Locality-sensitive hashing for protein classification

Determination of sequence similarity is a central issue in computational biology, a problem addressed primarily through BLAST, an alignment based heuristic which has underpinned much of the analysis and annotation of the genomic era. Despite their success, alignment-based approaches scale poorly with increasing data set size, and are not robust under structural sequence rearrangements. Successive waves of innovation in sequencing technologies – so-called Next Generation Sequencing (NGS) approaches – have led to an explosion in data availability, challenging existing methods and motivating novel approaches to sequence representation and similarity scoring, including adaptation of existing methods from other domains such as information retrieval. In this work, we investigate locality-sensitive hashing of sequences through binary document signatures, applying the method to a bacterial protein classification task. Here, the goal is to predict the gene family to which a given query protein belongs. Experiments carried out on a pair of small but biologically realistic datasets (the full protein repertoires of families of Chlamydia and Staphylococcus aureus genomes respectively) show that a measure of similarity obtained by locality sensitive hashing gives highly accurate results while offering a number of avenues which will lead to substantial performance improvements over BLAST..

Writing embodied practice from the inside : outside the exegesis

The textual turn is a good friend of expert spectating, where it assumes the role of writing-productive apparatus, but no friend at all of expert practices or practitioners (Melrose, 2003). Introduction The challenge of time-based embodied performance when the artefact is unstable As a former full-time professional practitioner with an embodied dance practice as performer, choreographer and artistic director for three decades, I somewhat unexpectedly entered the world of academia in 2000 after completing a practice-based PhD, which was described by its examiners as ‘pioneering’. Like many artists my intention was to deepen and extend my practice through formal research into my work and its context (which was intercultural) and to privilege the artist’s voice in a research world where it was too often silent. Practice as research, practice-based research, and practice-led research were not yet fully named. It was in its infancy and my biggest challenge was to find a serviceable methodology which did not betray my intentions to keep practice at the centre of the research. Over the last 15 years, practice led doctoral research, where examinable creative work is placed alongside an accompanying (exegetical) written component, has come a long way. It has been extensively debated with a range of theories and models proposed (Barrett & Bolt, 2007, Pakes, 2003 & 2004, Piccini, 2005, Philips, Stock & Vincs 2009, Stock, 2009 & 2010, Riley & Hunter 2009, Haseman, 2006, Hecq, 2012). Much of this writing is based around epistemological concerns where the research methodologies proposed normally incorporate a contextualisation of the creative work in its field of practice, and more importantly validation and interrogation of the processes of the practice as the central ‘data gathering’ method. It is now widely accepted, at least in the Australian creative arts context, that knowledge claims in creative practice research arise from the material activities of the practice itself (Carter, 2004). The creative work explicated as the tangible outcome of that practice is sometimes referred to as the ‘artefact’. Although the making of the artefact, according to Colbert (2009, p. 7) is influenced by “personal, experiential and iterative processes”, mapping them through a research pathway is “difficult to predict [for] “the adjustments made to the artefact in the light of emerging knowledge and insights cannot be foreshadowed”. Linking the process and the practice outcome most often occurs through the textual intervention of an exegesis which builds, and/or builds on, theoretical concerns arising in and from the work. This linking produces what Barrett (2007) refers to as “situated knowledge… that operates in relation to established knowledge” (p. 145). But what if those material forms or ‘artefacts’ are not objects or code or digitised forms, but live within the bodies of artist/researchers where the nature of the practice itself is live, ephemeral and constantly transforming, as in dance and physical performance? Even more unsettling is when the ‘artefact’ is literally embedded and embodied in the work and in the maker/researcher; when subject and object are merged. To complicate matters, the performing arts are necessarily collaborative, relying not only on technical mastery and creative/interpretive processes, but on social and artistic relationships which collectively make up the ‘artefact’. This chapter explores issues surrounding live dance and physical performance when placed in a research setting, specifically the complexities of being required to translate embodied dance findings into textual form. Exploring how embodied knowledge can be shared in a research context for those with no experiential knowledge of communicating through and in dance, I draw on theories of “dance enaction” (Warburton, 2011) together with notions of “affective intensities” and “performance mastery” (Melrose, 2003), “intentional activity” (Pakes, 2004) and the place of memory. In seeking ways to capture in another form the knowledge residing in live dance practice, thus making implicit knowledge explicit, I further propose there is a process of triple translation as the performance (the living ‘artefact’) is documented in multi-facetted ways to produce something durable which can be re-visited. This translation becomes more complex if the embodied knowledge resides in culturally specific practices, formed by world views and processes quite different from accepted norms and conventions (even radical ones) of international doctoral research inquiry. But whatever the combination of cultural, virtual and genre-related dance practices being researched, embodiment is central to the process, outcome and findings, and the question remains of how we will use text and what forms that text might take.

'Doing-things-with-music'-the newest arm of the industry

Even though revenues from recorded music have fallen dramatically over the past fifteen years, people across the world are not listening to less music. Actually, they listen to more recorded music than ever before. Recorded music permeates throughout almost every aspect of our daily lives...

Evaluation of features for leaf classification in challenging conditions

Fine-grained leaf classification has concentrated on the use of traditional shape and statistical features to classify ideal images. In this paper we evaluate the effectiveness of traditional hand-crafted features and propose the use of deep convolutional neural network (ConvNet) features. We introduce a range of condition variations to explore the robustness of these features, including: translation, scaling, rotation, shading and occlusion. Evaluations on the Flavia dataset demonstrate that in ideal imaging conditions, combining traditional and ConvNet features yields state-of-theart performance with an average accuracy of 97:3%�0:6% compared to traditional features which obtain an average accuracy of 91:2%�1:6%. Further experiments show that this combined classification approach consistently outperforms the best set of traditional features by an average of 5:7% for all of the evaluated condition variations.

Injury narrative text classification : a preliminary study

Description of a patient's injuries is recorded in narrative text form by hospital emergency departments. For statistical reporting, this text data needs to be mapped to pre-defined codes. Existing research in this field uses the Naïve Bayes probabilistic method to build classifiers for mapping. In this paper, we focus on providing guidance on the selection of a classification method. We build a number of classifiers belonging to different classification families such as decision tree, probabilistic, neural networks, and instance-based, ensemble-based and kernel-based linear classifiers. An extensive pre-processing is carried out to ensure the quality of data and, in hence, the quality classification outcome. The records with a null entry in injury description are removed. The misspelling correction process is carried out by finding and replacing the misspelt word with a soundlike word. Meaningful phrases have been identified and kept, instead of removing the part of phrase as a stop word. The abbreviations appearing in many forms of entry are manually identified and only one form of abbreviations is used. Clustering is utilised to discriminate between non-frequent and frequent terms. This process reduced the number of text features dramatically from about 28,000 to 5000. The medical narrative text injury dataset, under consideration, is composed of many short documents. The data can be characterized as high-dimensional and sparse, i.e., few features are irrelevant but features are correlated with one another. Therefore, Matrix factorization techniques such as Singular Value Decomposition (SVD) and Non Negative Matrix Factorization (NNMF) have been used to map the processed feature space to a lower-dimensional feature space. Classifiers with these reduced feature space have been built. In experiments, a set of tests are conducted to reflect which classification method is best for the medical text classification. The Non Negative Matrix Factorization with Support Vector Machine method can achieve 93% precision which is higher than all the tested traditional classifiers. We also found that TF/IDF weighting which works well for long text classification is inferior to binary weighting in short document classification. Another finding is that the Top-n terms should be removed in consultation with medical experts, as it affects the classification performance.

Higher order spectra based support vector machine for arrhythmia classification

Heart rate variability (HRV) refers to the regulation of the sinoatrial node, the natural pacemaker of the heart by the sympathetic and parasympathetic branches of the autonomic nervous system. HRV analysis is an important tool to observe the heart’s ability to respond to normal regulatory impulses that affect its rhythm. Like many bio-signals, HRV signals are non-linear in nature. Higher order spectral analysis (HOS) is known to be a good tool for the analysis of non-linear systems and provides good noise immunity. A computer-based arrhythmia detection system of cardiac states is very useful in diagnostics and disease management. In this work, we studied the identification of the HRV signals using features derived from HOS. These features were fed to the support vector machine (SVM) for classification. Our proposed system can classify the normal and other four classes of arrhythmia with an average accuracy of more than 85%.

Lighting invariant urban street classification

In this paper we propose the hybrid use of illuminant invariant and RGB images to perform image classification of urban scenes despite challenging variation in lighting conditions. Coping with lighting change (and the shadows thereby invoked) is a non-negotiable requirement for long term autonomy using vision. One aspect of this is the ability to reliably classify scene components in the presence of marked and often sudden changes in lighting. This is the focus of this paper. Posed with the task of classifying all parts in a scene from a full colour image, we propose that lighting invariant transforms can reduce the variability of the scene, resulting in a more reliable classification. We leverage the ideas of “data transfer” for classification, beginning with full colour images for obtaining candidate scene-level matches using global image descriptors. This is commonly followed by superpixellevel matching with local features. However, we show that if the RGB images are subjected to an illuminant invariant transform before computing the superpixel-level features, classification is significantly more robust to scene illumination effects. The approach is evaluated using three datasets. The first being our own dataset and the second being the KITTI dataset using manually generated ground truth for quantitative analysis. We qualitatively evaluate the method on a third custom dataset over a 750m trajectory.

North West Music Festival in Port Hedland, Western Australia

A travel article about a music festival in Port Hedland, Western Australia. At first, the crowd gathers in small groups, as though we’ve arrived at a picnic day. Girls in long skirts wearing bands in their hair call out across the wide lawn of the Turf Club, and run over to meet friends. They sit cross-legged in the sun, half swaying to the music, chatting. On stage, Thelma Plum, a girl with a voice from the 1960s, circles her lyrics with her hands. You wonder if she’s casting a spell, an appeal to the decade of revolutions...

Classification of echolocation calls from 14 species of bat by Support Vector Machines and Ensembles of Neural Networks

Calls from 14 species of bat were classified to genus and species using discriminant function analysis (DFA), support vector machines (SVM) and ensembles of neural networks (ENN). Both SVMs and ENNs outperformed DFA for every species while ENNs (mean identification rate – 97%) consistently outperformed SVMs (mean identification rate – 87%). Correct classification rates produced by the ENNs varied from 91% to 100%; calls from six species were correctly identified with 100% accuracy. Calls from the five species of Myotis, a genus whose species are considered difficult to distinguish acoustically, had correct identification rates that varied from 91 – 100%. Five parameters were most important for classifying calls correctly while seven others contributed little to classification performance.

Pollen image classification using the classifynder system: Algorithm comparison and a case study on New Zealand honey

We describe an investigation into how Massey University’s Pollen Classifynder can accelerate the understanding of pollen and its role in nature. The Classifynder is an imaging microscopy system that can locate, image and classify slide based pollen samples. Given the laboriousness of purely manual image acquisition and identification it is vital to exploit assistive technologies like the Classifynder to enable acquisition and analysis of pollen samples. It is also vital that we understand the strengths and limitations of automated systems so that they can be used (and improved) to compliment the strengths and weaknesses of human analysts to the greatest extent possible. This article reviews some of our experiences with the Classifynder system and our exploration of alternative classifier models to enhance both accuracy and interpretability. Our experiments in the pollen analysis problem domain have been based on samples from the Australian National University’s pollen reference collection (2,890 grains, 15 species) and images bundled with the Classifynder system (400 grains, 4 species). These samples have been represented using the Classifynder image feature set.We additionally work through a real world case study where we assess the ability of the system to determine the pollen make-up of samples of New Zealand honey. In addition to the Classifynder’s native neural network classifier, we have evaluated linear discriminant, support vector machine, decision tree and random forest classifiers on these data with encouraging results. Our hope is that our findings will help enhance the performance of future releases of the Classifynder and other systems for accelerating the acquisition and analysis of pollen samples.

A comparison of classification algorithms within the Classifynder pollen imaging system

We describe an investigation into how Massey University's Pollen Classifynder can accelerate the understanding of pollen and its role in nature. The Classifynder is an imaging microscopy system that can locate, image and classify slide based pollen samples. Given the laboriousness of purely manual image acquisition and identification it is vital to exploit assistive technologies like the Classifynder to enable acquisition and analysis of pollen samples. It is also vital that we understand the strengths and limitations of automated systems so that they can be used (and improved) to compliment the strengths and weaknesses of human analysts to the greatest extent possible. This article reviews some of our experiences with the Classifynder system and our exploration of alternative classifier models to enhance both accuracy and interpretability. Our experiments in the pollen analysis problem domain have been based on samples from the Australian National University's pollen reference collection (2890 grains, 15 species) and images bundled with the Classifynder system (400 grains, 4 species). These samples have been represented using the Classifynder image feature set. In addition to the Classifynder's native neural network classifier, we have evaluated linear discriminant, support vector machine, decision tree and random forest classifiers on these data with encouraging results. Our hope is that our findings will help enhance the performance of future releases of the Classifynder and other systems for accelerating the acquisition and analysis of pollen samples. © 2013 AIP Publishing LLC.

Classification of inventory data suit for managing Australian railway bridges

With a focus to optimising the life cycle performance of Australian Railway bridges, new bridge classification and environmental classification systems are proposed. The new bridge classification system is mainly to facilitate the implementation of novel Bridge Management System (BMS) which optimise the life cycle cost both at project level and network level while environment classification is mainly to improve accuracy of Remaining Service Potential (RSP) module of the proposed BMS. In fact, limited capacity of the existing BMS to trigger the maintenance intervention point is an indirect result of inadequacies of the existing bridge and environmental classification systems. The proposed bridge classification system permits to identify the intervention points based on percentage deterioration of individual elements and maintenance cost, while allowing performance based rating technique to implement for maintenance optimisation and prioritisation. Simultaneously, the proposed environment classification system will enhance the accuracy of prediction of deterioration of steel components.