Matching image sets via adaptive multi convex hull

Traditional nearest points methods use all the samples in an image set to construct a single convex or affine hull model for classification. However, strong artificial features and noisy data may be generated from combinations of training samples when significant intra-class variations and/or noise occur in the image set. Existing multi-model approaches extract local models by clustering each image set individually only once, with fixed clusters used for matching with various image sets. This may not be optimal for discrimination, as undesirable environmental conditions (eg. illumination and pose variations) may result in the two closest clusters representing different characteristics of an object (eg. frontal face being compared to non-frontal face). To address the above problem, we propose a novel approach to enhance nearest points based methods by integrating affine/convex hull classification with an adapted multi-model approach. We first extract multiple local convex hulls from a query image set via maximum margin clustering to diminish the artificial variations and constrain the noise in local convex hulls. We then propose adaptive reference clustering (ARC) to constrain the clustering of each gallery image set by forcing the clusters to have resemblance to the clusters in the query image set. By applying ARC, noisy clusters in the query set can be discarded. Experiments on Honda, MoBo and ETH-80 datasets show that the proposed method outperforms single model approaches and other recent techniques, such as Sparse Approximated Nearest Points, Mutual Subspace Method and Manifold Discriminant Analysis.

Multi-shot person re-identification via relational stein divergence

Person re-identification is particularly challenging due to significant appearance changes across separate camera views. In order to re-identify people, a representative human signature should effectively handle differences in illumination, pose and camera parameters. While general appearance-based methods are modelled in Euclidean spaces, it has been argued that some applications in image and video analysis are better modelled via non-Euclidean manifold geometry. To this end, recent approaches represent images as covariance matrices, and interpret such matrices as points on Riemannian manifolds. As direct classification on such manifolds can be difficult, in this paper we propose to represent each manifold point as a vector of similarities to class representers, via a recently introduced form of Bregman matrix divergence known as the Stein divergence. This is followed by using a discriminative mapping of similarity vectors for final classification. The use of similarity vectors is in contrast to the traditional approach of embedding manifolds into tangent spaces, which can suffer from representing the manifold structure inaccurately. Comparative evaluations on benchmark ETHZ and iLIDS datasets for the person re-identification task show that the proposed approach obtains better performance than recent techniques such as Histogram Plus Epitome, Partial Least Squares, and Symmetry-Driven Accumulation of Local Features.

A coupled SPH-DEM model for micro-scale structural deformations of plant cells during drying

A single plant cell was modeled with smoothed particle hydrodynamics (SPH) and a discrete element method (DEM) to study the basic micromechanics that govern the cellular structural deformations during drying. This two-dimensional particle-based model consists of two components: a cell fluid model and a cell wall model. The cell fluid was approximated to a highly viscous Newtonian fluid and modeled with SPH. The cell wall was treated as a stiff semi-permeable solid membrane with visco-elastic properties and modeled as a neo-Hookean solid material using a DEM. Compared to existing meshfree particle-based plant cell models, we have specifically introduced cell wall–fluid attraction forces and cell wall bending stiffness effects to address the critical shrinkage characteristics of the plant cells during drying. Also, a moisture domain-based novel approach was used to simulate drying mechanisms within the particle scheme. The model performance was found to be mainly influenced by the particle resolution, initial gap between the outermost fluid particles and wall particles and number of particles in the SPH influence domain. A higher order smoothing kernel was used with adaptive smoothing length to improve the stability and accuracy of the model. Cell deformations at different states of cell dryness were qualitatively and quantitatively compared with microscopic experimental findings on apple cells and a fairly good agreement was observed with some exceptions. The wall–fluid attraction forces and cell wall bending stiffness were found to be significantly improving the model predictions. A detailed sensitivity analysis was also done to further investigate the influence of wall–fluid attraction forces, cell wall bending stiffness, cell wall stiffness and the particle resolution. This novel meshfree based modeling approach is highly applicable for cellular level deformation studies of plant food materials during drying, which characterize large deformations.

Saliva proteome research: current status and future outlook

Human saliva harbours proteins of clinical relevance and about 30% of blood proteins are also present in saliva. This highlights that saliva can be used for clinical applications just as urine or blood. However, the translation of salivary biomarker discoveries into clinical settings is hampered by the dynamics and complexity of the salivary proteome. This review focuses on the current status of technological developments and achievements relating to approaches for unravelling the human salivary proteome. We discuss the dynamics of the salivary proteome, as well as the importance of sample preparation and processing techniques and their influence on downstream protein applications; post-translational modifications of salivary proteome and protein: protein interactions. In addition, we describe possible enrichment strategies for discerning post-translational modifications of salivary proteins, the potential utility of selected-reaction-monitoring techniques for biomarker discovery and validation, limitations to proteomics and the biomarker challenge and future perspectives. In summary, we provide recommendations for practical saliva sampling, processing and storage conditions to increase the quality of future studies in an emerging field of saliva clinical proteomics. We propose that the advent of technologies allowing sensitive and high throughput proteome-wide analyses, coupled to well-controlled study design, will allow saliva to enter clinical practice as an alternative to blood-based methods due to its simplistic nature of sampling, non-invasiveness, easy of collection and multiple collections by untrained professionals and cost-effective advantages.

Quantitation of gammaH2AX foci in tissue samples

DNA double-strand breaks (DSBs) are particularly lethal and genotoxic lesions, that can arise either by endogenous (physiological or pathological) processes or by exogenous factors, particularly ionizing radiation and radiomimetic compounds. Phosphorylation of the H2A histone variant, H2AX, at the serine-139 residue, in the highly conserved C-terminal SQEY motif, forming γH2AX, is an early response to DNA double-strand breaks1. This phosphorylation event is mediated by the phosphatidyl-inosito 3-kinase (PI3K) family of proteins, ataxia telangiectasia mutated (ATM), DNA-protein kinase catalytic subunit and ATM and RAD3-related (ATR)2. Overall, DSB induction results in the formation of discrete nuclear γH2AX foci which can be easily detected and quantitated by immunofluorescence microscopy2. Given the unique specificity and sensitivity of this marker, analysis of γH2AX foci has led to a wide range of applications in biomedical research, particularly in radiation biology and nuclear medicine. The quantitation of γH2AX foci has been most widely investigated in cell culture systems in the context of ionizing radiation-induced DSBs. Apart from cellular radiosensitivity, immunofluorescence based assays have also been used to evaluate the efficacy of radiation-modifying compounds. In addition, γH2AX has been used as a molecular marker to examine the efficacy of various DSB-inducing compounds and is recently being heralded as important marker of ageing and disease, particularly cancer3. Further, immunofluorescence-based methods have been adapted to suit detection and quantitation of γH2AX foci ex vivo and in vivo4,5. Here, we demonstrate a typical immunofluorescence method for detection and quantitation of γH2AX foci in mouse tissues.

Relevance feature discovery for text mining

It is a big challenge to guarantee the quality of discovered relevance features in text documents for describing user preferences because of large scale terms and data patterns. Most existing popular text mining and classification methods have adopted term-based approaches. However, they have all suffered from the problems of polysemy and synonymy. Over the years, there has been often held the hypothesis that pattern-based methods should perform better than term-based ones in describing user preferences; yet, how to effectively use large scale patterns remains a hard problem in text mining. To make a breakthrough in this challenging issue, this paper presents an innovative model for relevance feature discovery. It discovers both positive and negative patterns in text documents as higher level features and deploys them over low-level features (terms). It also classifies terms into categories and updates term weights based on their specificity and their distributions in patterns. Substantial experiments using this model on RCV1, TREC topics and Reuters-21578 show that the proposed model significantly outperforms both the state-of-the-art term-based methods and the pattern based methods.

Prevalence of methicillin resistance and virulence determinants of Staphylococcus aureus in diabetic foot ulcers

Background Diabetic foot ulceration (DFU) is a multifactorial process and is responsible for considerable morbidity and contributes to the increasing cost of health care worldwide. The diagnosis and identification of these ulcers remains a complex problem. Bacterial infection is promoted in the diabetic foot wound by decreased vascular supply and impaired host immune response. As conventional clinical microbiological methods are time-consuming and only identifies about 1% of the wound microbiota, detection of bacteria present in DFUs using molecular methods is highly advantageous and efficient. The aim of this study was to assess the virulence and methicillin resistance profiles of Staphylococcus aureus detected in DFUs using DNA-based methods. Methods A total of 223 swab samples were collected from 30 patients from March to October 2012. Bacterial DNA was extracted from the swab samples using standard procedures and was used to perform polymerase chain reaction (PCR) using specific oligonucleotide primers. The products were visualized using agarose gel electrophoresis. Results S. aureus was detected in 44.8% of samples. 25% of the S. aureus was methicillin-resistant S. aureus harboring the mecA gene. The alpha-toxin gene was present in 85% of the S. aureus positive samples. 61% of the S. aureus present in DFU samples harbored the exfoliatin factor A gene. Both the fibronectin factor A and fibronectin factor B gene were detected in 71% and 74% of the S. aureus positive samples. Conclusions DNA-based detection and characterization of bacteria in DFUs are rapid and efficient and can assist in accurate, targeted antibiotic therapy of DFU infections. The majority of S. aureus detected in this study were highly virulent and also resistant to methicillin. Further studies are required to understand the role of S. aureus in DFU trajectory.

Mortality attributable to smoking in Vietnamese men in 2008

Objective Smoking prevalence among Vietnamese men is among the highest in the world. Our aim was to provide estimates of tobacco attributable mortality to support tobacco control policies. Method We used the Peto–Lopez method using lung cancer mortality to derive a Smoking Impact Ratio (SIR) as a marker of cumulative exposure to smoking. SIRs were applied to relative risks from the Cancer Prevention Study, Phase II. Prevalence-based and hybrid methods, using the SIR for cancers and chronic obstructive pulmonary disease and smoking prevalence for all other outcomes, were used in sensitivity analyses. Results When lung cancer was used to measure cumulative smoking exposure, 28% (95% uncertainty interval 24–31%) of all adult male deaths (> 35 years) in Vietnam in 2008 were attributable to smoking. Lower estimates resulted from prevalence-based methods [24% (95% uncertainty interval 21–26%)] with the hybrid method yielding intermediate estimates [26% (95% uncertainty interval 23–28%)]. Conclusion Despite uncertainty in these estimates of attributable mortality, tobacco smoking is already a major risk factor for death in Vietnamese men. Given the high current prevalence of smoking, this has important implications not only for preventing the uptake of tobacco but also for immediate action to adopt and enforce stronger tobacco control measures.

Machine learning approaches to analysing textual injury surveillance data: A systematic review

Objective To synthesise recent research on the use of machine learning approaches to mining textual injury surveillance data. Design Systematic review. Data sources The electronic databases which were searched included PubMed, Cinahl, Medline, Google Scholar, and Proquest. The bibliography of all relevant articles was examined and associated articles were identified using a snowballing technique. Selection criteria For inclusion, articles were required to meet the following criteria: (a) used a health-related database, (b) focused on injury-related cases, AND used machine learning approaches to analyse textual data. Methods The papers identified through the search were screened resulting in 16 papers selected for review. Articles were reviewed to describe the databases and methodology used, the strength and limitations of different techniques, and quality assurance approaches used. Due to heterogeneity between studies meta-analysis was not performed. Results Occupational injuries were the focus of half of the machine learning studies and the most common methods described were Bayesian probability or Bayesian network based methods to either predict injury categories or extract common injury scenarios. Models were evaluated through either comparison with gold standard data or content expert evaluation or statistical measures of quality. Machine learning was found to provide high precision and accuracy when predicting a small number of categories, was valuable for visualisation of injury patterns and prediction of future outcomes. However, difficulties related to generalizability, source data quality, complexity of models and integration of content and technical knowledge were discussed. Conclusions The use of narrative text for injury surveillance has grown in popularity, complexity and quality over recent years. With advances in data mining techniques, increased capacity for analysis of large databases, and involvement of computer scientists in the injury prevention field, along with more comprehensive use and description of quality assurance methods in text mining approaches, it is likely that we will see a continued growth and advancement in knowledge of text mining in the injury field.

Reflections and encounters: Exploring awareness in an academic environment

Earlier work within the CSCW community treated the notion of awareness as an important resource for supporting shared work and work-related activities. However, new trends have emerged in recent times that utilize the notion of awareness beyond work-related activities and explore social, emotional and interpersonal aspects of people’s everyday lives. To investigate this broader notion of awareness, we carried out a field study using ethnographic and cultural probe based methods in an academic setting. Our aim was to study staff members’ everyday activities in their natural surroundings; understand how awareness beyond work-related activities plays out and how it is dealt with. Our field study results shed light on two broad and sometimes overlapping themes of interaction between staff members: 1) self-representations and 2) casual encounters. We provide examples from the field illustrating these two themes. In general, our results show how awareness is closely associated with people’s everyday lives, where they creatively and artfully utilize ordinary resources from their environments to carry out their routine activities. Using the results of our field study, we describe the design of a situated display called Panorama that is meant to support non-critical, non-work-related awareness within work environments.

Identifying candidate gene effects by restricting search space in a multivariate genetic analysis of white matter microstructure

Several genetic variants are thought to influence white matter (WM) integrity, measured with diffusion tensor imaging (DTI). Voxel based methods can test genetic associations, but heavy multiple comparisons corrections are required to adjust for searching the whole brain and for all genetic variants analyzed. Thus, genetic associations are hard to detect even in large studies. Using a recently developed multi-SNP analysis, we examined the joint predictive power of a group of 18 cholesterol-related single nucleotide polymorphisms (SNPs) on WM integrity, measured by fractional anisotropy. To boost power, we limited the analysis to brain voxels that showed significant associations with total serum cholesterol levels. From this space, we identified two genes with effects that replicated in individual voxel-wise analyses of the whole brain. Multivariate analyses of genetic variants on a reduced anatomical search space may help to identify SNPs with strongest effects on the brain from a broad panel of genes.

Damage detection in suspension bridges using vibration characteristics

This research developed a method to detect damage in suspension bridges using vibration characteristics. These bridges exhibit complex vibration and hence it is difficult to use traditional vibration based methods to detect damage in them. This research therefore proposed component specific damage indices and verified their capability to detect and locate damage in the main cables and hangers of suspension bridges.

The effect of HLA-DR genes on susceptibility to and severity of ankylosing spondylitis

Objective. To analyze the effect of HLA-DR genes on susceptibility to and severity of ankylosing spondylitis (AS). Methods. Three hundred sixty- three white British AS patients were studied; 149 were carefully assessed for a range of clinical manifestations, and disease severity was assessed using a structured questionnaire. Limited HLA class I typing and complete HLA-DR typing were performed using DNA-based methods. HLA data from 13,634 healthy white British bone marrow donors were used for comparison. Results. A significant association between DR1 and AS was found, independent of HLA-B27 (overall odds ratio [OR] 1.4, 95% confidence interval [95% CI] 1.1-1.8, P = 0.02; relative risk [RR] 2.7, 95% CI 1.5-4.8, P = 6 x 10-4 among homozygotes; RR 2.1, 95% CI 1.5-2.8, P = 5 x 10-6 among heterozygotes). A large but weakly significant association between DR8 and AS was noted, particularly among DR8 homozygotes (RR 6.8, 95% CI 1.6-29.2, P = 0.01 among homozygotes; RR 1.6, 95% CI 1.0-2.7, P = 0.07 among heterozygotes). A negative association with DR12 (OR 0.22, 95% CI 0.09-0.5, P = 0.001) was noted. HLA-DR7 was associated with younger age at onset of disease (mean age at onset 18 years for DR7-positive patients and 23 years for DR7-negative patients; Z score 3.21, P = 0.001). No other HLA class I or class H associations with disease severity or with different clinical manifestations of AS were found. Conclusion. The results of this study suggest that HLA-DR genes may have a weak effect on susceptibility to AS independent of HLA-B27, but do not support suggestions that they affect disease severity or different clinical manifestations.

On robust face recognition via sparse coding: The good, the bad and the ugly

In the field of face recognition, sparse representation (SR) has received considerable attention during the past few years, with a focus on holistic descriptors in closed-set identification applications. The underlying assumption in such SR-based methods is that each class in the gallery has sufficient samples and the query lies on the subspace spanned by the gallery of the same class. Unfortunately, such an assumption is easily violated in the face verification scenario, where the task is to determine if two faces (where one or both have not been seen before) belong to the same person. In this study, the authors propose an alternative approach to SR-based face verification, where SR encoding is performed on local image patches rather than the entire face. The obtained sparse signals are pooled via averaging to form multiple region descriptors, which then form an overall face descriptor. Owing to the deliberate loss of spatial relations within each region (caused by averaging), the resulting descriptor is robust to misalignment and various image deformations. Within the proposed framework, they evaluate several SR encoding techniques: l1-minimisation, Sparse Autoencoder Neural Network (SANN) and an implicit probabilistic technique based on Gaussian mixture models. Thorough experiments on AR, FERET, exYaleB, BANCA and ChokePoint datasets show that the local SR approach obtains considerably better and more robust performance than several previous state-of-the-art holistic SR methods, on both the traditional closed-set identification task and the more applicable face verification task. The experiments also show that l1-minimisation-based encoding has a considerably higher computational cost when compared with SANN-based and probabilistic encoding, but leads to higher recognition rates.

Rank regression for analyzing ordinal qualitative data for treatment comparison

Ordinal qualitative data are often collected for phenotypical measurements in plant pathology and other biological sciences. Statistical methods, such as t tests or analysis of variance, are usually used to analyze ordinal data when comparing two groups or multiple groups. However, the underlying assumptions such as normality and homogeneous variances are often violated for qualitative data. To this end, we investigated an alternative methodology, rank regression, for analyzing the ordinal data. The rank-based methods are essentially based on pairwise comparisons and, therefore, can deal with qualitative data naturally. They require neither normality assumption nor data transformation. Apart from robustness against outliers and high efficiency, the rank regression can also incorporate covariate effects in the same way as the ordinary regression. By reanalyzing a data set from a wheat Fusarium crown rot study, we illustrated the use of the rank regression methodology and demonstrated that the rank regression models appear to be more appropriate and sensible for analyzing nonnormal data and data with outliers.