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.

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.

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.

Planar waveguide refractive index profile reconstruction using global optimization

The approach taken here of reconstruction of the refractive index profile of planar waveguides involves solving a non-linear integral equation with Tikhonov regularization. Using global optimization with the new cutting angle and discrete gradient methods has yielded an acceptable reconstruction, even in the presence of significant noise in the data.

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.

Non-smooth optimization methods for computation of the conditional value-at-risk and portfolio optimization

We examine numerical performance of various methods of calculation of the Conditional Value-at-risk (CVaR), and portfolio optimization with respect to this risk measure. We concentrate on the method proposed by Rockafellar and Uryasev in (Rockafellar, R.T. and Uryasev, S., 2000, Optimization of conditional value-at-risk. Journal of Risk, 2, 21-41), which converts this problem to that of convex optimization. We compare the use of linear programming techniques against a non-smooth optimization method of the discrete gradient, and establish the supremacy of the latter. We show that non-smooth optimization can be used efficiently for large portfolio optimization, and also examine parallel execution of this method on computer clusters.

Comparative evaluation of pedestrian detection methods for mobile bus surveillance

We present a comparative evaluation of the state-of-art algorithms for detecting pedestrians in low frame rate and low resolution footage acquired by mobile sensors. Four approaches are compared: a) The Histogram of Oriented Gradient (HoG) approach [1]; b) A new histogram feature that is formed by the weighted sum of both the gradient magnitude and the filter responses from a set of elongated Gaussian filters [2] corresponding to the quantised orientation, called Histogram of Oriented Gradient Banks (HoGB) approach; c) The codebook based HoG feature with branch-and-bound (efficient subwindow search) algorithm [3] and; d) The codebook based HoGB approach. Results show that the HoG based detector achieves the highest performance in terms of the true positive detection, the HoGB approach has the lowest false positives whilst maintaining a comparable true positive rate to the HoG, and the codebook approaches allow computationally efficient detection.

Gradient edge map features for frontal face recognition under extreme illumination changes

Our aim in this paper is to robustly match frontal faces in the presence of extreme illumination changes, using only a single training image per person and a single probe image. In the illumination conditions we consider, which include those with the dominant light source placed behind and to the side of the user, directly above and pointing downwards or indeed below and pointing upwards, this is a most challenging problem. The presence of sharp cast shadows, large poorly illuminated regions of the face, quantum and quantization noise and other nuisance effects, makes it difficult to extract a sufficiently discriminative yet robust representation. We introduce a representation which is based on image gradient directions near robust edges which correspond to characteristic facial features. Robust edges are extracted using a cascade of processing steps, each of which seeks to harness further discriminative information or normalize for a particular source of extra-personal appearance variability. The proposed representation was evaluated on the extremely difficult YaleB data set. Unlike most of the previous work we include all available illuminations, perform training using a single image per person and match these also to a single probe image. In this challenging evaluation setup, the proposed gradient edge map achieved 0.8% error rate, demonstrating a nearly perfect receiver-operator characteristic curve behaviour. This is by far the best performance achieved in this setup reported in the literature, the best performing methods previously proposed attaining error rates of approximately 6–7%.

Very high pressure liquid chromatography using fully porous particles: Quantitative analysis of fast gradient separations without post-run times

Using a column packed with fully porous particles, four methods for controlling the flow rates at which gradient elution runs are conducted in very high pressure liquid chromatography (VHPLC) were tested to determine whether reproducible thermal conditions could be achieved, such that subsequent analyses would proceed at nearly the same initial temperature. In VHPLC high flow rates are achieved, producing fast analyses but requiring high inlet pressures. The combination of high flow rates and high inlet pressures generates local heat, leading to temperature changes in the column. Usually in this case a post-run time is input into the analytical method to allow the return of the column temperature to its initial state. An alternative strategy involves operating the column without a post-run equilibration period and maintaining constant temperature variations for subsequent analysis after conducting one or a few separations to bring the column to a reproducible starting temperature. A liquid chromatography instrument equipped with a pressure controller was used to perform constant pressure and constant flow rate VHPLC separations. Six replicate gradient separations of a nine component mixture consisting of acetophenone, propiophenone, butyrophenone, valerophenone, hexanophenone, heptanophenone, octanophenone, benzophenone, and acetanilide dissolved in water/acetonitrile (65:35, v/v) were performed under various experimental conditions: constant flow rate, two sets of constant pressure, and constant pressure operation with a programmed flow rate. The relative standard deviations of the response factors for all the analytes are lower than 5% across the methods. Programming the flow rate to maintain a fairly constant pressure instead of using instrument controlled constant pressure improves the reproducibility of the retention times by a factor of 5, when plotting the chromatograms in time.

Evaluation of electrochemical methods for determination of the seebeck coefficient of redox electrolytes

Recent advances in thermoelectrochemical cells, which are being developed for harvesting low grade waste heat, have shown the promise of cobalt bipyridyl salts as the active redox couple. The Seebeck coefficient, Se, of a redox couple determines the open circuit voltage achievable, for a given temperature gradient, across the thermoelectrochemical cell. Thus, the accurate determination of this thermodynamic parameter is key to the development and study of new redox electrolytes. Further, techniques for accurate determination of Se using only one half of the redox couple reduces the synthetic requirements. Here, we compare three different experimental techniques for measuring Se of a cobalt tris(bipyridyl) redox couple in ionic liquid electrolytes. The use of temperature dependent cyclic voltammetry (CV) in isothermal and non-isothermal cells was investigated in depth, and the Se values compared to those from thermo-electromotive force measurements. Within experimental error, the Se values derived from CV methods were found to be in accordance with those obtained from electromotive force (emf) measurements. The applicability of cyclic voltammetry techniques for determining Se when employing only one part of the redox couple was demonstrated.

DNA methylation and the social gradient of osteoporotic fracture: a conceptual model

INTRODUCTION: Although there is a documented social gradient for osteoporosis, the underlying mechanism(s) for that gradient remain unknown. We propose a conceptual model based upon the allostatic load theory, to suggest how DNA methylation (DNAm) might underpin the social gradient in osteoporosis and fracture. We hypothesise that social disadvantage is associated with priming of inflammatory pathways mediated by epigenetic modification that leads to an enhanced state of inflammatory reactivity and oxidative stress, and thus places socially disadvantaged individuals at greater risk of osteoporotic fracture. METHODS/RESULTS: Based on a review of the literature, we present a conceptual model in which social disadvantage increases stress throughout the lifespan, and engenders a proinflammatory epigenetic signature, leading to a heightened inflammatory state that increases risk for osteoporotic fracture in disadvantaged groups that are chronically stressed. CONCLUSIONS: Our model proposes that, in addition to the direct biological effects exerted on bone by factors such as physical activity and nutrition, the recognised socially patterned risk factors for osteoporosis also act via epigenetic-mediated dysregulation of inflammation. DNAm is a dynamic modulator of gene expression with considerable relevance to the field of osteoporosis. Elucidating the extent to which this epigenetic mechanism transduces the psycho-social environment to increase the risk of osteoporotic fracture may yield novel entry points for intervention that can be used to reduce individual and population-wide risks for osteoporotic fracture. Specifically, an epigenetic evidence-base may strengthen the importance of lifestyle modification and stress reduction programs, and help to reduce health inequities across social groups. MINI ABSTRACT: Our conceptual model proposes how DNA methylation might underpin the social gradient in osteoporotic fracture. We suggest that social disadvantage is associated with priming of inflammatory signalling pathways, which is mediated by epigenetic modifications, leading to a chronically heightened inflammatory state that places disadvantaged individuals at greater risk of osteoporosis.

Long-term impact of pneumococcal polysaccharide vaccination on nasopharyngeal carriage in children previously vaccinated with various pneumococcal conjugate vaccine regimes

Previously, the Fiji Pneumococcal Project (FiPP) evaluated reduced dose immunization schedules that incorporated pneumococcal protein conjugate and/or polysaccharide vaccine (PCV7 and 23vPPV, respectively). Immune hyporesponsiveness was observed in children vaccinated with 23vPPV at 12 months of age compared with children who did not receive 23vPPV.

Here we assess the long-term impact of 23vPPV vaccination on nasopharyngeal carriage rates and densities of Streptococcus pneumoniae, Haemophilus influenzae, Staphylococcus aureus and Moraxella catarrhalis. Nasopharyngeal swabs (n = 194) were obtained from healthy children who participated in FiPP (now aged 5–7 years). S. pneumoniae were isolated and identified by standard culture-based methods, and serotyped using latex agglutination and the Quellung reaction. Carriage rates and densities of S. pneumoniae, H. influenzae, S. aureus and M. catarrhalis were determined using real-time quantitative PCR.

There were no differences in the rate or density of S. pneumoniae, H. influenzae or M. catarrhalis carriage by PCV7 dose or 23vPPV vaccination in the vaccinated participants overall. However, differences were observed between the two main ethnic groups: Fijian children of Indian descent (Indo-Fijian) were less likely to carry S. pneumoniae, H. influenzae and M. catarrhalis, and there was evidence of a higher carriage rate of S. aureus compared with indigenous Fijian (iTaukei) children. Polysaccharide vaccination appeared to have effects that varied between ethnic groups, with 23vPPV vaccination associated with a higher carriage rate of S. aureus in iTaukei children, while there was a lower carriage rate of S. pneumoniae associated with 23vPPV vaccination in Indo-Fijian children.

Overall, polysaccharide vaccination had no long-term impact on pneumococcal carriage, but may have impacted on S. aureus carriage and have varying effects in ethnic groups, suggesting current WHO vaccine schedule recommendations against the use of 23vPPV in children under two years of age are appropriate.