Vai al contenuto principale della pagina
Autore: |
Rathore Pramod Singh
![]() |
Titolo: |
Deep Learning Techniques for Automation and Industrial Applications
![]() |
Pubblicazione: | Newark : , : John Wiley & Sons, Incorporated, , 2024 |
©2024 | |
Edizione: | 1st ed. |
Descrizione fisica: | 1 online resource (280 pages) |
Disciplina: | 670.42/7028 |
Soggetto topico: | Automation |
Altri autori: |
AhujaSachin
![]() ![]() ![]() ![]() ![]() |
Note generali: | Description based upon print version of record. |
6.4 Results and Discussions | |
Nota di contenuto: | Cover -- Series Page -- Title Page -- Copyright Page -- Contents -- Preface -- Chapter 1 Text Extraction from Images Using Tesseract -- 1.1 Introduction -- 1.1.1 Areas -- 1.1.2 Why Text Extraction? -- 1.1.3 Applications of OCR -- 1.2 Literature Review -- 1.3 Development Areas -- 1.3.1 React JavaScript (JS) -- 1.3.2 Flask -- 1.4 Existing System -- 1.5 Enhancing Text Extraction Using OCR Tesseract -- 1.6 Unified Modeling Language (UML) Diagram -- 1.6.1 Use Case Diagram -- 1.6.2 Model Architecture -- 1.6.3 Pseudocode -- 1.7 System Requirements -- 1.7.1 Software Requirements -- 1.7.2 Hardware Requirements -- 1.8 Testing -- 1.9 Result -- 1.10 Future Scope -- 1.11 Conclusion -- References -- Chapter 2 Chili Leaf Classification Using Deep Learning Techniques -- 2.1 Introduction -- 2.2 Objectives -- 2.3 Literature Survey -- 2.4 About the Dataset -- 2.5 Methodology -- 2.6 Result -- 2.7 Conclusion and Future Work -- References -- Chapter 3 Fruit Leaf Classification Using Transfer Learning Techniques -- 3.1 Introduction -- 3.2 Literature Review -- 3.3 Methodology -- 3.3.1 Image Preprocessing -- 3.3.2 Data Augmentation -- 3.3.3 Deep Learning Models -- 3.3.4 Accuracy Chart -- 3.3.5 Accuracy and Loss Graph -- 3.4 Conclusion and Future Work -- References -- Chapter 4 Classification of University of California (UC), Merced Land-Use Dataset Remote Sensing Images Using Pre-Trained Deep Learning Models -- 4.1 Introduction -- 4.2 Motivation and Contribution -- 4.2.1 Related Work -- 4.3 Methodology -- 4.3.1 Pre-Trained Models -- 4.3.2 Dataset -- 4.3.3 Training Processes -- 4.4 Experiments and Results -- 4.4.1 VGG Family -- 4.4.2 ResNet Family -- 4.4.2.1 ResNet101 -- 4.4.2.2 ResNet152 -- 4.4.3 MobileNet Family -- 4.4.4 Inception Family -- 4.4.5 Xception Family -- 4.4.6 DenseNet Family -- 4.4.7 NasNet Family -- 4.4.8 EfficientNet Family -- 4.4.9 ResNet Version 2. |
4.5 Conclusion -- References -- Chapter 5 Sarcastic and Phony Contents Detection in Social Media Hindi Tweets -- 5.1 Introduction -- 5.1.1 Sarcasm in Social Media Hindi Tweets -- 5.2 Literature Review -- 5.2.1 Literature Review of Sarcasm Detection Based on Data Analysis Without Machine Learning Algorithms -- 5.2.1.1 Other Related Works without Machine Learning Algorithms for Sarcasm Detection -- 5.2.2 Literature Review of Sarcasm Detection with Machine Learning Algorithms and Based on Manual Feature Engineering Approach -- 5.3 Research Gap -- 5.4 Objective -- 5.5 Proposed Methodology -- 5.6 Expected Outcomes -- References -- Chapter 6 Removal of Haze from Synthetic and Real Scenes Using Deep Learning and Other AI Techniques -- 6.1 Introduction -- 6.2 Formation of a Haze Model -- 6.3 Different Techniques of Single-Image Dehazing -- 6.3.1 Contrast Enhancement -- 6.3.2 Dark Channel Prior -- 6.3.3 Color Attenuation Prior -- 6.3.4 Fusion Techniques -- 6.3.5 Deep Learning -- 6.4 Results and Discussions -- 6.5 Output for Synthetic Scenes -- 6.6 Output for Real Scenes -- 6.7 Conclusions -- References -- Chapter 7 HOG and Haar Feature Extraction-Based Security System for Face Detection and Counting -- 7.1 Introduction -- 7.1.1 Need for a Better Security System -- 7.2 Literature Survey -- 7.3 Proposed Work -- 7.3.1 Tools Used -- 7.3.2 Algorithm of the Proposed System -- 7.3.2.1 HOG-Based Individual Counting -- 7.3.2.2 Haar-Based Individual Counting -- 7.3.2.3 Combination of HOG and Haar -- 7.3.2.4 AdaBoost Learning Technique -- 7.3.2.5 KLT Tracker -- 7.4 Experiments and Results -- 7.5 Conclusion and Scope of Future Work -- References -- Chapter 8 A Comparative Analysis of Different CNN Models for Spatial Domain Steganalysis -- 8.1 Introduction -- 8.2 General Framework -- 8.2.1 Dataset -- 8.2.2 Deep Learning CNN Models -- 8.2.2.1 XuNet. | |
8.2.2.2 Pretrained Networks -- 8.3 Experimental Results and Analysis -- 8.4 Conclusion and Discussion -- Acknowledgments -- References -- Chapter 9 Making Invisible Bluewater Visible Using Machine and Deep Learning Techniques-A Review -- 9.1 Introduction -- 9.1.1 Why is It Difficult to Measure Subsurface Groundwater? -- 9.1.2 What are High Level Tasks Involved in Groundwater Measurement? -- 9.2 Determination of Groundwater Potential (GWP) Parameters -- 9.2.1 Groundwater Potential (GWP) Parameters -- 9.2.2 Analysis of the Key GWP Parameters -- 9.3 GWP Determination: Methods and Techniques -- 9.4 GWP Output: Applications -- 9.5 GWP Research Gaps: Future Research Areas -- 9.6 Conclusion -- References -- Chapter 10 Fruit Leaf Classification Using Transfer Learning for Automation and Industrial Applications -- 10.1 Introduction -- 10.1.1 Overview of Fruit Leaf Classification and Its Relevance in Automation and Industrial Applications -- 10.1.2 Challenges of Building a Classification Model from Scratch -- 10.1.3 Introduction to Transfer Learning as a Solution -- 10.1.4 Overview of Popular Pre-Trained Models -- 10.1.4.1 Visual Geometry Group -- 10.1.4.2 Residual Network -- 10.1.4.3 Inception -- 10.2 Data Collection and Preprocessing -- 10.2.1 Importance of Data Collection and Preprocessing -- 10.2.2 Data Augmentation in Fruit Leaf Classification -- 10.2.3 Normalization and Resizing in Fruit Leaf Classification -- 10.3 Loading a Pre-Trained Model for Fruit Leaf Classification Using Transfer Learning -- 10.3.1 Code Examples for Implementing Transfer Learning Using TensorFlow -- 10.4 Training and Evaluation -- 10.4.1 Explanation of Training and Evaluation Process -- 10.4.2 Metrics for Measuring Model Performance -- 10.5 Applications in Automation and Industry -- 10.5.1 Benefits of Using Transfer Learning in Automation and Industrial Settings. | |
10.5.2 Case Studies of Fruit Leaf Classification in Industry Using Transfer Learning -- 10.6 Conclusion -- 10.7 Future Work -- References -- Chapter 11 Green AI: Carbon-Footprint Decoupling System -- 11.1 Introduction -- 11.2 CO2 Emissions in Sectors -- 11.3 Heating and Cooking Emissions -- 11.4 Automobile Systems Emission -- 11.5 Power Systems Emission -- 11.5.1 Map -- 11.6 Total CO2 Emission -- 11.6.1 Relationship Between Tables -- 11.6.2 Group by Clause -- 11.6.3 Offshore Wind Storage Integration Method -- 11.6.4 Offshore Floating Wind and Power Generation Technology (OFWPP) -- 11.6.5 Wind Power Plant for Storage Mixing -- 11.6.6 The Effect on the Environment when Using Battery Storage -- 11.7 Green AI With a Control Strategy of Carbon Emission -- 11.8 Green Software -- 11.9 Conclusion -- 11.10 Future Scope and Limitation -- References -- Chapter 12 Review of State-of-Art Techniques for Political Polarization from Social Media Network -- 12.1 Introduction -- 12.1.1 Social Media -- 12.2 Political Polarization -- 12.2.1 Identification of the Parties -- 12.2.2 Definition of Political Ideology -- 12.2.3 Voting Conduct (Definition) -- 12.2.4 Definition of Policy Positions -- 12.2.5 Definition of Affective Polarization -- 12.2.6 Identifiability of Parties (Definition) -- 12.2.7 Definition of Political Ideology -- 12.2.8 Definition of Voting Behavior -- 12.2.9 Policy Positions (Definition) -- 12.2.10 Party Sorting -- 12.2.11 Affective Polarization (Definition) -- 12.3 State-of-the-Art Techniques -- 12.3.1 Word Embedding (WE) -- 12.3.2 Customary Models -- 12.3.3 Models of Deep Neural Networks (DNN) -- 12.3.4 Single and Hybrid ML Techniques -- 12.3.4.1 Single Methods -- 12.3.4.2 Hybrid Approaches -- 12.3.5 Multitask Learning (V) -- 12.3.5.1 Learning-Related Problem -- 12.3.5.2 Multi-Task Learning MTL -- 12.3.5.3 Architectures for Multiple Tasks. | |
12.3.5.4 Two MTL Deep Learning Methods -- 12.3.6 Techniques for Deep Learning -- 12.4 Literature Survey -- 12.5 Conclusion -- References -- Chapter 13 Collaborative Design and Case Analysis of Mobile Shopping Apps: A Deep Learning Approach -- 13.1 Introduction -- 13.1.1 Basic Rules in Shopping App Interaction Design -- 13.1.1.1 User-Centered Design Rules -- 13.1.2 Visual Interface Consistency -- 13.2 Personalized Interaction Design Framework for Mobile Shopping -- 13.2.1 Modelized Interaction Information Framework -- 13.2.2 Interactive Design Path Analysis -- 13.2.3 Optimization Design in the Page System -- 13.3 Case Analysis -- 13.4 Conclusions -- References -- Chapter 14 Exploring the Potential of Machine Learning and Deep Learning for COVID-19 Detection -- 14.1 Introduction -- 14.2 Supervised Learning Techniques -- 14.3 Unsupervised Learning Techniques -- 14.4 Deep Learning Techniques -- 14.5 Reinforcement Learning Techniques -- 14.6 Comparison of Machine Learning and Deep Learning Techniques -- 14.7 Challenges and Limitations -- 14.8 Conclusion and Future Directions -- References -- Index -- EULA. | |
Sommario/riassunto: | This book provides state-of-the-art approaches to deep learning in areas of detection and prediction, as well as future framework development, building service systems and analytical aspects in which artificial neural networks, fuzzy logic, genetic algorithms, and hybrid mechanisms are used. Deep learning algorithms and techniques are found to be useful in various areas, such as automatic machine translation, automatic handwriting generation, visual recognition, fraud detection, and detecting developmental delays in children. "Deep Learning Techniques for Automation and Industrial Applications" presents a concise introduction to the recent advances in this field of artificial intelligence (AI). The broad-ranging discussion covers the algorithms and applications in AI, reasoning, machine learning, neural networks, reinforcement learning, and their applications in various domains like agriculture, manufacturing, and healthcare. Applying deep learning techniques or algorithms successfully in these areas requires a concerted effort, fostering integrative research between experts from diverse disciplines from data science to visualization. This book provides state-of-the-art approaches to deep learning covering detection and prediction, as well as future framework development, building service systems, and analytical aspects. For all these topics, various approaches to deep learning, such as artificial neural networks, fuzzy logic, genetic algorithms, and hybrid mechanisms, are explained. Audience The book will be useful to researchers and industry engineers working in information technology, data analytics network security, and manufacturing. Graduate and upper-level undergraduate students in advanced modeling and simulation courses will find this book very useful. |
Titolo autorizzato: | Deep Learning Techniques for Automation and Industrial Applications ![]() |
ISBN: | 1-394-23425-2 |
1-394-23427-9 | |
1-394-23426-0 | |
Formato: | Materiale a stampa ![]() |
Livello bibliografico | Monografia |
Lingua di pubblicazione: | Inglese |
Record Nr.: | 9910877827803321 |
Lo trovi qui: | Univ. Federico II |
Opac: | Controlla la disponibilità qui |