A novel classification approach based on Extreme Learning Machine and Wavelet Neural Networks

Multimedia Tools and Applications - In this paper, we present a novel classification approach based on Extreme Learning Machine (ELM) and Wavelet Neural Networks. We introduce two novel...     

Convolutional neural network with joint stepwise character/word modeling based system for scene text recognition

Multimedia Tools and Applications - Text recognition in the wild is a challenging task in the field of computer vision and machine learning. Existing optical character recognition engines cannot...     

A passivity‐based simple adaptive synergetic control for a class of nonlinear systems

For a class of nonlinear systems with the representation {A(x), B(x), C} and where the system parameters and dynamics are unknown, a simple adaptive synergetic controller ensuring the asymptotic convergence of the system to a desired manifold is proposed based on the technique of simple adaptive control (SAC). It is well known that the design of the synergetic control (SC) law requires a thorough knowledge of the system parameters and dynamics. Such problem obstructs the synthesis of the SC law and the designer is prompted to pass through the estimation methods, which, in turn, poses a problem of increasing the computation time of the control algorithm. To cope with this problem, a solution is proposed by modifying the original SC law to develop an SAC‐like adaptive SC law without the need of prior knowledge of the system. The stability of the proposed adaptive controller is formally proven via the Lyapunov approach. Experimental application to a quadrotor system is given to validate the theoretical results.     

Efficient recursive least squares parameter estimation algorithm for accurate nanoCMOS variable gain amplifier performances

ABSTRACT

With the aggressive scaling of integrated circuit technology, parametric estimation is a critical task for designers who looked for solutions to the challenges of some Nanoscale CMOS parameters. This paper presented the prediction of primary parameters of CMOS transistor for 16 nm to 10 nm process nodes using both of Bisquare Weights (BW) method and a novel recursive least squares (RLS) parameter estimation algorithm. The proposed RLS algorithm consists of the minimisation of a quadratic criterion relating to the prediction error in order to attain the best estimated parameters of the developed mathematical model. The obtained results thanks to the proposed RLS algorithm were better than those reached using the BW method. Comparisons between Predictive Technology Model (PTM) data and parameters estimated with RLS algorithm were made to check the validity and the consistency of the proposed algorithm. These predicted primary parameters were helpful to estimate and to optimise the performances of the Variable Gain Amplifier (VGA) which was a basic circuit element with a key role in the design of new upcoming receivers.     

Study of planar structure applying reciprocity technique combined with MGEC and analysis of discontinuity

The 3D structure electromagnetic computation presents several difficulties related to the volume mesh. In fact, the entire volume space must be taken into account even the smallest details. In this article, we propose a formulation based on the reciprocity theorem combined with the generalized equivalent circuit method to model a planar 3D structure with both coaxial and planar excitation. The major advantage of this formulation is the fact to reduce the computational volume into 2D ones in the discontinuity plane. In addition, we focused on the calculation of the discontinuity between the excitation source and the planar structure to determine the exact behavior of the electric coaxial excitation model. The obtained current density, electric field distributions, and the input impedance are presented and discussed in the following sections. An approximately good agreement of input impedance with those obtained by the simulator and measurement is shown.     

Bioconversion of shrimp shell waste for the production of antioxidant and chitosan used as fruit juice clarifier

The pH, proteolytic activity, extent of demineralisation and deprotenisation of shrimp waste were studied during 7 days of fermentation using Pseudomonas aeruginosa A2. After 3 days, pH dropped from 7.0 to 4.4 and then remained constant. Simultaneously, a demineralisation of 92% was achieved. However, protease activity reached its highest level (1230 U mL^?1) after 1 day of incubation, and a protein removal of 90% was achieved. Chitin obtained was converted to chitosan. This chitosan, with 73% deacetylation, was tested for clarification of different fruit juices. It was observed that low concentrations of chitosan (below to 1%) greatly increase the clarity of juices without affecting the nutritional value. The antioxidant activity of the hydrolysates produced during fermentation was tested. Hydrolysate obtained after 3 days showed the strongest scavenging activity (90%), which was comparable to the positive control BHA; however, that obtained after 1 day exhibited the highest ferric‐reducing antioxidant power (OD 700 nm = 1.7).     

Characterization of boride coatings on a ductile cast iron

In this work, the EN-GJS-400-15 cast iron was pack-borided in a powder mixture composed of 5% B₄C, 5% NaBF₄ and 90% SiC at the three temperatures: 900, 950 and 1000°C for 2, 4 and 6 h, respectively. The pack-borided EN-GJS-400-15 cast iron was characterized by the following experimental techniques: optical microscopy, XRD analysis and Microhardness Vickers tester. The growth kinetics of boride layers was also investigated. As a consequence, the boron activation energy was found to be 212.28 kJ mol^–1 for the EN-GJS-400-15 cast iron. Based on a regression model, a useful equation was derived to estimate the boride layer thickness as a function of the boriding parameters (time and temperature). A good agreement was then obtained between the predicted values of boride layers thicknesses and those measured experimentally. In addition, an iso-thickness diagram was proposed to be used as a simple tool to select the boride layers thicknesses according to the potential applications of EN-GJS-400-15 cast iron in industry.     

Electric load forecasting by using dynamic neural network

Electrical energy is fundamental for the wellbeing and for the economic development of any country. However, all countries must ensure access to essential resources and ensure the continuity of its supply. Due to the non-storable nature of electrical energy, the amount of consumed active power should always be equal the produced active power just to avoid power system frequency deviation problem. In order to keep the relationship production–consumption relation in compliance with different standards and to secure profitable operations of power system, electric load consumption must be predicted and controlled instantaneously. Several statistical and classical techniques are proposed in the literature but unfortunately all these methods are not accurate in a satisfactory manner. In this paper, a dynamic neural network is used for the prediction of daily power consumption. The suitability and the performance of the proposed approach is illustrated and verified with simulations on load data collected from French Transmission System Operator (RTE) website. The obtained results show that the accuracy and the efficiency are improved comparatively to conventional methods widely used in this field of research.     

Ceria and zirconia modified natural clay based nickel catalysts for dry reforming of methane

Ce and Zr promoted Fe/Cu-modified natural clay based catalysts were prepared and tested in dry reforming of methane (DRM) at temperatures from 600 to 800 °C. The physicochemical properties of these catalysts were analyzed by means of N₂ adsorption, X-ray diffraction (XRD). H₂-temperature programmed reduction (H₂-TPR) and CO₂-temperature programmed desorption (TPD). Ce and Zr promotion resulted in a considerable increase of the catalytic activity. This increase can be mainly ascribed to an improved reducibility of Ni species, together with slightly higher Ni⁰ crystal size, that, on the other hand, also catalyze undesired parallel reactions resulting in carbon formation, such as direct methane decomposition. Both Ce and Zr presence also promoted the presence of weak and medium strength basic sites, which are thought to favor CO₂ adsorption and desorption on the catalyst surface, leading to enhanced catalytic activity.