EngLib USM > Ω School of Civil Engineering >

Prediction of pm10 concentration using multiple linear regression and support vector machine

Prediction of pm10 concentration using multiple linear regression and support vector machine / Masezatti Zailan

Abstract Zarah berdiameter aerodinamik kurang daripada 10μm (PM10) adalah salah satu bahan pencemar udara yang boleh memberi kesan negatif kepada kesihatan terhadap manusia dan alam sekitar. Tujuan kajian ini adalah untuk meramalkan kepekatan bahan zarah untuk hari berikutnya (PM10D1) dengan menggunakan model Regrasi Linear Berganda (MLR) dan Mesin Vektor Sokongan (SVM). Parameter meteorologi dan gas yang digunakan dalam kajian ini adalah zarah terampai hari ini (PM10D0), kelajuan angin (WS), suhu (TEMP), kelembapan relatif (RH), sulfur dioksida (SO2), nitrogen dioksida (NO2), ozon (O3) dan karbon monoksida (CO). Data purata harian yang digunakan dalam kajian ini dibahagikan kepada data latihan (70%) dan data pengesahan (30%) dan digunakan dari tahun 2013 hingga 2015. Empat stesen pengawasan telah dipilih dalam kajian ini untuk meramalkan kepekatan PM10 untuk hari seterusnya (PM10D1) iaitu Jerantut yang bertindak sebagai stesen latar belakang, Nilai (kawasan perindustrian), Seberang Jaya (kawasan sub urban) dan Shah Alam (kawasan bandar). Hasil keseluruhan data yang diperolehi dari kajian ini menunjukkan bahawa stesen pemantauan Nilai menyumbang kepekatan PM10 paling tinggi berbanding stesen pemantauan yang lain. Ini menunjukkan bahawa Nilai adalah kawasan yang lebih tercemar kerana ia dikenali sebagai kawasan yang sangat maju. Hasilnya menunjukkan bahawa Regrasi Linear Berganda (MLR) adalah model terbaik dalam meramalkan kepekatan PM10 untuk hari berikutnya berbanding dengan model Mesin Sokongan Vektor (SVM). _______________________________________________________________________________________________________ Particulate matter with an aerodynamic diameter less than 10μm (PM10) is one of the most air pollutants that can give negative effect on human health and environment. The purpose of this research is to predict the particulate matter concentration for the next day (PM10D1) by using Multiple Linear Regression (MLR) and Support Vector Machine (SVM) models. The meteorological and gaseous parameters that are used in this study are particulate matter for today (PM10D0), wind speed (WS), temperature (TEMP), relative humidity (RH), sulphur dioxide (SO2), nitrogen dioxide (NO2), ozone (O3) and carbon monoxide (CO). The daily mean data that are used in this study are divided into training data (70%) and validation data (30%) and are used from 2013 until 2015. Four monitoring stations were selected in this study to predict the PM10 concentration for the next day (PM10D1) which are Jerantut which act as background station, Nilai (industrial area), Seberang Jaya (sub-urban area) and Shah Alam (urban area). The results of overall data that are obtained from this study has shown that Nilai monitoring stations contributed the highest mean value of PM10 concentration compared to the other monitoring stations. This indicated that Nilai is a more polluted area as it is known as a highly industrialised area. The results shows that Multiple Linear Regression (MLR) is the best model in predicting PM10 concentration for the next day compared to Support Vector Machine (SVM) model.

Contributor(s): Masezatti Zailan - Author Primary Item Type: Final Year Project Identifiers: Accession Number : 875007599 Language: English Subject Keywords: Particulate; aerodynamic; air pollutants First presented to the public: 6/1/2018 Original Publication Date: 8/3/2018 Previously Published By: Universiti Sains Malaysia Place Of Publication: School of Civil Engineering Citation: Extents: Number of Pages - 76 License Grantor / Date Granted:   / ( View License ) Date Deposited 2018-08-06 10:23:48.134 Date Last Updated 2019-01-07 11:24:32.9118 Submitter: Mohd Jasnizam Mohd Salleh

All Versions

• Help | 
• About | 
• Privacy Policy