Skip to content

Latest commit

 

History

History
26 lines (16 loc) · 1.07 KB

README.md

File metadata and controls

26 lines (16 loc) · 1.07 KB
Raw

ELEC 6410 (DSP) Project | Tanner Koza

This document serves to explain how to generate features in Python for classifying types of ADHD with an SVM. This markdown file can be viewed in its rendered version at this link: https://github.com/tannerkoza-auburn/dsp-project/tree/main.

Usage

  1. Open this project in a shell of your choice. Make sure you're in the dsp-project/ directory.
  2. Install packages. It is recommended to use a virtual environment.
pip install -r requirements.txt

  1. Place file containing data to classify (eg. data.mat) in data/ directory.

    NOTE: If file name is not data.mat, open scripts/compute_features.py in an editor and change the INPUT_FILE parameter to your file name. DO NOT change anything else.

  2. Run compute_features.py script. This will output a file called features.mat in the data/ directory.

python3 scripts/compute_features.py

  1. Load data/features.mat in MATLAB and process accordingly.

    ALSO: The MATLAB script scripts/test_features.m was used to validate performance.