Sine wave signal denoising using Convolutionauto-encoders

[spandana2004]

Pull Request for DL-Simplified 💡

Issue Title: Denoising a simple sine wave using Convolutional Autoencoders

• Info about the related issue (Aim of the project): The goal of this project is to denoise a simple sine wave using Convolutional Autoencoders. The noisy sine wave is cleaned up by reconstructing the signal through feature extraction and noise reduction.

• Name: Spandana A P

• GitHub ID: https://github.com/spandana2004

• Email ID: ap.spandana@gmail.com

• Identify yourself: contributor @ GSSoC 2024 Extd, Hacktoberfest 2024 Contributor

Closes: #918

Describe the add-ons or changes you've made 📃

In this PR, I have added a new feature that denoises a sine wave using a Convolutional Autoencoder. The steps include:

• Preprocessing the noisy sine wave
• Training a 1D Convolutional Autoencoder
• Visualizing the denoised signal along with the noisy and original signals

Type of change ☑️

What sort of change have you made:

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Code style update (formatting, local variables)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

How Has This Been Tested? ⚙️

• The code was tested using synthetic noisy sine wave data, and the model was trained on it.
• The output was visually compared by plotting the original, noisy, and denoised signals, showing effective noise reduction.

Checklist: ☑️

• My code follows the guidelines of this project.
• I have performed a self-review of my own code.
• I have commented my code, particularly wherever it was hard to understand.
• I have made corresponding changes to the documentation.
• My changes generate no new warnings.
• I have added things that prove my fix is effective or that my feature works.
• Any dependent changes have been merged and published in downstream modules.

[github-actions]

Our team will soon review your PR. Thanks @spandana2004 :)

[abhisheks008]

Please follow the project structure:

Project Folder
|- Dataset
   |- dataset.csv (dataset used for the particula project)
   |- README.md (brief about the dataset)
|- Images
   |- img1.png
   |- img2.png
   |- img3.png
|- Model
   |- project_folder.ipynb
   |- README.md
|- requirements.txt

• In the project folder's name, please remove the hyphen (-).
• Apart from this model, can you implement 2 more models which will fulfill the same purpose?

@spandana2004

[spandana2004]

@abhisheks008 will do the required changes, I had a doubt about what to be given in the images? is it the results? Can i implemented the other 2 models by creating a new issue?

[abhisheks008]

@abhisheks008 will do the required changes, I had a doubt about what to be given in the images? is it the results? Can i implemented the other 2 models by creating a new issue?

1. In the Images folder, you can put the EDA results, model accuracy heatmaps and so on.
2. No you need to create other two models inside this same .ipynb file.

@spandana2004