Prediction-ANN-ANFIS

Overview

This repository contains a machine learning project focused on prediction using Artificial Neural Networks (ANN) and Adaptive Neuro-Fuzzy Inference Systems (ANFIS). The project demonstrates the integration of data analysis, neural network modeling, and fuzzy logic techniques to predict results based on experimental data. This approach is commonly used in various scientific and engineering applications where data-driven predictions are necessary.

Files

• anfis_ejm.py: A custom Python library implementing the ANFIS (Adaptive Neuro-Fuzzy Inference System) model. This file contains functions for training and predicting using the ANFIS model.

• DATA.ipynb: A Jupyter Notebook that provides a detailed analysis of the project, including data loading, preprocessing, model training, and evaluation. It serves as a step-by-step guide for replicating the results and understanding the underlying methodology.

• data_isotermas.xlsx: An Excel file containing experimental data related to isotherms. This data is used to train the models and validate the predictions made by the ANFIS and ANN models.

• TrabajoFinal.pdf: A comprehensive report that documents the project, including methodology, experimental setup, results, and conclusions. This file provides a deeper understanding of the project and its implications.

Installation Requirements

To run this project, you need to have Python installed along with the following libraries:

• numpy
• pandas
• matplotlib
• scikit-learn
• anfis (Custom Python library for ANFIS)

You can install these dependencies using pip:

pip install numpy pandas matplotlib scikit-learn

Usage

Clone the Repository:

1. Start by cloning the repository to your local machine:

git clone https://github.com/fernandoflores2002/Prediction-ANN-ANFIS.git
cd Prediction-ANN-ANFIS

2. Open the Jupyter Notebook: To explore the analysis and modeling steps, open the DATA.ipynb notebook:

jupyter notebook DATA.ipynb

Run through the notebook to analyze the data, train the ANFIS and ANN models, and evaluate the results.

3. Review the Report: For a detailed explanation of the methodology, experimental setup, and results, refer to the TrabajoFinal.pdf report. This document provides an in-depth look at the predictions and conclusions drawn from the analysis.

How to Contribute

If you want to contribute to this project, feel free to fork the repository, make your changes, and submit a pull request. Suggestions for improvements are always welcome!

License

This project is licensed under the MIT License. See the LICENSE file for details.

Contact

For any questions or suggestions, please reach out to:

Cesar Fernando Flores Bautista [email protected]