In order to handle uncertainty in data, several uncertainty based models have been introduced. Perhaps the two most notable models among these are the fuzzy set introduced by Zadeh in 1965 and rough set introduced by Pawlak in 1982. These two models address two different aspects of uncertainty and these are complementary by nature. As a result their hybridization leads to better models. Particle Swarm Optimization (PSO) is an optimization technique that performs optimized search in the solution space for optimization by updation. In this chapter, we discuss on different types of PSOs and their application in classification, feature selection and rule generation. Further, we present several hybridization of PSO with fuzzy approach, rough approach and rough fuzzy approach in developing classification algorithms. Also, we discuss on a dynamic clustering algorithm which uses a rough fuzzy hybrid model embedded with PSO. We provide as an illustration the results of application of this algorithm on several real life data sets and provide its superiority through the computation of several index values for measuring classification accuracy like DB, D, α, ρ, α∗ and γ. Also, we compile some other applications of PSO. © Springer-Verlag Berlin Heidelberg 2015.