A posteriori real-time recurrent learning schemes for a recurrentneural network based nonlinear predictor

Recurrent neural networks (RNNs) are well established for the nonlinear and nonstationary signal prediction paradigm. Appropriate learning algorithms, such as the real-time recurrent learning (RTRL) algorithm, have been developed for that purpose. However, little is known about the RNN time-management policy. Here, insight is provided into the time-management of the RNN, and an a posteriori approach to the RNN based nonlinear signal prediction paradigm is offered. Based upon the chosen time-management policy, algorithms are developed, from the a priori learning-a priori error strategy through to the a posteriori learning-a posteriori error strategy. Compared with the a priori algorithms, the a posteriori algorithms offered are shown to provide a better prediction performance with little further expense in terms of computational complexity. Simulations undertaken on speech using the newly introduced algorithms confirm the theoretical results     

Towards the Optimal Learning Rate for Backpropagation

A backpropagation learning algorithm for feedforward neural networks withan adaptive learning rate is derived. The algorithm is based uponminimising the instantaneous output error and does not include anysimplifications encountered in the corresponding Least Mean Square (LMS)algorithms for linear adaptive filters. The backpropagation algorithmwith an adaptive learning rate, which is derived based upon the Taylorseries expansion of the instantaneous output error, is shown to exhibitbehaviour similar to that of the Normalised LMS (NLMS) algorithm. Indeed,the derived optimal adaptive learning rate of a neural network trainedby backpropagation degenerates to the learning rate of the NLMS for a linear activation function of a neuron. By continuity, the optimal adaptive learning rate for neural networks imposes additional stabilisationeffects to the traditional backpropagation learning algorithm.     

Study of the dead layer in germanium for the CDMS detectors

We present new measurements on a Cryogenic Dark Matter Search (CDMS) detector with electron, neutron, and gamma sources. The measurements have been performed to investigate the dead layer of one of the CDMS Z-dependent Ionization Phonon germanium detectors. The dead layer has been studied at both charge electrodes and at different electric field intensities. We also present a method to remove the dependence of athermal phonon measurements on event position.     

Synthesis of regional networks for the supply of energy and bioproducts

This article presents a method for the synthesis of regional renewable energy supply chains, based on Mixed-Integer Linear Programming (MILP). This method addresses the challenges presented by biomass resources. The main challenges are the distributive and varied availabilities regarding both location and time. This work also aims to maximise the economically viable utilisation of resources, accounting for the competition between energy and food production. A four-layer supply chain superstructure has been developed, which includes the harvesting, preparation, core processing and distribution of products. This considered system’s boundaries involve a region, which is then divided into zones for optimising conversion operations and transportation flows. An MILP model has been formulated with profit maximisation as the optimisation criterion. The environmental impact is evaluated by the carbon footprint. The sensitivity of the optimal solutions is analysed for different regions’ sizes, transportation costs, pre-processing alternatives and the co-production of food and energy.     

Analysis and online realization of the CCA approach for blind source separation.

A critical analysis of the canonical correlation analysis (CCA) approach in blind source separation (BSS) is provided. It is proved that by maximizing the autocorrelation functions of the recovered signals we can separate the source signals successfully. It is further shown that the CCA approach represents the same class of generalized eigenvalue decomposition (GEVD) problems as the matrix pencil method. Finally, online realizations of the CCA approach are discussed with a linear-predictor-based algorithm studied as an example.     

Influence of background and surround on image color matching

In this article, the corresponding‐color data for complex images reproduced on different media were obtained by simultaneous matching using an adjustment method. In our experiment printed color images and images displayed on a monitor were compared in different viewing conditions. The viewing condition varied in surround relative luminance and background. The experimental data show that surround relative luminance has little influence on color matching between printed and monitor images while changes in background modify color appearance. These results were used to evaluate different chromatic adaptation transforms (CAT). We found that for the same viewing conditions the SHARP transform shows the best agreement between the experimental and predicted data. SHARP transform can not predict accurately corresponding colors for blue and black regions. Therefore, we proposed new CAT that shows better characteristics than other transforms for cyan, green, and black colors and similar characteristics for other colors. © 2007 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 17, 244–251, 2007     

Influence of solvent and temperature on extraction of phenolic compounds from grape seed,antioxidant activity and colour of extract

This study was aimed to investigate the influence of solvent (water and ethanol in concentration: 50%, 70% and 96%) and extraction temperature (25–80) °C on polyphenols extraction of grape seed (Vitis vinifera L. cv. “Frankovka”) cultivated in Eastern Croatia. The best results were reached using 50% ethanol at 80 °C. The most abundant individual polyphenolic compound was catechin which makes the average of 45.11% of the total phenolic content followed by epicatechin (34.45%), procyanidin B₂ (12.90%), gallic acid (5.34%), gallocatechin (1.58%), epicatechin gallate (1.01%). The antioxidant activity of extracts was determined by DPPH‐method and it was highly dependent on extraction solvent and temperature. The total extractable proanthocyanidins content of extract had the highest positive correlation (r = 0.994) with antioxidant activity, which indicated that these compounds might be the most important antioxidant in examined grape seed extracts. Relationship between phenolic content and colour of extracts was observed.     

Characterisation of Signal Modality: Exploiting Signal Nonlinearity in Machine Learning and Signal Processing

A novel method for online tracking of the changes in the nonlinearity within both real-domain and complex–valued signals is introduced. This is achieved by a collaborative adaptive signal processing approach based on a hybrid filter. By tracking the dynamics of the adaptive mixing parameter within the employed hybrid filtering architecture, we show that it is possible to quantify the degree of nonlinearity within both real- and complex-valued data. Implementations for tracking nonlinearity in general and then more specifically sparsity are illustrated on both benchmark and real world data. It is also shown that by combining the information obtained from hybrid filters of different natures it is possible to use this method to gain a more complete understanding of the nature of the nonlinearity within a signal. This also paves the way for building multidimensional feature spaces and their application in data/information fusion.