Text mining with semantic annotation : using enriched text representation for entity-oriented retrieval, semantic relation identification and text clustering

This project is a step forward in the study of text mining where enhanced text representation with semantic information plays a significant role. It develops effective methods of entity-oriented retrieval, semantic relation identification and text clustering utilizing semantically annotated data. These methods are based on enriched text representation generated by introducing semantic information extracted from Wikipedia into the input text data. The proposed methods are evaluated against several start-of-art benchmarking methods on real-life data-sets. In particular, this thesis improves the performance of entity-oriented retrieval, identifies different lexical forms for an entity relation and handles clustering documents with multiple feature spaces.

Pre-processing for approximate Bayesian computation in image analysis

Most of the existing algorithms for approximate Bayesian computation (ABC) assume that it is feasible to simulate pseudo-data from the model at each iteration. However, the computational cost of these simulations can be prohibitive for high dimensional data. An important example is the Potts model, which is commonly used in image analysis. Images encountered in real world applications can have millions of pixels, therefore scalability is a major concern. We apply ABC with a synthetic likelihood to the hidden Potts model with additive Gaussian noise. Using a pre-processing step, we fit a binding function to model the relationship between the model parameters and the synthetic likelihood parameters. Our numerical experiments demonstrate that the precomputed binding function dramatically improves the scalability of ABC, reducing the average runtime required for model fitting from 71 hours to only 7 minutes. We also illustrate the method by estimating the smoothing parameter for remotely sensed satellite imagery. Without precomputation, Bayesian inference is impractical for datasets of that scale.

The use of a Riesz fractional differential-based approach for texture enhancement in image processing

Texture enhancement is an important component of image processing that finds extensive application in science and engineering. The quality of medical images, quantified using the imaging texture, plays a significant role in the routine diagnosis performed by medical practitioners. Most image texture enhancement is performed using classical integral order differential mask operators. Recently, first order fractional differential operators were used to enhance images. Experimentation with these methods led to the conclusion that fractional differential operators not only maintain the low frequency contour features in the smooth areas of the image, but they also nonlinearly enhance edges and textures corresponding to high frequency image components. However, whilst these methods perform well in particular cases, they are not routinely useful across all applications. To this end, we apply the second order Riesz fractional differential operator to improve upon existing approaches of texture enhancement. Compared with the classical integral order differential mask operators and other first order fractional differential operators, we find that our new algorithms provide higher signal to noise values and superior image quality.

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.

Identifying weak linear features with the "coalescing shortest path image transform"

The detection of line-like features in images finds many applications in microanalysis. Actin fibers, microtubules, neurites, pilis, DNA, and other biological structures all come up as tenuous curved lines in microscopy images. A reliable tracing method that preserves the integrity and details of these structures is particularly important for quantitative analyses. We have developed a new image transform called the "Coalescing Shortest Path Image Transform" with very encouraging properties. Our scheme efficiently combines information from an extensive collection of shortest paths in the image to delineate even very weak linear features. © Copyright Microscopy Society of America 2011.

DroplIT, an improved image analysis method for droplet identification in high-throughput crystallization trials

The application of robotics to protein crystallization trials has resulted in the production of millions of images. Manual inspection of these images to find crystals and other interesting outcomes is a major rate-limiting step. As a result there has been intense activity in developing automated algorithms to analyse these images. The very first step for most systems that have been described in the literature is to delineate each droplet. Here, a novel approach that reaches over 97% success rate and subsecond processing times is presented. This will form the seed of a new high-throughput system to scrutinize massive crystallization campaigns automatically. © 2010 International Union of Crystallography Printed in Singapore-all rights reserved.

Multi-modal deformable medical image registration

Non-rigid image registration is an essential tool required for overcoming the inherent local anatomical variations that exist between images acquired from different individuals or atlases. Furthermore, certain applications require this type of registration to operate across images acquired from different imaging modalities. One popular local approach for estimating this registration is a block matching procedure utilising the mutual information criterion. However, previous block matching procedures generate a sparse deformation field containing displacement estimates at uniformly spaced locations. This neglects to make use of the evidence that block matching results are dependent on the amount of local information content. This paper presents a solution to this drawback by proposing the use of a Reversible Jump Markov Chain Monte Carlo statistical procedure to optimally select grid points of interest. Three different methods are then compared to propagate the estimated sparse deformation field to the entire image including a thin-plate spline warp, Gaussian convolution, and a hybrid fluid technique. Results show that non-rigid registration can be improved by using the proposed algorithm to optimally select grid points of interest.

A Likelihood-Maximizing Framework for Enhanced In-Car Speech Recognition Based on Speech Dialog System Interaction

Speech recognition in car environments has been identified as a valuable means for reducing driver distraction when operating noncritical in-car systems. Under such conditions, however, speech recognition accuracy degrades significantly, and techniques such as speech enhancement are required to improve these accuracies. Likelihood-maximizing (LIMA) frameworks optimize speech enhancement algorithms based on recognized state sequences rather than traditional signal-level criteria such as maximizing signal-to-noise ratio. LIMA frameworks typically require calibration utterances to generate optimized enhancement parameters that are used for all subsequent utterances. Under such a scheme, suboptimal recognition performance occurs in noise conditions that are significantly different from that present during the calibration session – a serious problem in rapidly changing noise environments out on the open road. In this chapter, we propose a dialog-based design that allows regular optimization iterations in order to track the ever-changing noise conditions. Experiments using Mel-filterbank noise subtraction (MFNS) are performed to determine the optimization requirements for vehicular environments and show that minimal optimization is required to improve speech recognition, avoid over-optimization, and ultimately assist with semireal-time operation. It is also shown that the proposed design is able to provide improved recognition performance over frameworks incorporating a calibration session only.

A survey of radiographers' confidence and self-perceived accuracy in frontline image interpretation and their continuing educational preferences

Introduction The provision of a written comment on traumatic abnormalities of the musculoskeletal system detected by radiographers can assist referrers and may improve patient management, but the practice has not been widely adopted outside the United Kingdom. The purpose of this study was to investigate Australian radiographers’ perceptions of their readiness for practice in a radiographer commenting system and their educational preferences in relation to two different delivery formats of image interpretation education, intensive and non-intensive. Methods A cross-sectional web-based questionnaire was implemented between August and September 2012. Participants included radiographers with experience working in emergency settings at four Australian metropolitan hospitals. Conventional descriptive statistics, frequency histograms, and thematic analysis were undertaken. A Wilcoxon signed-rank test examined whether a difference in preference ratings between intensive and non-intensive education delivery was evident. Results The questionnaire was completed by 73 radiographers (68% response rate). Radiographers reported higher confidence and self-perceived accuracy to detect traumatic abnormalities than to describe traumatic abnormalities of the musculoskeletal system. Radiographers frequently reported high desirability ratings for both the intensive and the non-intensive education delivery, no difference in desirability ratings for these two formats was evident (z = 1.66,P = 0.11). Conclusions Some Australian radiographers perceive they are not ready to practise in a frontline radiographer commenting system. Overall, radiographers indicated mixed preferences for image interpretation education delivered via intensive and non-intensive formats. Further research, preferably randomised trials, investigating the effectiveness of intensive and non-intensive education formats of image interpretation education for radiographers is warranted.

Detecting rare events using Kullback-Leibler divergence

One main challenge in developing a system for visual surveillance event detection is the annotation of target events in the training data. By making use of the assumption that events with security interest are often rare compared to regular behaviours, this paper presents a novel approach by using Kullback-Leibler (KL) divergence for rare event detection in a weakly supervised learning setting, where only clip-level annotation is available. It will be shown that this approach outperforms state-of-the-art methods on a popular real-world dataset, while preserving real time performance.

Integrating field survey data with satellite image data to improve shallow water seagrass maps : the role of AUV and snorkeller surveys

Repeatable and accurate seagrass mapping is required for understanding seagrass ecology and supporting management decisions. For shallow (< 5 m) seagrass habitats, these maps can be created by integrating high spatial resolution imagery with field survey data. Field survey data for seagrass is often collected via snorkelling or diving. However, these methods are limited by environmental and safety considerations. Autonomous Underwater Vehicles (AUVs) are used increasingly to collect field data for habitat mapping, albeit mostly in deeper waters (>20 m). Here we demonstrate and evaluate the use and potential advantages of AUV field data collection for calibration and validation of seagrass habitat mapping of shallow waters (< 5 m), from multispectral satellite imagery. The study was conducted in the seagrass habitats of the Eastern Banks (142 km2), Moreton Bay, Australia. In the field, georeferenced photos of the seagrass were collected along transects via snorkelling or an AUV. Photos from both collection methods were analysed manually for seagrass species composition and then used as calibration and validation data to map seagrass using an established semi-automated object based mapping routine. A comparison of the relative advantages and disadvantages of AUV and snorkeller collected field data sets and their influence on the mapping routine was conducted. AUV data collection was more consistent, repeatable and safer in comparison to snorkeller transects. Inclusion of deeper water AUV data resulted in mapping of a larger extent of seagrass (~7 km2, 5 % of study area) in the deeper waters of the site. Although overall map accuracies did not differ considerably, inclusion of the AUV data from deeper water transects corrected errors in seagrass mapped at depths to 5 m, but where the bottom is visible on satellite imagery. Our results demonstrate that further development of AUV technology is justified for the monitoring of seagrass habitats in ongoing management programs.

Investigation of fiducial marker and soft-tissue image guidance techniques in prostate radiation therapy

This thesis examines and compares imaging methods used during the radiotherapy treatment of prostate cancer. The studies found that radiation therapists were able to localise and target the prostate consistently with planar imaging techniques and that the use of small gold markers in the prostate reduced the variation in prostate localisation when using volumetric imaging. It was concluded that larger safety margins are required when using volumetric imaging without gold markers.

An external field prior for the hidden Potts model with application to cone-beam computed tomography

In images with low contrast-to-noise ratio (CNR), the information gain from the observed pixel values can be insufficient to distinguish foreground objects. A Bayesian approach to this problem is to incorporate prior information about the objects into a statistical model. A method for representing spatial prior information as an external field in a hidden Potts model is introduced. This prior distribution over the latent pixel labels is a mixture of Gaussian fields, centred on the positions of the objects at a previous point in time. It is particularly applicable in longitudinal imaging studies, where the manual segmentation of one image can be used as a prior for automatic segmentation of subsequent images. The method is demonstrated by application to cone-beam computed tomography (CT), an imaging modality that exhibits distortions in pixel values due to X-ray scatter. The external field prior results in a substantial improvement in segmentation accuracy, reducing the mean pixel misclassification rate for an electron density phantom from 87% to 6%. The method is also applied to radiotherapy patient data, demonstrating how to derive the external field prior in a clinical context.

Reflexive and automatic violence: A function of aberrant perceptual inhibition

It’s commonly assumed that psychiatric violence is motivated by delusions, but here the concept of a reversed impetus is explored, to understand whether delusions are formed as ad-hoc or post-hoc rationalizations of behaviour or in advance of the actus reus. The reflexive violence model proposes that perceptual stimuli has motivational power and this may trigger unwanted actions and hallucinations. The model is based on the theory of ecological perception, where opportunities enabled by an object are cues to act. As an apple triggers a desire to eat, a gun triggers a desire to shoot. These affordances (as they are called) are part of the perceptual apparatus, they allow the direct recognition of objects – and in emergencies they enable the fastest possible reactions. Even under normal circumstances, the presence of a weapon will trigger inhibited violent impulses. The presence of a victim will also, but under normal circumstances, these affordances don’t become violent because negative action impulses are totally inhibited, whereas in psychotic illness, negative action impulses are treated as emergencies and bypass frontal inhibitory circuits. What would have been object recognition becomes a blind automatic action. A range of mental illnesses can cause inhibition to be bypassed. At its most innocuous, this causes both simple hallucinations (where the motivational power of an object is misattributed). But ecological perception may have the power to trigger serious violence also –a kind that’s devoid of motives or planning and is often shrouded in amnesia or post-rational delusions.