This paper presents a multiobjective evolutionary algorithm to optimize radial basis function neural networks (RBFNNs) in order to approach target functions from a set of input-output pairs. The procedure allows the application of heuristics to improve the solution of the problem at hand by including some new genetic operators in the evolutionary process. These new operators are based on two well-known matrix transformations: singular value decomposition (SVD) and orthogonal least squares (OLS), which have been used to define new mutation operators that produce local or global modifications in the radial basis functions (RBFs) of the networks (the individuals in the population in the evolutionary procedure). After analyzing the efficiency of the different operators, we have shown that the global mutation operators yield an improved procedure to adjust the parameters of the RBFNNs.

Extended gate fi eld-effect transistor (EGFET) is a device composed of a conventional ion-sensitive electrode and a MOSFET device, which can be applied to the measurement of ion content in a solution. This structure has a lot of advantages as compared to the Ion-Sensitive Field Effect Transistor (ISFET). In this work, we constructed an EGFET by connecting the sensing structure fabricated with SnO 2 to a commercial MOSFET (CD4007UB). From the numerical simulation of site binding model it is possible to determine some of the desirable characteristics of the fi lms. We investigate and compare SnO 2 fi lms prepared using both the Sol-gel and the Pechini methods. The aim is an amorphous material for the EGFET. The SnO 2 powder was obtained at different calcinating temperatures (200 -500 0 C) and they were investigated by X-ray diffraction (XRD), infrared spectroscopy (IR), thermogravimetric analysis (TGA) and differential thermal analysis (DTA). The fi lms were investigated as pH sensors (range 2-11).

A fundamental problem for disabled or elderly people is to manage their homes while carrying out an almost normal life, which implies using and interacting with a number of home devices. Recent studies in smart homes have proposed methods to use a laser pointer for interacting with home devices, which represents a more user-friendly and less expensive home device control environment. However, detecting the laser spot on the original non-filtered images, using standard and non-expensive cameras, and considering real home environments with varying conditions, is currently an open problem.This paper proposes a hybrid technique, where a classic technique used in image detection processes, such as Template Matching, has been combined with a Fuzzy Rule

No abstract

Porous silicon (PS) films were investigated by Raman, and photoluminescence spectroscopies using different laser excitations at 488.0, 514.5, 632.8, and 782.0 nm. The exposure of PS layers to high laser powers causes an increase in the 480 cm −1 Raman intensity and a shift and enhancement of the PL emission. A laser-assisted surface reaction is proposed to explain these observations. The analysis of the first-and second-order Raman spectra showed that the band gaps of the PS films are indirect as in bulk c-Si. The Raman phonon and the PL spectra and also the spectral distribution of the linear polarization degree (LPD) of PS layers were shown to be dependent on the laser excitation energy. This dependence cannot be explained within the quantum confinement model. A mechanism for the PL emission in PS layers is presented in which the radioactive recombination of electron-hole pairs occurs in localized centres (the Si -O -SiR moieties) at the pore/crystallite interface. These quasi-molecular centres are Jahn-Teller active, i.e. the radioactive recombination is a phonon-assisted phenomenon.

In this paper we propose a new approach for laser-based environment device control systems based on the automatic design of a Fuzzy Rule-Based System for laser pointer detection. The idea is to improve the success rate of the previous approaches decreasing as much as possible the false offs and increasing the success rate in images with laser spot, i.e., the detection of a false laser spot (since this could lead to dangerous situations). To this end, we propose to analyze both, the morphology and color of a laser spot image together, thus developing a new robust algorithm. Genetic Fuzzy Systems have also been employed to improve the laser spot system detection by means of a fine tuning of the involved membership functions thus reducing the system false offs, which is the main objective in this problem. The system presented in this paper, makes use of a Fuzzy Rule-Based System adjusted by a Genetic Algorithm, which, based on laser morphology and color analysis, shows a better success rate than previous approaches.

No abstract

No abstract