AI and Machine Learning Projects

This repository showcases a collection of projects and solutions in the fields of artificial intelligence and machine learning. It serves as a hub for various models, algorithms, and applications demonstrating core concepts and practical implementations.

Contents

1. Hidden Markov Coin Analysis
   Description: Implementation of a Hidden Markov Model (HMM) to analyze sequences of coin toss outcomes and determine the most likely sequence of coin choices.
   Key Features:

   • Transition and emission probability matrices for state analysis.
   • Computation of the most likely sequence of states using HMM principles.
   • Probability calculation for observation sequences.
     Folder: HiddenMarkovModel-CoinAnalysis

2. Image Segmentation for LTE and 5G Classification
   Description: Instance segmentation project using U-Net to classify LTE and 5G signals from images.
   Key Features:

   • U-Net architecture for image segmentation.
   • Segmentation of LTE, 5G, and noise regions in images.
   • Demonstrates deep learning applications in telecommunication-related tasks.
     Folder: Image-Segmentation-4G-5G

3. Global Terrorism Analysis
   Description: Analysis of global terrorism trends using datasets spanning 1970 to 2016.
   Key Features:

   • Visualizations of year-wise and region-wise terrorism data.
   • Analysis of terrorism trends in Ireland.
   • Interactive maps showing clustering of casualties.
     Folder: Global-Terrorism-Analysis

4. Speed Dating Analysis
   Description: Predictive analysis and visualization of speed dating outcomes based on participant attributes.
   Key Features:

   • Predictive modeling of likeability and dating preferences.
   • Relationship analysis between self-reported and partner-rated attributes.
   • Visualizations of participant attributes and outcomes.
     Folder: Speed-Dating-Analysis

5. N Puzzle Astar IDAstar Solver
   Description: Implementation of a sliding puzzle solver using A* and IDA* algorithms.
   Key Features:

   • Solves N x N sliding puzzles using heuristic search algorithms.
   • Implements Manhattan distance heuristic for A* and IDA* algorithms.
   • Checks for puzzle solvability before attempting a solution.
     Folder: N-Puzzle-Astar-IDAstar-Solver

6. Reinforcement Learning: Grid World Simulation
   Description: Simulation of a grid world for reinforcement learning using Q-Learning and Value Iteration.
   Key Features:

   • Supports Q-Learning and Value Iteration for agent decision-making.
   • Incorporates obstacles, pitfalls, and goal states with respective rewards and penalties.
   • Generates an optimal policy mapping each grid cell to an action.
     Folder: Reinforcement-Learning-Grid-World

Usage

Clone the repository:

git clone https://github.com/your-username/AI-and-ML.git
cd AI-and-ML