A distribution density-based methodology for driving data cluster analysis: A case study for an extended-range electric city bus

作者：

Highlights：

• Reducing feature vector dimension while maintaining most sample information.

• Introducing the DBSACN algorithm to cluster driving data.

• Constructing fuel consumption-related feature vector.

• Making cluster analysis focus on differences of samples in fuel consumption.

• Establishing the relationship between fuel consumption and driving conditions.

摘要

•Reducing feature vector dimension while maintaining most sample information.•Introducing the DBSACN algorithm to cluster driving data.•Constructing fuel consumption-related feature vector.•Making cluster analysis focus on differences of samples in fuel consumption.•Establishing the relationship between fuel consumption and driving conditions.

论文关键词：Driving conditions,Clustering,Principal component analysis,Driving features,Dynamic programming

论文评审过程：Received 8 November 2016, Revised 26 March 2017, Accepted 3 August 2017, Available online 4 August 2017, Version of Record 18 September 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.08.006