A generalized data windowing scheme for adaptive conjugate gradient algorithms

The performance of the modified adaptive conjugate gradient (CG) algorithms based on the iterative CG method for adaptive filtering is highly related to the ways of estimating the correlation matrix and the cross-correlation vector. The existing approaches of implementing the CG algorithms using the data windows of exponential form or sliding form result in either loss of convergence or increase in misadjustment. This paper presents and analyzes a new approach to the implementation of the CG algorithms for adaptive filtering by using a generalized data windowing scheme. For the new modified CG algorithms, we show that the convergence speed is accelerated, the misadjustment and tracking capability comparable to those of the recursive least squares (RLS) algorithm are achieved. Computer simulations demonstrated in the framework of linear system modeling problem show the improvements of the new modifications.

Frequency-domain beamformers using conjugate gradient techniques for speech enhancement

A multiple-iteration constrained conjugate gradient (MICCG) algorithm and a single-iteration constrained conjugate gradient (SICCG) algorithm are proposed to realize the widely used frequency-domain minimum-variance-distortionless-response (MVDR) beamformers and the resulting algorithms are applied to speech enhancement. The algorithms are derived based on the Lagrange method and the conjugate gradient techniques. The implementations of the algorithms avoid any form of explicit or implicit autocorrelation matrix inversion. Theoretical analysis establishes formal convergence of the algorithms. Specifically, the MICCG algorithm is developed based on a block adaptation approach and it generates a finite sequence of estimates that converge to the MVDR solution. For limited data records, the estimates of the MICCG algorithm are better than the conventional estimators and equivalent to the auxiliary vector algorithms. The SICCG algorithm is developed based on a continuous adaptation approach with a sample-by-sample updating procedure and the estimates asymptotically converge to the MVDR solution. An illustrative example using synthetic data from a uniform linear array is studied and an evaluation on real data recorded by an acoustic vector sensor array is demonstrated. Performance of the MICCG algorithm and the SICCG algorithm are compared with the state-of-the-art approaches.

An intelligent forex monitoring system

The need for intelligent monitoring systems has become a necessity to keep track of the complex forex market. The vast currency market is a foreign concept to the average individual. However, once it is broken down into simple terms, the average individual can begin to understand the foreign exchange market and use it as a financial instrument for future investing. We attempt to compare the performance of a Takagi-Sugeno, type neuro-fuzzy system and a feedforward neural network trained using the scaled conjugate gradient algorithm to predict the average monthly forex rates. We considered the exchange values of Australian dollar with respect to US dollar, Singapore dollar, New Zealand dollar, Japanese yen and United Kingdom pounds. The connectionist models were trained using 70% of the data and remaining was used for testing and validation purposes. It is observed that the proposed connectionist models were able to predict the average forex rates one month ahead accurately. Experiment results also reveal that the neuro-fuzzy technique performed better than the neural network

Australian forex market anaylsis using connectionist models

The need for intelligent monitoring systems has become a necessity to keep track of the complex forex market. The forex market is difficult to understand by an average individual. However, once the market is broken down into simple terms, the average individual can begin to understand the foreign exchange market and use it as a financial instrument for future investing. This paper is an attempt to compare the performance of a Takagi-Sugeno type neuro-fuzzy system and a feed forward neural network trained using the scaled conjugate gradient algorithm to predict the average monthly forex rates. The exchange values of Australian dollar are considered with respect to US dollar, Singapore dollar, New Zealand dollar, Japanese yen and United Kingdom pound. The connectionist models were trained using 70% of the data and remaining was used for testing and validation purposes. It is observed that the proposed connectionist models were able to predict the average forex rates one month ahead accurately. Experiment results also reveal that neuro-fuzzy technique performed better than the neural network.

Detection and classification of road signs in natural environments

An automatic road sign recognition system first locates road signs within images captured by an imaging sensor on-board of a vehicle, and then identifies the detected road signs. This paper presents an automatic neural-network-based road sign recognition system. First, a study of the existing road sign recognition research is presented. In this study, the issues associated with automatic road sign recognition are described, the existing methods developed to tackle the road sign recognition problem are reviewed, and a comparison of the features of these methods is given. Second, the developed road sign recognition system is described. The system is capable of analysing live colour road scene images, detecting multiple road signs within each image, and classifying the type of road signs detected. The system consists of two modules: detection and classification. The detection module segments the input image in the hue-saturation-intensity colour space, and then detects road signs using a Multi-layer Perceptron neural-network. The classification module determines the type of detected road signs using a series of one to one architectural Multi-layer Perceptron neural networks. Two sets of classifiers are trained using the Resillient-Backpropagation and Scaled-Conjugate-Gradient algorithms. The two modules of the system are evaluated individually first. Then the system is tested as a whole. The experimental results demonstrate that the system is capable of achieving an average recognition hit-rate of 95.96% using the scaled-conjugate-gradient trained classifiers.

Improved particle swarm optimization-based artificial neural network for rainfall-runoff modeling

This paper presents the application of an improved particle swarm optimization (PSO) technique for training an artificial neural network (ANN) to predict water levels for the Heshui watershed, China. Daily values of rainfall and water levels from 1988 to 2000 were first analyzed using ANNs trained with the conjugate-gradient, gradient descent and Levenberg-Marquardt neural network (LM-NN) algorithms. The best results were obtained from LM-NN and these results were then compared with those from PSO-based ANNs, including conventional PSO neural network (CPSONN) and improved PSO neural network (IPSONN) with passive congregation. The IPSONN algorithm improves PSO convergence by using the selfish herd concept in swarm behavior. Our results show that the PSO-based ANNs performed better than LM-NN. For models run using a single parameter (rainfall) as input, the root mean square error (RMSE) of the testing dataset for IPSONN was the lowest (0.152 m) compared to those for CPSONN (0.161 m) and LM-NN (0.205 m). For multi-parameter (rainfall and water level) inputs, the RMSE of the testing dataset for IPSONN was also the lowest (0.089 m) compared to those for CPSONN (0.105 m) and LM-NN (0.145 m). The results also indicate that the LM-NN model performed poorly in predicting the low and peak water levels, in comparison to the PSO-based ANNs. Moreover, the IPSONN model was superior to CPSONN in predicting extreme water levels. Lastly, IPSONN had a quicker convergence rate compared to CPSONN.

Depression and its expression : art as problem solver

This workshop will focus on the ways in which ollr Journal Double Dialogues dealt with the question of the 'Anatomy of Pain'. In this workshop, by a process of demonstration and interaction, we will look at the theme of the representation of pain and engage with the ways in which different disciplines (psychological. visual, performative, philosophical. aesthetic and literary) explored this question. Emphasis will be given to the 'double dialogue' nature of the discourse in which practitioners of the arts have found a 'language' from aesthetics, history, theory, and philosophy that has succeeded in establishing a dialogue between the art-work and the discourse that might spring from the work itself or provide a relevant context. This session will draw on the e.xpertise of the audience for discussions and experiment within the Double Dialogue model.

Parallelization of the discrete gradient method of non-smooth optimization and its applications

We investigate parallelization and performance of the discrete gradient method of nonsmooth optimization. This derivative free method is shown to be an effective optimization tool, able to skip many shallow local minima of nonconvex nondifferentiable objective functions. Although this is a sequential iterative method, we were able to parallelize critical steps of the algorithm, and this lead to a significant improvement in performance on multiprocessor computer clusters. We applied this method to a difficult polyatomic clusters problem in computational chemistry, and found this method to outperform other algorithms.

Residual thermal stresses in a Fe3Al/Al2O3 gradient coating system

To combine the merits of both metals and ceramics into one material, many researchers have been studying the deposition of alumina coating using plasma spray on metal substrates. However, as the coatings are deposited at a high temperature, residual thermal stresses develop due to the mismatch of thermal expansion coefficients of the coating and substrate and these are responsible for the initiation and expansion of cracks, which induce the possible failure of the entire material. In this paper, the residual thermal-structural analysis of a Fe3Al/Al2O3 gradient coating on carbon steel substrate is performed using finite element modelling to simulate the plasma spray. The residual thermal stress fields are obtained and analyzed on the basis of temperature fields in gradient coatings during fabrication. The distribution of residual thermal stresses including radial, axial and shear stresses shows stress concentration at the interface between the coatings and substrate. The mismatch between steel substrate and composite coating is still the dominant factor for the residual stresses

The response of ground and bark foraging insectivorous birds across an urban–forest gradient

This paper assesses the response of four common species of forest dependant insectivorous birds to an urban–forest gradient. The presence or absence was recorded for each species in landscapes that varied in landscape and site level attributes. Landscapes were classified into three categories based on their level of urbanisation. Broad comparisons across the landscapes were used to determine species specific response to increasing levels of urbanisation. Site level attributes were modelled to predict the patch occupancy for each species in each of the landscape types. Two broad trends were identified: the superb fairy wren (Malurus cyaneus) and white-browed scrubwren (Sericornis frontalis) displayed a tolerance to urbanisation and the eastern yellowrobin (Eosaltrica australis) and white throated treecreeper (Cormobates leucophaeus) demonstrated a threshold response to urbanisation. The density of roads (−ve) and the extent of tree cover (+ve) in a landscape were highly correlated with the occurrence of urban sensitive species while at the site level the density of roads and density of rivers were the strongest contributors to their presence. The marked differences in the isolation and connectivity of patches where the threshold for urban sensitive species ceases are the likely contributors to their decline and sensitivity to suburban habitats. Conservation and management of urban sensitive species is largely dependant on the way urban development is managed. Of critical importance is careful planning in urban-fringe environments.

Vascular plant and small mammal communities over an elevational gradient

Plant species richness and plant and small mammal beta diversity decline over the elevational gradient in the Otway ranges. These patterns are influenced by climate, habitat and spatial structure. This highlights the need to preserve continuous habitat and understand the influence of climate, to conserve communities in the changing future.

Computer-assisted image analysis of liver collagen: relationship to Ishak scoring and hepatic venous pressure gradient

Histopathological scoring of disease stage uses descriptive categories without measuring the amount of fibrosis. Collagen, the major component of fibrous tissue, can be quantified by computer-assisted digital image analysis (DIA) using histological sections. We determined relationships between DIA, Ishak stage, and hepatic venous pressure gradient (HVPG) reflecting severity of fibrosis. One hundred fifteen patients with hepatitis C virus (HCV) who had undergone transplantation had 250 consecutive transjugular liver biopsies combined with HVPG (median length, 22 mm; median total portal tracts, 12), evaluated using the Ishak system and stained with Sirus red for DIA. Liver collagen was expressed as collagen proportionate area (CPA). Median CPA was 6% (0.2-45), correlating with Ishak stage (stage 6 range, 13%-45%), and with HVPG (r = 0.62; P < 0.001). Median CPA was 4.1% when HVPG was less than 6 mm Hg and 13.8% when HVPG was 6 mm Hg or more (P < 0.0001) and 6% when HVPG was less than 10 mm Hg and 17.3% when HVPG was 10 mm Hg or higher (P < 0.0001). Only CPA, not Ishak stage/grade, was independently associated by logistic regression, with HVPG of 6 mm Hg or more [odds ratio, 1.206; 95% confidence interval (CI), 1.094-1.331; P < 0.001], or HVPG of 10 mm Hg or more (odds ratio, 1.105; 95% CI, 1.026-1.191; P = 0.009). CPA increased by 50% (3.6%) compared with 20% in HVPG (1 mm Hg) in 38 patients with repeated biopsies. Conclusion: CPA assessed by DIA correlated with Ishak stage scores and HVPG measured contemporaneously. CPA was a better histological correlate with HVPG than Ishak stage, had a greater numerical change when HVPG was low, and resulted in further quantitation of fibrosis in cirrhosis.

Transport properties in ionic liquids and ionic liquid mixtures : the challenges of NMR pulsed field gradient diffusion measurements

Pulsed field gradient NMR is a powerful method for the measurement of diffusion coefficients in liquids and solids and has begun to attract much attention in the ionic liquids field. However, aspects of the methodology as traditionally applied to solutions may not be uniformly applicable in these more viscous and chemically complex systems. In this paper we present data which shows that the Pulsed Gradient Spin Echo (PGSE) method in particular suffers from intrinsic internal gradients and can produce apparent diffusion coefficients which vary by as much as 20% for different ¹H nuclei within a given moleculean obvious anomaly. In contrast, we show that the Pulsed Gradient Stimulated Echo method does not suffer from this problem to the same extent and produces self-consistent data to a high degree of accuracy (better than 1%). This level of significance has allowed the detection, in this work, of subtle mixing effects in [C₃mpyr][NTf₂] and [C₄mpyr][NTf₂] mixtures.

Surface evolution of a gradient structured Ti in hydrogen peroxide solution

In this work, the interaction between hydrogen peroxide (H₂O₂) and a gradient structured Ti was investigated extensively. The gradient structured Ti (SMAT Ti) was produced by surface mechanical attrition treatment (SMAT), and then it was immersed in H₂O₂ solution for different time until 48 h at room temperature (25 °C). The structure and surface morphology evolution were examined by Raman spectra and scanning electron microscopy (SEM). The formation mechanism of nanoporous titania was discussed based on above results.