Random projections on manifolds of symmetric positive definite matrices for image classification

Recent advances suggest that encoding images through Symmetric Positive Definite (SPD) matrices and then interpreting such matrices as points on Riemannian manifolds can lead to increased classification performance. Taking into account manifold geometry is typically done via (1) embedding the manifolds in tangent spaces, or (2) embedding into Reproducing Kernel Hilbert Spaces (RKHS). While embedding into tangent spaces allows the use of existing Euclidean-based learning algorithms, manifold shape is only approximated which can cause loss of discriminatory information. The RKHS approach retains more of the manifold structure, but may require non-trivial effort to kernelise Euclidean-based learning algorithms. In contrast to the above approaches, in this paper we offer a novel solution that allows SPD matrices to be used with unmodified Euclidean-based learning algorithms, with the true manifold shape well-preserved. Specifically, we propose to project SPD matrices using a set of random projection hyperplanes over RKHS into a random projection space, which leads to representing each matrix as a vector of projection coefficients. Experiments on face recognition, person re-identification and texture classification show that the proposed approach outperforms several recent methods, such as Tensor Sparse Coding, Histogram Plus Epitome, Riemannian Locality Preserving Projection and Relational Divergence Classification.

Automatic classification of human epithelial type 2 cell indirect immunofluorescence images using cell pyramid matching

This paper describes a novel system for automatic classification of images obtained from Anti-Nuclear Antibody (ANA) pathology tests on Human Epithelial type 2 (HEp-2) cells using the Indirect Immunofluorescence (IIF) protocol. The IIF protocol on HEp-2 cells has been the hallmark method to identify the presence of ANAs, due to its high sensitivity and the large range of antigens that can be detected. However, it suffers from numerous shortcomings, such as being subjective as well as time and labour intensive. Computer Aided Diagnostic (CAD) systems have been developed to address these problems, which automatically classify a HEp-2 cell image into one of its known patterns (eg. speckled, homogeneous). Most of the existing CAD systems use handpicked features to represent a HEp-2 cell image, which may only work in limited scenarios. We propose a novel automatic cell image classification method termed Cell Pyramid Matching (CPM), which is comprised of regional histograms of visual words coupled with the Multiple Kernel Learning framework. We present a study of several variations of generating histograms and show the efficacy of the system on two publicly available datasets: the ICPR HEp-2 cell classification contest dataset and the SNPHEp-2 dataset.

Improved image set classification via joint sparse approximated nearest subspaces

Existing multi-model approaches for image set classification extract local models by clustering each image set individually only once, with fixed clusters used for matching with other image sets. However, this may result in the two closest clusters to represent different characteristics of an object, due to different undesirable environmental conditions (such as variations in illumination and pose). To address this problem, we propose to constrain the clustering of each query image set by forcing the clusters to have resemblance to the clusters in the gallery image sets. We first define a Frobenius norm distance between subspaces over Grassmann manifolds based on reconstruction error. We then extract local linear subspaces from a gallery image set via sparse representation. For each local linear subspace, we adaptively construct the corresponding closest subspace from the samples of a probe image set by joint sparse representation. We show that by minimising the sparse representation reconstruction error, we approach the nearest point on a Grassmann manifold. Experiments on Honda, ETH-80 and Cambridge-Gesture datasets show that the proposed method consistently outperforms several other recent techniques, such as Affine Hull based Image Set Distance (AHISD), Sparse Approximated Nearest Points (SANP) and Manifold Discriminant Analysis (MDA).

Resistance of microbial populations in DDT-contaminated and uncontaminated soils

One DDT-contaminated soil and two uncontaminated soils were used to enumerate DDT-resistant microbes (bacteria, actinomycetes and fungi) by using soil dilution agar plates in media either with 150 μg DDT ml -1 or without DDT at different temperatures (25, 37 and 55°C). Microbial populations in this study were significantly (p<0.001) affected by DDT in the growth medium. However, the numbers of microbes in long-term contaminated and uncontaminated soils were similar, presumably indicating that DDT-resistant microbes had developed over a long time exposure. The tolerance of isolated soil microbes to DDT varied in the order fungi>actinomycetes>bacteria. Bacteria from contaminated soil were more resistant to DDT than bacteria from uncontaminated soils. Microbes isolated at different temperatures also demonstrated varying degrees of DDT resistance. For example, bacteria and actinomycetes isolated at all incubation temperatures were sensitive to DDT. Conversely fungi isolated at all temperatures were unaffected by DDT.

DDT resistance and transformation by different microbial strains isolated from DDT-contaminated soils and compost materials

Bioremediation is a potential option to treat 1, 1, 1-trichloro-2, 2 bis (4-chlorophenyl) ethane (DDT) contaminated sites. In areas where suitable microbes are not present, the use of DDT resistant microbial inoculants may be necessary. It is vital that such inoculants do not produce recalcitrant breakdown products e.g. 1, 1-dichloro-2, 2-bis (4-chlorophenyl) ethylene (DDE). Therefore, this work aimed to screen DDT-contaminated soil and compost materials for the presence of DDT-resistant microbes for use as potential inoculants. Four compost amended soils, contaminated with different concentrations of DDT, were used to isolate DDT-resistant microbes in media containing 150 mg I -1 DDT at three temperatures (25, 37 and 55°C). In all soils, bacteria were more sensitive to DDT than actinomycetes and fungi. Bacteria isolated at 55°C from any source were the most DDT sensitive. However DDT-resistant bacterial strains showed more promise in degrading DDT than isolated fungal strains, as 1, 1-dichloro 2, 2-bis (4-chlorophenyl) ethane (DDD) was a major bacterial transformation product, while fungi tended to produce more DDE. Further studies on selected bacterial isolates found that the most promising bacterial strain (Bacillus sp. BHD-4) could remove 51% of DDT from liquid culture after 7 days growth. Of the amount transformed, 6% was found as DDD and 3% as DDE suggesting that further transformation of DDT and its metabolites occurred.

Polarization of forecast densities : a new approach to time series classification

Time series classification has been extensively explored in many fields of study. Most methods are based on the historical or current information extracted from data. However, if interest is in a specific future time period, methods that directly relate to forecasts of time series are much more appropriate. An approach to time series classification is proposed based on a polarization measure of forecast densities of time series. By fitting autoregressive models, forecast replicates of each time series are obtained via the bias-corrected bootstrap, and a stationarity correction is considered when necessary. Kernel estimators are then employed to approximate forecast densities, and discrepancies of forecast densities of pairs of time series are estimated by a polarization measure, which evaluates the extent to which two densities overlap. Following the distributional properties of the polarization measure, a discriminant rule and a clustering method are proposed to conduct the supervised and unsupervised classification, respectively. The proposed methodology is applied to both simulated and real data sets, and the results show desirable properties.

A pilot study on affective classification of facial images for emerging news topics

The proliferation of news reports published in online websites and news information sharing among social media users necessitates effective techniques for analysing the image, text and video data related to news topics. This paper presents the first study to classify affective facial images on emerging news topics. The proposed system dynamically monitors and selects the current hot (of great interest) news topics with strong affective interestingness using textual keywords in news articles and social media discussions. Images from the selected hot topics are extracted and classified into three categorized emotions, positive, neutral and negative, based on facial expressions of subjects in the images. Performance evaluations on two facial image datasets collected from real-world resources demonstrate the applicability and effectiveness of the proposed system in affective classification of facial images in news reports. Facial expression shows high consistency with the affective textual content in news reports for positive emotion, while only low correlation has been observed for neutral and negative. The system can be directly used for applications, such as assisting editors in choosing photos with a proper affective semantic for a certain topic during news report preparation.

Large scale read classification for next generation sequencing

Next Generation Sequencing (NGS) has revolutionised molecular biology, resulting in an explosion of data sets and an increasing role in clinical practice. Such applications necessarily require rapid identification of the organism as a prelude to annotation and further analysis. NGS data consist of a substantial number of short sequence reads, given context through downstream assembly and annotation, a process requiring reads consistent with the assumed species or species group. Highly accurate results have been obtained for restricted sets using SVM classifiers, but such methods are difficult to parallelise and success depends on careful attention to feature selection. This work examines the problem at very large scale, using a mix of synthetic and real data with a view to determining the overall structure of the problem and the effectiveness of parallel ensembles of simpler classifiers (principally random forests) in addressing the challenges of large scale genomics.

The relationship between N2O, NO, and N2 fluxes from fertilized and irrigated dryland soils of the Aral Sea Basin, Uzbekistan

Microbial respiratory reduction of nitrous oxide (N2O) to dinitrogen (N2) via denitrification plays a key role within the global N-cycle since it is the most important process for converting reactive nitrogen back into inert molecular N2. However, due to methodological constraints, we still lack a comprehensive, quantitative understanding of denitrification rates and controlling factors across various ecosystems. We investigated N2, N2O and NO emissions from irrigated cotton fields within the Aral Sera Basin using the He/O2 atmosphere gas flow soil core technique and an incubation assay. NH4NO3 fertilizer, equivalent to 75 kg ha−1 and irrigation water, adjusting the water holding capacity to 70, 100 and 130% were applied to the incubation vessels to assess its influence on gaseous N emissions. Under soil conditions as they are naturally found after concomitant irrigation and fertilization, denitrification was the dominant process and N2 the main end product of denitrification. The mean ratios of N2/N2O emissions increased with increasing soil moisture content. N2 emissions exceeded N2O emissions by a factor of 5 ± 2 at 70% soil water holding capacity (WHC) and a factor of 55 ± 27 at 130% WHC. The mean ratios of N2O/NO emissions varied between 1.5 ± 0.4 (70% WHC) and 644 ± 108 (130% WHC). The magnitude of N2 emissions for irrigated cotton was estimated to be in the range of 24 ± 9 to 175 ± 65 kg-N ha−1season−1, while emissions of NO were only of minor importance (between 0.1 to 0.7 kg-N ha−1 season−1). The findings demonstrate that for irrigated dryland soils in the Aral Sera Basin, denitrification is a major pathway of N-loss and that substantial amounts of N-fertilizer are lost as N2 to the atmosphere for irrigated dryland soils.

Social networking and digital gaming media convergence : Classification and its consequences for appropriation

Abstract Within the field of Information Systems, a good proportion of research is concerned with the work organisation and this has, to some extent, restricted the kind of application areas given consideration. Yet, it is clear that information and communication technology deployments beyond the work organisation are acquiring increased importance in our lives. With this in mind, we offer a field study of the appropriation of an online play space known as Habbo Hotel. Habbo Hotel, as a site of media convergence, incorporates social networking and digital gaming functionality. Our research highlights the ethical problems such a dual classification of technology may bring. We focus upon a particular set of activities undertaken within and facilitated by the space – scamming. Scammers dupe members with respect to their ‘Furni’, virtual objects that have online and offline economic value. Through our analysis we show that sometimes, online activities are bracketed off from those defined as offline and that this can be related to how the technology is classified by members – as a social networking site and/or a digital game. In turn, this may affect members’ beliefs about rights and wrongs. We conclude that given increasing media convergence, the way forward is to continue the project of educating people regarding the difficulties of determining rights and wrongs, and how rights and wrongs may be acted out with respect to new technologies of play online and offline.

Greenhouse gas emissions from sub-tropical agricultural soils after addition of organic by-products

As the cost of mineral fertilisers increases globally, organic soil amendments (OAs) from agricultural sources are increasingly being used as substitutes for nitrogen. However, the impact of OAs on the production of greenhouse gases (CO2 and N2O) is not well understood. A 60-day laboratory incubation experiment was conducted to investigate the impacts of applying OAs (equivalent to 296 kg N ha−1 on average) on N2O and CO2 emissions and soil properties of clay and sandy loam soils from sugar cane production. The experiment included 6 treatments, one being an un-amended (UN) control with addition of five OAs being raw mill mud (MM), composted mill mud (CM), high N compost (HC), rice husk biochar (RB), and raw mill mud plus rice husk biochar (MB). These OAs were incubated at 60, 75 and 90% water-filled pore space (WFPS) at 25°C with urea (equivalent to 200 kg N ha−1) added to the soils thirty days after the incubation commenced. Results showed WFPS did not influence CO2 emissions over the 60 days but the magnitude of emissions as a proportion of C applied was RB < CM < MB < HC