Driver behavior analysis based on big data New models for fleet management Real data driven models Figure A. Proposed big data based driver behavior analysis model for fleet managementPurpose: In this study, the deficiencies of fleet management systems have been examined from both big data and driver behavior perspectives, and the driver/driving behavior has been analyzed on real data and as a result, big data based new models have been proposed to perform data analysis. With 6 different scenarios on big data, new models have been developed with big data-based approaches that determine the differences in behavior of the drivers in the fleet, the behavior at various locations and the behavior at specific points. Theory and Methods:In this study, the deficiencies of fleet management systems have been examined both in terms of big data and driver/driving behavior, real scenarios has been determined and map reduce based models have been proposed to solve this problem with the real big fleet data for the first time. Results:From the obtained results, it was determined that (1) in particular, among drivers exceeding the speed limit of more than 50%, certain drivers have a 30% share of these violations compared to other drivers. (2) Even if the average speed is the same, there can be 6 times the difference in speed violations number between drivers, similar to that, even if the number of speed violations are the same, there could be a 2-fold difference in violation times. (3) According to the seasonal analysis, the highest number of speed violations occur in the summer season. However, speed violation duration occurred in autumn at most.(4) Roads where speed limit is exceeded in Ankara are Yenimahalle with a rate of 23.6% on a district basis, Saray with a rate of 4.62% on a quarter basis, Eskişehir road with a rate of 6.85% on intercity roads basis , and Anadolu Boulevard with 2.74% on urban roads basis. Finally, (5) it has been found that differences of near 300% occur in the analysis of 3 different radar points according to the number of speed violations before and after 1 kilometer of radar points. Conclusion:As a result, by using big data analytics, fleets can be used more easily and manageable within the scope of driver/driving behavior. These models can be used to prevent cost and work loss, and these analyzes for Ankara province can be used for other provinces. It is also considered that different values can be produced such as the analysis made at speed radar points.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.