Creating Predictive Models for Forecasting the Accident Rate in Mountain Roads Using VANETs
Monitoring the road network status of an entire country in a visual way (as traditionally) is very hard, so different mechanisms to do it in an automatic manner have been investigated. In particular, nomadic pervasive sensing platforms based on VANETs have been recently deployed. However, the level of road damage is a relative variable, and it is necessary to predict the particular impact of the same in each case, in order to prioritize the conditioning works. Therefore, in this paper a predictive model for forecasting the accident rate in mountain roads, considering the measures previously obtained through a nomadic sensing environment (and through the weather office) is defined. The model considers the type of road under study as well as different analysis scales to perform the calculations. The model is based on Taylor’s series and multivariate functions. Real data related to Valais (Switzerland) road network is employed to construct and validate the proposed model.
KeywordsVehicular ad-hoc networks Prediction models Data analysis Pervasive sensing
This publication was produced in the framework of the RCSO NOSE project. Borja Bordel has received funding from the Ministry of Education through the FPU program (grant number FPU15/03977); and Ramón Alcarria thanks the Spanish Ministry of Education, Culture and Sport for the professor’s mobility program (José Castillejo’s 2017 grant).
Additionally, these results were supported by the Ministry of Economy and Competitiveness through SEMOLA project (TEC2015-68284-R) and from the Autonomous Region of Madrid through MOSI-AGIL-CM project (grant P2013/ICE-3019, co-funded by EU Structural Funds FSE and FEDER).
- 1.Federal Statistical Office (FSO): Land use in Switzerland. Results of the Swiss land use statistics. https://www.bfs.admin.ch/bfsstatic/dam/assets/348992/master. Accessed 26 Aug 2017
- 2.Roads and traffic 2017 - Developments, facts, figures. Annual publication of the Federal Roads Office. https://www.astra.admin.ch/astra/en/home/documentation/facts-and-figures.html. Accessed 26 Aug 2017
- 3.Dupont, A., Bocchi, Y., Rizzo, G.: NOSE: a NOmadic scalable ecosystem for pervasive sensing, computing and communication. In: International Conference on Innovative Mobile and Internet Services in Ubiquitous Computing, pp. 884–893. Springer, Cham, July 2017Google Scholar
- 4.NOSE dashboard. https://nose-e3fe0.firebaseapp.com/app/#/dashboard/sTemp. Accessed 26 Aug 2017
- 7.Quartieri, J., Mastorakis, N.E., Iannone, G., Guarnaccia, C., D’ambrosio, S., Troisi, A., Lenza, T.L.L.: A review of traffic noise predictive models. In: Recent Advances in Applied and Theoretical Mechanics, 5th WSEAS International Conference on Applied and Theoretical Mechanics (MECHANICS 2009) Puerto De La Cruz, Tenerife, Canary Islands, Spain, pp. 14–16, December 2009Google Scholar
- 12.Lin, L., Li, J., Chen, F., Ye, J., Huai, J.P.: Road traffic speed prediction: a probabilistic model fusing multi-source data. IEEE Transactions on Knowledge and Data Engineering (2017)Google Scholar
- 16.Amini, S., Gerostathopoulos, I., Prehofer, C.: Big data analytics architecture for real-time traffic control. In: 2017 5th IEEE International Conference on Models and Technologies for Intelligent Transportation Systems (MT-ITS), pp. 710–715. IEEE, June 2017Google Scholar
- 22.Dufour, L., Genoud, D., Ladevie, B., Bezian, J.J.: Heating and hot water industrial prediction system for residential district. In: 2016 30th International Conference on Advanced Information Networking and Applications Workshops (WAINA), pp. 821–826. IEEE, March 2016Google Scholar