Accuracy Comparison of Vehicle Classification System Using Interval Type-2 Fuzzy Inference System

Vehicle Class is an important parameter in road traffic measurement. In this paper authors developed an algorithm to find the accuracy of the system for vehicle classification using different techniques. The algorithm mainly reads the inference system and applies various input samples, check the class of each sample and calculate the accuracy. The class is identified by checking the wheel base, ground clearance and body length of the vehicle which are taken as axle distance, chassis height and body length respectively. Initially the classification was done using Type-1 fuzzy inference system and then using adaptive neuro-fuzzy inference system(ANFIS). The accuracy of ANFIS is higher than type1 FIS but still not acceptable, hence the performance of the system needs to be further optimised in order to be adopted for the practical working system. For the purpose of enhancing the accuracy of the system the authors have decided to use type-2 fuzzy logic. The problem of uncertainty and imperfection in the data will be handled very effectively than type-1 fuzzy or adaptive neuro-fuzzy inference system. It is clear that the accuracy of type-2 FIS itself is better than ANFIS and it is apparently expected that if type-2 system is hybridised with neural network the accuracy will increase significantly.