Semantic-associative visual content labelling and retrieval: A multimodal approach

A novel framework referred to as collaterally confirmed labelling (CCL) is proposed, aiming at localising the visual semantics to regions of interest in images with textual keywords. Both the primary image and collateral textual modalities are exploited in a mutually co-referencing and complementary fashion. The collateral content and context-based knowledge is used to bias the mapping from the low-level region-based visual primitives to the high-level visual concepts defined in a visual vocabulary. We introduce the notion of collateral context, which is represented as a co-occurrence matrix of the visual keywords. A collaborative mapping scheme is devised using statistical methods like Gaussian distribution or Euclidean distance together with collateral content and context-driven inference mechanism. We introduce a novel high-level visual content descriptor that is devised for performing semantic-based image classification and retrieval. The proposed image feature vector model is fundamentally underpinned by the CCL framework. Two different high-level image feature vector models are developed based on the CCL labelling of results for the purposes of image data clustering and retrieval, respectively. A subset of the Corel image collection has been used for evaluating our proposed method. The experimental results to-date already indicate that the proposed semantic-based visual content descriptors outperform both traditional visual and textual image feature models. (C) 2007 Elsevier B.V. All rights reserved.

Collaterally cued labelling framework underpinning semantic-level visual content descriptor

In this paper, we introduce a novel high-level visual content descriptor devised for performing semantic-based image classification and retrieval. The work can be treated as an attempt for bridging the so called "semantic gap". The proposed image feature vector model is fundamentally underpinned by an automatic image labelling framework, called Collaterally Cued Labelling (CCL), which incorporates the collateral knowledge extracted from the collateral texts accompanying the images with the state-of-the-art low-level visual feature extraction techniques for automatically assigning textual keywords to image regions. A subset of the Corel image collection was used for evaluating the proposed method. The experimental results indicate that our semantic-level visual content descriptors outperform both conventional visual and textual image feature models.

A compositional framework for hardware/software co-design

We describe a compositional framework, together with its supporting toolset, for hardware/software co-design. Our framework is an integration of a formal approach within a traditional design flow. The formal approach is based on Interval Temporal Logic and its executable subset, Tempura. Refinement is the key element in our framework because it will derive from a single formal specification of the system the software and hardware parts of the implementation, while preserving all properties of the system specification. During refinement simulation is used to choose the appropriate refinement rules, which are applied automatically in the HOL system. The framework is illustrated with two case studies. The work presented is part of a UK collaborative research project between the Software Technology Research Laboratory at the De Montfort University and the Oxford University Computing Laboratory.

Understanding cumulative risk

This paper summarizes the theory of simple cumulative risks—for example, the risk of food poisoning from the consumption of a series of portions of tainted food. Problems concerning such risks are extraordinarily difficult for naı¨ve individuals, and the paper explains the reasons for this difficulty. It describes how naı¨ve individuals usually attempt to estimate cumulative risks, and it outlines a computer program that models these methods. This account predicts that estimates can be improved if problems of cumulative risk are framed so that individuals can focus on the appropriate subset of cases. The paper reports two experiments that corroborated this prediction. They also showed that whether problems are stated in terms of frequencies (80 out of 100 people got food poisoning) or in terms of percentages (80% of people got food poisoning) did not reliably affect accuracy.

Sparse kernel density estimation technique based on zero-norm constraint

A sparse kernel density estimator is derived based on the zero-norm constraint, in which the zero-norm of the kernel weights is incorporated to enhance model sparsity. The classical Parzen window estimate is adopted as the desired response for density estimation, and an approximate function of the zero-norm is used for achieving mathemtical tractability and algorithmic efficiency. Under the mild condition of the positive definite design matrix, the kernel weights of the proposed density estimator based on the zero-norm approximation can be obtained using the multiplicative nonnegative quadratic programming algorithm. Using the -optimality based selection algorithm as the preprocessing to select a small significant subset design matrix, the proposed zero-norm based approach offers an effective means for constructing very sparse kernel density estimates with excellent generalisation performance.

Regression based D-optimality experimental design for sparse kernel density estimation

This paper derives an efficient algorithm for constructing sparse kernel density (SKD) estimates. The algorithm first selects a very small subset of significant kernels using an orthogonal forward regression (OFR) procedure based on the D-optimality experimental design criterion. The weights of the resulting sparse kernel model are then calculated using a modified multiplicative nonnegative quadratic programming algorithm. Unlike most of the SKD estimators, the proposed D-optimality regression approach is an unsupervised construction algorithm and it does not require an empirical desired response for the kernel selection task. The strength of the D-optimality OFR is owing to the fact that the algorithm automatically selects a small subset of the most significant kernels related to the largest eigenvalues of the kernel design matrix, which counts for the most energy of the kernel training data, and this also guarantees the most accurate kernel weight estimate. The proposed method is also computationally attractive, in comparison with many existing SKD construction algorithms. Extensive numerical investigation demonstrates the ability of this regression-based approach to efficiently construct a very sparse kernel density estimate with excellent test accuracy, and our results show that the proposed method compares favourably with other existing sparse methods, in terms of test accuracy, model sparsity and complexity, for constructing kernel density estimates.

Precipitation and latent heating distributions from satellite passive microwave radiometry. Part I: improved method and uncertainties

A revised Bayesian algorithm for estimating surface rain rate, convective rain proportion, and latent heating profiles from satellite-borne passive microwave radiometer observations over ocean backgrounds is described. The algorithm searches a large database of cloud-radiative model simulations to find cloud profiles that are radiatively consistent with a given set of microwave radiance measurements. The properties of these radiatively consistent profiles are then composited to obtain best estimates of the observed properties. The revised algorithm is supported by an expanded and more physically consistent database of cloud-radiative model simulations. The algorithm also features a better quantification of the convective and nonconvective contributions to total rainfall, a new geographic database, and an improved representation of background radiances in rain-free regions. Bias and random error estimates are derived from applications of the algorithm to synthetic radiance data, based upon a subset of cloud-resolving model simulations, and from the Bayesian formulation itself. Synthetic rain-rate and latent heating estimates exhibit a trend of high (low) bias for low (high) retrieved values. The Bayesian estimates of random error are propagated to represent errors at coarser time and space resolutions, based upon applications of the algorithm to TRMM Microwave Imager (TMI) data. Errors in TMI instantaneous rain-rate estimates at 0.5°-resolution range from approximately 50% at 1 mm h−1 to 20% at 14 mm h−1. Errors in collocated spaceborne radar rain-rate estimates are roughly 50%–80% of the TMI errors at this resolution. The estimated algorithm random error in TMI rain rates at monthly, 2.5° resolution is relatively small (less than 6% at 5 mm day−1) in comparison with the random error resulting from infrequent satellite temporal sampling (8%–35% at the same rain rate). Percentage errors resulting from sampling decrease with increasing rain rate, and sampling errors in latent heating rates follow the same trend. Averaging over 3 months reduces sampling errors in rain rates to 6%–15% at 5 mm day−1, with proportionate reductions in latent heating sampling errors.

In vitro immunomodulatory activity of Lactobacillus fermentum CECT5716 and Lactobacillus salivarius CECT5713: two probiotic strains isolated from human breast milk

Commensal bacteria, including some species of lactobacilli commonly present in human breast milk, appear to colonize the neonatal gut and contribute to protection against infant infections, suggesting that lactobacilli could potentially modulate immunity. In this study, we evaluated the potential of two Lactobacillus strains isolated from human milk to modulate the activation and cytokine profile of peripheral blood mononuclear cell (PBMC) subsets in vitro. Moreover, these effects were compared to the same probiotic species of non-milk origin. Lactobacillus salivarius CECT5713 and Lactobacillus fermentum CECT5716 at 105, 106 and 107 bacteria/mL were co-cultured with PBMC (106/mL) from 8 healthy donors for 24 h. Activation status (CD69 and CD25 expressions) of natural killer (NK) cells (CD56+), total T cells (CD3+), cytotoxic T cells (CD8+) and CD4+ T cells was determined by flow cytometry. Regulatory T cells (Treg) were also quantified by intracellular Foxp3 evaluation. Regarding innate immunity, NK cells were activated by addition of both Lactobacillus strains, and in particular, the CD8+ NK subset was preferentially induced to highly express CD69 (90%, p<0.05). With respect to acquired immunity, approximately 9% of CD8+ T cells became activated after co-cultivation with L. fermentum or L salivarius. Although CD4+ T cells demonstrated a weaker response, there was a preferential activation of Treg cells (CD4+CD25+Foxp3+) after exposure to both milk probiotic bacteria (p<0.05). Both strains significantly induced the production of a number of cytokines and chemokines, including TNFα, IL-1β, IL-8, MIP-1α, MIP-1β, and GM-CSF, but some strain-specific effects were apparent. This work demonstrates that L salivarius CECT5713 and L. fermentum CECT5716 enhanced both natural and acquired immune responses, as evidenced by the activation of NK and T cell subsets and the expansion of Treg cells, as well as the induction of a broad array of cytokines.

Self-organising neural networks for adaptive control

Self-organizing neural networks have been implemented in a wide range of application areas such as speech processing, image processing, optimization and robotics. Recent variations to the basic model proposed by the authors enable it to order state space using a subset of the input vector and to apply a local adaptation procedure that does not rely on a predefined test duration limit. Both these variations have been incorporated into a new feature map architecture that forms an integral part of an Hybrid Learning System (HLS) based on a genetic-based classifier system. Problems are represented within HLS as objects characterized by environmental features. Objects controlled by the system have preset targets set against a subset of their features. The system's objective is to achieve these targets by evolving a behavioural repertoire that efficiently explores and exploits the problem environment. Feature maps encode two types of knowledge within HLS — long-term memory traces of useful regularities within the environment and the classifier performance data calibrated against an object's feature states and targets. Self-organization of these networks constitutes non-genetic-based (experience-driven) learning within HLS. This paper presents a description of the HLS architecture and an analysis of the modified feature map implementing associative memory. Initial results are presented that demonstrate the behaviour of the system on a simple control task.

Using self-organising feature maps for the control of artificial organisms

Variations on the standard Kohonen feature map can enable an ordering of the map state space by using only a limited subset of the complete input vector. Also it is possible to employ merely a local adaptation procedure to order the map, rather than having to rely on global variables and objectives. Such variations have been included as part of a hybrid learning system (HLS) which has arisen out of a genetic-based classifier system. In the paper a description of the modified feature map is given, which constitutes the HLSs long term memory, and results in the control of a simple maze running task are presented, thereby demonstrating the value of goal related feedback within the overall network.

Nonlinear model structure design and construction using orthogonal least squares and D-optimality design

A very efficient learning algorithm for model subset selection is introduced based on a new composite cost function that simultaneously optimizes the model approximation ability and model robustness and adequacy. The derived model parameters are estimated via forward orthogonal least squares, but the model subset selection cost function includes a D-optimality design criterion that maximizes the determinant of the design matrix of the subset to ensure the model robustness, adequacy, and parsimony of the final model. The proposed approach is based on the forward orthogonal least square (OLS) algorithm, such that new D-optimality-based cost function is constructed based on the orthogonalization process to gain computational advantages and hence to maintain the inherent advantage of computational efficiency associated with the conventional forward OLS approach. Illustrative examples are included to demonstrate the effectiveness of the new approach.

Neurofuzzy design and model construction of nonlinear dynamical processes from data

A common problem in many data based modelling algorithms such as associative memory networks is the problem of the curse of dimensionality. In this paper, a new two-stage neurofuzzy system design and construction algorithm (NeuDeC) for nonlinear dynamical processes is introduced to effectively tackle this problem. A new simple preprocessing method is initially derived and applied to reduce the rule base, followed by a fine model detection process based on the reduced rule set by using forward orthogonal least squares model structure detection. In both stages, new A-optimality experimental design-based criteria we used. In the preprocessing stage, a lower bound of the A-optimality design criterion is derived and applied as a subset selection metric, but in the later stage, the A-optimality design criterion is incorporated into a new composite cost function that minimises model prediction error as well as penalises the model parameter variance. The utilisation of NeuDeC leads to unbiased model parameters with low parameter variance and the additional benefit of a parsimonious model structure. Numerical examples are included to demonstrate the effectiveness of this new modelling approach for high dimensional inputs.

Nonlinear model structure detection using optimum experimental design and orthogonal least squares

A very efficient learning algorithm for model subset selection is introduced based on a new composite cost function that simultaneously optimizes the model approximation ability and model adequacy. The derived model parameters are estimated via forward orthogonal least squares, but the subset selection cost function includes an A-optimality design criterion to minimize the variance of the parameter estimates that ensures the adequacy and parsimony of the final model. An illustrative example is included to demonstrate the effectiveness of the new approach.

Evaluation of the time resolved fluorescence immunoassay (TRFIA) for the detection of varicella zoster virus (VZV) antibodies following vaccination of healthcare workers

Determination of varicella zoster virus (VZV) immunity in healthcare workers without a history of chickenpox is important for identifying those in need of vOka vaccination. Post immunisation, healthcare workers in the UK who work with high risk patients are tested for seroconversion. To assess the performance of the time-resolved fluorescence immunoassay (TRFIA) for the detection of antibody in vaccinated as well as unvaccinated individuals, a cut-off was first calculated. VZV-IgG specific avidity and titres six weeks after the first dose of vaccine were used to identify subjects with pre-existing immunity among a cohort of 110 healthcare workers. Those with high avidity (≥60%) were considered to have previous immunity to VZV and those with low or equivocal avidity (<60%) were considered naive. The former had antibody levels ≥400mIU/mL and latter had levels <400mIU/mL. Comparison of the baseline values of the naive and immune groups allowed the estimation of a TRFIA cut-off value of >130mIU/mL which best discriminated between the two groups and this was confirmed by ROC analysis. Using this value, the sensitivity and specificity of TRFIA cut-off were 90% (95% CI 79-96), and 78% (95% CI 61-90) respectively in this population. A subset of samples tested by the gold standard Fluorescence Antibody to Membrane Antigen (FAMA) test showed 84% (54/64) agreement with TRFIA.

Inter-relationships between small, dense low-density lipoprotein (LDL), plasma triacylglycerol and LDL apoprotein B in an atherogenic lipoprotein phenotype in free-living subjects

A predominance of small, dense low-density lipoprotein (LDL) is a major component of an atherogenic lipoprotein phenotype, and a common, but modifiable, source of increased risk for coronary heart disease in the free-living population. While much of the atherogenicity of small, dense LDL is known to arise from its structural properties, the extent to which an increase in the number of small, dense LDL particles (hyper-apoprotein B) contributes to this risk of coronary heart disease is currently unknown. This study reports a method for the recruitment of free-living individuals with an atherogenic lipoprotein phenotype for a fish-oil intervention trial, and critically evaluates the relationship between LDL particle number and the predominance of small, dense LDL. In this group, volunteers were selected through local general practices on the basis of a moderately raised plasma triacylglycerol (triglyceride) level (>1.5 mmol/l) and a low concentration of high-density-lipoprotein cholesterol (<1.1 mmol/l). The screening of LDL subclasses revealed a predominance of small, dense LDL (LDL subclass pattern B) in 62% of the cohort. As expected, subjects with LDL subclass pattern B were characterized by higher plasma triacylglycerol and lower high-density lipoprotein cholesterol (<1.1 mmol/l) levels and, less predictably, by lower LDL cholesterol and apoprotein B levels (P<0.05; LDL subclass A compared with subclass B). While hyper-apoprotein B was detected in only five subjects, the relative percentage of small, dense LDL-III in subjects with subclass B showed an inverse relationship with LDL apoprotein B (r=-0.57; P<0.001), identifying a subset of individuals with plasma triacylglycerol above 2.5 mmol/l and a low concentration of LDL almost exclusively in a small and dense form. These findings indicate that a predominance of small, dense LDL and hyper-apoprotein B do not always co-exist in free-living groups. Moreover, if coronary risk increases with increasing LDL particle number, these results imply that the risk arising from a predominance of small, dense LDL may actually be reduced in certain cases when plasma triacylglycerol exceeds 2.5 mmol/l.