Introduction

Propelled by the increasingly availability of data, multisensor data fusion has been used to combine and analyse different data sources to improve the reliability and accuracy of a given measurement. Although in the recent years, significant developments have occurred in the field of multisensor data fusion, the concept of combining different data sources to improve accuracy is hardly new. What has evolved in the past years is the emergence of new sensors and the advances in the use of machine learning techniques, which have made the real time multisensor fusion of data possible.

The general idea behind data fusion is that the combination of results from multiple data sources, leads to more and better information, than using a single data source. Multiple data sources providing redundant information increase reliability and reduce uncertainty. Complementary information from distinct sources enhances the quality of the output information, by either increasing the spatial and temporal coverage, increase robustness, reduce noise and increase estimation accuracy, which would not be possible to achieve by using just information from a single individual data source.

There are various methods to perform data fusion: Bayesian belief networks, Machine Learning (ML), fuzzy logic, state estimation and decision fusion.  This data fusion tools framework makes use of Machine Learning algorithms to perform the data fusion.

Data fusion tools

The data fusion tools are a framework to combine different data sets to perform subsoil schematisations and parametrisations. The data fusion tools are a python package and can be found here.

Before starting

It is recommended to work with Python virtual environments. The main purpose of Python virtual environments is to create an isolated environment for Python projects. This means that each project can have its own dependencies, regardless of what dependencies every other project has. This avoids issues with packages dependencies. The virtual environment should be installed and activated in order to run this tutorial.

To create a virtual environment using conda:

conda create -n datafusiontools python=3.9

To activate the environment:

conda activate datafusiontools

Installation

For users

To install data fusion tools you simply need to install the data fusion package on your environment:

pip install git+https://bitbucket.org/DeltaresGEO/datafusiontools

For developers

To use data fusion tools as a developer you need to clone the data fusion tools repository into your local machine (you need git installed on your machine):

git clone git+https://bitbucket.org/DeltaresGEO/datafusiontools

Every time you want to work on it it is good practice to to make sure that the code is up-to-date. You can update you code by running the following git command inside the project folder:

git pull

Once you cloned the repository you should have a similar structure in your machine:

To contribute you need install the environmental file that it is available on the repository. Navigate to the location where you repository is installed.

If you do not have yet the data fusion tools virtual environment installed, you need to create the environment:

conda env create -f ./env.yml

If you already have a data fusion virtual environment you need to update the environment:

conda env update -f ./env.yml

Then you need to install the data fusion tools package into your environment:

pip install -e .

Usage

The data fusion tools documentation can be found here.

The documentation consists of the description of the methods and tutorials.

Overview of the development procedure


Film - Software ontwikkelingen data fusion tools.mkv

  • No labels