{"id":15432816,"url":"https://github.com/gugarosa/evolutionary_ensembles","last_synced_at":"2025-04-19T17:46:41.212Z","repository":{"id":55486451,"uuid":"234546564","full_name":"gugarosa/evolutionary_ensembles","owner":"gugarosa","description":"📄 Official implementation regarding the paper \"Creating Classifier Ensembles through Meta-heuristic Algorithms for Aerial Scene Classification\".","archived":false,"fork":false,"pushed_at":"2022-10-05T12:16:22.000Z","size":7485,"stargazers_count":8,"open_issues_count":0,"forks_count":3,"subscribers_count":4,"default_branch":"master","last_synced_at":"2024-10-18T07:40:13.686Z","etag":null,"topics":["aerial-scene","ensemble-classifier","implementation","machine-learning","meta-heuristic","paper"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/gugarosa.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2020-01-17T12:43:41.000Z","updated_at":"2023-07-06T12:34:09.000Z","dependencies_parsed_at":"2023-01-19T06:31:36.071Z","dependency_job_id":null,"html_url":"https://github.com/gugarosa/evolutionary_ensembles","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gugarosa%2Fevolutionary_ensembles","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gugarosa%2Fevolutionary_ensembles/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gugarosa%2Fevolutionary_ensembles/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gugarosa%2Fevolutionary_ensembles/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/gugarosa","download_url":"https://codeload.github.com/gugarosa/evolutionary_ensembles/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":249752147,"owners_count":21320449,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["aerial-scene","ensemble-classifier","implementation","machine-learning","meta-heuristic","paper"],"created_at":"2024-10-01T18:28:42.109Z","updated_at":"2025-04-19T17:46:41.193Z","avatar_url":"https://github.com/gugarosa.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Creating Classifier Ensembles through Meta-heuristic Algorithms for Aerial Scene Classification\n\n*This repository holds all the necessary code to run the very-same experiments described in the paper \"Creating Classifier Ensembles through Meta-heuristic Algorithms for Aerial Scene Classification\".*\n\n---\n\n## References\n\nIf you use our work to fulfill any of your needs, please cite us:\n\n```BibTex\n@inproceedings{Ferreira:21,\n  author={Ferreira, Álvaro R. and de Rosa, Gustavo H. and Papa, João P. and Carneiro, Gustavo and Faria, Fabio A.},\n  booktitle={2020 25th International Conference on Pattern Recognition (ICPR)}, \n  title={Creating Classifier Ensembles through Meta-heuristic Algorithms for Aerial Scene Classification}, \n  year={2021},\n  volume={},\n  number={},\n  pages={415-422},\n  doi={10.1109/ICPR48806.2021.9412938}\n}\n```\n\n---\n\n## Structure\n\n  * `data/`\n    * `RSDataset`: Folder containing the RSDataset data;\n    * `RSSCN7`: Folder containing the RSSCN7 data;\n    * `UCMerced_LandUse`: Folder containing the UCMerced_LandUse data;\n  * `models/`\n    * `ensemble.py`: Ensemble-based methods, such as weight-based and majority voting;\n  * `utils/`\n    * `constants.py`: Constants definitions;\n    * `dictionary.py`: Creates a dictionary of classes and labels;\n    * `load.py`: Loads the dataset according to desired format;\n    * `metrics.py`: Provides several metrics calculations;\n    * `mh.py`: Wraps the meta-heuristic classes;\n    * `wrapper.py`: Wraps the optimization tasks;\n\n---\n\n## Package Guidelines\n\n### Installation\n\nYou may just install the pre-needed requirements under your most preferred Python 3+ environment (raw, conda, virtualenv, whatever):\n\n```Python\npip3 install -r requirements.txt\n```\n\n---\n\n## Usage\n\n### Majority Voting\n\nOur first ensemble-based baseline is to use the Majority Voting in order to create a count-based ensemble. With that in mind, just run the following script with the input arguments:\n\n```Python\npython3 majority_voting.py -h\n```\n\n*Note that it will output a helper file in order to assist in choosing the correct arguments for the script.*\n\n### Optimizing Weight-Based or Boolean-Based Ensembles\n\nAfter defining the Majority Voting baselines, now we can proceed and try to find the most suitable weights for the ensemble (one can use a weight-based or a boolean-based approach) through a meta-heuristic optimization process. Just choose the following scripts and invoke their helper:\n\n```Python\npython3 ensemble_learning.py -h\n```\n\nand\n\n```Python\npython3 ensemble_learning_with_gp.py -h\n```\n\nand\n\n```Python\npython3 ensemble_learning_with_umda.py -h\n```\n\n*Note that Genetic Programming- and Univariate Marginal Distribution Algorithm-based optimization are included in different scripts due to their particular structure defined in the Opytimizer library.*\n\n### Post-Optimization Processing\n\nFinally, after concluding the optimization step over the validation sets, it is now possible to load back the best weights found during the optimization procedure and apply them into a weight-based ensemble over the testing set. Run the following script in order to fulfill that purpose:\n\n```Python\npython3 process_optimization_history.py -h\n```\n\n*Note that the optimization process will always output a `.pkl` file, while the other scripts will output a `*.txt` file.*\n\n### Bash Script\n\nInstead of invoking every script to conduct the experiments, it is also possible to use the provided shell script, as follows:\n\n```Bash\n./pipeline.sh\n```\n\nSuch a script will conduct every step needed to accomplish the experimentation used throughout this paper. Furthermore, one can change any input argument that is defined in the script.\n\n### (Optional) Diversity Metrics\n\nAs an optional procedure, one can also calculate some diversity metrics between classifiers. Please use the following script in order to accomplish such an approach:\n\n```Python\npython3 diversity_metrics.py -h\n```\n\n*Note that this script will also calculate both classifier accuracies over the desired dataset and fold.*\n\n---\n\n## Support\n\nWe know that we do our best, but it is inevitable to acknowledge that we make mistakes. If you ever need to report a bug, report a problem, talk to us, please do so! We will be available at our bests at this repository or aalvin10@gmail.com and ffaria@unifesp.br.\n\n---\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgugarosa%2Fevolutionary_ensembles","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgugarosa%2Fevolutionary_ensembles","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgugarosa%2Fevolutionary_ensembles/lists"}