Macroscopic Lane Change Model—A Flexible Event-Tree-Based Approach for the Prediction of Lane Change on Freeway Traffic

• Main Authors: Christina Ng, Susilawati Susilawati, Md Abdus Samad Kamal, Irene Chew Mei Leng
• Format: Article
• Language: English
• Published: MDPI AG 2021-05-01
• Series: Smart Cities
• Subjects: logistic regression; cell size; multiple lane changes; cell transmission model
• Online Access: https://www.mdpi.com/2624-6511/4/2/44

Binary logistic regression has been used to estimate the probability of lane change (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>L</mi><mi>C</mi></mrow></semantics></math></inline-formula>) in the Cell Transmission Model (CTM). These models remain rigid, as the flexibility to predict <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>L</mi><mi>C</mi></mrow></semantics></math></inline-formula> for different cell size configurations has not been accounted for. This paper introduces a relaxation method to refine the conventional binary logistic <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>L</mi><mi>C</mi></mrow></semantics></math></inline-formula> model using an event-tree approach. The <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>L</mi><mi>C</mi></mrow></semantics></math></inline-formula> probability for increasing cell size and cell length was estimated by expanding the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>L</mi><mi>C</mi></mrow></semantics></math></inline-formula> probability of a pre-defined model generated from different configurations of speed and density differences. The reliability of the proposed models has been validated with NGSIM trajectory data. The results showed that the models could accurately estimate the probability of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>L</mi><mi>C</mi></mrow></semantics></math></inline-formula> with a slight difference between the actual <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>L</mi><mi>C</mi></mrow></semantics></math></inline-formula> and predicted <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>L</mi><mi>C</mi></mrow></semantics></math></inline-formula> (95% Confidence Interval). Furthermore, a comparison of prediction performance between the proposed model and the actual observations has verified the model’s prediction ability with an accuracy of 0.69 and Area Under Curve (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>A</mi><mi>U</mi><mi>C</mi></mrow></semantics></math></inline-formula>) value above 0.6. The proposed method was able to accommodate the presence of multiple <i>LC</i>s when cell size changes. This is worthwhile to explore the importance of such consequences in affecting the performance of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>L</mi><mi>C</mi></mrow></semantics></math></inline-formula> prediction in the CTM model.