Understanding the usage of a product is essential for any manufacturer in particular for further development. Driving style of the driver is a significant factor in the usage of a city bus. This work proposes a new method to observe various driving manoeuvres in regular operations and identify the patterns in these manoeuvres. The significant advance in this method over other engineering approaches is the use of uncompressed data instead of transformations into certain Performance indicators. Here, the time series inputs were preserved and prepared as 10-second-frames using a sliding window technique and fed into Kohonen’s Self-organizing Map (SOM) algorithm. This produced a high accuracy in the identification and classification of maneuvres and at the same time to a highly interpretable solution that can be readily used for suggesting improvements. The proposed method is applied to comparing the driving styles of two drivers driving in a similar environment; the differences are illustrated using frequency distributions of identified manoeuvres and then interpreted for the amelioration of fuel consumption.

+More

engineering approaches uncompressed data selforganizing map som method amelioration of fuel consumption style sliding window technique driving manoeuvres identification and classification of maneuvres time series frequency distributions of

Sivakkumaran Lakshminarayanan,.Application of Self-Organizing Maps on Time Series Data for identifying interpretable Driving Manoeuvres. 12 (1),1-11.

Sivakkumaran Lakshminarayanan,"Application of Self-Organizing Maps on Time Series Data for identifying interpretable Driving Manoeuvres" 12

Sivakkumaran Lakshminarayanan,"Application of Self-Organizing Maps on Time Series Data for identifying interpretable Driving Manoeuvres"

Barreto, G.A. (2007). Time series prediction with the self-organizing map: A review. In Perspectives of Neural-Symbolic Integration. https://doi.org/10.1007/978-3-540-73954-8_6. Springer, Berlin, (pp. 135–158).

Rohani, M., & Buhari, R. (2014). How much money can be saved? impact of driving style on bus fuel consumption. In InCIEC 2013. https://doi.org/10.1007/978-981-4585-02-6_35. Springer, (pp. 399–411).

Hastie, T., Tibshirani, R., Friedman, J. (2009). The elements of statistical learning: data mining, inference, and prediction. New York: Springer Science & Business Media. isbn=9780387848587, http://citeseerx.ist.psu.edu/viewdoc/download?. https://doi.org/10.1.1.158.8831&rep=rep1&type=pdf. Accessed 24 Apr 2020.

Nouveliere, L., Braci, M., Menhour, L., Luu, H., Mammar, S. (2008). Fuel consumption optimization for a city bus. In UKACC Control conference. (pp. 1–6), isbn=978-0-9556152-1-4. http://ukacc.group.shef.ac.uk/proceedings/control2008/papers/p50.pdf. Accessed 24 Apr 2020.

Wehrens, R., & Buydens, L.M.C. (2007). Self- and super-organizing maps in R: The kohonen package. Journal of Statistical Software, 21(5), 1–19. https://doi.org/10.18637/jss.v021.i05.

Weisstein, E.W. (2019). Inflection point. http://mathworld.wolfram.com/InflectionPoint.html. Accessed 24 Apr 2020.

LogiCom GmbH (2017). Fms-standard. http://www.fms-standard.com/Bus/faq.htm. kohonenPaper.

Wehrens, R., & Kruisselbrink, J. (2018). Flexible self-organizing maps in kohonen 3.0.Journal of Statistical Software, Articles, 87(7), 1–18. https://doi.org/10.18637/jss.v087.i07. https://www.jstatsoft.org/v087/i07. Accessed 24 Apr 2020.

Stanton, N. (2019). Driving Style Modelling with Adaptive Neuro-Fuzzy Inference System and Real Driving Data, (pp. 481–90). Cham: Springer.

Carrese, S., Gemma, A., La Spada, S. (2013). Impacts of driving behaviours, slope and vehicle load factor on bus fuel consumption and emissions: a real case study in the city of rome. Procedia-Social and Behavioral Sciences, 87, 211–221.

Zhao, M. (2019). Modeling driving behavior at single-lane roundabouts. PhD thesis. https://doi.org/10.24355/dbbs.084-201903071236-0. https://publikationsserver.tu-braunschweig.de/receive/dbbs_mods_00066445. Accessed 24 Apr 2020.

Tibshirani, R., Walther, G., Hastie, T. (2001). Estimating the number of clusters in a data set via the gap statistic. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 63(2), 411–423.

HPL SC (2002). Introduction to the controller area network (can). Application Report SLOA101, 1–17. Texas Instruments, http://www.rpi.edu/dept/ecse/mps/sloa101.pdf.

Frey, H.C., Rouphail, N.M., Zhai, H., Farias, T.L., Gonçalves, G.A. (2007). Comparing real-world fuel consumption for diesel-and hydrogen-fueled transit buses and implication for emissions. Transportation Research Part D: Transport and Environment, 12(4), 281–291.

Kohonen, T. (1990). The self organizing maps. Proceedings of IEEE, 78, 1464–1480. https://doi.org/10.1109/5.58325. https://ieeexplore.ieee.org/document/58325. Accessed 24 Apr 2020.