Yuanchang Xie

TL;DR: In this article, Support Vector Machine (SVM) models were used for predicting motor vehicle crashes. But, the results showed that SVM models do not overfit the data and offer similar, if not better, performance than Back-Propagation Neural Network (BPNN) models documented in previous research.

TL;DR: The results show that in general both types of neural network models perform better than the NB regression model in terms of data prediction and that BNNs could be used for other useful analyses in highway safety, including the development of accident modification factors and for improving the prediction capabilities for evaluating different highway design alternatives.

TL;DR: Two types of wavelet Kalman filter models based on Daubechies 4 and Haar mother wavelets are investigated and the test results show that both proposed waveletKalman Filter models outperform the direct Kalman Filter model in terms of mean absolute percentage error and root mean square error.

TL;DR: In this paper, a series of models were compared using data collected on rural frontage roads in Texas and the results showed that both types of neural network models perform better than the NB regression model in terms of statistical fit and prediction.

TL;DR: A detailed review and systematic comparison of existing microscopic lane- changing models that are related to roadway traffic simulation is conducted to provide a better understanding of respective properties, including strengths and weaknesses of the lane-changing models, and to identify potential for model improvement using existing and emerging data collection technologies.