Advances in AI for Financial, Cyber, and Healthcare Analytics: A Multidisciplinary Approach comprehensively explores how artificial intelligence and machine learning are reshaping decision-making, predictive modelling, and operational strategies across three critical sectors-finance, cybersecurity, and healthcare.
Across nine chapters, the book delves into the foundations of financial analytics and explores AI’s role in market prediction, fraud detection, and risk analysis.
It progresses into healthcare applications such as disease classification using ResNet, ethical implications of AI decisions, and the evolution of human-centred, edge-driven healthcare systems. In the cybersecurity domain, it addresses predictive threat modelling, smart home authentication, and biometric identification through advanced AI techniques.
Key Features:
- Unifies financial, healthcare, and cyber analytics through AI-driven solutions
- Demonstrates practical implementations with code examples and case studies
- Covers cutting-edge technologies like CNN-LSTM, attention models, and edge computing
- Addresses ethical, technical, and human-centred dimensions of AI
Table of Contents
Chapter 1 Introduction to Financial Analytics and Machine Learning- Introduction
- Performance Analysis
- Risk Management
- Forecasting and Prediction
- Optimization
- Types of Financial Data
- Time Series Data
- Transactional Data
- Macroeconomic Data
- Alternative Data
- Role of Machine Learning in Finance
- Predictive Analytics
- Risk Management
- Algorithmic Trading
- Fraud Detection
- Portfolio Optimization
- Sentiment Analysis
- Customer Experience Enhancement
- Challenges and Opportunities in Financial Data
- Challenges in Financial Data
- Data Quality and Availability
- High Dimensionality
- Non-Stationarity
- Imbalanced Data
- Overfitting
- Interpretability and Transparency
- Opportunities in Financial Data
- Alternative Data Sources
- Real-Time Analytics
- Automation and Efficiency
- Regtech
- Scalable Insights
- Collaborative Intelligence
- Conclusion
- References
- A. Aminu, Rajneesh Kumar Singh, Gaurav Kumar, Arun Prakash Agarwal and S.
- Introduction
- Human Activity
- Machine Learning Methods Used Recognition of Human Activities
- Deep Learning-Based Approaches for Human Activity Recognition
- Hybrid Deep Learning-Based Models
- Attention Mechanism-Based Deep Learning Models for Human Activity Recognition
- Conclusion
- References
- Introduction
- Literature Survey
- Proposed Implementation
- Dataset
- Image Preprocessing
- Image Segmentation
- Feature Extraction
- Classification
- Results
- Getting Rid of Black Areas in Data
- Discussion
- Conclusion
- References
- Introduction
- Fairness and Non-Discrimination
- Transparency and Explainability
- Accountability
- Privacy and Data Protection
- Safety and Security
- Human-Centric Design
- Sustainability
- Literature Review
- Methodology
- Research Design
- Data Collection
- Management of Bias in Training Data
- Data Governance and Ethics
- Bias Detection and Influence
- Role of Diverse Data
- Data Governance Practices
- Stakeholder Views on Ethical Data Usage
- Alleviating Algorithmic Bias
- Importance of Diversity in Data
- Data Governance Should Be Strong
- Ethics in Ai Development
- Recommendations for Stakeholders
- For Organizations
- Conclusion
- References
- Introduction
- Mechanism of Achieving Predictive Capabilities
- Machine Learning Algorithms
- Anomaly Detection Techniques
- Behavioral Analysis
- Threat Intelligence
- Continuous Monitoring
- Workflow for Anticipating Cyber Threats Using Ai
- Data Collection
- Sources of Data
- Data Preprocessing
- Cleaning and Normalization
- Model Selection and Training
- Anomaly Detection
- Real-Time Monitoring
- Threat Prediction
- Predictive Analytics
- Ai-Driven Systems for Handling Threats
- Techniques for Handling Known Threats
- Techniques for Handling Unknown Threats
- Conclusion
- References
- Mahesh K. Singh, G. J. Lakshmi, V. Satyanarayana and Sanjeev Kumar Introductİon
- Related Work
- Comparatİve Analysİs of Proposed Methods
- Non-Cryptographic Solutions
- Cryptographic Solutions
- Solutions Dependent on Asymmetric Keys
- Applications Not Involving the Internet of Things
- Otp Authentication
- Wi-Fi-Enabled Home Automation and Monitoring System
- Result and Discussion
- Conclusİon and Future Scope
- References
- Introduction
- Related Work
- Methodology for Biometric Resolutions
- Motion Trajectories Extraction
- Extrapolation from An Anthropometric Profile Captured
- Hmm Classifier
- Trajectory Extraction for Motion Analysis
- Result and Discussion
- Conclusion
- References
- Introduction
- The Role of Ai in Addressing Cyber Threats
- Ai-Driven Threat Detection
- Ai in Malware Analysis
- Ai for Fraud Detection and Prevention
- Biometric Security Using Ai
- Ai in Multi-Factor Authentication (Mfa)
- Ai in Vulnerability Scanning and Patch Management
- Ai in Defending Enterprise Networks
- Ai and Quantum-Resistant Security
- Cyber Resilience Through Ai-Driven Response Systems
- Ai in Building Self-Learning Cyber Defense Systems
- Challenges and Limitations of Ai in Cyber Security
- Ethical Concerns in Ai-Driven Security
- Conclusion
- References
- Subject Index
Author
- Ashwani Kumar
- Mohit Kumar
- Avinash Kumar Sharma
