Plant Health Monitoring System - Lab Codes
This repository consists of three distinct laboratory exercises—lab_1, lab_2, and lab_3—each designed to focus on different aspects of programming: system diagnostics, regression analysis, and genetic algorithms. Below are detailed descriptions and instructions for each lab.
Lab 1: Gardening System Diagnostics
Description: Lab_1 features a Python script aimed at diagnosing plant health issues based on symptoms such as yellow leaves, brown tips, wilting, spots on leaves, and stunted growth. The script uses a series of diagnostic rules to simulate a gardening advisory system, helping users to understand potential plant health problems based on visual cues.
How to Run:
To execute the diagnostics, navigate to the src directory and run the gardening system script using Python. This script does not require any external libraries, making it easy to run with a basic Python setup.
Requirements:
- Python 3.8 or later
Lab 2: Linear Regression via Gradient Descent
Description: Lab_2 demonstrates a basic implementation of linear regression using gradient descent. It includes a script that generates random data points, applies linear regression to predict outcomes, and visually represents these predictions along with the regression line using a scatter plot. This exercise is perfect for understanding the fundamentals of machine learning in data prediction.
How to Run:
Navigate to the src directory and run the linear regression script. This script will produce a graphical output showing the data points and the fitted line, highlighting the regression model's accuracy and performance.
Requirements:
- Python 3.8 or later
- NumPy
- Matplotlib
Lab 3: Genetic Algorithm for Optimization
Description: In lab_3, a genetic algorithm is employed to optimize a mathematical function over a series of constraints. The script iteratively enhances a population of solutions using fitness assessments, crossover, and mutation techniques. This lab is an excellent demonstration of evolutionary algorithms used for solving optimization problems in complex scenarios.
How to Run:
To run the genetic algorithm simulation, execute the corresponding script in the src directory. The output will detail each generation's best fitness and the global best solution found during the simulation.
Requirements:
- Python 3.8 or later
Each lab is designed to provide hands-on experience with practical applications in programming, data analysis, and algorithmic optimization. These labs are not only educational but also lay the groundwork for more advanced exploration in each topic.