the-data-alchemists-manipal/mindwave

MindWave is an open-source project designed for beginners to learn about data science, machine learning, deep learning, and reinforcement learning algorithms using Python. The project offers a platform for implementing relevant algorithms, with open-source tools and libraries.

English | हिंदी

MindWave

MindWave is an open-source project aimed at beginners who want to learn about Data Science, Machine Learning, Deep Learning, and Reinforcement Learning algorithms in Python. This project aims to provide a platform for beginners to implement the relevant algorithms in Python.

Overview

Data Science, Machine Learning, Deep Learning, Reinforcement Learning, and Open Source are all closely related, each building on the foundation of the previous concept.

Data Science involves the use of statistical and computational methods to analyze and interpret complex data sets. Open-source tools and libraries like Python and R, along with their respective ecosystems of libraries, have been critical to the democratization of data science, making it easier and more accessible for researchers, businesses, and individuals to analyze and make sense of data.

Computer vision is the field of artificial intelligence that enables computers and systems to extract meaningful information from visual data and interpret it in the same way humans do. Various computer vision libraries like OpenCV have made it easier for developers to perform various operations on visual data, be it recognition of objects, segmentation of images, etc.

Machine Learning is a subfield of data science that focuses on the development of algorithms and models that can learn from data and make predictions or decisions without being explicitly programmed. Open-source tools like scikit-learn, TensorFlow, and Keras have been instrumental in the growth and innovation of machine learning, making it easier for researchers and developers to build and train models, and deploy them into real-world applications.

Deep Learning is a subfield of machine learning that focuses on building and training neural networks, which are capable of learning and making predictions from very large and complex data sets. Open-source libraries like TensorFlow and PyTorch have been instrumental in the development and democratization of deep learning, providing a vast array of tools and algorithms for building and training neural networks, and enabling researchers and businesses to develop cutting-edge AI applications.

Reinforcement Learning is a subfield of machine learning that involves training agents to make decisions in an environment to maximize a reward signal. Open-source libraries like OpenAI's Gym and Stable Baselines have made it easier for researchers and developers to experiment with and develop reinforcement learning algorithms and models, and deploy them into real-world applications.

Open Source has played a critical role in the growth and success of data science, machine learning, deep learning, and reinforcement learning. The collaborative nature of open source allows for faster development and innovation, enables customization and extension of existing tools and libraries, and fosters a supportive community of users and contributors. Additionally, open source promotes transparency and accountability, making it easier for researchers and developers to share their work and reproduce their results, advancing the field as a whole. Overall, open source has been essential to the democratization of AI, enabling more people to participate in its development and benefit from its applications.

Contributing to MindWave

• If you have a new idea, create an issue and wait for it to be assigned before starting work on it.
• If you want to submit an improvement to an existing algorithm, create an issue describing your improvement in detail to facilitate analysis by others.
• Issues will be assigned on a first come, first serve basis, and you can ask to be assigned by commenting on the issue. It is preferred that you work only on the issue assigned to you.
• Check out the reference code in the relevant directory and write your own code basis that.
• Fork the repository (first time) and push your code to create a pull request (PR).
• All pull requests must be made from a branch. Create a separate branch for each issue you are working on and make the PR once it is complete.
• The files should be uploaded directly into the corresponding folder (eg. Machine Learning, Deep Learning, etc.) and linked in the README.md file of the respective folder. Do not create new folders within the concept folders unless instructed to do so.
• Please be courteous to the reviewers as they will always be polite to you.

Tech Stack Used

Code of Conduct

You can find our Code of Conduct here.

License

This project follows the MIT License.

Contributors

(Back to top)

mindwave's Issues

Brain Tumor Detection using VGG-16

💥 Proposal

Brain Tumor Detection using VGG-16 through images
Dataset to be used : https://www.kaggle.com/datasets/navoneel/brain-mri-images-for-brain-tumor-detection

Face Mask Detection Using CNN

What actually my model does

During Covid-19 period wearing mask is crucial one, so I've developed a ML project which can detect multiple faces and show the result. I've even worked on Arduino which turns the camera towards the face and send the signal to the machine to detect the face using OpenCV and displayed the result.

Different Model used to detect the faces?

• I tried detecting faces using available pretrained models like YOLO, RESNET-50 and many more, after detecting the face I've cropped out the faces and sent it to my model and it will detect whether mask is present or not.
• Using Arduino I've implemented 360° rotated camera and the ML model will detect the faces and displays the result.

Additional context

CNN Architecture of the model

---

Accuracy, loss of the model

Acuracy Percentage of the model

Testing snapshot of the Model

Logistic Regression on the Titanic Dataset

💥 Proposal

To implement the Logistic Regression algorithm on the Titanic Dataset.
Link to the Dataset: https://www.kaggle.com/datasets/pavlofesenko/titanic-extended

movie recommendation

@khusheekapoor
i would to do this issue
i am a GSSOC'23 contributor
the dataset i am gonna use is :-https://www.kaggle.com/datasets/grouplens/movielens-20m-dataset

Adding ML algorithms with example datasets

💥 Proposal

I can implement and add all ML algorithms like Linear Regression, Logistic Regression, Random Forest, Support Vector Machine etc.
This will be a easy to understand addition such that any newbie in ML can implement by themselves.

Support Vector Machines (SVMs) on Diabetes Dataset.

💥 Proposal

the datasheet I will used here is :https://www.kaggle.com/datasets/mathchi/diabetes-data-set
I am GSSoC23 contributor assign me this project

add contributors graph

💥 Proposal

I want to add conributors graph in readme.Please assign this issue to me under GSSOC

SARSA on the Taxi Environment

💥 Proposal

To implement the SARSA algorithm on the Taxi Environment.
Link to the Environment: https://www.gymlibrary.dev/environments/toy_text/taxi/

Hypertuned prediction model on diabetes dataset

@khusheekapoor
the dataset i will use is here-https://www.kaggle.com/datasets/uciml/pima-indians-diabetes-database
please assign this project to me
i am GSSOC'23 contributor

Linear Regression on the California Housing Dataset

💥 Proposal

To implement the Linear Regression algorithm on the California Housing Dataset.
Link to the Dataset: https://www.kaggle.com/datasets/camnugent/california-housing-prices

Implementation of Generative Adversarial Network (GAN) for MNIST Handwritten Digits From Scratch in Keras

💥 Proposal

I want to implement a Generative Adversarial Network (GAN) from scratch using the Keras framework to generate realistic MNIST handwritten digits. This GAN will consist of a generator and a discriminator, where the generator will learn to generate realistic digits, and the discriminator will learn to distinguish between real and generated digits.

I would like to request that you please assign it to me under the tag/label GSSoC'23.

Implementing Sentiment Analyzer using RNN

💥 Proposal

Implementing a sentiment analyzer using RNN and NLP techniques to train the model on word2ve dataset.

Running Injury Prediction using Random Forest

💥 Proposal

Running Injury Prediction using Random Forest Algo
Dataset Used : https://www.kaggle.com/datasets/shashwatwork/injury-prediction-for-competitive-runners

Fashion MNIST - Deep Learning Keras

💥 Proposal

Using ANN and Keras API on Fashion MNIST dataset
Dataset used : https://www.kaggle.com/datasets/zalando-research/fashionmnist

Automate Google Search using Python.

💥 Proposal
In this project I had an idea to automate google search using python by automation the user can be helpful to search anything on google by using this tool

Music genre classification and hypertuning it

to create a music genre classifier and hypertune it to make its best version
@khusheekapoor

obesity classification

@khusheekapoor
i would like to work on this issue
this will classify obesity into different categories
the dataset i am gonna use is :- https://www.kaggle.com/datasets/sujithmandala/obesity-classification-dataset?select=Obesity+Classification.csv

Breast Cancer Prediction using ANN

💥 Proposal

Predicting breast cancer, whether it is malignant or benign, using ANN
Dataset used : https://www.kaggle.com/datasets/yasserh/breast-cancer-dataset

Music Genre Classification

💥 Proposal

Hi I am Kruti shah a second year engineering student .
I want to work on classifying genres in music using K-Nearest Neighbors.
I am a contributor in GSsoc'23 .
Hoping you could assign this to me .
(A clear and concise description of what the proposal is.)

LeNet on the MNIST Dataset

💥 Proposal

To implement the LeNet Architecture on the MNIST Dataset.
Link to the Dataset: https://www.kaggle.com/datasets/hojjatk/mnist-dataset

Model to recognize a particular language using NLP, sklearn, pickle, streamlit.

💥 Proposal

This is the approach what I am following:

This is a language detection model with detects the language of the text provided.
Steps
Data processing:
1.Removing the inconsistencies such as capital letters and punctuations from the dataset.
Model building:
1.Using pipeline, Convert the text into number format so that the input can be fed into the model.
2.Using TFIDF vectorization method as a second step of the pipeline.
3.Applying Logistic regression and generating the output.

Accuracy can be reached up to 97% percent by using these steps.

After these steps, exporting the model using pickle.

@khusheekapoor ,
Please assign it to me as a part of @GSSOC'23 Contribution.
Thank you.

Price Suggestion Model - To suggest prices for products when you are selling them in a marketplace like Amazon

💥 Proposal

Hello, I am Siddhant Dutta - I am a GSSOC'23 Contributor. This is my resume - Resume

Introduction

The Price Suggestion Model is an open-source project aimed at predicting the prices of products listed on online marketplaces like Amazon. The goal is to provide sellers with accurate price suggestions for their products based on various attributes such as brand, category, description, name, shipping, and item condition. This project utilizes machine learning algorithms, including LGBM and Neural Networks, to predict prices and employs techniques like Bayesian search and ensemble methods to optimize model performance.

Objectives

1. Develop a machine learning model capable of predicting prices for products listed on online marketplaces.
2. Implement various algorithms, including LGBM and Neural Networks, to achieve accurate price predictions.
3. Utilize techniques such as Bayesian search and ensemble methods to optimize the performance of the price prediction model.
4. Evaluate the model's performance using metrics such as Mean Squared Error (MSE) and Root Mean Squared Logarithmic Error (RMSLE).
5. Provide an open-source solution that can be used by sellers on marketplaces like Amazon to improve their pricing strategies.

Deliverables:

The project will deliver the following components:

1. Source code of the price suggestion model implemented in Python.
2. Preprocessing scripts for cleaning and transforming the dataset.
3. Jupyter notebooks or Python scripts showcasing the implementation of various machine learning algorithms.
4. A trained model file that can be used for price prediction as well as the h5 weight file of the final deep learning model.
5. Documentation detailing the project's methodology, including preprocessing steps, algorithm selection, hyperparameter tuning, and evaluation metrics.

Methodology:

1. Obtain a suitable dataset from platforms like Kaggle, containing product attributes and their corresponding prices.
2. Preprocess the dataset, including cleaning and transforming the data, handling missing values, and encoding categorical variables.
3. Split the dataset into training, cross-validation & testing sets to train and evaluate the machine learning models.
4. Implement machine learning algorithms, including LGBM and Neural Networks, to build the price prediction model.
5. Utilize techniques like Bayesian search and ensemble methods to optimize the model's hyperparameters and overall performance.
6. Evaluate the model's performance using custom loss functions & metrics such as MSE and RMSLE, comparing the predicted prices with the actual prices in the test dataset.
7. Iterate and refine the model based on the evaluation results to improve accuracy.

Timeline

EDA, Data Cleaning & preprocessing: 1 week
Feature Engineering Model implementation: 2 weeks
Optimization & Evaluation and refinement: 1 week
Documentation and finalization: 1 week

💥Proposal for Linear Regression on the Housing Prices in Metropolitan Areas of India Dataset

💥 Proposal

To implement the Linear Regression algorithm on the Housing Prices in Metropolitan Areas of India Dataset.
Link to the Dataset: https://www.kaggle.com/datasets/ruchi798/housing-prices-in-metropolitan-areas-of-india

I would like to work on this project for Linear Regression. But I need to start working on it post 7 June, due to my end semester exams. I will try to work on the LeNet issue in the next 21 days, by taking breaks between my studies.

Fake News Prediction using Logistic Regression

I would like to work on this project where i will be building a Fake News Prediction System using Machine Learning with Python. I will be using Logistic Regression model for prediction.

@khusheekapoor Please assign this issue to me

Customer churn prediction using ANN

💥 Proposal

Here we are going to measure how and why are customers leaving the business, i.e. Customer churn prediction using artificial neural networks.

Spotify : Music Recommendor System

💥 Proposal

I would ike to work on spotify/YT music music recommendor system , which would recommend the correct choice of songs to the users according to their previous watch lists and genre.

To classify whether a person is a smoker or not in UK

PROPOSAL:

Using Classifier Models From sklearn we will predict whether a person is a smoker or not in UK.We will also see which model has better accuracy after performing EDA
Link to dataset:https://www.kaggle.com/datasets/utkarshx27/smoking-dataset-from-uk/code

Emotion Detection Model

💥 Emotion Detection Model

This model is designed solely to identify the human emotions (Angry, Happy, Sad, Surprised, Normal).
Using Unsupervised Models of Machine Learning

Kindly Assign this work to me @khusheekapoor
Thank You.
@gssoc23

Energy Efficiency Enhancement Using DL

💥 Proposal

Assessing the energy efficiency of building using various parameters.
Dataset link : https://www.kaggle.com/datasets/elikplim/eergy-efficiency-dataset

Image Caption Generator using Deep Learning

💥 Proposal

CNN models on HAR Dataset

💥 Proposal

I am a GSSOC'23 Contributor
I am willing to implement different CNN models on Human Activity Recognition(HAR) dataset.
Dataset Link - https://www.kaggle.com/datasets/meetnagadia/human-action-recognition-har-dataset
So, Kindly assign it to me.

Proposal for Image Classification

💥 Proposal

Hello everyone I am a fellow GSSOC contributer and want propose an image classification project that focuses on understanding the mathematical concepts behind machine learning algorithms and their implementations with standard libraries like TensorFlow or PyTorch. I believe this project will provide valuable insights to users by demystifying the inner workings of image classification algorithms.

Semi Supervised Classification using AutoEncoders

💥 Proposal

Using any partially labeled dataset and classify it using AutoEncoders instead of traditional CNN for better prediction and feature extraction. For any application like fraud detection, handwriting detection etc.

Parkinson's Disease Prediction Model Using Machine Learning

💥 Proposal

This model is designed to build a system that can predict whether a person has Parkinson's disease or not with the help of Machine Learning. I will use Support Vector Machine(SVM) model for the prediction. I would like to contribute to this project as a part of @GSSOC'23.
Please assign the task to me. Thank you.

💥Proposal for Logistic Regression on the Credit Card Fraud Dataset

💥 Proposal

To implement the Logistic Regression algorithm on the Credit Card Fraud Dataset.
Link to the Dataset: https://www.kaggle.com/datasets/dhanushnarayananr/credit-card-fraud

I would like to work on this project for Logistic Regression. But I need to start working on it post 7 June, due to my end semester exams. I will try to work on the LeNet issue in the next 21 days, by taking breaks between my studies.

Implement ML algorithms from scratch

💥 Proposal

Use some simple dataset and implement the whole ML algorithm like a regression from the ground up showing all the math behind it in a jupyter notebook and later showing the similarities with how they are implemented in standard libraries like pytorch or tensorflow. Finally, give a demo on how to use the library functions. This should give the user a sense of what's going on inside the hood.

Heart Disease Classification using SVM, k-Nearest Neighbors (KNN), and Random Forest

💥 Proposal

I propose implementing multiple machine learning algorithms, including Support Vector Machines (SVM), k-Nearest Neighbors (KNN), and Random Forest, for heart disease classification. These algorithms are known for their effectiveness in handling classification tasks and can provide complementary insights into the dataset.

### Steps:

Dataset: dataset is available on the UCI Machine Learning Repository and contains various clinical attributes for heart disease classification. the link to dataset: https://archive.ics.uci.edu/ml/datasets/heart+Disease

Preprocessing: Handle missing values, normalize numerical features, and encode categorical variables if necessary.

Model Implementation:
a. SVM: Use scikit-learn or a similar library to implement the SVM algorithm. Configure hyperparameters (kernel type, regularization parameter) and train the model on the preprocessed dataset.
b. KNN: Implement the KNN algorithm using scikit-learn. Experiment with different values of k (number of neighbors) and explore distance metrics for optimal performance.
c. Random Forest: Use the scikit-learn library to implement the Random Forest algorithm. Adjust hyperparameters like the number of trees, maximum depth, and feature subsampling to optimize the model.

Model Evaluation: Assess the performance of each algorithm using metrics like accuracy, precision, recall, and F1-score. Compare the results of SVM, KNN, and Random Forest to determine their individual strengths and weaknesses.

Documentation: Document the implementation steps, including dataset preprocessing, algorithm configurations, and performance evaluation results for each algorithm.

Exoplanet Detection Using ML and DL

Detecting exoplanets using Machine Learning and Deep Learning algorithms
Link to dataset : https://www.kaggle.com/datasets/keplersmachines/kepler-labelled-time-series-data

adding Open Source section

💥 Proposal

adding a opne source section in mindwave so user can get started with open source
can you assign this to me, I want to work on this under GSSoC'23

add readme badges

💥 Proposal

I want to add readme badges .Please assign this issue to me under GSSOC

Linear Regression for Medical insurance cost prediction

💥 Proposal

To implement Linear Regression on Medical cost personal dataset.
Link to dataset - https://www.kaggle.com/datasets/mirichoi0218/insurance

Sentiment Analysis on the Amazon Reviews Dataset

💥 Proposal

To perform Exploratory Data Analysis. Visualization, and Sentiment Analysis on the Amazon Reviews Dataset.
Link to Dataset: https://www.kaggle.com/datasets/bittlingmayer/amazonreviews

Search Bot which summarizes the result

Aim

To make a User Friendly search bot which summarizes the result requested by the user.

What does this project do

• The search bot locates the relevant webpage and extracts the text content from it using the Beautiful Soup library.
• Using Gensim Library I've summarized the result.
• With an interface created using the Tkinter GUI toolkit that enables the user to easily enter their search query in the text box and initiate the search by clicking the submit button.
• The search bot also allows users to create a word cloud visualization of the summary using the WordCloud library. This feature is particularly useful in visualizing the most prominent words in the summary and providing a quick overview of the main themes and ideas presented in the content.

---

Flow chart of the process

• Text summarization
  
• Whole process
  

---

Snapshot of the project

Movie_recommendation_system using ann

💥 Proposal

A movie recommendation system, or a movie recommender system, is an Ml based approach for filtering or predicting the users’ film preferences based on their past choices and behavior.
This will be implemented using ANN.
The link to the dataset that will be used is :https://www.kaggle.com/datasets/rounakbanik/the-movies-dataset

Loan Repayment System

💥 Proposal

(A clear and concise description of what the proposal is.)
With the help of this project we can predict weather or nor a borrower will pay back their loan.
I will use ANN and Deep Learning for this project and EDA for better understanding of dataset.

Malaria diseases detection using deep learning

hey @khusheekapoor i would like to work on this project...please assign this to me :)

SMS Spam Classifier Using Naive Bayes and NLTK

💥 Proposal

I would like to work on an SMS spam classifier that uses the Naive Bayes model and NLTK to convert text into computer code. Also going to build a Streamlit website for the implementation of the model

I would ask you to assign me this project so that I can start working as soon as possible

In anticipation of your reply

Covid Detection on X-RAY scans using CNN

💥 Proposal

I would like to submit this proposal of building a Covid Detection CNN model that take XRAYS and input and classifies wether its a covid positive or a negative.

Im going to perform data preparation by extracting data from two datasets
https://github.com/ieee8023/covid-chestxray-dataset : for the covid positive xrays
https://www.kaggle.com/paultimothymooney/chest-xray-pneumonia : for negative or normal xrays

i would like to start my contribution by working on this project.

In anticipation of your reply.

SARSA on Cartpole Problem

💥 Proposal

Hey, I am GSSOC Contributor.
I want to implement SARSA Algorithm on Cartpole problem.
Kindly, assign to me.

Document classification using DL

I would like to add a document classification model. The model will predict if an image is of Aadhaar Card, Pan Card, Driving License, Passport or Voter ID.