In order to reduce the traffic load and improve the system's lifetime, a cluster-based routing protocol has attracted more attention. In cluster-based sensor networks, energy can be conserved by combining redundant data from nearby sensors into cluster head nodes before forwarding the data to the destination. The lifespan of the whole network can also be expanded by the clustering of sensor nodes and through data aggregation. In this paper, we propose a cluster-based routing protocol which uses the location information of sensors to assist in network clustering. Our protocol partitions the entire network into several clusters by a particle swarm optimization (PSO) clustering algorithm. In each cluster, a cluster head is selected to deal with data aggregation or compression of nearby sensor nodes. For this clustering technique, the correct selection of the number of clusters is challenging and important. To cope with this issue, an energy dissipation model is used in our protocol to automatically estimate the optimal number of clusters. Several variations of PSO-clustering algorithm are proposed to improve the performance of our protocol. Simulation results show that the performance of our protocol is better than other protocols.

Image segmentation denotes a process by which an image is partitioned into non-intersecting regions and each region is homogeneous. Utilizing histogram information to aim at segmenting an image is a commonly used method for many applications. In this paper, we view the image segmentation as an optimization problem. We find a curve which gives the best fit to the given image histogram, and the parameters in the curve are determined by using the particle swarm optimization algorithm. The experimental results to confirm the proposed approach are also included.

This paper presents a novel method to speed up neural network (NN) based face detection systems. NN-based face detection can be viewed as a classification and search problem. The proposed method formulates the face search problem as an integer nonlinear optimization problem (INLP) and expands the basic particle swarm optimization (PSO) to handle it. PSO works with a population of particles, each representing a subwindow in an input image. The subwindows are evaluated by how well they match a NN based face filter. A face is indicated when the filter response of the best particle is above a given threshold. Experiments on a set of 42 test images show the effectiveness of the proposed approach. Moreover, the effect of PSO parameter settings on the search performance was investigated.