Wireless sensor networks (WSNs) consist of a large number of small devices or nodes, called micro controller units (MCUs) and located in homes and/or offices, to be operated through the internet from anywhere, making these devices smarter and more efficient. Quality of service routing is one of the critical challenges in WSNs, especially in surveillance systems. To improve the efficiency of the network, in this article we proposes a distributed learning fractal algorithm (DFLA) to design the control topology of a wireless sensor network (WSN), whose nodes are the MCUs distributed in a physical space and which are connected to share parameters of the sensors such as concentrations of C O 2 , humidity, temperature within the space or adjustment of the intensity of light inside and outside the home or office. For this, we start defining the production rules of the L-systems to generate the Hilbert fractal, since these rules facilitate the generation of this fractal, which is a fill-space curve. Then, we model the optimization of a centralized control topology of WSNs and proposed a DFLA to find the best two nodes where a device can find the highly reliable link between these nodes. Thus, we propose a software defined network (SDN) with strong mobility since it can be reconfigured depending on the amount of nodes, also we employ a target coverage because distributed learning fractal algorithm (DLFA) only consider reliable links among devices. Finally, through laboratory tests and computer simulations, we demonstrate the effectiveness of our approach by means of a fractal routing in WSNs, by using a large amount of WSNs devices (from 16 to 64 sensors) for real time monitoring of different parameters, in order to make efficient WSNs and its application in a forthcoming Smart City.

No abstract

No abstract

Abstract-The aim of this work is to define a no-referenced perceptual image quality estimator applying the perceptual concepts of the Chromatic Induction Model The approach consists in comparing the received image, presumably degraded, against the perceptual versions (different distances) of this image degraded by means of a Model of Chromatic Induction, which uses some of the human visual system properties. Also we compare our model with an original estimator in image quality assessment, PSNR. Results are highly correlated with the ones obtained by PSNR for image (99.32% Lenna and 96.95% for image Baboon), but this proposal does not need an original image or a reference one in order to give an estimation of the quality of the degraded image.

Abstract-Searching for a missing person is not an easy task to accomplish,so over the years search methods have been developed, the problem is that the methods currently available have certain limitations and these limitations are reflected in time location. Time location in a person search is a very important factor that rescuers cannot afford to waste because the missing person is exposed to great dangers. In people search the vision system of the human being plays a very important role. The human visual system has the ability to detect and identify objects such as trees, walls, people among others besides to estimate the distance to them, this gives the human being the possibility of moving in their environment. With the development of artificial intelligence primarily to computer vision it is possible to model the human visual perception and generate computer software needed to simulate these capabilities. Using computer vision is expected to search for any missing person designing and implementing algorithms in order to an Unmanned Aerial Vehicle perform this task, also thanks to the speed of this is expected to reduce the time location. By using of a Unmanned Aerial Vehicle is not intended to replace the human being in the difficult task of searching and rescuing people but rather is intended to serve as a support tool in performing this difficult task.