{"id":15059344,"url":"https://github.com/gustavohfmo/sisc","last_synced_at":"2026-04-07T19:31:37.169Z","repository":{"id":243572850,"uuid":"812671860","full_name":"GustavoHFMO/SISC","owner":"GustavoHFMO","description":"Algorithms proposed in the following master dissertation: OLIVEIRA, Gustavo Henrique Ferreira de Miranda. Previsão de séries temporais na presença de mudança de conceito: uma abordagem baseada em PSO. 2018. Dissertação de Mestrado. Universidade Federal de Pernambuco.","archived":false,"fork":false,"pushed_at":"2024-06-09T15:23:20.000Z","size":9982,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-01-21T17:09:41.118Z","etag":null,"topics":["concept-drift","data-stream","elm","sisc-m","sisc-p","time-series"],"latest_commit_sha":null,"homepage":"https://repositorio.ufpe.br/handle/123456789/29987","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/GustavoHFMO.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"COPYING.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-06-09T14:58:14.000Z","updated_at":"2024-06-09T21:02:07.000Z","dependencies_parsed_at":"2024-06-09T23:38:16.484Z","dependency_job_id":null,"html_url":"https://github.com/GustavoHFMO/SISC","commit_stats":null,"previous_names":["gustavohfmo/sisc"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GustavoHFMO%2FSISC","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GustavoHFMO%2FSISC/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GustavoHFMO%2FSISC/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GustavoHFMO%2FSISC/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/GustavoHFMO","download_url":"https://codeload.github.com/GustavoHFMO/SISC/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":234988228,"owners_count":18918097,"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":["concept-drift","data-stream","elm","sisc-m","sisc-p","time-series"],"created_at":"2024-09-24T22:41:44.950Z","updated_at":"2026-04-07T19:31:37.163Z","avatar_url":"https://github.com/GustavoHFMO.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"#  Dynamic Swarm Intelligence for Time Series Forecasting in the Presence of Concept Drift [[DOI]](https://doi.org/10.1007/s42979-025-04247-z)\n\n## 📄 Paper\n[SISC (SN Computer Science 2025)](https://github.com/GustavoHFMO/SISC/blob/main/10.%20Dynamic%20swarm%20intelligence.pdf)\n\n\u003e OLIVEIRA, Gustavo HFM et al. Dynamic Swarm Intelligence for Time Series Forecasting in the Presence of Concept Drift. SN Computer Science, 2025.\n\n## Problem\nTime series forecasting methods do not effectively handle concept drift, especially with delayed adaptation.\n\n## Contribution\n- First use of dynamic swarm intelligence for concept drift in time series forecasting.\n- Proposed multi-model drift detection using swarm behavior.\n- Introduced reuse of past swarm models for faster adaptation to recurring concepts.\n\n## Results\n- Competitive forecasting performance across datasets.\n- Improved drift detection and reduced adaptation delay.\n\n## Usage\n```\n# Cloning the repository\ngit clone https://github.com/GustavoHFMO/SISC.git\n\n# Acessing the repository\ncd SISC\n\n# Installing the dependencies\npip install -r requirements.txt\n\n# Running the codes (Description bellow)\npython generate_synthetic_series.py\npython run_regressors.py\npython run_online_algorithms.py\n```\n\n1. The module [generate_synthetic_series.py](https://github.com/GustavoHFMO/SISC/blob/main/generate_synthetic_series.py) explains how to generate the synthetic series used in the work. Result:\n\n![](https://github.com/GustavoHFMO/SISC/blob/main/images/time_series_generation.png)\n\n\n2. The module [run_regressors.py](https://github.com/GustavoHFMO/SISC/blob/main/run_regressors.py) shows how to run the following regressors trained by swarm algorithms: `IDPSO+ELM`, `PSO+ELM` and `PSO+MLP`. Result:\n\n![](https://github.com/GustavoHFMO/SISC/blob/main/images/Regressors_prediction.png)\n\n\n3. The module [run_online_algorithms.py](https://github.com/GustavoHFMO/SISC/blob/main/run_online_algorithms.py) explain how to executes the algorithms described below in real and synthetic time series.\n\n## [SISC-P](https://github.com/GustavoHFMO/SISC/blob/main/algoritmos_online/SISC_P.py)\n\u003e OLIVEIRA, Gustavo HFM et al. Dynamic Swarm Intelligence for Time Series Forecasting in the Presence of Concept Drift. SN Computer Science, 2025.\n\n## [SISC-M](https://github.com/GustavoHFMO/SISC/blob/main/algoritmos_online/SISC_M.py)\n\u003e OLIVEIRA, Gustavo HFM et al. Dynamic Swarm Intelligence for Time Series Forecasting in the Presence of Concept Drift. SN Computer Science, 2025.\n\n## [IDPSO-ELM-S:](https://github.com/GustavoHFMO/SISC/blob/master/algoritmos_online/IDPSO_ELM_S.py)\n\u003e OLIVEIRA, Gustavo HFMO et al. Time series forecasting in the presence of concept drift: A pso-based approach. In: 2017 IEEE 29th International Conference on Tools with Artificial Intelligence (ICTAI). IEEE, 2017. p. 239-246.\n\n## [IDPSO-ELM-B:](https://github.com/GustavoHFMO/SISC/blob/master/algoritmos_online/IDPSO_ELM_B.py)\n\u003e OLIVEIRA, Gustavo HFMO et al. Time series forecasting in the presence of concept drift: A pso-based approach. In: 2017 IEEE 29th International Conference on Tools with Artificial Intelligence (ICTAI). IEEE, 2017. p. 239-246.\n\n## [ELM-FEDD:](https://github.com/GustavoHFMO/SISC/blob/master/algoritmos_online/ELM_FEDD.py)\n\u003e R. C. Cavalcante, L. L. Minku, and A. L. Oliveira, “FEDD: Feature Extraction for Explicit Concept Drift Detection in time series,” in Neural Networks (IJCNN), 2016 International Joint Conference on. IEEE, 2016, pp. 740–747.\n\n## [ELM-ECDD:](https://github.com/GustavoHFMO/SISC/blob/master/algoritmos_online/ELM_ECDD.py)\n\u003e R. C. Cavalcante and A. L. Oliveira, “An approach to handle concept drift in financial time series based on extreme learning machines and explicit drift detection,” in Neural Networks (IJCNN), 2015 International Joint Conference on. IEEE, 2015, pp. 1–8.\n\n## [ELM-DDM:](https://github.com/GustavoHFMO/SISC/blob/master/algoritmos_online/ELM_DDM.py)\n\u003e R. C. Cavalcante and A. L. Oliveira, “An approach to handle concept drift in financial time series based on extreme learning machines and explicit drift detection,” in Neural Networks (IJCNN), 2015 International Joint Conference on. IEEE, 2015, pp. 1–8.\n\n## [RPSO-ELM:](https://github.com/GustavoHFMO/SISC/blob/main/algoritmos_online/RPSO_ELM.py)\n\u003e RAKITIANSKAIA, A. S.; ENGELBRECHT, A. P. Training feedforward neural networks with dynamic particle swarm optimisation. Swarm Intelligence, Springer, v. 6, n. 3, p. 233–270, 2012. \n\n![](https://github.com/GustavoHFMO/SISC/blob/main/images/SISC_P_execution.png)\n\n## License\nThis project is under a GNU General Public License (GPL) Version 3. See [LICENSE](https://www.gnu.org/licenses/gpl-3.0-standalone.html) for more information.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgustavohfmo%2Fsisc","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgustavohfmo%2Fsisc","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgustavohfmo%2Fsisc/lists"}