/MADRN

The code for paper: A Deep Neural Network Based Method for Magnetic Anomaly Detection.

Primary LanguagePythonApache License 2.0Apache-2.0

MAD residual network (MADRN)

By Yizhen Wang.

Table of Contents

  1. Introduction
  2. Citation
  3. Overview of network
  4. Getting started

Introduction

This is a Keras implementation of A Deep Neural Network Based Method for Magnetic Anomaly Detection. with datasets and pretrained models.

Citation

If you use these models in your research, please cite:

@article{wang2022deep,
  title={A deep neural network based method for magnetic anomaly detection},
  author={Wang, Yizhen and Han, Qi and Zhao, Guanyi and Li, Minghui and Zhan, Dechen and Li, Qiong},
  journal={IET Science, Measurement \& Technology},
  volume={16},
  number={1},
  pages={50--58},
  year={2022},
  publisher={Wiley Online Library}
}

Overview of network

Figure 1: The architecture of MADRN.

Getting started

Datasets

Download or generate the datasets like the given datasets form, and put them in the in the datasets folder.

The datasets is avaliable at: https://drive.google.com/drive/folders/1p5xO6Ptx5RJnOvCdoH5DmcP3_g1Hu4pA?usp=drive_link

Requirements

To install requirements:

pip install -r requirements.txt

Training and Evaluation

To run MADRN with different parameters in the paper, run this command:

python ./tests/Training_all.py

To run the MADRN in the paper, run this command:

python ./tests/Test.py