Electronics

Wavelets are known to be a valuable tool for analyzing hyperspectral images. In this letter, we propose to further improve their performance by means of a novel classificationdriven design scheme that aims at deriving a wavelet that best represents in terms of between-class discrimination capability the spectral signatures conveyed by a given hyperspectral image. This is achieved by adopting a polyphase representation of the wavelet filter bank and formulating the wavelet optimization problem within a particle-swarm-optimization (PSO) framework. Experimental results show that the proposed wavelet design method outperforms the popular Daubechies wavelets whatever the classifier type adopted in the classification process.

A problem of major interest for local governmental authorities is the monitoring of the number of cars invading the streets and the open parking lots. Different technologies have been used for such purpose. An emerging one is based on the use of remotely sensed images of very high spatial resolution, in particular those acquired from unmanned aerial vehicles. In this paper, we present a method to count objects in urban environments, with a focus on cars. It relies on an opportune sequence of processing and analysis steps so that to handle images of very few centimeters of resolution. Experimental results on real images are reported and discussed.

Automatic methods are a convenient solution to extract buildings from remote sensing images. In this paper, we propose an unsupervised method to extract buildings by means of the Gabor filters and morphological operators. Our proposed method starts from a set of the Gabor filter parameters which is selected empirically to generate a two-dimensional impulse response. The convolution of the impulse response with the image of interest enhances the buildings and attenuates the background. Moreover, morphological operators are applied to further refine the resulting class of interest. The developed algorithm is applied on many remotely sensed images; the obtained results are highly satisfactory and promising.

System reliability is an important performance index for many real-life systems, such logistic information system, electric power systems, computer systems and transportation systems. These systems can be modelled as stochastic-flow networks (SFNs) composed of arcs and nodes. In this paper, we investigate components assignment problem for stochastic flow networks subject to two constraints namely total lead-time, and system reliability. A new approach based on random weighted genetic algorithm (RWGA) is proposed for searching an optimal components assignment which leads to maximizing system reliability and minimizing total lead time. The results revealed that an optimal components assignment leads to the maximum reliability and minimum total lead-time using the proposed approach. Keyword Component Assignment Problem, Genetic Algorithm, Lead-Time, System Reliability.

Abstract— Components assignment problem subject to multiple constraints is generally considered as a multiobjective components assignment problem (MCAP). In this research work, an MCAP subject to three constraints, namely the network reliability, the total assignment cost, and the total lead-time is considered and solved. The mathematical formulation of the MCAP is given based on the constraints mentioned above (network reliability, total assignment cost, and total lead-time). Furthermore, an approach based on multiobjective particle swarm optimization (MOPSO) is presented to solve the MCAP problem. The main goal is to search for the best-assigned components that maximize network reliability and minimize both the total assignment cost and the total lead-time. The results revealed that MOPSO is more efficient than other optimization approaches based on single or multiobjective genetic algorithms. In addition, there is no need to convert the problem into minimization or maximization a...