Modeling discretionary lane-changing decisions using an improved fuzzy cognitive map with association rule mining

ABSTRACT

The discretionary lane-changing process consists of two phases. The first phase is decision making on lane-changing, and the second phase is the execution of this decision. The first phase has a complex structure that is affected by many parameters. In this phase, some parameters are present that affect lane-changing directly, while some other indirect parameters motivate drivers to perform lane-changing. This study focuses on discovering the parameters that prompt drivers to change lanes. The parameters determined as a result of the interviews with the drivers were examined in the field study. Then, the impact of the parameters for lane-changing were discovered using association rule mining and the proposed Significant Association Features Extractor (SigAFE) algorithm. Fuzzy Cognitive Map (FCM) discretionary lane-changing decision models were developed using the impact values that were discovered using the SigAFE algorithm. The performances of the models were revealed with the actual data of the field study.

KEYWORDS:

• Apriori algorithm
• association rule mining
• discretionary lane-changing
• fuzzy cognitive map
• lane-changing decisions

Disclosure statement

No potential conflict of interest was reported by the author(s).