Predictive Methods in Next-Generation Computing : An Approach Toward Sustainability

• Autore: Sathiyaraj R
• Pubblicazione: Newark : , : John Wiley & Sons, Incorporated, , 2025; ©2025
• Edizione: 1st ed.
• Descrizione fisica: 1 online resource (341 pages)
• Disciplina: 004.678
• Soggetto topico: Predictive analytics
• Altri autori: SathiyarajR DhanarajRajesh Kumar KumarK. Arun JhaveriRutvij H AbbasA. Mohamed
• Nota di contenuto: Cover -- Series Page -- Title Page -- Copyright Page -- Contents -- Preface -- Chapter 1 Introduction to Intelligent Computational Technologies -- 1.1 Introduction -- 1.2 Literature Survey -- 1.3 Methodology -- 1.4 Simulation Metrics -- 1.4.1 Identification of E-Governance Adoption and Assessment Factors -- 1.4.2 Sample Data Collection Using Questionnaire -- 1.4.3 Respondent Details -- 1.4.4 Fuzzy Conjoint Model -- 1.4.4.1 Calculation of Weight for Each Respondent -- 1.4.4.2 Calculating the Similarity Degree -- 1.5 Computation -- 1.5.1 Computation of Fuzzy Vector of Responses -- 1.5.2 Computation of Similarity Degree -- 1.5.3 Result Analysis -- 1.5.4 Validation -- 1.5.5 Limitations and Future Study -- 1.6 Summary -- Bibliography -- Chapter 2 Design of Smart and Sustainable Applications Using Intelligent Computational Techniques -- 2.1 Introduction -- 2.2 Background -- 2.2.1 Adoption Models and Theories -- 2.3 Methodology -- 2.3.1 Simulation Metrics -- 2.3.2 Identification of E-Governance Adoption and Assessment Factors -- 2.3.3 Sample Data Collection Using Questionnaire -- 2.3.4 Respondent Details -- 2.3.5 Fuzzy Conjoint Model -- 2.3.5.1 Calculating the Similarity Degree -- 2.4 Result Analysis -- 2.5 Conclusion -- References -- Chapter 3 Intelligent Predictive Analysis for Sustainable Global Development -- 3.1 Introduction -- 3.2 Literature Survey -- 3.2.1 Concepts of ANN -- 3.3 Proposed Work -- 3.3.1 Layout of a Neural Network -- 3.3.2 Neural Network Structure -- 3.3.3 Back-Propagation Neural Network -- 3.3.4 SVM -- 3.3.5 Learning Sequence of NN -- 3.3.6 Forage Progressive Network -- 3.3.7 Neural Network Learning -- 3.3.8 Model Somatic Cell -- 3.3.9 Fabricated Visual Structure -- 3.3.10 Neuron Weight Adjustment -- 3.4 Results and Discussion -- 3.4.1 Normalization of Knowledge -- 3.4.2 Testing and Validation -- 3.4.3 Error Measures. ; 3.4.4 Prediction Analysis -- 3.4.5 Overall Prediction Analysis -- 3.4.6 Actual and Predicted Value Analysis -- 3.4.7 Overall Actual and Predicted Value Analysis -- 3.5 Summary -- References -- Chapter 4 Intelligent Transport System and Traffic Management Frameworks -- 4.1 Introduction -- 4.2 Background Study -- 4.3 Methodology -- 4.3.1 Segmentation-Fuzzy Clustering -- 4.3.2 Fuzzy Clustering -- 4.4 Artificial Neural Network (ANN) -- 4.5 Proposed Methodology -- 4.5.1 Detection and Extraction of Traffic Sign -- 4.5.1.1 Image Extraction and Pre-Processing Using YCbCr -- 4.5.1.2 Active Appearance Model (AAM) -- 4.5.1.3 Extracting the Region of Interest -- 4.5.1.4 Edge Detection Using Sobel Operator -- 4.5.1.5 Segmentation Using Adaptive Fuzzy Clustering -- 4.5.1.6 Tracking the Detected Sign -- 4.5.2 Recognition of Traffic Sign -- 4.5.2.1 MTANN Training Model for Classification -- 4.5.2.2 Multiple MTANN Training Models -- 4.5.2.3 MTANN Classification -- 4.6 Results and Discussion -- 4.6.1 LiU Traffic Sign Database -- 4.6.2 Investigations of Various Classification Techniques -- 4.7 Summary -- References -- Chapter 5 Internet of Things in Smart and Secure Applications Development-Based Sustainability -- 5.1 Introduction -- 5.2 Literature Survey -- 5.3 Methodology -- 5.3.1 Module for the Database -- 5.3.2 Information Preparation Section -- 5.3.3 Database Module -- 5.3.4 Data Preprocessing Module -- 5.3.5 Optimal Feature Selection Module -- 5.3.6 Classification Module -- 5.4 Generative Adversarial Network -- 5.5 Datasets Used in This Work -- 5.5.1 NSL-KDD Dataset -- 5.5.2 CIC-DDoS Dataset -- 5.6 Performance Measures Used for Evaluation -- 5.7 Conclusion -- References -- Chapter 6 Modern Application for Smart Applications in Traffic Management -- 6.1 Introduction -- 6.2 Related Work -- 6.3 Delimited Spaces: Proposed Method -- 6.3.1 Bag of Features (BoF). ; 6.4 Implementation Details -- 6.4.1 Datasets -- 6.4.2 Experiment 2: Original and Split Dictionaries -- 6.4.3 Experiment 3: Feature Fusion -- 6.4.4 Results: Delimited Spaces -- 6.5 Non-Delimited Spaces: Proposed Method -- 6.5.1 Background Subtraction for Hypothesis Generation -- 6.5.2 Results: Non-Delimited Spaces -- 6.6 Conclusion -- References -- Chapter 7 Artificial Intelligence and Deep Learning in Healthcare: Evaluation, Opportunities, Challenges and Future Prospects Technologies in Healthcare Systems -- 7.1 Introduction -- 7.1.1 Artificial Intelligence -- 7.1.2 Deep Intelligence -- 7.2 Applications of AI and Deep Learning in Healthcare -- 7.2.1 Medical Imaging -- 7.2.2 Personalized Medicine -- 7.2.3 Precision Diagnostics -- 7.2.4 Predictive Analytics -- 7.2.5 Drug Discovery -- 7.2.6 Drug Development -- 7.2.7 Remote Patient Monitoring -- 7.2.8 Electronic Health Records -- 7.3 Development of Deep Learning and Artificial Intelligence in Healthcare Sector -- 7.4 Analytics of Healthcare Data Through AI And DL -- 7.4.1 Machine Learning Models -- 7.4.1.1 Supervised Learning -- 7.4.1.2 Unsupervised Learning -- 7.4.2 Reinforcement Learning -- 7.4.3 Natural Language Processing (NLP) -- 7.4.4 Machine Vision -- 7.4.5 Data Mining -- 7.4.6 Artificial Neural Networks -- 7.4.7 Fuzzy Logic -- 7.4.8 Expert System -- 7.5 Deep Learning Models -- 7.5.1 Convolutional Neural Networks (CNNs) -- 7.5.2 Network Based on Long Short-Term Memory (LSTM) -- 7.5.3 Recurrent Neural Networks (RNNs) -- 7.5.4 Generative Adversarial Network (GANs) -- 7.5.5 Radial Basis Function Networks (RBFNs) -- 7.5.6 Multilayer Perceptrons (MLPs) -- 7.5.7 Self-Organizing Maps (SOMs) -- 7.6 Potential of AI and Deep Learning Models in Healthcare -- 7.7 The Rise of AI and DL in Drug Discovery -- 7.8 Application of AI in Drug Discovery -- 7.9 Challenges of AI And DL Models. ; 7.10 Future Vision in Developing Rural Health -- 7.10.1 Telemedicine -- 7.10.2 Disease Prediction and Prevention -- 7.10.3 Resource Allocation -- 7.10.4 Personalized Medicine -- 7.11 Conclusion -- References -- Chapter 8 Heart CAP: Heart Disease Classification: Autoencoders and Principal Components -- 8.1 Introduction -- 8.2 Related Study -- 8.3 Model Architecture -- 8.3.1 Cleveland Heart Disease Dataset -- 8.3.2 Data Preparation -- 8.3.3 Feature Scaling -- 8.3.4 Dimensionality Reduction Techniques -- 8.3.4.1 Principal Component Analysis (PCA) -- 8.3.4.2 Autoencoder Architecture -- 8.4 Results -- 8.4.1 Classification Performance -- 8.4.2 Analysis of Principal Component and Feature Coefficients -- 8.4.3 Analysis of Autoencoder Features -- 8.4.4 Analysis of Receiver Operating Characteristics -- 8.5 Conclusion -- References -- Chapter 9 Application of Intelligent Computational Techniques in the Development of Smart Cities -- 9.1 Introduction -- 9.1.1 Organization of the Chapter -- 9.2 Motivation and Justification -- 9.3 Iris Recognition System -- 9.4 Algorithm for Iris Recognition System -- 9.5 Block Diagram of Iris Recognition System -- 9.5.1 Edge Detection -- 9.5.2 Variance -- 9.5.3 Support Vector Machine -- 9.6 Performance Analysis of Various Biometric Method -- 9.6.1 Performance Evaluation -- 9.6.1.1 False Acceptance Ratio (FAR) -- 9.6.1.2 False Rejection Ratio (FRR) -- 9.6.2 Result and Discussion -- 9.7 Summary -- Bibliography -- Chapter 10 Security and Privacy Issues in Data Processing with Predictive Models -- 10.1 Introduction -- 10.2 Literature Survey -- 10.3 System Model -- 10.3.1 Cryptic Framework -- 10.3.2 Prediction Framework -- 10.4 System Algorithm -- 10.5 Results and Discussion -- 10.5.1 Examining the Security Model's Performance -- 10.5.2 Duration of Key Generation -- 10.5.3 Performance Analysis of Prediction Model. ; 10.5.3.1 Description of the Dataset -- 10.5.4 Performance Metrics -- 10.5.4.1 Sensitivity -- 10.5.4.2 Specificity -- 10.5.4.3 F-Measure -- 10.5.4.4 Diabetes Prediction -- 10.6 Summary of Contributions -- References -- Chapter 11 SmartMed: A Blockchain-Based Intelligent System for Managing Patient Data -- 11.1 Introduction -- 11.1.1 The Need for the Digitization of Medical Records -- 11.1.2 What is Blockchain? -- 11.1.3 How to Use Blockchain to Digitize Medical Records -- 11.2 Literature Survey -- 11.2.1 State-of-the-Art -- 11.2.2 Research Gap -- 11.3 SmartMed: Proposed System -- 11.4 SmartMed: Model Implementation -- 11.4.1 Software Requirements -- 11.4.2 User Registration -- 11.4.3 Login -- 11.4.4 Upload Records -- 11.4.5 View Records -- 11.4.6 Grant/Revoke Permissions -- 11.4.7 Encryption of Medical Records -- 11.4.8 Need for Encryption -- 11.4.9 Symmetric vs. Asymmetric Encryption -- 11.5 Result Analysis Using Hybrid Model -- 11.5.1 Scenario 1: Patient Uploads a Record -- 11.5.2 Scenario 2: Patient Views the Uploaded Record -- 11.5.3 Scenario 3: Patient Grants Access to His/Her Records to a Doctor -- 11.5.4 Scenario 4: Patient Revokes Access to His/Her Records from a Doctor -- 11.5.5 Scenario 5: Doctor Views the Patient Record -- 11.5.6 Scenario 6: Doctor Uploads a Record for the Patient -- 11.6 SmartMed: Performance Evaluation -- 11.6.1 Latency/Delay -- 11.6.2 Resource Utilization -- 11.7 Conclusion and Perspective -- References -- Chapter 12 Trinity: A Blockchain-Based Stablecoin Lending Protocol Using Decentralized Credit Default Swaps -- 12.1 Introduction -- 12.1.1 Background and Related Work -- 12.2 Motivation and Problem Statement -- 12.3 Methodology -- 12.3.1 Option Fees Exchanged Among the Participants -- 12.4 Discussions -- 12.4.1 Stakeholders in Protocol -- 12.4.2 Tokens in Protocol -- 12.4.3 Components of the Protocol. ; 12.4.4 Option Price Calculation.
• Sommario/riassunto: Predictive Methods in Next-Generation Computing is essential for anyone looking to understand how next-generation computing technologies are driving predictive models to create smarter, safer, and more sustainable solutions across diverse fields.
• Titolo autorizzato: Predictive Methods in Next-Generation Computing
• ISBN: 1-394-24882-2; 1-394-24881-4; 9781394248810
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9911069824303321
• Lo trovi qui: Univ. Federico II