Constructive feedforward neural networks using Hermite polynomial activation functions

In this paper, a constructive one-hidden-layer network is introduced where each hidden unit employs a polynomial function for its activation function that is different from other units. Specifically, both a structure level as well as a function level adaptation methodologies are utilized in constructing the network. The functional level adaptation scheme ensures that the "growing" or constructive network has different activation functions for each neuron such that the network may be able to capture the underlying input-output map more effectively. The activation functions considered consist of orthonormal Hermite polynomials. It is shown through extensive simulations that the proposed network yields improved performance when compared to networks having identical sigmoidal activation functions.     

Modeling and Control of Linear Two-time Scale Systems: Applied to Single-Link Flexible Manipulator

This paper deals with the problem of H _∞ control of linear two-time scale systems. The authors’ attention is focused on the robust regulation of the system based on a new modeling approach under the assumption of norm-boundedness of the fast dynamics. In the proposed approach, the fast dynamics are treated as a norm-bounded disturbance (dynamic uncertainty). In this view, the synthesis is performed only for the certain dynamics of the two-time scale system, whose order is less than that of the original system. It should be noted, however, that this scheme is significantly different from the conventional approaches of order reduction for linear two-time scale systems. Specifically, in the present work, explicitly or implicitly, all the dynamics of the system are taken into consideration. In other words, the portion that is treated as a perturbation is incorporated in the design by its maximum possible gain – in the L ₂ sense – over different values of the inputs. One of the advantagesof this approach is that – unlike in the conventional approaches of the order reduction – the reduced-order system still keeps some information of the ‘deleted’ subsystem. Also, we consider the robust stability analysis and stability bound improvement of perturbed parameter (ɛ) in the two-time scale systems by using linear fractional transformations and structured singular values (μ) approach. In this direction, by introducing the parametric uncertainty and dynamic uncertainty in the two-time scale systems, we represent the system as a standard μ-interconnection framework by using linear fractional transformations, and derive a set of new stability conditions for the system in the frequency domain. The exact solution of ɛ-bound is characterized. It is shown that, in spite of the coupling between the dynamic uncertainties and certain dynamics, the designed H _∞ controller stabilizes the overall closed-loop system, in the presence of norm-bounded disturbances. To show the effectiveness of the approach, the modeling of the single-link flexible manipulator and control of the Tip-position of the manipulator by utilizing the mentioned method are presented in the case study.     

Application of adaptive constructive neural networks to image compression

The objective of the paper is the application of an adaptive constructive one-hidden-layer feedforward neural networks (OHL-FNNs) to image compression. Comparisons with fixed structure neural networks are performed to demonstrate and illustrate the training and the generalization capabilities of the proposed adaptive constructive networks. The influence of quantization effects as well as comparison with the baseline JPEG scheme are also investigated. It has been demonstrated through several experiments that very promising results are obtained as compared to presently available techniques in the literature.     

Feedback linearization of a flexible manipulator near its rigid body manifold

It is shown that a ‘slow’ 2n-dimensional manifold exists in the 4n-dimensional state space of an n-link manipulator with n flexible joints. While the flexible manifold is not linearizable by feedback, its restriction to'the slow manifold is. A method is given for computing a feedback control which achieves an approximate linearization.     

Influence of carbohydrate source and buffer on rumen fermentation characteristics, milk yield, and milk composition in late-lactation Holstein cows

The effects of concentrate-to-forage ratio and buffer on rumen fermentation and production parameters were examined in four rumen-cannulated cows (240 +/- 18 d in milk) fed a total mixed ration ad libitum in a 4 x 4 Latin square design. The treatments were a 50:50 concentrate to forage ratio with [1.2% of dry matter, (DM)] and without (0% of DM) buffer and a 75:25 concentrate to forage ratio with (1.2% of DM) and without (0% of DM) buffer. Rumen pH declined in response to increased concentrate but was not influenced by buffer. In the absence of the buffer, rumen acetate declined and propionate was elevated at the higher level of concentrate inclusion. The milk fat concentration was lower for cows fed the high concentrate diet without buffer; however, the addition of buffer to the diet prevented the milk fat depression. Milk fat depression was associated with elevated trans-C18:1 fatty acids in milk, which provides additional support for an inhibitory effect of these fatty acids on mammary fat synthesis. We concluded that the potential of nutrition as a tool to alter milk composition is greater in later lactation as these animals are better able to cope with the negative effects of high grain diets, and the treatment response is greater than in early lactation.     

Effects of temperature and impurities on the DC conductivity of snow

Several major parameters affecting the electrical behavior of natural snow, namely volume conductivity and density, liquid water content and conductivity of water melted from snow, are crucial for the characterization of the electrical performance of snow-covered HV insulators. However, little study has been devoted to this subject, despite of its importance. These parameters are found to vary significantly with snow composition and purity as well as with other parameters, such as temperature, airborne pollutants, electric field strength and polarity. From laboratory experiments carried out on a large number of snow samples, it was found that DC conductivity of snow shows a peak at about -2degC. This apparently curious behavior near the melting temperature is attributed to important changes to the microstructure of snow. A correlation between DC conductivity and snow temperature was established     

Influence of plasma treatment on CNT absorption of cotton fabric and its electrical conductivity and antibacterial activity

In this study, effect of plasma pretreatment on the absorption of carboxilated carbon nanotubes (CNTs) on the surface of cotton fabrics was investigated. Treated samples were characterised using a Raman spectrophotometer. Also, the morphological properties of samples were studied using a scanning electron microscope. Electrical resistance and interactions between CNTs and plasma-treated cotton functional groups at the surface were also evaluated. Antibacterial activity of cotton fabric when modified by low temperature plasma and stabilised with CNTs was also investigated. Results showed a uniform coating of CNTs on the plasma-treated cotton fabric and it was found that the plasma treatment is effective on improving CNTs absorption by cotton fabric. Generally, cotton fabric characterisation, such as antibacterial activity and electrical conductivity, after plasma treatment and loading CNT are improved.     

Multi-objective discrete urban road network design

This paper addresses the problem of designing urban road networks in a multi-objective decision making framework. Given a base network with only two-way links, and the candidate lane addition and link construction projects, the problem is to find the optimal combination of one-way and two-way links, the optimal selection of network capacity expansion projects, and the optimal lane allocations on two-way links to optimize the reserve capacity of the network, and two new travel time related performance measures. The problem is considered in two variations; in the first scenario, two-way links may have different numbers of lanes in each direction and in the second scenario, two-way links must have equal number of lanes in each direction. The proposed variations are formulated as mixed-integer programming problems with equilibrium constraints. A hybrid genetic algorithm, an evolutionary simulated annealing, and a hybrid artificial bee colony algorithm are proposed to solve these two new problems. A new measure is also proposed to evaluate the effectiveness of the three algorithms. Computational results for both problems are presented.     

A corrective feedback design for nonlinear systems with fast actuators

Recent two-time-scale results can be derived from a geometric framework which allows further extensions and computational improvements. In this note the two-time scale behavior of singularly perturbed systems is exploited to design slow and fast controls and to combine them into a composite control. As an illustration, we present a corrective design to compensate for fast actuator dynamics modeled as singular perturbations.     

Critical moisture content for microbial growth in dried food‐processing residues

BACKGROUND: Food‐processing residues are good feedstocks for biofuel and biochemical production because they have high energy content and are abundant. Year‐round biofuel and biochemical production requires proper storage to prevent microbial decomposition and thermal runaway. In this study, microbial activity of tomato pomace (TP), grape pomace (GP), fermented grape pomace (FGP) and sugar beet pulp (SBP) was monitored at nine different moisture contents. RESULTS: Maximum and cumulative respirations for each feedstock with respect to moisture content followed a sigmoidal relationship. The critical moisture content below which no microbial activity was detected for SBP, TP, FGP and GP was 24–31, 16–21, 23–33 and 43–46% (dry basis) respectively. A logarithmic relationship was observed (R² = 0.94) between critical moisture content and initial water‐soluble carbohydrate (WSC) content of the processing residues. CONCLUSION: The critical moisture content below which no microbial activity was detected and the relationship between critical moisture content and initial WSC content were determined in this study for four food‐processing residues. Both parameters permit evaluation of the potential for deterioration of food‐processing residues during storage based on moisture content and WSC content. Copyright © 2010 Society of Chemical Industry