Giter Site home page Giter Site logo

alexning98 / dpgnn-gasleak Goto Github PK

View Code? Open in Web Editor NEW

This project forked from forestr/dpgnn-gasleak

0.0 0.0 0.0 4.95 MB

Code and data for replicating the work in ‘Towards deep probabilistic graph neural network for natural gas leak detection and localization without labeled anomaly data’ by Zhang et al. (2023). The paper proposes a deep probabilistic graph neural network for modeling spatial sensor dependency and localizing natural gas leaks.

License: GNU General Public License v3.0

Python 100.00%

dpgnn-gasleak's Introduction

DPGNN-GasLeak (Deep Probabilistic Graph Neural Network for Natural Gas Leak Detection)

This repository contains code and data for replicating the work in the paper 'Towards deep probabilistic graph neural network for natural gas leak detection and localization without labeled anomaly data' by Zhang et al. (2023). The paper proposes a deep probabilistic graph neural network that integrates an attention-based graph neural network and variational Bayesian inference to model spatial sensor dependency and localize natural gas leaks.

Getting Started

These instructions will help you set up the project on your local machine for development and testing purposes.

Prerequisites

  • Install PyTorch and any required dependencies on your development environment.

Data Preprocessing

Preprocess the benchmark dataset as described in section 4.2 of the paper to normalize the time-series data.

Model Implementation

  1. Implement the attention-based graph neural network as described in section 3.1 of the paper using PyTorch’s built-in neural network modules and functions.
  2. Implement the variational Bayesian inference component as described in section 3.2 of the paper using PyTorch’s probabilistic programming capabilities.
  3. Integrate the attention-based graph neural network and variational Bayesian inference components to create the VB_GAnomaly model as described in section 3.3 of the paper.

Training

Train the VB_GAnomaly model on the preprocessed benchmark dataset using PyTorch’s optimization and training capabilities.

Evaluation

Evaluate the performance of the trained VB_GAnomaly model on a test dataset using the evaluation metrics described in section 3.4 of the paper.

License

This project is licensed under the GPL License.

dpgnn-gasleak's People

Contributors

forestr avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.