Sparse representation with multi-manifold analysis for texture classification from few training images

Texture classification is one of the most important tasks in computer vision field and it has been extensively investigated in the last several decades. Previous texture classification methods mainly used the template matching based methods such as Support Vector Machine and k-Nearest-Neighbour for classification. Given enough training images the state-of-the-art texture classification methods could achieve very high classification accuracies on some benchmark databases. However, when the number of training images is limited, which usually happens in real-world applications because of the high cost of obtaining labelled data, the classification accuracies of those state-of-the-art methods would deteriorate due to the overfitting effect. In this paper we aim to develop a novel framework that could correctly classify textural images with only a small number of training images. By taking into account the repetition and sparsity property of textures we propose a sparse representation based multi-manifold analysis framework for texture classification from few training images. A set of new training samples are generated from each training image by a scale and spatial pyramid, and then the training samples belonging to each class are modelled by a manifold based on sparse representation. We learn a dictionary of sparse representation and a projection matrix for each class and classify the test images based on the projected reconstruction errors. The framework provides a more compact model than the template matching based texture classification methods, and mitigates the overfitting effect. Experimental results show that the proposed method could achieve reasonably high generalization capability even with as few as 3 training images, and significantly outperforms the state-of-the-art texture classification approaches on three benchmark datasets. © 2014 Elsevier B.V. All rights reserved.

Enhancing medical named entity recognition with an extended segment representation technique

Objective : The objective of this paper is to formulate an extended segment representation (SR) technique to enhance named entity recognition (NER) in medical applications.

Methods : An extension to the IOBES (Inside/Outside/Begin/End/Single) SR technique is formulated. In the proposed extension, a new class is assigned to words that do not belong to a named entity (NE) in one context but appear as an NE in other contexts. Ambiguity in such cases can negatively affect the results of classification-based NER techniques. Assigning a separate class to words that can potentially cause ambiguity in NER allows a classifier to detect NEs more accurately; therefore increasing classification accuracy.

Results : The proposed SR technique is evaluated using the i2b2 2010 medical challenge data set with eight different classifiers. Each classifier is trained separately to extract three different medical NEs, namely treatment, problem, and test. From the three experimental results, the extended SR technique is able to improve the average F1-measure results pertaining to seven out of eight classifiers. The kNN classifier shows an average reduction of 0.18% across three experiments, while the C4.5 classifier records an average improvement of 9.33%.

Neural spike representation using Cepstrum

Neural spikes define the human brain function. An accurate extraction of spike features leads to better understanding of brain functionality. The main challenge of feature extraction is to mitigate the effect of strong background noises. To address this problem, we introduce a new feature representation for neural spikes based on Cepstrum of multichannel recordings. Simulation results indicated that the proposed method is more robust than the existing Haar wavelet method.

Numerical investigation of influence of the Martensite Volume Fraction on dp steels fracture behavior on the basis of digital material representation model

Development of the methodology for creating reliable digital material representation (DMR) models of dual-phase steels and investigation of influence of the martensite volume fraction on fracture behavior under tensile load are the main goals of the paper. First, an approach based on image processing algorithms for creating a DMR is described. Then, obtained digital microstructures are used as input for the numerical model of deformation, which takes into account mechanisms of ductile fracture. Ferrite and martensite material model parameters are evaluated on the basis of micropillar compression tests. Finally, the model is used to investigate the impact of the martensite volume fraction on the DP steel behavior under plastic deformation. Results of calculations are presented and discussed in the paper.

Migration exhibitions and the question of identity: reflections on the history of the representation of migration in Australian museums, 1986-2011

Museums and Migration explores the ways in which museum spaces - local, regional, national - have engaged with the history of migration, including internal migration, emigration and immigration.

Digital material representation and testing of metal foams

In recent years, metal foams are becoming more and more popular due to their high energy absorption ability and low density, which are being widely used in automotive engineering and aerospace engineering. As a design guide, foams can be characterised by several main geometric parameters, such as pore size, pore shape, spatial distribution and arrangement and so on. Considering most foam materials have random distributions of cell size and cell shape, the digital material representation and modelling of such materials become more complex. Cell size and shape effects on mechanical behaviours of metal foams have been found and investigated numerically and experimentally in authors' previous studies in which the authors have developed a digital framework for the representation, modelling and evaluation of multi-phase materials including metal foams. In this study, 2-/3-D finite element models are both developed to represent metal foams with random cell distributions and then a series of digital testing are simulated to investigate the mechanical behaviours of such foams. For validation and verification purpose, the results obtained from 2-/3-D models have been compared and good agreement has been found which demonstrated the effectiveness of the digital framework developed for metal forms. © (2014) Trans Tech Publications, Switzerland.

A reassessment of non-union employee representation in the UK: developments since the 'ICE' age

In light of new legislation pertaining to information and consultation in the UK, the need to reassess the realms of employee involvement and participation, especially non-union forms, is critically apparent. This article explores the character of non-union employee representation arrangements established in the context of the Information and Consultation of Employees Regulations 2004, drawing on case study evidence from two UK-based manufacturing organisations. The findings highlight some important dynamics concerning the use of non-union employee representation; not least that the Information and Consultation of Employees Regulations have impacted in very different ways from those anticipated by the legislation.

Assessment of habitat representation across a network of marine protected areas with implications for the spatial design of monitoring

Networks of marine protected areas (MPAs) are being adopted globally to protect ecosystems and supplement fisheries management. The state of California recently implemented a coast-wide network of MPAs, a statewide seafloor mapping program, and ecological characterizations of species and ecosystems targeted for protection by the network. The main goals of this study were to use these data to evaluate how well seafloor features, as proxies for habitats, are represented and replicated across an MPA network and how well ecological surveys representatively sampled fish habitats inside MPAs and adjacent reference sites. Seafloor data were classified into broad substrate categories (rock and sediment) and finer scale geomorphic classifications standard to marine classification schemes using surface analyses (slope, ruggedness, etc.) done on the digital elevation model derived from multibeam bathymetry data. These classifications were then used to evaluate the representation and replication of seafloor structure within the MPAs and across the ecological surveys. Both the broad substrate categories and the finer scale geomorphic features were proportionately represented for many of the classes with deviations of 1-6% and 0-7%, respectively. Within MPAs, however, representation of seafloor features differed markedly from original estimates, with differences ranging up to 28%. Seafloor structure in the biological monitoring design had mismatches between sampling in the MPAs and their corresponding reference sites and some seafloor structure classes were missed entirely. The geomorphic variables derived from multibeam bathymetry data for these analyses are known determinants of the distribution and abundance of marine species and for coastal marine biodiversity. Thus, analyses like those performed in this study can be a valuable initial method of evaluating and predicting the conservation value of MPAs across a regional network.

Indonesia's national parties and the representation of a diverse society

 This study explores laws that promote the nationalisation of Indonesia’s political parties, and considers what this means for the representation of a diverse society. Overall, the research finds that the laws have restricted the development of political parties, but not for the reasons commonly expected.

Structured representation learning from complex data

This thesis advances several theoretical and practical aspects of the recently introduced restricted Boltzmann machine - a powerful probabilistic and generative framework for modelling data and learning representations. The contributions of this study represent a systematic and common theme in learning structured representations from complex data.

Mixed-norm sparse representation for multi view face recognition

Face recognition with multiple views is a challenging research problem. Most of the existing works have focused on extracting shared information among multiple views to improve recognition. However, when the pose variation is too large or missing, 'shared information' may not be properly extracted, leading to poor recognition results. In this paper, we propose a novel method for face recognition with multiple view images to overcome the large pose variation and missing pose issue. By introducing a novel mixed norm, the proposed method automatically selects candidates from the gallery to best represent a group of highly correlated face images in a query set to improve classification accuracy. This mixed norm combines the advantages of both sparse representation based classification (SRC) and joint sparse representation based classification (JSRC). A trade off between the ℓ1-norm from SRC and ℓ2,1-norm from JSRC is introduced to achieve this goal. Due to this property, the proposed method decreases the influence when a face image is unseen and has large pose variation in the recognition process. And when some face images with a certain degree of unseen pose variation appear, this mixed norm will find an optimal representation for these query images based on the shared information induced from multiple views. Moreover, we also address an open problem in robust sparse representation and classification which is using ℓ1-norm on the loss function to achieve a robust solution. To solve this formulation, we derive a simple, yet provably convergent algorithm based on the powerful alternative directions method of multipliers (ADMM) framework. We provide extensive comparisons which demonstrate that our method outperforms other state-of-the-arts algorithms on CMU-PIE, Yale B and Multi-PIE databases for multi-view face recognition.

Learning vector representation of medical objects via EMR-driven nonnegative restricted Boltzmann machines (eNRBM)

Electronic medical record (EMR) offers promises for novel analytics. However, manual feature engineering from EMR is labor intensive because EMR is complex - it contains temporal, mixed-type and multimodal data packed in irregular episodes. We present a computational framework to harness EMR with minimal human supervision via restricted Boltzmann machine (RBM). The framework derives a new representation of medical objects by embedding them in a low-dimensional vector space. This new representation facilitates algebraic and statistical manipulations such as projection onto 2D plane (thereby offering intuitive visualization), object grouping (hence enabling automated phenotyping), and risk stratification. To enhance model interpretability, we introduced two constraints into model parameters: (a) nonnegative coefficients, and (b) structural smoothness. These result in a novel model called eNRBM (EMR-driven nonnegative RBM). We demonstrate the capability of the eNRBM on a cohort of 7578 mental health patients under suicide risk assessment. The derived representation not only shows clinically meaningful feature grouping but also facilitates short-term risk stratification. The F-scores, 0.21 for moderate-risk and 0.36 for high-risk, are significantly higher than those obtained by clinicians and competitive with the results obtained by support vector machines.