DAEA: code for "A Duplication Analysis-Based Evolutionary Algorithm for Biobjective Feature Selection"
DAEA is a MATLAB-based evolutionary algorithm designed for solving biobjective feature selection problems in classification tasks. It leverages duplication analysis to enhance the efficiency and effectiveness of the feature selection process.
This implementation is based on the code of SM-MOEA and PlatEMO. Please refer to the original paper A Duplication Analysis-Based Evolutionary Algorithm for Biobjective Feature Selection for detailed information about the algorithm's overview, methodology, and benchmark results.
This code was developed for feature selection tasks in classification. The framework can be adapted to other feature selection scenarios with minor modifications.
- 🎉🎉 Coming soon
| Feature | Support / To be supported |
|---|---|
| Efficient Feature Selection | 🔥Support |
| Multi-Objective Optimization | 🔥Support |
| Classification Task Support | 🔥Support |
| MATLAB Implementation | 🔥Support |
| High-Dimensional Data Support | 🔥Support |
| More Application Scenarios | 🚀Coming soon |
Important
This implementation requires MATLAB. Ensure you have MATLAB installed on your system.
Note
The code is based on MATLAB. Please download the required libraries if necessary.
- Download the code and dataset from the repository.
- Open MATLAB and set the working directory to the project root.
- Run the
main_DAEA.mscript. - You can choose the provided "dataset.mat" file in the "dataset" folder for testing.
% an example
% you can find the code in `main_DAEA.m` file
algorithmName = 'DAEA';
dataNameArray = {'colon'}; % dataset
global maxFES
maxFES = 100; % max number of iteration
global choice
choice = 0.6; % the threshold choose features
global sizep
sizep = 300; % size of populationXu H, Xue B, Zhang M. A Duplication Analysis-Based Evolutionary Algorithm for Biobjective Feature Selection[J]. IEEE Transactions on Evolutionary Computation, 2020, 25(2): 205-218.
Tian Y, Cheng R, Zhang X, et al. PlatEMO: A MATLAB Platform for Evolutionary Multi-Objective Optimization [Educational Forum][J]. IEEE Computational Intelligence Magazine, 2017, 12(4): 73-87.
Cheng F, Chu F, Xu Y, et al. A Steering-Matrix-Based Multiobjective Evolutionary Algorithm for High-Dimensional Feature Selection[J]. IEEE transactions on cybernetics, 2021, 52(9): 9695-9708.
This project is based on the implementation of SM-MOEA and PlatEMO. Please refer to their respective licenses for details.
If you encounter any issues or have questions regarding DAEA, please feel free to contact me.
If you find this work helpful, please consider giving me a ⭐!