scholarly journals A data calibration method for micro air quality detectors based on a LASSO regression and NARX neural network combined model

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Bing Liu ◽  
Yueqiang Jin ◽  
Dezhi Xu ◽  
Yishu Wang ◽  
Chaoyang Li
Keyword(s):  
Neural Network ◽  
Air Quality ◽  
Influencing Factors ◽  
Control Point ◽  
Measurement Data ◽  
Pollutant Concentration ◽  
Lasso Regression ◽  
Narx Model ◽  
Narx Neural Network ◽  
Better Than

AbstractStudies have shown that there is a certain correlation between air pollution and various human diseases, especially lung diseases, so it is very meaningful to monitor the concentration of pollutants in the air. Compared with the national air quality monitoring station (national control point), the micro air quality detector has the advantage that it can monitor the concentration of pollutants in real time and grid, but its measurement accuracy needs to be improved. This paper proposes a model combining the least absolute selection and shrinkage operator (LASSO) regression and nonlinear autoregressive models with exogenous inputs (NARX) to calibrate the data measured by the micro air quality detector. Before establishing the LASSO-NARX model, correlation analysis is used to test whether the correlation between the concentration of air pollutants and its influencing factors is significant, and to find out the main factors that affect the concentration of pollutants. Due to the multicollinearity between various influencing factors, LASSO regression is used to further screen the influencing factors and give the quantitative relationship between the pollutant concentration and various influencing factors. In order to improve the prediction accuracy of pollutant concentration, the predicted value of each pollutant concentration in the LASSO regression model and the measurement data of the micro air quality detector are used as input variables, and the LASSO-NARX model is constructed using the NARX neural network. Several indicators such as goodness of fit, root mean square error, mean absolute error and relative mean absolute percent error are used to compare various air quality models. The results show that the prediction results of the LASSO-NARX model are not only better than the LASSO model alone and the NARX model alone, but also better than the commonly used multilayer perceptron and radial basis function neural network. Using this model to calibrate the measurement data of the micro air quality detector can increase the accuracy by 61.3–91.7%.

scholarly journals A Data Calibration Method of Micro Air Quality Detector Based on LASSO Regression and NARX Neural Network Combined Model

2021 ◽  
Author(s):  
Bing Liu ◽  
Yueqiang Jin ◽  
Dezhi Xu ◽  
Yishu Wang ◽  
Chaoyang Li
Keyword(s):  
Neural Network ◽  
Air Quality ◽  
Influencing Factors ◽  
Control Point ◽  
Measurement Data ◽  
Lasso Regression ◽  
National Control ◽  
Narx Model ◽  
Narx Neural Network ◽  
Better Than

Abstract Studies have shown that there is a certain correlation between air pollution and various human diseases, especially lung diseases, so it is very meaningful to monitor the concentration of pollutants in the air. Compared with the national air quality monitoring station (national control point), the micro air quality detector has the advantage that it can monitor the concentration of pollutants in real time and grid, but its measurement accuracy needs to be improved. In this paper, the measurement data of the micro air quality detector is calibrated with the help of the LASSO regression and NARX neural network combination (LASSO-NARX) model using the data measured by the national control point. First, correlation analysis is used to test whether the correlation between the concentration of air pollutants and its influencing factors is significant. Second, LASSO regression is used to give the quantitative relationship between pollutant concentration and various influencing factors. Third, the predicted value of each pollutant concentration in the LASSO regression model and the measurement data of the micro air quality detector are used as input variables, and the LASSO-NARX model is constructed using the NARX neural network. Finally, several indicators such as Root Mean Square Error, goodness of fit, Mean Absolute Error and Relative Mean Absolute Percent Error are used to compare various air quality models. The results show that the prediction results of the LASSO-NARX model are not only better than the LASSO model alone and the NARX model alone, but also better than the commonly used multilayer perceptron and radial basis function neural network. The LASSO-NARX model performed equally well on the training set and test set, indicating that the model has excellent generalization capabilities. Using this model to calibrate the measurement data of the micro air quality detector can increase the accuracy by 61.3% to 91.7%.

scholarly journals Application of combined model of stepwise regression analysis and artificial neural network in data calibration of miniature air quality detector

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Bing Liu ◽  
Qingbo Zhao ◽  
Yueqiang Jin ◽  
Jiayu Shen ◽  
Chaoyang Li
Keyword(s):  
Neural Network ◽  
Air Quality ◽  
Regression Model ◽  
Multilayer Perceptron ◽  
Stepwise Regression ◽  
Control Point ◽  
Measurement Data ◽  
Environmental Indicators ◽  
Air Pollutant ◽  
Mlp Model

AbstractIn this paper, six types of air pollutant concentrations are taken as the research object, and the data monitored by the micro air quality detector are calibrated by the national control point measurement data. We use correlation analysis to find out the main factors affecting air quality, and then build a stepwise regression model for six types of pollutants based on 8 months of data. Taking the stepwise regression fitting value and the data monitored by the miniature air quality detector as input variables, combined with the multilayer perceptron neural network, the SRA-MLP model was obtained to correct the pollutant data. We compared the stepwise regression model, the standard multilayer perceptron neural network and the SRA-MLP model by three indicators. Whether it is root mean square error, average absolute error or average relative error, SRA-MLP model is the best model. Using the SRA-MLP model to correct the data can increase the accuracy of the self-built point data by 42.5% to 86.5%. The SRA-MLP model has excellent prediction effects on both the training set and the test set, indicating that it has good generalization ability. This model plays a positive role in scientific arrangement and promotion of miniature air quality detectors. It can be applied not only to air quality monitoring, but also to the monitoring of other environmental indicators.

scholarly journals Deep Learning Convolutional Neural Network for the Retrieval of Land Surface Temperature from AMSR2 Data in China

Sensors ◽  
2019 ◽  
Vol 19 (13) ◽  
pp. 2987 ◽  
Author(s):  
Jiancan Tan ◽  
Nusseiba NourEldeen ◽  
Kebiao Mao ◽  
Jiancheng Shi ◽  
Zhaoliang Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Surface Temperature ◽  
Convolutional Neural Network ◽  
Land Surface Temperature ◽  
Land Surface ◽  
Measurement Data ◽  
Retrieval Algorithm ◽  
Observation Data ◽  
Moderate Resolution Imaging Spectroradiometer ◽  
Better Than

A convolutional neural network (CNN) algorithm was developed to retrieve the land surface temperature (LST) from Advanced Microwave Scanning Radiometer 2 (AMSR2) data in China. Reference data were selected using the Moderate Resolution Imaging Spectroradiometer (MODIS) LST product to overcome the problem related to the need for synchronous ground observation data. The AMSR2 brightness temperature (TB) data and MODIS surface temperature data were randomly divided into training and test datasets, and a CNN was constructed to simulate passive microwave radiation transmission to invert the surface temperature. The twelve V/H channel combinations (7.3, 10.65, 18.7, 23.8, 36.5, 89 GHz) resulted in the most stable and accurate CNN retrieval model. Vertical polarizations performed better than horizontal polarizations; however, because CNNs rely heavily on large amounts of data, the combination of vertical and horizontal polarizations performed better than a single polarization. The retrievals in different regions indicated that the CNN accuracy was highest over large bare land areas. A comparison of the retrieval results with ground measurement data from meteorological stations yielded R2 = 0.987, RMSE = 2.69 K, and an average relative error of 2.57 K, which indicated that the accuracy of the CNN LST retrieval algorithm was high and the retrieval results can be applied to long-term LST sequence analysis in China.

scholarly journals Evaluating Visibility Range on Air Pollution using NARX Neural Network

2021 ◽  
Vol 9 (2) ◽  
pp. 540-547
Keyword(s):  
Neural Network ◽  
Air Pollution ◽  
Air Quality ◽  
Air Pollutant ◽  
Restriction Factors ◽  
Network Efficiency ◽  
Independent Variables ◽  
Visibility Range ◽  
Least Area ◽  
Narx Neural Network

Evaluating air visibility range is considered as one of the apparent criteria of air quality. Haze air as a conclusion of air pollution causes unpleasant breathing, psychological effects, and visibility restriction. In this study, NARX neural network applied to determine air visibility restriction factors. Data of air quality control stations of Baghshomal, Rastebazar, and Abresan in Tabriz City, Iran used which include PM2.5, PM10, NO2, SO2, O3, and CO for the duration of four years from 2013 to 2017 that considered as independent variables. NARX neural network created to find each pollutant relation to visibility restriction and networks used for simulation to analysis network results in conspectuses condition. The results showed that PM10 pollutant has the most influence on-air visibility with R=0.9 in the train, R=0.728 in the test, and R=0.75 in validation process. Also error results of the PM10 obtained as MSE=0.054. Moreover, simulation results demonstrated the least area integral between curves according to ascending order for six pollutant factors and verified PM10 accuracy in NARX network simulation. The total result as study conclusion verified NARX neural network efficiency to evaluate air visibility range while using air pollutant parameters.

Time series modelling, NARX neural network and hybrid KPCA–SVR approach to forecast the foreign exchange market in Mauritius

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Lydie Myriam Marcelle Amelot ◽  
Ushad Subadar Agathee ◽  
Yuvraj Sunecher
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Exchange Rates ◽  
Foreign Exchange ◽  
Foreign Exchange Market ◽  
Exchange Market ◽  
Content Type ◽  
Time Series Modelling ◽  
Narx Model ◽  
Narx Neural Network

PurposeThis study constructs time series model, artificial neural networks (ANNs) and statistical topologies to examine the volatility and forecast foreign exchange rates. The Mauritian forex market has been utilized as a case study, and daily data for nominal spot rate (during a time period of five years spanning from 2014 to 2018) for EUR/MUR, GBP/MUR, CAD/MUR and AUD/MUR have been applied for the predictions.Design/methodology/approachAutoregressive integrated moving average (ARIMA) and generalized autoregressive conditional heteroskedasticity (GARCH) models are used as a basis for time series modelling for the analysis, along with the non-linear autoregressive network with exogenous inputs (NARX) neural network backpropagation algorithm utilizing different training functions, namely, Levenberg–Marquardt (LM), Bayesian regularization and scaled conjugate gradient (SCG) algorithms. The study also features a hybrid kernel principal component analysis (KPCA) using the support vector regression (SVR) algorithm as an additional statistical tool to conduct financial market forecasting modelling. Mean squared error (MSE) and root mean square error (RMSE) are employed as indicators for the performance of the models.FindingsThe results demonstrated that the GARCH model performed better in terms of volatility clustering and prediction compared to the ARIMA model. On the other hand, the NARX model indicated that LM and Bayesian regularization training algorithms are the most appropriate method of forecasting the different currency exchange rates as the MSE and RMSE seemed to be the lowest error compared to the other training functions. Meanwhile, the results reported that NARX and KPCA–SVR topologies outperformed the linear time series models due to the theory based on the structural risk minimization principle. Finally, the comparison between the NARX model and KPCA–SVR illustrated that the NARX model outperformed the statistical prediction model. Overall, the study deduced that the NARX topology achieves better prediction performance results compared to time series and statistical parameters.Research limitations/implicationsThe foreign exchange market is considered to be instable owing to uncertainties in the economic environment of any country and thus, accurate forecasting of foreign exchange rates is crucial for any foreign exchange activity. The study has an important economic implication as it will help researchers, investors, traders, speculators and financial analysts, users of financial news in banking and financial institutions, money changers, non-banking financial companies and stock exchange institutions in Mauritius to take investment decisions in terms of international portfolios. Moreover, currency rates instability might raise transaction costs and diminish the returns in terms of international trade. Exchange rate volatility raises the need to implement a highly organized risk management measures so as to disclose future trend and movement of the foreign currencies which could act as an essential guidance for foreign exchange participants. By this way, they will be more alert before conducting any forex transactions including hedging, asset pricing or any speculation activity, take corrective actions, thus preventing them from making any potential losses in the future and gain more profit.Originality/valueThis is one of the first studies applying artificial intelligence (AI) while making use of time series modelling, the NARX neural network backpropagation algorithm and hybrid KPCA–SVR to predict forex using multiple currencies in the foreign exchange market in Mauritius.

scholarly journals Performance Comparison of Malaysian Air Pollution Index Prediction Using Nonlinear Autoregressive Exogenous Artificial Neural Network and Support Vector Machine

2021 ◽  
Vol 287 ◽  
pp. 04001
Author(s):  
Rosminah Mustakim ◽  
Mazlina Mamat
Keyword(s):  
Neural Network ◽  
Support Vector Machine ◽  
Air Quality ◽  
Regression Model ◽  
Quality Parameters ◽  
Kernel Functions ◽  
Series Data ◽  
Support Vector ◽  
Nonlinear Autoregressive ◽  
Narx Model

This paper compares the performance of Nonlinear Autoregressive Exogenous (NARX) Neural Network and Support Vector Machine (SVM) regression model to predict the Air Pollutant Index (API) in Malaysia. Two models namely the NARX and SVM regression were developed using the API and air quality time series data from three monitoring stations: Pasir Gudang, TTDI Jaya and Larkin. Hourly data of API and air quality parameters collected in year 2016 and 2018 were utilized to produce one step ahead API prediction. The air quality parameters consist of the NO2, SO2, CO, O3, PM2.5, PM10 concentration as well as three meteorological parameters which are wind speed, wind direction and ambient temperature. The NARX model was realized using a series-parallel feed-forward network. For the SVM regression model, different kernel functions: Linear, Quadratic, Cubic, Fine Gaussian, Medium Gaussian and Coarse Gaussian were evaluated. The performance of NARX and SVM regression was measured using the Root Mean Square Error (RMSE) and Coefficient of Determination (R2) values. Results show that the NARX model outperformed the SVM regression model in both 2016 and 2018 data respectively.

scholarly journals A Recursive Update Model for Estimating High-Resolution LAI Based on the NARX Neural Network and MODIS Times Series

2019 ◽  
Vol 11 (3) ◽  
pp. 219 ◽  
Author(s):  
Jian Wang ◽  
Jindi Wang ◽  
Yuechan Shi ◽  
Hongmin Zhou ◽  
Limin Liao
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Time Series ◽  
High Resolution ◽  
Spatial Resolution ◽  
High Spatial Resolution ◽  
Long Time Series ◽  
Long Time ◽  
Narx Model ◽  
Narx Neural Network

Leaf area index (LAI) remote sensing data products with a high resolution (HR) and long time series are in demand in a wide variety of applications. Compared with long time series LAI products with 1 km resolution, LAI products with high spatial resolution are difficult to acquire because of the lack of remote sensing observations in long-term sequences and the lack of estimation methods applicable to highly variable land-cover types. To address these problems, we proposed a recursive update model to estimate 30 m resolution LAI based on the updated Nonlinear Auto-Regressive with Exogenous Inputs (NARX) neural network and MODIS time series. First, we used a variety of HR satellite remote sensing observations to produce HR datasets for recent years. Historical low spatial resolution MODIS products were employed as background information and used to calculate the initial parameters of the NARX neural network for each pixel. Subsequently, one year’s reflectance from the HR dataset was used as the new observation that was input into the NARX model to estimate the HR LAI of that year, and the background and HR data were then used for remodeling to update the NARX model parameters. This procedure was recursively repeated year by year until both MODIS background data and all HR data were involved in the modeling. Finally, we obtained an LAI time series with 30 m resolution. In the cropland study area in Hebei Province, China, the results were compared with LAI measurements from ground sites in 2013 and 2014. A high degree of similarity existed between the results for the two study years (RMSE2013=0.288 and RMSE2014=0.296). The HR LAI estimates showed favorable spatiotemporal continuity and were in good agreement with the multisample ground survey LAI measurements. The results indicated that for data with a rapid revisit cycle and high spatial resolution, the recursive update model based on the NARX neural network has excellent LAI estimation performance and fairly strong fault-tolerance capability.

Sign in / Sign up

Export Citation Format

Share Document