From d66a5b595ec406e03a993dcaf4c11f3fc0f253e6 Mon Sep 17 00:00:00 2001 From: MayDay9939 Date: Sat, 30 Mar 2024 17:27:38 +0800 Subject: [PATCH] updated readme file for submission --- Project_Original.ipynb | 10 ---------- README.md | 15 ++++++++++++++- 2 files changed, 14 insertions(+), 11 deletions(-) diff --git a/Project_Original.ipynb b/Project_Original.ipynb index 6c69c5e..7480f66 100644 --- a/Project_Original.ipynb +++ b/Project_Original.ipynb @@ -1,15 +1,5 @@ { "cells": [ - { - "cell_type": "markdown", - "id": "cda961ffb493d00c", - "metadata": { - "collapsed": false - }, - "source": [ - "# CSC 3105 Project" - ] - }, { "cell_type": "markdown", "id": "f3c2c7fc8009f6bc", diff --git a/README.md b/README.md index 2f7e142..647437f 100644 --- a/README.md +++ b/README.md @@ -78,4 +78,17 @@ The notebook is structured as follows: 3. **Model Training and Evaluation**: The notebook trains various machine learning models on the data and evaluates their performance. It also saves the trained models to a file for future use. -4. **Model Visualization**: The notebook visualizes the performance of the trained models using various plots and metrics. \ No newline at end of file +4. **Model Visualization**: The notebook visualizes the performance of the trained models using various plots and metrics. + + +## Notebook Files Overview + +Here is a brief description of each Jupyter notebook file included in this project: + +1. **Project.ipynb**: The primary method utilized for submission is showcased in this notebook, which outlines the outcomes of applying wavelet transformation to the data. This technique enables the analysis of various frequencies of a signal across different scales, aiding in the identification of patterns that change over time. + +2. **Project_DFT.ipynb**: This notebook contains the results of applying a Discrete Fourier Transform (DFT) to the data. The DFT is used to transform the data from the time domain to the frequency domain, which can reveal important patterns and features in the data. + +3. **Project_Original.ipynb**: This notebook contains the analysis performed on the raw Channel Impulse Response (CIR) data. Unlike the other notebooks, it does not apply transformations such as wavelet or DFT to the data. Instead, it works directly with the original, untransformed data, providing a baseline for comparison with the transformed data. + +4. **Project_OLD.ipynb**: This notebook contains our initial approach to the project. It serves as a record of our early ideas and experiments, and may contain different methods and techniques compared to the final approach. \ No newline at end of file