Genome Composition Study

This repository contains the code for the paper "Effects of Optimal Genetic Material in the Initial Population of Evolutionary Algorithms" presented at the 2023 IEEE Symposium Series on Computational Intelligence. For more information on the work, you can check out the paper on IEEE Xplore.

Folder Structure

There are three folders for the code, data and figures generated by the evaluation:

• code - contains all the code, most importantly the script for generating the test data and the jupyter notebook used for evaluation. Besides the test scripts, code from the preliminary evaluation as well as the sub-repository for the T-EA is also here.
• data - is the output folder for the test data, both for the preliminary test and the actual benchmark. Also already contains the compressed data from the tests.
• figures - contains the generated pdf figures from the evaluation of the data.

Installing

Python version 3.9.6 was used for this repository.

The t-ea pymoo implementation is required to run the code in this repository. This needs to be initialized after cloning the repository:

git clone https://github.com/tobeneck/genome_composition_study.git
cd genome_composition_study
git submodule init
git submodule update

After this, the required packages can be installed from the requirements.txt file:

python3 -m venv venv
source venv/bin/activate
pip3 install -r requirements.txt

Generating the Test Data

As mentioned, the test data is already available in the data/sphere_function_data_out folder. This test data is generated using the code/benchmark_sphere.py script:

cd code
python3 benchmark_sphere.py

The output of the test data woll be saved to the data folder. It can be evaluated using the code/paper_plots.ipynb notebook.

Citation

If you have used this work for research purposes, you can cite it with:

T. Benecke and S. Mostaghim, "Effects of Optimal Genetic Material in the Initial Population of Evolutionary Algorithms," 2023 IEEE Symposium Series on Computational Intelligence (SSCI), Mexico City, Mexico, 2023, pp. 1386-1391, doi: 10.1109/SSCI52147.2023.10372037

Bibtex:

@INPROCEEDINGS{benecke_ssci_2023,
  author={Benecke, Tobias and Mostaghim, Sanaz},
  booktitle={2023 IEEE Symposium Series on Computational Intelligence (SSCI)}, 
  title={Effects of Optimal Genetic Material in the Initial Population of Evolutionary Algorithms}, 
  year={2023},
  pages={1386-1391},
  doi={10.1109/SSCI52147.2023.10372037}
}

Acknowledgement

This work is part of the Research Initiative "SmartProSys: Intelligent Process Systems for the Sustainable Production of Chemicals" funded by the Ministry for Science, Energy, Climate Protection and the Environment of the State of Saxony-Anhalt.