An improved Fuzzy C Means clustering algorithm and its application in traffic condition recognition

This paper proposes an improved FCM algorithm aiming at many problems in Fuzzy C Means algorithm, such as being sensitive to initial conditions, usually leading to local minimum results. The new algorithm can obtain global optimal solutions through a new simple and efficient selecting rule of the initial cluster centers, furthermore alternating optimization in terms of a novel separable criterion. By comparative testing with custom FCM, the new algorithms not only have fewer numbers of iterations and have higher accuracy, but also more suitable for problems with not balanced classified samples. Finally, the new algorithm is applied in traffic condition recognition and the result shows that the new clustering approach is promising for the dynamic identification of road traffic state.