Optimizing PM2.5 Forecasting Accuracy with Hybrid Meta-Heuristic and Machine Learning Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909238214787072 |
|---|---|
| author | Ghafariasl, Parviz Zeinalnezhad, Masoomeh Ahmadishokooh, Amir |
| author_facet | Ghafariasl, Parviz Zeinalnezhad, Masoomeh Ahmadishokooh, Amir |
| contents | Timely alerts about hazardous air pollutants are crucial for public health. However, existing forecasting models often overlook key factors like baseline parameters and missing data, limiting their accuracy. This study introduces a hybrid approach to address these issues, focusing on forecasting hourly PM2.5 concentrations using Support Vector Regression (SVR). Meta-heuristic algorithms, Grey Wolf Optimization (GWO) and Particle Swarm Optimization (PSO), optimize SVR Hyper-parameters "C" and "Gamma" to enhance prediction accuracy. Evaluation metrics include R-squared (R2), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE). Results show significant improvements with PSO-SVR (R2: 0.9401, RMSE: 0.2390, MAE: 0.1368) and GWO-SVR (R2: 0.9408, RMSE: 0.2376, MAE: 0.1373), indicating robust and accurate models suitable for similar research applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_01647 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Optimizing PM2.5 Forecasting Accuracy with Hybrid Meta-Heuristic and Machine Learning Models Ghafariasl, Parviz Zeinalnezhad, Masoomeh Ahmadishokooh, Amir Neural and Evolutionary Computing Artificial Intelligence Machine Learning Timely alerts about hazardous air pollutants are crucial for public health. However, existing forecasting models often overlook key factors like baseline parameters and missing data, limiting their accuracy. This study introduces a hybrid approach to address these issues, focusing on forecasting hourly PM2.5 concentrations using Support Vector Regression (SVR). Meta-heuristic algorithms, Grey Wolf Optimization (GWO) and Particle Swarm Optimization (PSO), optimize SVR Hyper-parameters "C" and "Gamma" to enhance prediction accuracy. Evaluation metrics include R-squared (R2), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE). Results show significant improvements with PSO-SVR (R2: 0.9401, RMSE: 0.2390, MAE: 0.1368) and GWO-SVR (R2: 0.9408, RMSE: 0.2376, MAE: 0.1373), indicating robust and accurate models suitable for similar research applications. |
| title | Optimizing PM2.5 Forecasting Accuracy with Hybrid Meta-Heuristic and Machine Learning Models |
| topic | Neural and Evolutionary Computing Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2407.01647 |