| Description |
1 online resource (xv, 356 pages) : illustrations (chiefly color) |
| Series |
Intelligent systems reference library, 1868-4408 ; volume 231 |
|
Intelligent systems reference library ; v. 231.
|
| Contents |
Intro -- Preface -- Contents -- Part I Crime and Security -- 1 Artificial Intelligence for Cybersecurity: Threats, Attacks and Mitigation -- 1.1 Introduction -- 1.2 Cybersecurity -- 1.2.1 Attacks -- 1.2.2 Threats -- 1.2.3 AI as a Tool for Cyber-Attacks -- 1.3 Conventional Solutions -- 1.4 Intervention of AI -- 1.4.1 Recent Trends -- 1.4.2 AI Based Mitigation of Cyberthreats -- 1.5 Conclusion -- References -- 2 A Survey on Deep Learning Models to Detect Hate Speech and Bullying in Social Media -- 2.1 Introduction -- 2.2 Methodology -- 2.2.1 Convolution-Based Methods -- 2.2.2 Sequential Deep Learning Based Methods -- 2.2.3 Transformer-Based Methods -- 2.3 Conclusion -- References -- 3 A Deep Learning Based System to Estimate Crowd and Detect Violence in Videos -- 3.1 Introduction -- 3.2 Related Work -- 3.3 Methodology -- 3.3.1 Crowd Estimation -- 3.3.2 Violence Detection -- 3.4 Implementation -- 3.5 Results and Analysis -- 3.6 Future Enhancement -- 3.7 Conclusion -- References -- 4 Role of ML and DL in Detecting Fraudulent Transactions -- 4.1 Introduction -- 4.1.1 Introduction to Fraudulent Transaction -- 4.1.2 Influence of Online Banking on Fraudulent Transaction -- 4.1.3 Statistics of Fraudulent Transactions -- 4.1.4 Current Preventive Systems -- 4.1.5 Introduction to Artificial Intelligence -- 4.1.6 Introduction to Deep Learning -- 4.2 Different Detection Systems for Fraud -- 4.2.1 Hidden Markov Model -- 4.2.2 Artificial Neural Network (ANN) -- 4.2.3 Autoencoder -- 4.2.4 Convolutional Neural Network -- 4.2.5 Rule-Based Method -- 4.2.6 Generative Adversarial Network -- 4.3 Future Scope -- 4.4 Conclusion -- References -- Part II Agriculture and Education -- 5 Employing Image Processing and Deep Learning in Gradation and Classification of Paddy Grain -- 5.1 Introduction: State of Agriculture Sector in India |
|
5.1.1 Problems and Challenges Faced by the Agriculture Segment of India -- 5.1.2 Problem Statement and Paper Organization -- 5.2 Background: The Role of Artificial Intelligence in Agriculture Sector -- 5.2.1 Usability of Artificial Intelligence and Machine Learning in Agriculture -- 5.3 Literature Review -- 5.4 Proposed Approach: Image Processing -- 5.4.1 Involved Steps -- 5.4.2 Materials and Tools -- 5.5 Methodology and Implementation -- 5.5.1 Plan and Proposed Architecture -- 5.5.2 The CNN Architecture -- 5.5.3 Implementation -- 5.5.4 GUI Creation and Testing -- 5.6 Results and Discussion -- 5.7 Future Work -- 5.8 Conclusion -- References -- 6 Role of Brand Love in Green Purchase Intention: Analytical Study from User's Perspective -- 6.1 Introduction -- 6.1.1 Green Purchase Intention -- 6.1.2 Brand Love -- 6.1.3 Significance and Scope of Study -- 6.2 Review of Literature -- 6.3 Research Methodology -- 6.3.1 Research Model -- 6.3.2 Description of Variables -- 6.3.3 Research Questions -- 6.3.4 Hypothesis -- 6.4 Results and Discussion -- 6.4.1 Structural Equation Model -- 6.4.2 Multi-group Analysis -- 6.4.3 C. Variances -- 6.5 Findings -- 6.6 Suggestions -- 6.7 Conclusion -- 6.8 Questionnaire -- References -- 7 Effect of Online Review Rating on Purchase Intention -- 7.1 Introduction -- 7.1.1 Role of Review Rating in Social Media -- 7.1.2 Effect of Review Rating on Purchase Intention -- 7.1.3 Objective of the Study -- 7.2 Literature Review -- 7.2.1 Review Rating on Purchase Intention -- 7.3 Methodology -- 7.4 Analysis and Interpretation -- 7.5 Results and Discussion -- 7.6 Conclusion -- References -- 8 Artificial Intelligence: Paving the Way to a Smarter Education System -- 8.1 Introduction -- 8.2 Education and Its Many Challenges -- 8.2.1 Rising Cost of Education Worldwide -- 8.2.2 Reaching the Less Privileged and Promoting Women's Education |
|
8.2.3 Addressing Different Learning Needs -- 8.2.4 Learning Needs of the Differently-Abled -- 8.2.5 Setting High Standards and Maintaining Quality of Education -- 8.2.6 Overcoming the Age-Old Problem of Rote Learning -- 8.2.7 The Ever-Increasing Burden on the Education System -- 8.3 The Role of Technology in Transforming the Education Sector -- 8.3.1 Massive Open Online Courses (MOOC) -- 8.3.2 Virtual Reality (VR) in Education -- 8.3.3 Augmented Reality (AR) for Immersive Learning -- 8.3.4 Artificial Intelligence (AI) in Education -- 8.4 Leveraging AI for Transforming the EdTech Space -- 8.4.1 Benefits of AI for Students -- 8.4.2 Benefits for Educators -- 8.4.3 Benefits for Management and Administrators of Education Institutes -- 8.5 Assessing Tech Readiness to Embrace AI Using the SAMR Model -- 8.6 The Challenges and Limitations of AI in Education -- 8.7 Top AI Solutions Their Key Features, and Benefits -- 8.8 Conclusion -- References -- Part III Emotion and Mental Health -- 9 Using Deep Learning to Recognize Emotions Through Speech Analysis -- 9.1 Introduction -- 9.2 Related Works -- 9.3 Proposed Methodology -- 9.3.1 Mel-Frequency Cepstral Coefficients -- 9.3.2 Prediction Models Using Neural Networks -- 9.3.3 Performance Metrics -- 9.4 Experimental Result -- 9.4.1 Dataset Preparation -- 9.4.2 MFCC Extraction -- 9.4.3 Training of Neural Network Model -- 9.4.4 Prediction Using Model -- 9.5 Discussion -- 9.5.1 Performance Comparison of CNN and LSTM on Two Emotions -- 9.5.2 Performance Comparison of CNN and LSTM on Four Emotions -- 9.6 Conclusion -- References -- 10 Face Emotion Detection for Autism Children Using Convolutional Neural Network Algorithms -- 10.1 Introduction -- 10.2 Literature Survey -- 10.3 Background of the Research -- 10.3.1 Existing Classifier -- 10.3.2 Multi-model System -- 10.4 Proposed Emotion Detection Model |
|
10.4.1 Face Detection -- 10.4.2 Face Cropping -- 10.4.3 Pre-processing and Data Augmentation -- 10.4.4 Convolution Neural Network-Based Emotion Detection -- 10.5 Results and Discussion -- 10.5.1 Evaluation Metrics -- 10.5.2 Comparative Analysis -- 10.5.3 Comparative Analysis with Other Classifiers -- 10.6 Conclusion -- References -- 11 Prevention of Global Mental Health Crisis with Transformer Neural Networks -- 11.1 Introduction -- 11.2 Background -- 11.2.1 Motivation -- 11.2.2 From an Invisible Problem to a Global Crisis -- 11.2.3 Can COVID-19 Pandemic Seed a Global Mental Health Crisis? -- 11.2.4 Call for Action by Editorials and Experts -- 11.2.5 Dimensions of the Global Crisis in Mental Health -- 11.3 Design of Deep Learning Solution for Mental Health -- 11.3.1 Key Ideas in Deep Learning for Mental Health -- 11.3.2 Landscape -- 11.3.3 Design of AI Solution to Avert the Global Mental Heath Crisis -- 11.3.4 Design of AI to Improve Thinking Patterns: Views of Self/Future -- 11.3.5 Detailed Design -- 11.4 Mental Health Screening at Scale -- 11.4.1 Approaches for Pandemic Scale Screening -- 11.4.2 Deep Learning in Mental Health Screening -- 11.5 Mental Health Diagnosis and Resilience Detection -- 11.5.1 Modelling of Neuroplasticity/Resilience Using Deep Learning -- 11.5.2 Diagnosis with Multimodal Deep Learning -- 11.5.3 Modelling of Cognitive Behavior: View of Self and Future -- 11.6 Cognitive Therapy -- 11.6.1 Reinforcement Learning and GPT-n for Therapy Conversations -- 11.6.2 Privacy Safe On-device ML, Distillation Versus Few Shot Learning -- 11.7 Future Directions: AI Architecture for Mental Health -- 11.7.1 Triad-Therapy Using Multimodal Encoder-Decoder Modelling -- 11.7.2 Addressing Needs of Countries with NLP Beyond English Language -- 11.7.3 Implications of Findings and Scope for Future Work -- 11.8 Conclusion -- References |
|
12 Diagnosis of Mental Illness Using Deep Learning: A Survey -- 12.1 Introduction -- 12.2 Concept of ML and DL -- 12.3 Deep Learning in Mental Health -- 12.3.1 Concept of Bioinformatics in Deep Learning -- 12.4 Mental Health Disorders -- 12.4.1 Anxiety Disorders -- 12.4.2 Mood Disorders -- 12.4.3 Psychotic Disorders -- 12.4.4 Dementia -- 12.5 Diagnosis Using Deep Learning -- 12.6 Challenges and Future Scope -- 12.7 Conclusion -- References -- Part IV Healthcare Informatics and Management -- 13 Skin Disease Detection and Classification Using Deep Learning: An Approach to Automate the System of Dermographism for Society -- 13.1 Introduction -- 13.2 Background -- 13.2.1 Skin Disease Nature -- 13.2.2 Data Set Description -- 13.3 Literature Review -- 13.4 Proposed Method -- 13.4.1 Data Pre-processing -- 13.4.2 Performance Metrics -- 13.4.3 Implementation -- 13.5 Results and Discussion -- 13.6 Conclusions and Future Scope -- References -- 14 A Deep Learning Techniques for Brain Tumor Severity Level (K-CNN-BTSL) Using MRI Images -- 14.1 Introduction -- 14.2 Related Work -- 14.3 Problem Statement -- 14.4 Proposed Work: K-CNN-BTSL (Brain Tumor Severity Level) -- 14.4.1 Preprocessing -- 14.4.2 Image Segmentation -- 14.4.3 Feature Extraction -- 14.5 K-CNN-BTSL -- 14.6 Results and Discussion -- 14.6.1 Testing with Benign Input -- 14.6.2 Testing with MALIGNANT Input -- 14.7 Conclusion -- References -- 15 COVID-19 Detection in X-Rays Using Image Processing CNN Algorithm -- 15.1 Introduction -- 15.2 Method and Materials -- 15.2.1 About X-Rays Dataset -- 15.2.2 CNN Architecture -- 15.2.3 Basic Requirement -- 15.3 Methodology -- 15.4 Experimental Analysis -- 15.5 Discussion -- 15.5.1 Some Issues Handled by Deep Learning -- 15.5.2 Advantage of the Proposed Model -- 15.6 Conclusion and Future Direction -- References |
| Summary |
Artificial intelligence (AI) has the potential to provide innovative solutions to various societal issues and real-world social challenges. AI is useful in combating some of the seemingly unsolvable social crises facing the world today. Be it disaster awareness and management or demand forecasting, or healthcare informatics or disease outbreaks like COVID-19, the AI plays a pivotal role everywhere. AI has the potential to address some of the societal issues that indirectly pose challenges like cybercrime, agriculture, education, economy, and health. The book covers several applications of AI as solutions to different societal issues, which include economic empowerment, smart education system, COVID-19 detection & management, emotion detection, fraudulent transactions, applications in agriculture and health informatics, etc. The book will be helpful for the academicians and researchers working with various areas of societal issues, data science, artificial intelligence, and machine learning.-- Provided by publisher |
| Bibliography |
Includes bibliographical references |
| Notes |
Anupam Biswas, Department of Computer Science and Engineering, National Institute Of Technology Silchar, Cachar, India. Vijay Bhaskar Semwal, National Institute of Technology Bhopal, Bhopal, India. Durgesh Singh, Department of Computer Science, PDPM, Indian Institute of Information Technology, Jabalpur, India |
|
Print version record |
| Subject |
Artificial intelligence -- Social aspects
|
|
Computers and civilization.
|
|
Social problems -- Data processing
|
|
Artificial intelligence -- Social aspects
|
|
Computers and civilization
|
| Form |
Electronic book
|
| Author |
Biswas, Anupam, editor.
|
|
Semwal, Vijay Bhaskar, editor
|
|
Singh, Durgesh, editor
|
| ISBN |
9783031124198 |
|
3031124197 |
|
