The realization of road traffic prediction not only provides real-time and effective information for travelers, but also helps them select the optimal route to reduce travel time. Road traffic prediction offers traffic guidance for travelers and relieves traffic jams. In this paper, a real-time road traffic state prediction based on autoregressive integrated moving average (ARIMA) and the Kalman filter is proposed. First, an ARIMA model of road traffic data in a time series is built on the basis of historical road traffic data. Second, this ARIMA model is combined with the Kalman filter to construct a road traffic state prediction algorithm, which can acquire the state, measurement, and updating equations of the Kalman filter. Third, the optimal parameters of the algorithm are discussed on the basis of historical road traffic data. Finally, four road segments in Beijing are adopted for case studies. Experimental results show that the real-time road traffic state prediction based on ARIMA and the Kalman filter is feasible and can achieve high accuracy.

Real-time road traffic state prediction based on ARIMA and Kalman filter

A multi-time-scale fusion prediction model for the gas utilization rate in a blast furnace

High-aspect-ratio structures have become increasingly important in MEMS devices. In situ, real-time critical dimension and depth measurement for high-aspect-ratio structures is critical for optimizing the deep etching process. Through-focus scanning optical microscopy (TSOM) is a high-throughput and inexpensive optical measurement method for critical dimension and depth measurement. Thus far, TSOM has only been used to measure targets with dimension of 1 μm or less, which is far from sufficient for MEMS. Deep learning is a powerful tool that improves the TSOM performance by taking advantage of additional intensity information. In this work, we propose a convolutional neural network model-based TSOM method for measuring individual high-aspect-ratio trenches on silicon with width up to 30 μm and depth up to 440 μm. Experimental demonstrations are conducted and the results show that the proposed method is suitable for measuring the width and depth of high-aspect-ratio trenches with a standard deviation and error of approximately a hundred nanometers or less. The proposed method can be applied to the semiconductor field.

/pdf/mems-high-aspect-ratio-trench-three-dimensional-measurement-1fgavf6w.pdf

MEMS High Aspect Ratio Trench Three-Dimensional Measurement Using Through-Focus Scanning Optical Microscopy and Deep Learning Method

Remote estimation of inherent optical properties was greatly challenged by significant spatial-temporal variation and the extreme complexity of bio-optical properties in inland turbid water. The multiband quasi-analytical algorithm has advantages over traditional band ratio and semi-analytical algorithm in that it is based on the remote sensing reflectance model derived from radiative transfer equation and does not need the parameterization of absorption coefficients. An improved model, which used, was developed to retrieve inherent optical properties in high turbid inland water. As a first step, the backscattering coefficient at reference wavelength [bbp(λ0)] was retrieved directly by support vector machine optimization algorithm instead of step 2 in the quasi analytical algorithm for the high correlation between bbp(λ0) and remote sensing reflectance at the near-infrared wavelength. The second step, a semi-analytical support vector machine algorithm, was used to retrieve spectral shape of bbp(λ) instead...

Deriving inherent optical property for highly turbid productive inland water from MERIS data by semi-analytical model: A case study in Taihu Lake, China

The quality of the coal fed to the boiler in thermal power plant is significant to the miming efficiency and the safety of the boiler. In order to guarantee the efficiency and the safety, it is necessary to measure accurately the quality of the coal. However, the quality of the coal is not stable and cannot be measured online, which causes many problems. Therefore, a prediction model based on support vector regression (SVR) is proposed for the carbon content of pulverized coal in this paper. Firstly, main auxiliary variables are selected through correlation analysis and the data is preprocessed with normalization. Secondly, the optimal kernel function is determined through comparative analysis for different kernel functions and model parameters are determined by using grid search method. Thirdly, the SVR model is constructed through 5 steps and its training results are analyzed. Finally, the obtained model is tested by using the industrial running data and the predicted results using the SVR model are compared with these obtained by using the BP-ANN model. The results show that the SVR model is more accurate, holds better performance of promotion, and can predict the carbon content of coal boiler of the duct pulverized well.

SVR based prediction modeling for carbon content of pulverized coal in primary air pipe of thermal power plant boiler

【】By combining several parameters selection approaches of Support Vector Machine(SVM), this paper proposes a method that defines parameters directly by analyzing training samples. Experimental results based on several standard test data sets show that the method achieves better prediction accuracy and consumes less time compared to traditional grid search methods. It provides one way to deal with the problem of selecting parameters and time consuming in application of SVM. 【Key words】Support Vector Machine(SVM); regression; parameters selection

Yan Guo-hua

Papers

Parameters Selection Method for Support Vector Machine Regression