prompt Engineering
6 Generative Models Evaluation and Metrics
7 Does Chat GAI Models Cheat? - GAI Pitfalls and Their Proposed Solutions
8 Generative AI the Next Generation: Challenges and Opportunities
9 Conclusions
References
Creating Ad Campaigns Using Generative AI
1 Introduction
2 Foundations
3 Methodology
3.1 Preliminaries
3.2 Encoder-Decoder Architecture
4 Empirical Results
4.1 Datasets
4.2 Evaluation Metrics
4.3 The Effect of Attention
4.4 The Effect of Reinforcement
4.5 The Effect of Pre-training
5 Conclusion
References
Unlocking the Potential of Generative Artificial Intelligence in Drug Discovery
1 Introduction
2 The Generative Model's Toolkit
2.1 The Power of Big Data in Drug Discovery
2.2 Molecular Representations
3 Generative Models: A Brief Overview
3.1 Artificial Neural Networks
3.2 (RNN)-Based Models
3.3 (AE)-Based Models
3.4 GAN-Based Models
3.5 Transfer Learning
3.6 Reinforcement Learning
3.7 Evaluation Metrics
4 Applications of Generative Models in Drug Design
4.1 3D Generative Models
4.2 Success Stories in Early Drug Discovery
5 Concluding Remarks and Future Perspectives
References
Privacy in Generative Models: Attacks and Defense Mechanisms
1 Introduction
2 Generative Adversarial Network
3 Privacy Attacks in Generative Models.
3.1 Membership Inference Attack
3.2 Model Inversion Attacks
3.3 Future Directions
4 Privacy-Preserving Mechanisms in GANs
4.1 Differential Privacy
4.2 Privacy-Preserving Approaches in GANs
4.3 Future Directions
5 Summary
References
Generative Adversarial Network for Synthetic Image Generation Method: Review, Analysis, and Perspective
1 Introduction
2 Generative Adversarial Networks (GAN) Model
3 Formula of Various GANs Model
4 Review of the Applications of GANs to Synthetic Image Generation Studies
5 Conclusions
References
Image Rendering with Generative Adversarial Networks
1 Introduction
2 Neural Rendering
2.1 Image-Based Neural Rendering
2.2 Geometric Neural Rendering
3 Generative Models
3.1 Brief History of Generative Adversarial Networks
3.2 Basic GAN Architecture
3.3 GAN-Based Methods for Image Synthesis
4 Applications of Generative Models for Image Rendering
5 Challenges and Future Directions
6 Conclusion
References
Dsmk-DcSeg-Lap, a Generative Adversarial Network Guided by Dark-Chanel and Segmentation to Smoke Removal in Laparoscopic Images
1 Introduction
2 Related Work
3 Background
3.1 Artificial Neural Network
3.2 U-Net
3.3 Conditional GAN y Pix2Pix
4 Dark-Channel and Segmentation
4.1 Hazy Image Formation
4.2 Dark Channel Prior (DCP)
4.3 Segmentation
5 GAN Powered by Dark-Channel and Segmentation
5.1 Training
6 Metrics
7 Results and Discussion
7.1 Quantitative Analysis
7.2 Qualitative Analysis
8 Conclusion
References
Generative AI Use in the Construction Industry
1 A General Overview for Generative AI
2 Technological Requirements for Generative AI Application in the AEC-FM Industry
2.1 Internet of Things (IoT)
2.2 Distributed Ledger Technology
2.3 Computing Technologies.
2.4 Deep Learning
2.5 Natural Language Processing
2.6 Knowledge Graph
2.7 Computer Vision
2.8 Immersive Technologies
3 Generative AI Applications in the AEC-FM Industry
4 BIM as a Generative AI Facilitator for the AEC-FM Industry Applications
5 Gaps and Trends for Generative AI Research in the AEC-FM Industry
5.1 Keyword Co-occurrence Analysis for Generative AI Use in the AEC-FM Industry
6 Future Prospects for Generative AI in the AEC-FM Activities
References
Generative AI Applications in the Health and Well-Being Domain: Virtual and Robotic Assistance and the Need for Niche Language Models (NLMs)
1 Applications
2 Recent Advances
3 Bots-Non-embodied, Virtual Health Assistants
4 Robotic Assistants and Companions
5 Advantages and Challenges-The Case of Nursing
5.1 Adults
5.2 Elders
5.3 Children
-6 Summary-Limitations and Future Challenges
References
Generative Adversarial Network Based Deep Learning Method for Machine Vision Inspection
1 Introduction
2 Automatic Generation Method of Image Samples Besed on Generative Adversarial Network
2.1 Schematic Diagram of CycleGAN Method
3 Automatic Defect Image Inspection Based on Generative Adversarial Networks
3.1 Unsupervised Generative Adversarial Network Model
4 Experimental Results and Analysis
4.1 Experiments and Results Foe CycleGan Based Dataset Augmentation
4.2 Experimental Results and Analysis for Automatic Defect Image Inspection Based on Generative Adversarial Networks
5 Conclusion
References
Generative Adversarial Networks for Stain Normalisation in Histopathology
1 Histopathology
2 Style Transfer
2.1 Generative Models
2.2 Similarity Metrics
2.3 Loss Functions
2.4 Multi-generator Methods
-3 Stain Normalisation
3.1 Traditional Normalisation
4 Generative Stain Normalisation.
4.1 Single Generator Normalisation Approaches
4.2 Multi-generator Normalisation Approaches
5 Augmentation and Synthesis in Histopathology
6 Conclusion
References
Augmenting Data from Epileptic Brain Seizures Using Deep Generative Networks
1 Introduction
2 Characterization of Brain Seizures in Vitro
3 Capturing Epileptic Waves with a Deep GAN Model
4 Training a Convolutional Network on Augmented Seizure Data
5 Discussion
6 Conclusions
References
Can Generative Artificial Intelligence Foster Belongingness, Social Support, and Reduce Loneliness? A Conceptual Analysis
1 Introduction
2 Literature
2.1 Artificial Intelligence
2.2 Sense of Belonging, Loneliness, and Social Support
3 Short-Term Artificial Intelligence Social Gains?
4 The Dark Side of Chatbot Social Interaction
5 Conclusion
References
The SEARCH for AI-Informed Wellbeing Education: A Conceptual Framework
1 Introduction
2 Why Use Generative AI in Wellbeing Education?
3 The SEARCH for AI-Driven Wellbeing Education
3.1 Strengths
3.2 Emotional Management
3.3 Attention and Awareness
3.4 Relationships
3.5 Coping
3.6 Habits and Goals
3.7 Summary of AI-Enhanced SEARCH Framework
4 Conclusion
References
Generative AI to Understand Complex Ecological Interactions
1 Introduction
2 Biodiversity in Restoration Ecology
3 Plant Interactions
4 Distribution Learning for Vegetation Patches
5 Transfer Learning in Community Ecology
6 Data Augmentation for Plant Communities
7 Synthetic Data for Successional Trajectories
8 Summary
References
On the Effect of Loss Function in GAN Based Data Augmentation for Fault Diagnosis of an Industrial Robot
1 Introduction
2 Methodology
2.1 On GAN
2.2 On Wasserstein GAN and Conditional Wasserstein GAN
2.3
2.4 On SW-CycleGAN
3 Experiments
3.1 The Industrial Robot Test Rig and Data Set
3.2 Experimental Settings of VGAN
3.3 Experimental Settings of SW-CycleGAN
4 Results and Discussion
4.1 Results on VGAN
4.2 Results on SW-CycleGAN
5 Conclusion
References
Underwater Acoustic Noise Modeling Based on Generative-Adversarial- Network
1 Introduction
2 Analysis of Real Underwater Noise
3 GAN-Based Underwater Noise Simulator
3.1 Introduction of GAN
3.2 GAN Structure for Noise Simulations
4 Numerical Simulations and Discussions
4.1 Parametric Configuration of GAN-Based Noise Simulator
4.2 Accuracy Analysis for GAN and Traditional Non-gaussian Models
4.3 Complexity Analysis
5 Conclusions
References
How Generative AI Is Transforming Medical Imaging: A Practical Guide
1 Generative AI for Images: What It Is and How It Works
-2 GANs, VAEs and Diffusion Models: What Are They?
3 How Can Generative AI Help Medical Imaging?
4 What Are the Pros and Cons of Generative AI for Medical Imaging?
5 How Generative AI Has Improved Medical Imaging: A Showcase of Successful Applications
5.1 Generating Mammogram Images with Contextual Information Using GANs
5.2 Augmenting Medical Images Using Semi-supervised GANs and Attention Mechanism
5.3 EndoVAE: An Innovative Variational Autoencoder for Endoscopic Image Generation
5.4 Restoring Medical Images with Variational Autoencoders
5.5 Brain Imaging Made Easy with Latent Diffusion Models
5.6 Creating Realistic 3D Medical Images with Denoising Diffusion Models
6 Generative AI Outlook: A Game-Changer for Healthcare and Biomedical Research
6.1 Key Takeaways and Findings of the Chapter
-6.2 Recommendations for Generative AI Users and Stakeholders
6.3 Future Directions for Generative AI Research for Medical Imaging
References.
Generative AI in Medical Imaging and Its Application in Low Dose Computed Tomography (CT) Image Denoising.

Applications of generative AI /

Podobné jednotky