Generative Artificial Intelligence

R. Nidhya, PhD, is an assistant professor in the Department of Computer Science & Engineering, Madanapalle Institute of Technology & Science, affiliated with Jawaharlal Nehru Technical University, Anantapuram, India. She has published many research papers in international journals and her research interests include wireless body area networks, network security, and data mining. D. Pavithra, PhD, is an assistant professor at Dr. NGP Institute of Technology, Coimbatore, Tamil Nadu, India. Her current research interests include autism, machine learning, and deep learning. Manish Kumar, PhD, is an assistant professor at The School of Computer Science & Engineering, VIT, Chennai, India. His research interests include soft computing applications for bioinformatics problems and computational intelligence. A. Dinesh Kumar, PhD, is an associate professor at KL (Deemed to be University), Vijayawada, Andhra Pradesh, India. His current research interests include wireless body area networks, wireless sensor networks, network security, and artificial intelligence. S. Balamurugan, PhD, is the Director of Research and Development, Intelligent Research Consultancy Services (iRCS), Coimbatore, Tamil Nadu, India. He is also Director of the Albert Einstein Engineering and Research Labs (AEER Labs), as well as Vice-Chairman of the Renewable Energy Society of India (RESI), India. He has published 50+ books, 200+ international journals/conferences, and 35 patents.

• Preface xiii1 Exploring the Creative Frontiers: Generative AI Unveiled 1Generated Using ChatGPT1.1 Introduction 11.1.1 Definition and Significance of Generative AI 11.1.2 Historical Overview and Development 21.2 Foundational Concepts 41.2.1 Neural Networks and Generative Models 41.2.2 Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs) 51.3 Applications Across Domains 71.3.1 Creative Arts: Music, Visual Arts, Literature 71.3.2 Content Generation: Text, Images, Videos 81.3.3 Scientific Research and Data Augmentation 91.3.4 Healthcare and Drug Discovery 101.3.5 Gaming and Virtual Environments 121.4 Ethical Considerations 131.5 Future Prospects and Challenges 151.6 Conclusion 16Reference 172 An Efficient Infant Cry Detection System Using Machine Learning and Neuro Computing Algorithms 19Swarna Kuchibhotla, Kantheti Mohana, Alapati Yomitha, Sruthi Yedavalli, Hima Deepthi Vankayalapati and Kyamakya Kyandoghere2.1 Introduction 202.2 Literature Survey 212.3 Methodology 232.3.1 Database 242.3.2 Feature Extraction 252.3.2.1 Short-Term Energy 252.3.2.2 Mel-Frequency Cepstral Coefficients 262.3.2.3 Spectrograms 272.3.3 Classification 292.3.4 Convolutional Neural Network (CNN) 292.3.5 Recurrent Neural Network (RNN) 312.3.6 Regularized Discriminant Analysis (RDA) 312.3.7 Multi-Layer Perceptron (MLP) 332.4 Experimental Results 332.5 Conclusion 35References 353 Improved Brain Tumor Segmentation Utilizing a Layered CNN Model 39Bilal Hikmat Rasheed and P. Sudhakaran3.1 Introduction 403.2 Related Works 413.3 Methodology 423.4 Numerical Results 453.5 Conclusion 49References 494 Natural Language Processing in Generative Adversarial Network 53P. Dhivya, A. Karthikeyan, S. Pradeep and H. Umamaheswari4.1 Introduction 544.2 Literature Survey 574.3 The Implementation of NLP in GAN for Generating Images and Summaries 614.3.1 Working of Sequence Generative Adversarial Network (SeqGAN) 614.3.2 Working of Generative Adversarial Transformer (GAT) 634.3.2.1 Steps to Incorporate NLP in GAN 644.3.3 Implementation of NLP in GAN 654.3.4 Generate the Image Using Textual Description 684.3.5 Text Summarization 694.3.5.1 Graph-Based Summarization 714.4 Conclusion 77References 775 Modeling A Deep Learning Network Model for Medical Image Panoptic Segmentation 81Jyothsna Devi Koppagiri and Gouranga Mandal5.1 Introduction 815.2 Related Works 845.3 Methodology 855.3.1 Deep Masking Convolutional Model (DMCM) 855.4 Numerical Results and Discussion 875.5 Conclusion 91References 916 A Hybrid DenseNet Model for Dental Image Segmentation Using Modern Learning Approaches 93Pulipati Nagaraju and S. V. Sudha6.1 Introduction 946.2 Related Works 956.3 Methodology 966.3.1 Dataset 966.3.2 Dense Transformer Model 976.3.3 DenseNet Model 1006.4 Numerical Results and Discussion 1006.4.1 Discussion 1036.5 Conclusion 104References 1047 Modeling A Two-Tier Network Model for Unconstraint Video Analysis Using Deep Learning 107P. Naga Bhushanam and Selva Kumar S.7.1 Introduction 1087.2 Related Works 1097.3 Methodology 1107.4 Numerical Results and Discussion 1137.5 Conclusion 117References 1188 Detection of Peripheral Blood Smear Malarial Parasitic Microscopic Images Utilizing Convolutional Neural Network 121Tamal Kumar Kundu, Smritilekha Das and R. Nidhya8.1 Introduction 1228.2 Malaria 1248.2.1 Malaria-Infected Red Blood Cells with Types 1248.3 Literature Survey 1258.4 Proposed Methodology and Algorithm 1308.4.1 Proposed Algorithm 1358.5 Result Analysis 1358.5.1 Dataset 1358.5.2 Preprocessing of Data 1358.5.3 Splitting of Dataset 1378.5.4 Classification 1378.5.5 Model Prediction and Performance Metrics 1378.5.6 CNN Learning Curves 1388.6 Discussion 1398.7 Conclusion 1398.8 Future Scope 139References 1409 Exploring the Efficacy of Generative AI in Constructing Dynamic Predictive Models for Cybersecurity Threats: A Research Perspective 143T. Manasa and K. Padmanaban9.1 Introduction 1449.2 Related Works 1459.3 Methodology 1469.3.1 Pre-Processing 1479.3.2 Classifier 1479.3.3 Optimization 1489.4 Numerical Results and Discussion 1499.5 Conclusion 152References 15210 Poultry Disease Detection: A Comparative Analysis of CNN, SVM, and YOLO v3 Algorithms for Accurate Diagnosis 155Spoorthi Shetty and Mangala Shetty10.1 Introduction 15610.2 Literature Review 15710.3 Objectives 15810.3.1 Accurate Disease and Early Disease Identification 15810.3.2 Multi-Class Disease Identification 15810.3.3 Automation and Real-Time Disease Monitoring 15910.3.4 Better Accuracy 15910.4 Methodology 15910.4.1 Dataset 15910.4.2 Data Preprocessing 16010.4.3 Image Preprocessing 16110.4.4 Data Augmentation 16110.4.5 Extracting Region of Interest 16210.5 Results and Discussion 16510.6 Conclusion 169References 17011 Generative AI-Enhanced Deep Learning Model for Crop Type Analysis Based on Clustered Feature Vectors and Remote Sensing Imagery 173B. Bazeer Ahamed, D. Yuvaraj and Saif Saad Alnuaimi11.1 Introduction 17411.2 Related Works 17611.3 Methodology 17811.3.1 Saliency Analysis 18011.3.2 Saliency Region Analysis with Belief Networking 18111.3.3 Group Analysis 18211.3.4 Classification 18311.3.5 Parameter Setup 18311.4 Numerical Results and Discussion 18411.4.1 Dataset 18611.4.2 Classification Results and Discussions 18711.5 Conclusion 190References 19312 Cardiovascular Disease Prediction with Machine Learning: An Ensemble-Based Regressive Neighborhood Model 197Yuvaraj Duraisamy, Salar Faisal Noori and Shakir Mahoomed Abas12.1 Introduction 19712.2 Related Works 20012.3 Methodology 20012.3.1 Pre-Processing 20012.3.2 Feature Selection 20212.3.3 Classification 20212.4 Numerical Results and Discussion 20312.5 Conclusion 206References 20713 Detection of IoT Attacks Using Hybrid RNN-DBN Model 209Pavithra D., Bharathraj R., Poovizhi P., Libitharan K. and Nivetha V.13.1 Introduction 21013.2 Related Work 21213.3 Methodology 21613.3.1 Dataset Used 21613.3.2 Data Preprocessing 21713.3.3 Data Normalization 21713.3.4 Multi-Class Classification 21813.3.5 Splitting Dataset 21913.3.6 RNN-DBN 21913.4 Experiments and Results 22113.5 Conclusion and Future Scope 224References 22414 Identification of Foliar Pathologies in Apple Foliage Utilizing Advanced Deep Learning Techniques 227Tamal Kumar Kundu, Smritilekha Das and R. Nidhya14.1 Introduction 22814.2 Literature Survey 22914.2.1 Disease Detection Using Machine and Deep Learning Techniques (2015–2021) 22914.2.2 Disease Detection Using Transfer Learning (2015–2021) 23214.3 Different Diseases of Leaves 23314.4 Dataset 23614.5 Proposed Methodology 23914.6 Data Analysis 24014.7 Pre-Processing Technique 24114.8 Data Visualization 24214.9 Evolutionary Progression and Genesis of Model 24214.9.1 Evolution Model 24314.9.2 Model Performance 244References 24615 Enhancing Cloud Security Through AI-Driven Intrusion Detection Utilizing Deep Learning Methods and Autoencoder Technology 249P.V. Sivarambabu, Richa Agrawal, Arepalli Tirumala, Shaik Mahaboob Subani, Veeraswamy Parisae and S. V. L. Sowjanya Nukala15.1 Introduction 25015.2 Related Work 25115.3 Proposed Methodology 25315.3.1 DL-Based IDS for Cloud Security 25315.4 Results and Discussion 25415.4.1 Performance Analysis 25815.4.1.1 Accuracy 25915.4.1.2 Precision 26015.4.1.3 Recall 26015.4.1.4 F1 Score 26115.4.1.5 AUC-Area Under the Curve 26115.5 Conclusion 262References 26216 YouTube Comment Analysis Using LSTM Model 265Pavithra D., Poovizhi P., Rokeshkumar G., Bharathvaj T. and Mageshkumar M.16.1 Introduction 26616.2 Related Work 26616.3 Literature Survey 26716.4 Existing System 27216.5 Methodology 27316.6 Result and Discussion 27516.7 Conclusion 280References 280Index 283