Welcome to the Engineering Company Machine Learning Projects repository! This repository contains two distinct projects related to machine learning, each housed within its respective folder.
Inside the robot folder, you'll find a machine learning project focused on identifying anomalies in the behavior of robots. This project utilizes unsupervised learning techniques to detect whether a robot is functioning correctly or exhibiting abnormal behavior.
- Code Resolution: The Jupyter Notebook file (
Final_report.ipynb) contains the code implementation for the anomaly detection model. - Solution Explanation: The PDF document (
Robot.pdf) provides a detailed explanation of the solution approach, methodology, and findings.
The nilm folder contains a machine learning project aimed at resolving the Non-Intrusive Load Monitoring (NILM) problem using supervised learning techniques. NILM involves disaggregating the total electricity consumption of a building into individual appliances without the need for intrusive sensors.
- Code Resolution: The Jupyter Notebook file (
NILM.ipynb) contains the code implementation for the NILM problem solution. - Solution Explanation: The PDF document (
Non Intrusive Load Monitoring (NILM).pdf) offers a comprehensive explanation of the solution strategy, algorithms employed, and results obtained.
Feel free to explore each project folder to delve into the code implementations and solution explanations provided. You can run the Jupyter Notebooks locally on your machine to reproduce the results or further customize the models as needed.
If you have any feedback, suggestions, or improvements regarding these projects, we welcome your contributions! Feel free to open issues or pull requests, and our team will review them promptly.
Thank you for your interest in the Engineering Company Machine Learning Projects. We hope you find the contents of this repository insightful and valuable for your machine learning endeavors. Happy coding!