AI for Software Engineering Assignments

This repository contains various assignments and projects related to AI for Software Engineering. Below is a summary of each project.

1. AI Workflow

Directory: AI_Workflow

A comprehensive guide on the AI development workflow, covering the entire lifecycle of an AI project.

• Key Topics: Problem definition, data collection & preprocessing, model development, evaluation, and deployment.
• Case Studies:
  • Crop Disease Detection: Using CNNs to detect crop diseases.
  • Patient Readmission Risk: Using XGBoost to predict hospital readmission risk.

2. AI Powered Development

Directory: AI_Powered

Explores the use of AI tools to enhance software development processes.

• Code Completion: Demonstrates using AI tools (like GitHub Copilot/Tabnine) for tasks such as sorting dictionaries.
• Automated Testing: Utilizes AI-driven testing frameworks (like Selenium/Testim.io) to automate login page testing.

3. AI Tools (Iris Classification)

Directory: AI_Tools

A classic machine learning project for classifying Iris flowers.

• Dataset: Iris dataset (Iris.csv).
• Goal: Train a model to classify iris species based on sepal and petal measurements.
• Files: iris.ipynb (Model training), iris.py.

4. Edge AI and AI-Driven IoT

Directory: Edge_AI_and_AI_Driven_IoT

Focuses on deploying AI models on edge devices and integrating AI with IoT.

• Edge AI Prototype: Trash classification model using TensorFlow Lite for edge deployment (e.g., Raspberry Pi).
• AI-Driven IoT Concept: Conceptual design of a smart agriculture system using IoT sensors and AI for crop yield prediction.

5. Automatic Diagnosis of Breast Cancer

Directory: iuss-23-24-automatic-diagnosis-breast-cancer

A machine learning project for diagnosing breast cancer.

• Dataset: Kaggle Breast Cancer Dataset (data.csv).
• Goal: Classify tumors as Malignant (M) or Benign (B) using features computed from breast mass images.
• Model: Random Forest Classifier implemented in breast_diagnosis.ipynb.

6. Sleep Disorder Prediction (ML Week 2)

Directory: ML_WEEK_2

Predicts the presence of sleep disorders (Insomnia, Sleep Apnea) based on lifestyle and health metrics.

• Dataset: Sleep Health and Lifestyle Dataset.
• Models: Support Vector Machine (SVM), Decision Tree, and Random Forest.
• Key Findings: Strong correlations found between sleep quality/duration and stress levels/heart rate.

7. MNIST Digit Classification

Directory: MNIST

Handwritten digit classification using Deep Learning.

• Dataset: MNIST dataset.
• Frameworks: PyTorch (mnist_pytorch.ipynb) and TensorFlow (mnist_tensor.ipynb).
• Goal: Train CNN models to recognize handwritten digits (0-9).