Fuzzy-Logic Based Identification of Conventional Two-Lane Roads
- Felipe Barreno 1
- Matilde Santos 1
- Romana, Manuel G. 2
-
1
Universidad Complutense de Madrid
info
-
2
Universidad Politécnica de Madrid
info
- Álvaro Herrero (coord.)
- Carlos Cambra (coord.)
- Daniel Urda (coord.)
- Javier Sedano (coord.)
- Héctor Quintián (coord.)
- Emilio Corchado (coord.)
Editorial: Springer Suiza
ISBN: 978-3-030-57801-5, 978-3-030-57802-2
Año de publicación: 2021
Páginas: 418-428
Congreso: International Conference on Soft Computing Models in Industrial and Environmental Applications SOCO (15. 2020. Burgos)
Tipo: Aportación congreso
Resumen
This paper presents a Soft Computing based system to identify and classify conventional two-lane roads according to their geometrical characteristics. The variability of input information and the uncertainty generated by the overlapping of this information make fuzzy logic a suitable technique to address this problem. A fuzzy rule-based Mamdani-type inference system and a neurofuzzy system are applied. The roads geometrical features are measured by vehicle sensors and are used to classify the roads according to their real conditions. The conventional two-lane roads used for this research are located in the Madrid Region, Spain. The good results obtained with the fuzzy system suggests this intelligent system can be used to update the road databases; the theoretical class of road assigned to each road should be updated according to their present characteristics,as this is key to estimate the recommended speed for a safety and comfortable driving.