Prediction of Ambient Air Quality Based on Neural Network Technique

Kamal, Mahanijah Md; Jailani, Rozita; Shauri, Ruhizan Liza Ahmad

doi:10.1109/scored.2006.4339321

Cited by 33 publications

(15 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ANN and MLR models based on original raw data, as well as PC-ANN and PCR models based on four PC scores, are compared to obtain the accurate AQI prediction. The results show that the feed-forward ANN model, using ten original parameters as inputs, gives a high value of R 2 and low values of error rates that contrast to results from MLR model (Method 1). However, Method 2 (PC-ANN using Varimax method) gives better prediction of the results as compared to Method l in term of R 2 value and error rate values.…”

Section: Resultsmentioning

confidence: 93%

“…This problem is addressed by defining the Air Quality Index (AQI) of a given area. AQI system plays a vital part in conveying to both decision-makers and the public the situation of ambient air quality that extends from good to dangerous [2]. AQI, which is too known as Air Pollution Index ( (API) has been developed and spread by numerous agencies in U.S. Canada, Europe, Australia, China, Indonesia, Taiwan, etc [3].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Estimation of Air Quality Index by Merging Neural Network with Principal Component Analysis

Sarwat¹

2018

IJCA

View full text Add to dashboard Cite

The objective of this study is to merge the Principal Component Analysis (PCA) with Artificial Neural Network (ANN) techniques to get the precise results in estimating the Air Quality Index (AQI). This study is applied for Ain Sokhna city for year 2014. Principal components score (PCs) of 10 historical air quality and meteorological parameters are generated and selected appropriately as the input variables in ANN models for predicting AQI. ANN and Multiple Linear Regression (MLR) models are applied and compared for four methods to estimate the AQI. Ten air pollutant and metrological parameters (actual data) are used as input data in ANN and MLR for creating the first method. The other three methods (Varimax, Equamax and Quartimax) are generated by rotating the actual data using PCA to reduce the ten parameters into four PCs for each PCA method. Consequently, the four PCs of each method are used as input data in ANN (PC-ANN) and MLR (PCR) models. The performance of the methods has been compared using Coefficient of Determination (R 2 ), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE) and Mean Absolute Error (MAE). Considering the complexity of the air pollution phenomenon, it is found that the ANN model gives the best solution for all rotating PCs using Varimax method. The results show that the estimation of AQI by merging ANN with PCA (PC-ANN) gives more accurate results than merging MLR with PCA (PCR). This indicates that the ANN method can be applied successfully as a tool for decision making and problem solving for better atmospheric management.

show abstract

Section: Resultsmentioning

confidence: 93%

Section: Introductionmentioning

confidence: 99%

Estimation of Air Quality Index by Merging Neural Network with Principal Component Analysis

Sarwat¹

2018

IJCA

View full text Add to dashboard Cite

show abstract

“…The index is important in evaluating the air quality of different sources (Azid et al, 2014a). Once the compliance or lack of compliance determined, the data can be used to advise or caution the public in lieu of health effects (Kamal et al, 2006;Azid et al, 2014a). Poor air quality has both acute and chronic effects, especially to human health (Moustris et al, 2010).…”

Section: Introductionmentioning

confidence: 99%

Identification Source of Variation on Regional Impact of Air Quality Pattern Using Chemometric

Azid

Juahir

Ezani

et al. 2015

Aerosol Air Qual. Res.

View full text Add to dashboard Cite

This study intends to show the effectiveness of hierarchical agglomerative cluster analysis (HACA), discriminant analysis (DA), principal component analysis (PCA), factor analysis (FA) and multiple linear regressions (MLR) for assessing the air quality data and air pollution sources pattern recognition. The data sets of air quality for 12 months (January-December) in 2007, consisting of 14 stations around Peninsular Malaysia with 14 parameters (168 datasets) were applied. Three significant clusters -low pollution source (LPS) region, moderate pollution source (MPS) region, and slightly high pollution source (SHPS) region were generated via HACA. Forward stepwise of DA managed to discriminate 8 variables, whereas backward stepwise of DA managed to discriminate 9 out of 14 variables. The method of PCA and FA has identified 8 pollutants in LPS and SHPS respectively, as well as 11 pollutants in MPS region, where most of the pollutants are expected derived from industrial activities, transportation and agriculture systems. Four MLR models show that PM 10 categorize as the primary pollutant in Malaysia. From the study, it can be stipulated that the application of chemometric techniques can disclose meaningful information on the spatial variability of a large and complex air quality data. A clearer review about the air quality and a novel design of air quality monitoring network for better management of air pollution can be achieved.

show abstract

“…With increasingly of air pollution, it is important to investigate and predict air quality exactly for providing proper actions and controlling strategies so that the adverse effects to human health can be minimized. For predicting purposes, ANN and MLR were applied due to it has strong capability in predicting the complicated of data, can be trained accurately and gives a better performance compared to other models (Kamal et al 2006;Karatzas and Kaltsatos 2007).…”

Section: Introductionmentioning

confidence: 99%