The process of extracting the accurate geographical position of mobile target has a dominant efficacy on the performance of a wireless sensor network. The location information of moving node is a mandate requirement to process the data collected by the sensor nodes. The localization technique that finds the exact location of target node in a Internet of Things framework is applied for domain-specific applications. In this paper, a fuzzy driven approach embedded with Dimensionality based Particle Swarm Optimization algorithm is proposed. The Dimensionality based Particle Swarm Optimization (DPSO) is a variant of the traditional PSO and the particle deployment is done in each dimension of the co-ordinate of target node to obtain optimized values in the individual dimension. The anisotropic properties of propagation media (i.e., environmental factors) and the characteristics of devices (i.e., sending power) are considered to compute the Received Signal Strength (RSS). An Adaptive Neuro-Fuzzy Inference System (ANFIS) is developed to study these radio irregularities and a distinct set of rules are framed in the training phase to select the appropriate attenuation exponent value. The proposed algorithm can be applied in outdoor anisotropic environments. The DPSO model outperforms well in all localization instances for three test cases containing different trajectories, where the path of target node is randomly chosen. The results were compared with the existing algorithms such as PSO and HPSO in terms of average localization error and number of iterations required to attain convergence.