Prediction of air quality based on machine learning techniques
Not available
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | |
| التنسيق: | Master's thesis |
| اللغة: | الإنجليزية |
| منشور في: |
Universiti Teknologi Malaysia
2025
|
| الموضوعات: | |
| الوصول للمادة أونلاين: | https://utmik.utm.my/handle/123456789/41857 |
| Abstract | Abstract here |
| _version_ | 1854975103985516544 |
|---|---|
| author | Yang, Lei |
| author2 | Azlan Mohad Zain, supervisor |
| author_facet | Azlan Mohad Zain, supervisor Yang, Lei |
| author_sort | Yang, Lei |
| description | Not available |
| format | Master's thesis |
| id | utm-123456789-41857 |
| institution | Universiti Teknologi Malaysia |
| language | English |
| publishDate | 2025 |
| publisher | Universiti Teknologi Malaysia |
| record_format | dspace |
| record_pdf | Abstract |
| spelling | utm-123456789-418572025-08-21T10:05:00Z Prediction of air quality based on machine learning techniques Yang, Lei Azlan Mohad Zain, supervisor Science Not available The purpose of this project is to propose a combined prediction model based on ARIMA-SVM for air quality monitoring to improve the accuracy of air pollutant PM2.5 concentration prediction. Accuracy prediction of PM2.5 concentration is one of the greatest significance to the study of urban environmental pollution and air quality which can support more effective prevention measures. This project combines ARIMA and SVM models and uses the linear and nonlinear advantages of ARIMA and SVM models to predict and analyze air quality. The combined ARIMA-SVM model was compared with a single ARIMA model in terms of Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE). The results showed that the average percentage error of the combined ARIMA-SVM model was 9.32% and the average percentage error of the ARIMA model was 33.79%. In comparison, the average percentage error of the combined ARIMA-SVM model is reduced by 24.47%, which has a better prediction effect and higher prediction accuracy. zulraizam UTM 60 p. Thesis (Master of Science (Data Science)) - Universiti Teknologi Malaysia, 2023 2025-03-10T03:07:38Z 2025-03-10T03:07:38Z 2023 Master's thesis https://utmik.utm.my/handle/123456789/41857 vital:152846 valet-20230820-082942 ENG Closed Access UTM Complete Unpublished Completion application/pdf Universiti Teknologi Malaysia |
| spellingShingle | Science Yang, Lei Prediction of air quality based on machine learning techniques |
| thesis_level | Master |
| title | Prediction of air quality based on machine learning techniques |
| title_full | Prediction of air quality based on machine learning techniques |
| title_fullStr | Prediction of air quality based on machine learning techniques |
| title_full_unstemmed | Prediction of air quality based on machine learning techniques |
| title_short | Prediction of air quality based on machine learning techniques |
| title_sort | prediction of air quality based on machine learning techniques |
| topic | Science |
| url | https://utmik.utm.my/handle/123456789/41857 |
| work_keys_str_mv | AT yanglei predictionofairqualitybasedonmachinelearningtechniques |