Towards persistent localization and mapping with a continuous appearance-based topology

Appearance-based localization can provide loop closure detection at vast scales regardless of accumulated metric error. However, the computation time and memory requirements of current appearance-based methods scale not only with the size of the environment but also with the operation time of the platform. Additionally, repeated visits to locations will develop multiple competing representations, which will reduce recall performance over time. These properties impose severe restrictions on long-term autonomy for mobile robots, as loop closure performance will inevitably degrade with increased operation time. In this paper we present a graphical extension to CAT-SLAM, a particle filter-based algorithm for appearance-based localization and mapping, to provide constant computation and memory requirements over time and minimal degradation of recall performance during repeated visits to locations. We demonstrate loop closure detection in a large urban environment with capped computation time and memory requirements and performance exceeding previous appearance-based methods by a factor of 2. We discuss the limitations of the algorithm with respect to environment size, appearance change over time and applications in topological planning and navigation for long-term robot operation.

Correlation-based damage detection for complicated truss bridges using multi-layer genetic algorithms

The study presents a multi-layer genetic algorithm (GA) approach using correlation-based methods to facilitate damage determination for through-truss bridge structures. To begin, the structure’s damage-suspicious elements are divided into several groups. In the first GA layer, the damage is initially optimised for all groups using correlation objective function. In the second layer, the groups are combined to larger groups and the optimisation starts over at the normalised point of the first layer result. Then the identification process repeats until reaching the final layer where one group includes all structural elements and only minor optimisations are required to fine tune the final result. Several damage scenarios on a complicated through-truss bridge example are nominated to address the proposed approach’s effectiveness. Structural modal strain energy has been employed as the variable vector in the correlation function for damage determination. Simulations and comparison with the traditional single-layer optimisation shows that the proposed approach is efficient and feasible for complicated truss bridge structures when the measurement noise is taken into account.

Infertility, medical advice and treatment with fertility hormones and/or in vitro fertilisation: a population perspective from the Australian Longitudinal Study on Women's Health

OBJECTIVE: To identify the factors associated with infertility, seeking advice and treatment with fertility hormones and/or in vitro fertilisation (IVF) among a general population of women. METHODS: Participants in the Australian Longitudinal Study on Women's Health aged 28-33 years in 2006 had completed up to four mailed surveys over 10 years (n=9,145). Parsimonious multivariate logistic regression was used to identify the socio-demographic, biological (including reproductive histories), and behavioural factors associated with infertility, advice and hormonal/IVF treatment. RESULTS: For women who had tried to conceive or had been pregnant (n=5,936), 17% reported infertility. Among women with infertility (n=1031), 72% (n=728) sought advice but only 50% (n=356) used hormonal/IVF treatment. Women had higher odds of infertility when: they had never been pregnant (OR=7.2, 95% CI 5.6-9.1) or had a history of miscarriage (OR range=1.5-4.0) than those who had given birth (and never had a miscarriage or termination). CONCLUSION: Only one-third of women with infertility used hormonal and/or IVF treatment. Women with PCOS or endometriosis were the most proactive in having sought advice and used hormonal/IVF treatment. IMPLICATIONS: Raised awareness of age-related declining fertility is important for partnered women aged approximately 30 years to encourage pregnancy during their prime reproductive years and reduce the risk of infertility.

On the efficacy of techniques for evaluating multivariate volatility forecasts

The performance of techniques for evaluating multivariate volatility forecasts are not yet as well understood as their univariate counterparts. This paper aims to evaluate the efficacy of a range of traditional statistical-based methods for multivariate forecast evaluation together with methods based on underlying considerations of economic theory. It is found that a statistical-based method based on likelihood theory and an economic loss function based on portfolio variance are the most effective means of identifying optimal forecasts of conditional covariance matrices.

Visualisation of complex flows using texture-based techniques

Complex flow datasets are often difficult to represent in detail using traditional vector visualisation techniques such as arrow plots and streamlines. This is particularly true when the flow regime changes in time. Texture-based techniques, which are based on the advection of dense textures, are novel techniques for visualising such flows (i.e., complex dynamics and time-dependent). In this paper, we review two popular texture-based techniques and their application to flow datasets sourced from real research projects. The texture-based techniques investigated were Line Integral Convolution (LIC), and Image-Based Flow Visualisation (IBFV). We evaluated these techniques and in this paper report on their visualisation effectiveness (when compared with traditional techniques), their ease of implementation, and their computational overhead.

Optimisation of Banana streak virus (BSV) diagnostic assays

Bananas are one of the world�fs most important crops, serving as a staple food and an important source of income for millions of people in the subtropics. Pests and diseases are a major constraint to banana production. To prevent the spread of pests and disease, farmers are encouraged to use disease�] and insect�]free planting material obtained by micropropagation. This option, however, does not always exclude viruses and concern remains on the quality of planting material. Therefore, there is a demand for effective and reliable virus indexing procedures for tissue culture (TC) material. Reliable diagnostic tests are currently available for all of the economically important viruses of bananas with the exception of Banana streak viruses (BSV, Caulimoviridae, Badnavirus). Development of a reliable diagnostic test for BSV is complicated by the significant serological and genetic variation reported for BSV isolates, and the presence of endogenous BSV (eBSV). Current PCR�] and serological�]based diagnostic methods for BSV may not detect all species of BSV, and PCR�]based methods may give false positives because of the presence of eBSV. Rolling circle amplification (RCA) has been reported as a technique to detect BSV which can also discriminate between episomal and endogenous BSV sequences. However, the method is too expensive for large scale screening of samples in developing countries, and little information is available regarding its sensitivity. Therefore the development of reliable PCR�]based assays is still considered the most appropriate option for large scale screening of banana plants for BSV. This MSc project aimed to refine and optimise the protocols for BSV detection, with a particular focus on developing reliable PCR�]based diagnostics Initially, the appropriateness and reliability of PCR and RCA as diagnostic tests for BSV detection were assessed by testing 45 field samples of banana collected from nine districts in the Eastern region of Uganda in February 2010. This research was also aimed at investigating the diversity of BSV in eastern Uganda, identifying the BSV species present and characterising any new BSV species. Out of the 45 samples tested, 38 and 40 samples were considered positive by PCR and RCA, respectively. Six different species of BSV, namely Banana streak IM virus (BSIMV), Banana streak MY virus (BSMYV), Banana streak OL virus (BSOLV), Banana streak UA virus (BSUAV), Banana streak UL virus (BSULV), Banana streak UM virus (BSUMV), were detected by PCR and confirmed by RCA and sequencing. No new species were detected, but this was the first report of BSMYV in Uganda. Although RCA was demonstrated to be suitable for broad�]range detection of BSV, it proved time�]consuming and laborious for identification in field samples. Due to the disadvantages associated with RCA, attempts were made to develop a reliable PCR�]based assay for the specific detection of episomal BSOLV, Banana streak GF virus (BSGFV), BSMYV and BSIMV. For BSOLV and BSGFV, the integrated sequences exist in rearranged, repeated and partially inverted portions at their site of integration. Therefore, for these two viruses, primers sets were designed by mapping previously published sequences of their endogenous counterparts onto published sequences of the episomal genomes. For BSOLV, two primer sets were designed while, for BSGFV, a single primer set was designed. The episomalspecificity of these primer sets was assessed by testing 106 plant samples collected during surveys in Kenya and Uganda, and 33 leaf samples from a wide range of banana cultivars maintained in TC at the Maroochy Research Station of the Department of Employment, Economic Development and Innovation (DEEDI), Queensland. All of these samples had previously been tested for episomal BSV by RCA and for both BSOLV and BSGFV by PCR using published primer sets. The outcome from these analyses was that the newly designed primer sets for BSOLV and BSGFV were able to distinguish between episomal BSV and eBSV in most cultivars with some B�]genome component. In some samples, however, amplification was observed using the putative episomal�]specific primer sets where episomal BSV was not identified using RCA. This may reflect a difference in the sensitivity of PCR compared to RCA, or possibly the presence of an eBSV sequence of different conformation. Since the sequences of the respective eBSV for BSMYV and BSIMV in the M. balbisiana genome are not available, a series of random primer combinations were tested in an attempt to find potential episomal�]specific primer sets for BSMYV and BSIMV. Of an initial 20 primer combinations screened for BSMYV detection on a small number of control samples, 11 primers sets appeared to be episomal�]specific. However, subsequent testing of two of these primer combinations on a larger number of control samples resulted in some inconsistent results which will require further investigation. Testing of the 25 primer combinations for episomal�]specific detection of BSIMV on a number of control samples showed that none were able to discriminate between episomal and endogenous BSIMV. The final component of this research project was the development of an infectious clone of a BSV endemic in Australia, namely BSMYV. This was considered important to enable the generation of large amounts of diseased plant material needed for further research. A terminally redundant fragment (.1.3 �~ BSMYV genome) was cloned and transformed into Agrobacterium tumefaciens strain AGL1, and used to inoculate 12 healthy banana plants of the cultivars Cavendish (Williams) by three different methods. At 12 weeks post�]inoculation, (i) four of the five banana plants inoculated by corm injection showed characteristic BSV symptoms while the remaining plant was wilting/dying, (ii) three of the five banana plants inoculated by needle�]pricking of the stem showed BSV symptoms, one plant was symptomless while the remaining had died and (iii) both banana plants inoculated by leaf infiltration were symptomless. When banana leaf samples were tested for BSMYV by PCR and RCA, BSMYV was confirmed in all banana plants showing symptoms including those were wilting and/or dying. The results from this research have provided several avenues for further research. By completely sequencing all variants of eBSOLV and eBSGFV and fully sequencing the eBSIMV and eBSMYV regions, episomal BSV�]specific primer sets for all eBSVs could potentially be designed that could avoid all integrants of that particular BSV species. Furthermore, the development of an infectious BSV clone will enable large numbers of BSVinfected plants to be generated for the further testing of the sensitivity of RCA compared to other more established assays such as PCR. The development of infectious clones also opens the possibility for virus induced gene silencing studies in banana.

Bodyweight and other correlates of symptom detected breast cancers in a population offered screening

Objective: To determine factors associated with symptom detected breast cancers in a population offered screening. Methods We interviewed 1,459 Australian women aged 40–69, 946 with symptom detected and 513 with mammogram detected invasive breast cancers ≥1.1 cm in diameter, about their personal, mammogram and breast histories before diagnosis and reviewed medical records for tumour characteristics and mammogram dates, calculating ORs and 95% confidence intervals (CIs) for symptom- vs mammogram-detected cancers in logistic regression models. Results: Lack of regular mammograms (<2 mammograms in the 4.5 years before diagnosis) was the strongest correlate of symptom detected breast cancer (OR=3.04 for irregular or no mammograms). In women who had regular mammograms (≥2 mammograms in the 4.5 years before diagnosis), the independent correlates of symptom detected cancers were low BMI (OR <25kg/m2 vs ≥30kg/m2=2.18, 95% CI 1.23-3.84; p=0.008), increased breast density (available in 498 women) (OR highest quarter vs lowest =3.50, 95% CI 1.76-6.97; ptrend=0.004), high grade cancer and a larger cancer (each p<0.01). In women who did not have regular mammograms, the independent correlates were age <50 years, a first cancer and a ≥2cm cancer. Smoking appeared to modify the association of symptom detected cancer with low BMI (higher ORs for low BMI in current smokers) and estrogen receptor (ER) status (higher ORs for low BMI in ER− cancers). Conclusion: Women with low BMI may benefit from a tailored approach to breast cancer detection, particularly if they smoke.

Improved foreground detection via block-based classifier cascade with probabilistic decision integration

Background subtraction is a fundamental low-level processing task in numerous computer vision applications. The vast majority of algorithms process images on a pixel-by-pixel basis, where an independent decision is made for each pixel. A general limitation of such processing is that rich contextual information is not taken into account. We propose a block-based method capable of dealing with noise, illumination variations, and dynamic backgrounds, while still obtaining smooth contours of foreground objects. Specifically, image sequences are analyzed on an overlapping block-by-block basis. A low-dimensional texture descriptor obtained from each block is passed through an adaptive classifier cascade, where each stage handles a distinct problem. A probabilistic foreground mask generation approach then exploits block overlaps to integrate interim block-level decisions into final pixel-level foreground segmentation. Unlike many pixel-based methods, ad-hoc postprocessing of foreground masks is not required. Experiments on the difficult Wallflower and I2R datasets show that the proposed approach obtains on average better results (both qualitatively and quantitatively) than several prominent methods. We furthermore propose the use of tracking performance as an unbiased approach for assessing the practical usefulness of foreground segmentation methods, and show that the proposed approach leads to considerable improvements in tracking accuracy on the CAVIAR dataset.

Towards persistent indoor appearance-based localization, mapping and navigation using CAT-Graph

The challenge of persistent appearance-based navigation and mapping is to develop an autonomous robotic vision system that can simultaneously localize, map and navigate over the lifetime of the robot. However, the computation time and memory requirements of current appearance-based methods typically scale not only with the size of the environment but also with the operation time of the platform; also, repeated revisits to locations will develop multiple competing representations which reduce recall performance. In this paper we present a solution to the persistent localization, mapping and global path planning problem in the context of a delivery robot in an office environment over a one-week period. Using a graphical appearance-based SLAM algorithm, CAT-Graph, we demonstrate constant time and memory loop closure detection with minimal degradation during repeated revisits to locations, along with topological path planning that improves over time without using a global metric representation. We compare the localization performance of CAT-Graph to openFABMAP, an appearance-only SLAM algorithm, and the path planning performance to occupancy-grid based metric SLAM. We discuss the limitations of the algorithm with regard to environment change over time and illustrate how the topological graph representation can be coupled with local movement behaviors for persistent autonomous robot navigation.

On robust face recognition via sparse encoding : 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. Most of the relevant literature focuses on holistic descriptors in closed-set identification applications. The underlying assumption in 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 assumption is easily violated in the more challenging face verification scenario, where an algorithm is required to determine if two faces (where one or both have not been seen before) belong to the same person. In this paper, we first discuss why previous attempts with SR might not be applicable to verification problems. We then propose an alternative approach to face verification via SR. Specifically, we propose to use explicit SR encoding on local image patches rather than the entire face. The obtained sparse signals are pooled via averaging to form multiple region descriptors, which are then concatenated to form an overall face descriptor. Due to the deliberate loss spatial relations within each region (caused by averaging), the resulting descriptor is robust to misalignment & various image deformations. Within the proposed framework, we 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 proposed local SR approach obtains considerably better and more robust performance than several previous state-of-the-art holistic SR methods, in both verification and closed-set identification problems. The experiments also show that l1-minimisation based encoding has a considerably higher computational than the other techniques, but leads to higher recognition rates.

Damage assessment in reinforced concrete flexural members using modal strain energy based method

Damage assessment (damage detection, localization and quantification) in structures and appropriate retrofitting will enable the safe and efficient function of the structures. In this context, many Vibration Based Damage Identification Techniques (VBDIT) have emerged with potential for accurate damage assessment. VBDITs have achieved significant research interest in recent years, mainly due to their non-destructive nature and ability to assess inaccessible and invisible damage locations. Damage Index (DI) methods are also vibration based, but they are not based on the structural model. DI methods are fast and inexpensive compared to the model-based methods and have the ability to automate the damage detection process. DI method analyses the change in vibration response of the structure between two states so that the damage can be identified. Extensive research has been carried out to apply the DI method to assess damage in steel structures. Comparatively, there has been very little research interest in the use of DI methods to assess damage in Reinforced Concrete (RC) structures due to the complexity of simulating the predominant damage type, the flexural crack. Flexural cracks in RC beams distribute non- linearly and propagate along all directions. Secondary cracks extend more rapidly along the longitudinal and transverse directions of a RC structure than propagation of existing cracks in the depth direction due to stress distribution caused by the tensile reinforcement. Simplified damage simulation techniques (such as reductions in the modulus or section depth or use of rotational spring elements) that have been extensively used with research on steel structures, cannot be applied to simulate flexural cracks in RC elements. This highlights a big gap in knowledge and as a consequence VBDITs have not been successfully applied to damage assessment in RC structures. This research will address the above gap in knowledge and will develop and apply a modal strain energy based DI method to assess damage in RC flexural members. Firstly, this research evaluated different damage simulation techniques and recommended an appropriate technique to simulate the post cracking behaviour of RC structures. The ABAQUS finite element package was used throughout the study with properly validated material models. The damaged plasticity model was recommended as the method which can correctly simulate the post cracking behaviour of RC structures and was used in the rest of this study. Four different forms of Modal Strain Energy based Damage Indices (MSEDIs) were proposed to improve the damage assessment capability by minimising the numbers and intensities of false alarms. The developed MSEDIs were then used to automate the damage detection process by incorporating programmable algorithms. The developed algorithms have the ability to identify common issues associated with the vibration properties such as mode shifting and phase change. To minimise the effect of noise on the DI calculation process, this research proposed a sequential order of curve fitting technique. Finally, a statistical based damage assessment scheme was proposed to enhance the reliability of the damage assessment results. The proposed techniques were applied to locate damage in RC beams and slabs on girder bridge model to demonstrate their accuracy and efficiency. The outcomes of this research will make a significant contribution to the technical knowledge of VBDIT and will enhance the accuracy of damage assessment in RC structures. The application of the research findings to RC flexural members will enable their safe and efficient performance.

Image-based flow visualisation (IBFV) to enhance interpretation of complex flow patterns within a shallow tidal barrier estuary

We applied a texture-based flow visualisation technique to a numerical hydrodynamic model of the Pumicestone Passage in southeast Queensland, Australia. The quality of the visualisations using our flow visualisation tool, are compared with animations generated using more traditional drogue release plot and velocity contour and vector techniques. The texture-based method is found to be far more effective in visualising advective flow within the model domain. In some instances, it also makes it easier for the researcher to identify specific hydrodynamic features within the complex flow regimes of this shallow tidal barrier estuary as compared with the direct and geometric based methods.

Speaker diarization : "who spoke when"

Speaker diarization is the process of annotating an input audio with information that attributes temporal regions of the audio signal to their respective sources, which may include both speech and non-speech events. For speech regions, the diarization system also specifies the locations of speaker boundaries and assign relative speaker labels to each homogeneous segment of speech. In short, speaker diarization systems effectively answer the question of ‘who spoke when’. There are several important applications for speaker diarization technology, such as facilitating speaker indexing systems to allow users to directly access the relevant segments of interest within a given audio, and assisting with other downstream processes such as summarizing and parsing. When combined with automatic speech recognition (ASR) systems, the metadata extracted from a speaker diarization system can provide complementary information for ASR transcripts including the location of speaker turns and relative speaker segment labels, making the transcripts more readable. Speaker diarization output can also be used to localize the instances of specific speakers to pool data for model adaptation, which in turn boosts transcription accuracies. Speaker diarization therefore plays an important role as a preliminary step in automatic transcription of audio data. The aim of this work is to improve the usefulness and practicality of speaker diarization technology, through the reduction of diarization error rates. In particular, this research is focused on the segmentation and clustering stages within a diarization system. Although particular emphasis is placed on the broadcast news audio domain and systems developed throughout this work are also trained and tested on broadcast news data, the techniques proposed in this dissertation are also applicable to other domains including telephone conversations and meetings audio. Three main research themes were pursued: heuristic rules for speaker segmentation, modelling uncertainty in speaker model estimates, and modelling uncertainty in eigenvoice speaker modelling. The use of heuristic approaches for the speaker segmentation task was first investigated, with emphasis placed on minimizing missed boundary detections. A set of heuristic rules was proposed, to govern the detection and heuristic selection of candidate speaker segment boundaries. A second pass, using the same heuristic algorithm with a smaller window, was also proposed with the aim of improving detection of boundaries around short speaker segments. Compared to single threshold based methods, the proposed heuristic approach was shown to provide improved segmentation performance, leading to a reduction in the overall diarization error rate. Methods to model the uncertainty in speaker model estimates were developed, to address the difficulties associated with making segmentation and clustering decisions with limited data in the speaker segments. The Bayes factor, derived specifically for multivariate Gaussian speaker modelling, was introduced to account for the uncertainty of the speaker model estimates. The use of the Bayes factor also enabled the incorporation of prior information regarding the audio to aid segmentation and clustering decisions. The idea of modelling uncertainty in speaker model estimates was also extended to the eigenvoice speaker modelling framework for the speaker clustering task. Building on the application of Bayesian approaches to the speaker diarization problem, the proposed approach takes into account the uncertainty associated with the explicit estimation of the speaker factors. The proposed decision criteria, based on Bayesian theory, was shown to generally outperform their non- Bayesian counterparts.

Using Wikipedia to improve web service discovery

Building and maintaining software are not easy tasks. However, thanks to advances in web technologies, a new paradigm is emerging in software development. The Service Oriented Architecture (SOA) is a relatively new approach that helps bridge the gap between business and IT and also helps systems remain exible. However, there are still several challenges with SOA. As the number of available services grows, developers are faced with the problem of discovering the services they need. Public service repositories such as Programmable Web provide only limited search capabilities. Several mechanisms have been proposed to improve web service discovery by using semantics. However, most of these require manually tagging the services with concepts in an ontology. Adding semantic annotations is a non-trivial process that requires a certain skill-set from the annotator and also the availability of domain ontologies that include the concepts related to the topics of the service. These issues have prevented these mechanisms becoming widespread. This thesis focuses on two main problems. First, to avoid the overhead of manually adding semantics to web services, several automatic methods to include semantics in the discovery process are explored. Although experimentation with some of these strategies has been conducted in the past, the results reported in the literature are mixed. Second, Wikipedia is explored as a general-purpose ontology. The benefit of using it as an ontology is assessed by comparing these semantics-based methods to classic term-based information retrieval approaches. The contribution of this research is significant because, to the best of our knowledge, a comprehensive analysis of the impact of using Wikipedia as a source of semantics in web service discovery does not exist. The main output of this research is a web service discovery engine that implements these methods and a comprehensive analysis of the benefits and trade-offs of these semantics-based discovery approaches.

Damage diagnosis for complex steel truss bridges using multi-layer genetic algorithm

Considerate amount of research has proposed optimization-based approaches employing various vibration parameters for structural damage diagnosis. The damage detection by these methods is in fact a result of updating the analytical structural model in line with the current physical model. The feasibility of these approaches has been proven. But most of the verification has been done on simple structures, such as beams or plates. In the application on a complex structure, like steel truss bridges, a traditional optimization process will cost massive computational resources and lengthy convergence. This study presents a multi-layer genetic algorithm (ML-GA) to overcome the problem. Unlike the tedious convergence process in a conventional damage optimization process, in each layer, the proposed algorithm divides the GA’s population into groups with a less number of damage candidates; then, the converged population in each group evolves as an initial population of the next layer, where the groups merge to larger groups. In a damage detection process featuring ML-GA, as parallel computation can be implemented, the optimization performance and computational efficiency can be enhanced. In order to assess the proposed algorithm, the modal strain energy correlation (MSEC) has been considered as the objective function. Several damage scenarios of a complex steel truss bridge’s finite element model have been employed to evaluate the effectiveness and performance of ML-GA, against a conventional GA. In both single- and multiple damage scenarios, the analytical and experimental study shows that the MSEC index has achieved excellent damage indication and efficiency using the proposed ML-GA, whereas the conventional GA only converges at a local solution.