Clustering driving styles via image processing

It has become of key interest in the insurance industry to understand and extract information from telematics car driving data. Telematics car driving data of individual car drivers can be summarized in so-called speed acceleration heatmaps. The aim of this study is to cluster such speed acceleration heatmaps to different categories by analysing similarities and differences in these heatmaps. Making use of local smoothness properties, we propose to process these heatmaps as RGB images. Clustering can then be achieved by involving supervised information via a transfer learning approach using the pre-trained AlexNet to extract discriminative features. The K-means algorithm is then applied on these extracted discriminative features for clustering. The experiment results in an improvement of heatmap clustering compared to classical approaches.

[1]  Kili C. Wang,et al.  THE USE OF ANNUAL MILEAGE AS A RATING VARIABLE , 2015, ASTIN Bulletin.

[2]  Montserrat Guillén,et al.  Telematics and Gender Discrimination: Some Usage-Based Evidence on Whether Men’s Risk of Accidents Differs from Women’s , 2016 .

[3]  P. Rousseeuw.  Silhouettes: a graphical aid to the interpretation and validation of cluster analysis , 1987 .

[4]  Montserrat Guillén,et al.  Exposure as Duration and Distance in Telematics Motor Insurance Using Generalized Additive Models , 2017 .

[5]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[6]  Michel Denuit,et al.  Multivariate credibility modelling for usage-based motor insurance pricing with behavioural data , 2019, Annals of Actuarial Science.

[7]  Gerda Claeskens,et al.  Unravelling the predictive power of telematics data in car insurance pricing , 2017 .

[8]  Ronald M. Summers,et al.  Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning , 2016, IEEE Transactions on Medical Imaging.

[9]  Jun Bi,et al.  Assessing Driving Risk Using Internet of Vehicles Data: An Analysis Based on Generalized Linear Models , 2020, Sensors.

[10]  Yiik Diew Wong,et al.  Developing Singapore Driving Cycle for passenger cars to estimate fuel consumption and vehicular emissions , 2014 .

[11]  Yiyang Bian,et al.  Good drivers pay less: A study of usage-based vehicle insurance models , 2018 .

[12]  I. Jolliffe.  Principal Components in Regression Analysis , 1986 .

[13]  Tom V. Mathew,et al.  Development of real-world driving cycle: Case study of Pune, India , 2009 .

[14]  Mario V. Wüthrich.  Covariate selection from telematics car driving data , 2017 .

[15]  Antonella Santone,et al.  A “pay-how-you-drive” car insurance approach through cluster analysis , 2018, Soft Computing.

[16]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[17]  C. P. Lee,et al.  Development of a practical driving cycle construction methodology: A case study in Hong Kong , 2007 .

[18]  Guangyuan Gao,et al.  Claims frequency modeling using telematics car driving data , 2018, Scandinavian Actuarial Journal.

[19]  Trevor Hastie,et al.  An Introduction to Statistical Learning , 2013, Springer Texts in Statistics.

[20]  Montserrat Guillén,et al.  Using GPS data to analyse the distance travelled to the first accident at fault in pay-as-you-drive insurance , 2016 .

[21]  Robert Weidner,et al.  Telematic driving profile classification in car insurance pricing , 2016, Annals of Actuarial Science.