hasanyusuf01 / Codes

The repository encompasses of projects of machine learning , deeplearning , signal processing and image processing

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Codes

Text classification

Welcome to this notebook where I have created a deep neural network to classify MNIST handwritten digit images. MNIST is widely considered the "Hello World" of deep learning, and building a model on this dataset is an essential step for beginners.

Using the Keras library, I was able to gain a better understanding of the underlying concepts and techniques used in deep learning. It was an exciting and enriching experience to build a model that can accurately classify handwritten digits.

I hope this notebook can be a valuable resource for those looking to understand and build deep neural networks. With the knowledge gained from this project, one can explore further and tackle more challenging problems in the field of machine learning.

EEG Signal Classification using Classical Machine Learning Models

This repository contains code for performing classification on EEG signals using classical machine learning models. The code includes preprocessing steps, feature extraction, and training a classifier for 4 types of classification tasks.

Usage

To run this code, you can either use the provided Jupyter notebook or open it in Google Colab.

Open in Colab

You can directly run the notebook in Google Colab by clicking the link below:

Phyaat2 Phyaat2b

Installation

Install the required Python package using pip:

pip install phyaat

Data

The EEG data is obtained from the PhyAAt dataset. You can download the dataset using the provided utility functions in the code. The dataset includes signals from multiple subjects, and you can choose a specific subject for analysis.

Code Overview

  1. Data Preparation and Preprocessing

    • Download the EEG dataset for a specific subject.
    • Filter the EEG data using a highpass filter.
  2. Feature Extraction

    • Extract rhythmic features for the desired classification task.
  3. Model Training

    • Normalize the features.
    • Train a Random Forest classifier using the training data.
  4. Model Evaluation

    • Predict class labels for the test dataset.
    • Calculate and display the testing accuracy of the model.

Getting Started

Follow the steps mentioned in the notebook to run the code and analyze the EEG signal classification results.


Intensity transformation

Malware detection (cybersecurity branch)

About

The repository encompasses of projects of machine learning , deeplearning , signal processing and image processing


Languages

Language:Jupyter Notebook 100.0%