Traffic Speed Time Series Short Term Forecasting Using Aggregated Model

Modeling the behavior of groundwater levels is necessary to implement sustainable groundwater resource management. Groundwater is a non-linear and complex system, which can be modeled by data-driven models. This study evaluates the performances of data-driven models, support vector machine regression (SVR) and artificial neural network (ANN), for forecasting groundwater levels of confined and unconfined systems at 1-, 2-, and 3-month ahead. This is the first time that confined and unconfined aquifers have been compared using data-driven models. In addition, to identify the optimal input combination, a hybrid gamma test (GT) and genetic algorithm (GA) was used. The coefficient of correlation (R), Mean Absolute Error (MAE), root mean squared error (RMSE), Nash–Sutcliffe efficiency (NSE), and developed discrepancy ratio (DDR) were applied to evaluate the SVR and ANN models. Results showed that the SVR and ANN models were more accurate for the unconfined system than the confined system for forecasts up to 3-month ahead. In both hydrogeological systems for 1-month ahead, the models performed better than for 2- and 3-month ahead forecasts, and the accuracy of the models decreased as the months ahead increased. The SVR model performed better than the ANN model for 1-, 2-, and 3-month ahead groundwater-level forecasting. The SVR model could be successfully used in predicting monthly groundwater in confined and unconfined systems.

Application of robust principal component analysis–multivariate adaptive regression splines for the determination of °API gravity in crude oil samples using ATR-FTIR spectroscopy

Gas–solid fluidized beds are complex particle systems, and the electrostatic behavior of particles in fluidized beds is even more complex, which is influenced by numerous factors such as particle properties and operating conditions. Current studies focus on the effect of a certain factor on particle charging without a global picture. Furthermore, there is no mathematical model that can describe the interaction of multiple factors on particle charging because it is difficult to build a model for such a complex system. Therefore, a new approach is needed. In this study, a model capable of accurately predicting the surface charge density of particles in monodispersed gas–solid fluidized beds within a certain range was developed based on the literature and experimental data through several machine learning methods including kernel ridge regression (KRR), support vector machine regression (SVR), and multilayer perceptron (MLP). SVR and MLP models gave the best results with R2 equal to 0.980 and 0.979, respectively. However, the sensitivity analysis showed that the MLP model was more reliable than the SVR model. In conclusion, the feasibility of using machine learning to analyze the charging behavior of particles in fluidized beds is demonstrated, and the proposed MLP model can serve as an accurate correlative tool for fast and effective estimation of particle surface charge density in gas–solid fluidized beds.

Driving Decision-making Mechanism (DDM) is identified as the key technology to ensure the driving safety of autonomous vehicle, which is mainly influenced by vehicle states and road conditions. However, previous studies have seldom considered road conditions and their coupled effects on driving decisions. Therefore, road conditions are introduced into DDM in this paper, and are based on a Support Vector Machine Regression (SVR) model, which is optimized by a weighted hybrid kernel function and a Particle Swarm Optimization (PSO) algorithm, this study designs a DDM for autonomous vehicle. Then, the SVR model with RBF (Radial Basis Function) kernel function and BP (Back Propagation) neural network model are tested to validate the accuracy of the optimized SVR model. The results show that the optimized SVR model has the best performance than other two models. Finally, the effects of road conditions on driving decisions are analyzed quantitatively by comparing the reasoning results of DDM with different reference index combinations, and by the sensitivity analysis of DDM with added road conditions. The results demonstrate the significant improvement in the performance of DDM with added road conditions. It also shows that road conditions have the greatest influence on driving decisions at low traffic density, among those, the most influential is road visibility, then followed by adhesion coefficient, road curvature and road slope, while at high traffic density, they have almost no influence on driving decisions.

Short-term traffic speed prediction is a promising research topic in intelligent transportation systems (ITSs), which also plays an important role in the real-time decision-making of traffic control and guidance systems. However, the urban traffic speed has strong temporal, spatial correlation and the characteristic of complex nonlinearity and randomness, which makes it challenging to accurately and efficiently forecast short-term traffic speeds. We investigate the relevant literature and found that although most methods can achieve good prediction performance with the complete sample data, when there is a certain missing rate in the database, it is difficult to maintain accuracy with these methods. Recent studies have shown that deep learning methods, especially long short-term memory (LSTM) models, have good results in short-term traffic flow prediction. Furthermore, the attention mechanism can properly assign weights to distinguish the importance of traffic time sequences, thereby further improving the computational efficiency of the prediction model. Therefore, we propose a framework for short-term traffic speed prediction, including data preprocessing module and short-term traffic prediction module. In the data preprocessing module, the missing traffic data are repaired to provide a complete dataset for subsequent prediction. In the prediction module, a combined deep learning method that is an attention-based LSTM (ATT-LSTM) model for predicting short-term traffic speed on urban roads is proposed. The proposed framework was applied to the urban road network in Nanshan District, Shenzhen, Guangdong Province, China, with a 30-day traffic speed dataset (floating car data) used as the experimental sample. Results show that the proposed method outperforms other deep learning algorithms (such as recurrent neural network (RNN) and convolutional neural network (CNN)) in terms of both calculating efficiency and prediction accuracy. The attention mechanism can significantly reduce the error of the LSTM model (up to 12.4%) and improves the prediction performance.

Empirical approach for strength prediction of geopolymer stabilized clayey soil using support vector machines

Support vector machine regression (SVR) technique was used for predicting the uniaxial compressive strength of FRP confined concrete. Two different SVR models, viz. SVR model for carbon fiber reinforced polymer confined concrete and SVR model for glass fiber reinforced polymer confined concrete, were developed. The prediction efficacy of developed SVR models was compared with that of ANN and existing empirical FRP strength prediction models. Furthermore, for assessing variable contributions in strength prediction process, a sensitivity analysis is also presented. The study showed that SVR could be a powerful alternative physical tool for strength prediction of FRP confined concrete.

Towards an effective cross-task mental workload recognition model using electroencephalography based on feature selection and support vector machine regression

In this paper, taking the typical dangerous driving behaviors of following the preceding car too close and abnormal ways to change lane as the research object, the identification indicators are selected. Using the UC-win/Road software to build the scene, the samples to be identified were obtained, and support vector machine regression and BP neural network recognition models were constructed respectively to identify dangerous driving behaviors and compare their accuracy. The results showed that the driving behavior recognition model based on support vector regression can effectively identify the driving behavior, and the accuracy of discriminant inference was significantly higher than that based on BP neural network, both reaching over 92%. At the same time, the average prediction time was also obvious reduced. The research results have important theoretical and practical significance for the performance evaluation of behavior recognition models and the development of road traffic safety.

This study aimed to compare stepwise multiple linear regression (SMLR), partial least squares regression (PLSR) and support vector machine regression (SVMR) for estimating soil total nitrogen (TN) contents with laboratory visible/near-infrared reflectance (Vis/NIR) of selected coarse and heterogeneous soils. Moreover, the effects of the first (1st) vs. second (2nd) derivative of spectral reflectance and the importance wavelengths were explored. The TN contents and the Vis/NIR were measured in the laboratory. Several methods were employed for Vis/NIR data pre-processing. The SMLR, PLSR and SVMR models were calibrated and validated using independent datasets. Results showed that the SVMR and the PLSR models had similar performances, and better performances than the SMLR. The spectral bands near 1450, 1850, 2250, 2330 and 2430 nm in the PLSR model were important wavelengths. In addition, the 1st derivative was more appropriate than the 2nd derivative for spectral data pre-processing. PLSR was the most suitable method for estimating TN contents in this study. SVMR may be a promising technique, and its potential needs to be further explored. Moreover, the future studies using outdoor and airborne/satellite hyperspectral data for estimating TN content are necessary for testing the findings.

In order to quantitatively predictive the content of the coalbed methane (CBM), we make use of the known parameters of the core tests data to establish the support vector machine regression model between the core data and coal-bed methane content. The model is based on the small sample size theory. Using the model, we can predict the volume of gas content. We choose the coal seam thickness, coal vitrinite reflectance value and coal ash 3 parameters as input feature vectors, and coal-bed methane content as the output vector of support vector machine regression prediction model. Application of the proposed model in Binchang mining shows that the prediction error between the measured results and prediction are small and meet the accuracy requirements.

Choosing appropriate multivariate calibration and preprocessing transformation techniques is important in the determination of soil organic carbon (SOC) content based on visible and near-infrared (Vis–NIR) spectroscopy. The performance levels of partial least-squares regression (PLSR), support vector machine regression (SVMR), and wavelet neural network (WNN) calibration methods coupled with different preprocessing approaches were compared using three kinds of criteria, including the coefficient of determination (R2), root mean square error (RMSE), and residual prediction deviation (RPD). A total of 328 soil samples collected from the south bank of Hangzhou Bay were used as the dataset for the calibration–validation procedure and SOC content inversion. The effects of spectra preprocessing transformation methods were evaluated for raw spectra, Savitzky–Golay smoothing with the first derivatives of reflectance (FDR) and Savitzky–Golay smoothing with logarithm of reciprocal of the reflectance (log R−1). The results indicate that the SVMR is superior to the PLSR, and WNN models for SOC content prediction. The combination of the SVMR model with FDR provided the best prediction results for the SOC content, with R2p = 0.92, RPDP = 2.82, RMSEP = 0.36%, and a kappa correlation coefficient of interpolation as high as 0.97. The FDR of Vis–NIR spectroscopy combined with the SVMR model is recommended over the PLSR and WNN modeling techniques for the high-accuracy determination of the SOC content.

Development of a screening method for adulteration detection in coconut milk via mid-infrared spectroscopy: A study of linear and nonlinear regression method

The monitoring and replacement of lubricating oil has an important impact on mechanical equipment. In this study, based on the infrared spectroscopy monitoring method, an acid value index prediction model is established. The support vector machine regression method is used to quantitatively analyze the acid number of the oil sample, which verifies the stability and predictive ability of the quantitative prediction model, and we provide a theoretical basis and practical examples for the online monitoring of oil indicators. In addition, a support vector machine regression model is established by observing the changing law of the spectral absorption peak and selecting the dominant wavelength, and it is compared against the prediction algorithm of the long- and short-term memory network. By comparing the deviation relationship between the predicted value and the real chemical value, the feasibility of the infrared spectroscopy prediction model is verified. The experimental results show that the correlation coefficient between the predicted value of the model and the actual measured value reaches 0.98. This proves that the prediction effect of the prediction model based on the infrared spectrum data and the support vector machine regression method is better than that of the long- and short-term memory network trend prediction model, and the predicted results are reliable.

To improve the forecasting accuracy of short-term traffic flow and provide precise and reliable traffic information for traffic management units and travelers, this study proposes a hybrid prediction model that is based on the characteristics of K-nearest neighbor (KNN) method and support vector regression (SVR). The proposed hybrid model, i.e. KNN-SVR, mimics the search mechanism of the KNN method to reconstruct a time series of historical traffic flow that is similar to the current traffic flow. Then, the SVR is used for short-term traffic flow forecasting. Using actual traffic flow data, we study the effect of the traffic flows on target and adjacent section roads and analyze the forecasting accuracy of the proposed model. Results show that the KNN-SVR model that considers the target and adjacent section roads has the best performance, having a mean absolute percentage error (MAPE) of 8.29%. The forecasting error of the KNN-SVR model that considers only the target section road is slightly large, having an average MAPE of 9.16%. Furthermore, the forecasting accuracy of the KNN-SVR model is better than that of traditional prediction models, such as the KNN method, SVR, and neural networks.