We have great pleasure in presenting First edition “Applications of Artificial Intelligence” written for students of UG courses. The related matters are written in a simple and easily understandable.
This volume is an attempt to pro vide the students with thorough understanding of Applications of Artificial Intelligence. We have presented the subject matter in a systematic manner with liberal use of charts and diagrams where ever necessary so as to make it interesting and sustain students’ interest.
Contents –
Unit – 1 Infrastructure and Platforms for Building Applications using AI
Hardware used in Building AI Applications: Processors, CPU, GPU, TPU, NPU, Memory, RAM, VRAM, Storage, HDD, SSD Platforms for Building Applications using AI: Online Platforms (Example: Google AutoML, H2O.ai, Teachable Machine or Similar Platforms – for practice only), Desktop (No-code/Lowcode) Platforms (Orange Data Mining, KNIME, Weka, RapidMiner or similar tools – for practice only).
Edge AI: Concept, Applications in Daily Life in Devices Like Refrigerators, Led Bulbs, Surveillance Cameras, Micro Ovens, Smart Cars/Scooters, Edge AI in Smart Appliances.
Unit – 2 Foundations of Data
Foundations of Data, Types, Ethics and Utility in Building Applications using AI Importance of Data in Building AI Applications: Data as the Fuel for AI, Role of Big Data in Training AI Models.
Conceptual Foundations of Data: Data vs. Information vs. Knowledge.
Structure of Data: Structured, Semi-Structured, and Unstructured Data.
Modalities of Data: Text, Image, Audio, Video, Tabular, Time-Series, and Spatial Data. Formats of Data: Text Formats (CSV, JSON, XML), Image Formats (JPEG, GIF, PNG), Audio/Video (MP3, WAV, MP4, AVI).
Data Repositories: Definition of Public Datasets; Definition of Private Datasets, Importance of Public Datasets, Popular Public Dataset Repositories (Example – Kaggle, Hugging Face Datasets, UCI Machine Learning Repository, Google Dataset Search or similar ones – for demonstration only), Dataset Licensing and usage Rights.
Ethics, Privacy in Data Usage: Privacy Concerns Related to Data usage, Regulations Governing Data usage, GDPR, HIPAA (Overview), Ethical use of Data, Responsible AI Data Practices.
Unit – 3 The AI Data Pipeline: From Collection to Model Readiness
The AI Data Pipeline: Stages and Components: Key Stages (Data Collection, Annotation, Preprocessing, Splitting, Feeding into AI Models.
Core Components: Ingestion, Storage, Processing, Validation, Delivery.
Data Collection Methods for AI: Manual Input (Surveys, forms, human-curated entries), Sensors & IoT Devices (Realtime data from physical environments), System Logs & Transactions, Web Scraping (Automated extraction from websites), APIs (Structured data access from external platforms).
Data Annotation and Labelling: Definition & Importance, Annotation Methods: Manual Annotation, Automated Annotation, Types of Annotation: Classification, Bounding Boxes, Segmentation, Transcription, Named Entity Recognition (NER)
Data Cleaning and Preprocessing: Importance of Data Cleaning, Understanding “Dirty” Data: Missing Values, Duplicates, Incorrect Formats, Outliers, Noise, Steps in Data Cleaning: Identify Issues, Handle Errors (Imputation, Removal), Validate Cleaned Data
Data Splitting: Splitting Data into Training Set and Test Set. Data Transformation Techniques: Normalization, Transformation, Feature Engineering.
Unit – 4 AI in Commerce – Transforming the Consumer Experience
Introduction to AI in Commerce, Recommendation Engines (Collaborative & Content-Based), Chatbots and Virtual Assistants, Sentiment Analysis and Review Mining, Inventory Optimization and Demand Forecasting, Ethical Issues related to use of AI in Commerce and Business: Bias, Privacy, and Transparency.
Unit – 5 AI in Business Operations – Driving Efficiency and Insight
AI in Business Intelligence and Predictive Analytics, Financial Applications: Fraud Detection, Risk Modelling, HR Applications: Resume Screening, Employee Analytics, Supply Chain Automation and Optimization, AI in Marketing: Customer Segmentation, Lead Scoring, Strategic Adoption of AI in Enterprises, Explainable AI in E-Commerce.
