Unusual Event Detection in Crowded Scenes Using Bag of LBPs in spatio-temporal patches

Modelling events in densely crowded environments remains challenging, due to the diversity of events and the noise in the scene. We propose a novel approach for anomalous event detection in crowded scenes using dynamic textures described by the Local Binary Patterns from Three Orthogonal Planes (LBP-TOP) descriptor. The scene is divided into spatio-temporal patches where LBP-TOP based dynamic textures are extracted. We apply hierarchical Bayesian models to detect the patches containing unusual events. Our method is an unsupervised approach, and it does not rely on object tracking or background subtraction. We show that our approach outperforms existing state of the art algorithms for anomalous event detection in UCSD dataset.

User-representative feature selection for keystroke dynamics

Continuous user authentication with keystroke dynamics uses characters sequences as features. Since users can type characters in any order, it is imperative to find character sequences (n-graphs) that are representative of user typing behavior. The contemporary feature selection approaches do not guarantee selecting frequently-typed features which may cause less accurate statistical user-representation. Furthermore, the selected features do not inherently reflect user typing behavior. We propose four statistical based feature selection techniques that mitigate limitations of existing approaches. The first technique selects the most frequently occurring features. The other three consider different user typing behaviors by selecting: n-graphs that are typed quickly; n-graphs that are typed with consistent time; and n-graphs that have large time variance among users. We use Gunetti’s keystroke dataset and k-means clustering algorithm for our experiments. The results show that among the proposed techniques, the most-frequent feature selection technique can effectively find user representative features. We further substantiate our results by comparing the most-frequent feature selection technique with three existing approaches (popular Italian words, common n-graphs, and least frequent ngraphs). We find that it performs better than the existing approaches after selecting a certain number of most-frequent n-graphs.

Barriers to information transfer for multi-trauma patients upon discharge from the Emergency Department in a tertiary level hospital

Purpose: Communication is integral to effective trauma care provision. This presentation will report on barriers to meaningful information transfer for multi-trauma patients upon discharge from the Emergency Department (ED) to the care areas of Intensive Care Unit, High Dependency Unit, and Perioperative Services. This is an ongoing study at one tertiary level hospital in Queensland. Method: This is a multi-phase, mixed method study. In Phase 1 data were collected about information transfer. This Phase was initially informed by a comprehensive literature review, then via focus groups, chart audit, staff survey and review of national and international trauma forms. Results: The barriers identified related to nursing handover, documented information, time inefficiency, patient complexity and stability and time of transfer. Specifically this included differences in staff expectations and variation in the nursing handover processes, no agreed minimum dataset of information handed over, missing, illegible or difficult to find information in documentation (both medical and nursing), low compliance with some forms used for documentation. Handover of these patients is complex with information coming from many sources, dealing with issues is more difficult for these patients when transferred out of hours. Conclusions and further directions: This study investigated the current communication processes and standards of information transfer to identify barriers and issues. The barriers identified were the structure used for documentation, processes used (e.g. handover), patient acuity and time. This information is informing the development, implementation and evaluation of strategies to ameliorate the issues identified.

Using Bayesian methods for the estimation of uncertainty in complex statistical models

The research objectives of this thesis were to contribute to Bayesian statistical methodology by contributing to risk assessment statistical methodology, and to spatial and spatio-temporal methodology, by modelling error structures using complex hierarchical models. Specifically, I hoped to consider two applied areas, and use these applications as a springboard for developing new statistical methods as well as undertaking analyses which might give answers to particular applied questions. Thus, this thesis considers a series of models, firstly in the context of risk assessments for recycled water, and secondly in the context of water usage by crops. The research objective was to model error structures using hierarchical models in two problems, namely risk assessment analyses for wastewater, and secondly, in a four dimensional dataset, assessing differences between cropping systems over time and over three spatial dimensions. The aim was to use the simplicity and insight afforded by Bayesian networks to develop appropriate models for risk scenarios, and again to use Bayesian hierarchical models to explore the necessarily complex modelling of four dimensional agricultural data. The specific objectives of the research were to develop a method for the calculation of credible intervals for the point estimates of Bayesian networks; to develop a model structure to incorporate all the experimental uncertainty associated with various constants thereby allowing the calculation of more credible credible intervals for a risk assessment; to model a single day’s data from the agricultural dataset which satisfactorily captured the complexities of the data; to build a model for several days’ data, in order to consider how the full data might be modelled; and finally to build a model for the full four dimensional dataset and to consider the timevarying nature of the contrast of interest, having satisfactorily accounted for possible spatial and temporal autocorrelations. This work forms five papers, two of which have been published, with two submitted, and the final paper still in draft. The first two objectives were met by recasting the risk assessments as directed, acyclic graphs (DAGs). In the first case, we elicited uncertainty for the conditional probabilities needed by the Bayesian net, incorporated these into a corresponding DAG, and used Markov chain Monte Carlo (MCMC) to find credible intervals, for all the scenarios and outcomes of interest. In the second case, we incorporated the experimental data underlying the risk assessment constants into the DAG, and also treated some of that data as needing to be modelled as an ‘errors-invariables’ problem [Fuller, 1987]. This illustrated a simple method for the incorporation of experimental error into risk assessments. In considering one day of the three-dimensional agricultural data, it became clear that geostatistical models or conditional autoregressive (CAR) models over the three dimensions were not the best way to approach the data. Instead CAR models are used with neighbours only in the same depth layer. This gave flexibility to the model, allowing both the spatially structured and non-structured variances to differ at all depths. We call this model the CAR layered model. Given the experimental design, the fixed part of the model could have been modelled as a set of means by treatment and by depth, but doing so allows little insight into how the treatment effects vary with depth. Hence, a number of essentially non-parametric approaches were taken to see the effects of depth on treatment, with the model of choice incorporating an errors-in-variables approach for depth in addition to a non-parametric smooth. The statistical contribution here was the introduction of the CAR layered model, the applied contribution the analysis of moisture over depth and estimation of the contrast of interest together with its credible intervals. These models were fitted using WinBUGS [Lunn et al., 2000]. The work in the fifth paper deals with the fact that with large datasets, the use of WinBUGS becomes more problematic because of its highly correlated term by term updating. In this work, we introduce a Gibbs sampler with block updating for the CAR layered model. The Gibbs sampler was implemented by Chris Strickland using pyMCMC [Strickland, 2010]. This framework is then used to consider five days data, and we show that moisture in the soil for all the various treatments reaches levels particular to each treatment at a depth of 200 cm and thereafter stays constant, albeit with increasing variances with depth. In an analysis across three spatial dimensions and across time, there are many interactions of time and the spatial dimensions to be considered. Hence, we chose to use a daily model and to repeat the analysis at all time points, effectively creating an interaction model of time by the daily model. Such an approach allows great flexibility. However, this approach does not allow insight into the way in which the parameter of interest varies over time. Hence, a two-stage approach was also used, with estimates from the first-stage being analysed as a set of time series. We see this spatio-temporal interaction model as being a useful approach to data measured across three spatial dimensions and time, since it does not assume additivity of the random spatial or temporal effects.

Towards condition-invariant sequence-based route recognition

In this paper we present a novel algorithm for localization during navigation that performs matching over local image sequences. Instead of calculating the single location most likely to correspond to a current visual scene, the approach finds candidate matching locations within every section (subroute) of all learned routes. Through this approach, we reduce the demands upon the image processing front-end, requiring it to only be able to correctly pick the best matching image from within a short local image sequence, rather than globally. We applied this algorithm to a challenging downhill mountainbiking visual dataset where there was significant perceptual or environment change between repeated traverses of the environment, and compared performance to applying the feature-based algorithm FAB-MAP. The results demonstrate the potential for localization using visual sequences, even when there are no visual features that can be reliably detected.

A suspicious behaviour detection using a context space model for smart surveillance systems

Video surveillance systems using Closed Circuit Television (CCTV) cameras, is one of the fastest growing areas in the field of security technologies. However, the existing video surveillance systems are still not at a stage where they can be used for crime prevention. The systems rely heavily on human observers and are therefore limited by factors such as fatigue and monitoring capabilities over long periods of time. This work attempts to address these problems by proposing an automatic suspicious behaviour detection which utilises contextual information. The utilisation of contextual information is done via three main components: a context space model, a data stream clustering algorithm, and an inference algorithm. The utilisation of contextual information is still limited in the domain of suspicious behaviour detection. Furthermore, it is nearly impossible to correctly understand human behaviour without considering the context where it is observed. This work presents experiments using video feeds taken from CAVIAR dataset and a camera mounted on one of the buildings Z-Block) at the Queensland University of Technology, Australia. From these experiments, it is shown that by exploiting contextual information, the proposed system is able to make more accurate detections, especially of those behaviours which are only suspicious in some contexts while being normal in the others. Moreover, this information gives critical feedback to the system designers to refine the system.

Characterisation of the TaNF-Y family of transcription factors in wheat

Light plays a unique role for plants as it is both a source of energy for growth and a signal for development. Light captured by the pigments in the light harvesting complexes is used to drive the synthesis of the chemical energy required for carbon assimilation. The light perceived by photoreceptors activates effectors, such as transcription factors (TFs), which modulate the expression of light-responsive genes. Recently, it has been speculated that increasing the photosynthetic rate could further improve the yield potential of three carbon (C3) crops such as wheat. However, little is currently known about the transcriptional regulation of photosynthesis genes, particularly in crop species. Nuclear factor Y (NF-Y) TF is a functionally diverse regulator of growth and development in the model plant species, with demonstrated roles in embryo development, stress response, flowering time and chloroplast biogenesis. Furthermore, a light-responsive NF-Y binding site (CCAAT-box) is present in the promoter of a spinach photosynthesis gene. As photosynthesis genes are co-regulated by light and co-regulated genes typically have similar regulatory elements in their promoters, it seems likely that other photosynthesis genes would also have light-responsive CCAAT-boxes. This provided the impetus to investigate the NF-Y TF in bread wheat. This thesis is focussed on wheat NF-Y members that have roles in light-mediated gene regulation with an emphasis on their involvement in the regulation of photosynthesis genes. NF-Y is a heterotrimeric complex, comprised of the three subunits NF-YA, NF-YB and NF-YC. Unlike the mammalian and yeast counterparts, each of the three subunits is encoded by multiple genes in Arabidopsis. The initial step taken in this study was the identification of the wheat NF-Y family (Chapter 3). A search of the current wheat nucleotide sequence databases identified 37 NF-Y genes (10 NF-YA, 11 NF-YB, 14 NF-YC & 2 Dr1). Phylogenetic analysis revealed that each of the three wheat NF-Y (TaNF-Y) subunit families could be divided into 4-5 clades based on their conserved core regions. Outside of the core regions, eleven motifs were identified to be conserved between Arabidopsis, rice and wheat NF-Y subunit members. The expression profiles of TaNF-Y genes were constructed using quantitative real-time polymerase chain reaction (RT-PCR). Some TaNF-Y subunit members had little variation in their transcript levels among the organs, while others displayed organ-predominant expression profiles, including those expressed mainly in the photosynthetic organs. To investigate their potential role in light-mediated gene regulation, the light responsiveness of the TaNF-Y genes were examined (Chapters 4 and 5). Two TaNF-YB and five TaNF-YC members were markedly upregulated by light in both the wheat leaves and seedling shoots. To identify the potential target genes of the light-upregulated NF-Y subunit members, a gene expression correlation analysis was conducted using publically available Affymetrix Wheat Genome Array datasets. This analysis revealed that the transcript expression levels of TaNF-YB3 and TaNF-YC11 were significantly correlated with those of photosynthesis genes. These correlated express profiles were also observed in the quantitative RT-PCR dataset from wheat plants grown under light and dark conditions. Sequence analysis of the promoters of these wheat photosynthesis genes revealed that they were enriched with potential NF-Y binding sites (CCAAT-box). The potential role of TaNF-YB3 in the regulation of photosynthetic genes was further investigated using a transgenic approach (Chapter 5). Transgenic wheat lines constitutively expressing TaNF-YB3 were found to have significantly increased expression levels of photosynthesis genes, including those encoding light harvesting chlorophyll a/b-binding proteins, photosystem I reaction centre subunits, a chloroplast ATP synthase subunit and glutamyl-tRNA reductase (GluTR). GluTR is a rate-limiting enzyme in the chlorophyll biosynthesis pathway. In association with the increased expression of the photosynthesis genes, the transgenic lines had a higher leaf chlorophyll content, increased photosynthetic rate and had a more rapid early growth rate compared to the wild-type wheat. In addition to its role in the regulation of photosynthesis genes, TaNF-YB3 overexpression lines flower on average 2-days earlier than the wild-type (Chapter 6). Quantitative RT-PCR analysis showed that there was a 13-fold increase in the expression level of the floral integrator, TaFT. The transcript levels of other downstream genes (TaFT2 and TaVRN1) were also increased in the transgenic lines. Furthermore, the transcript levels of TaNF-YB3 were significantly correlated with those of constans (CO), constans-like (COL) and timing of chlorophyll a/b-binding (CAB) expression 1 [TOC1; (CCT)] domain-containing proteins known to be involved in the regulation of flowering time. To summarise the key findings of this study, 37 NF-Y genes were identified in the crop species wheat. An in depth analysis of TaNF-Y gene expression profiles revealed that the potential role of some light-upregulated members was in the regulation of photosynthetic genes. The involvement of TaNF-YB3 in the regulation of photosynthesis genes was supported by data obtained from transgenic wheat lines with increased constitutive expression of TaNF-YB3. The overexpression of TaNF-YB3 in the transgenic lines revealed this NF-YB member is also involved in the fine-tuning of flowering time. These data suggest that the NF-Y TF plays an important role in light-mediated gene regulation in wheat.

Evidence for CRHR1 in multiple sclerosis using supervised machine learning and meta-analysis in 12 566 individuals

The primary genetic risk factor in multiple sclerosis (MS) is the HLA-DRB1*1501 allele; however, much of the remaining genetic contribution to MS has yet to be elucidated. Several lines of evidence support a role for neuroendocrine system involvement in autoimmunity which may, in part, be genetically determined. Here, we comprehensively investigated variation within eight candidate hypothalamic-pituitary-adrenal (HPA) axis genes and susceptibility to MS. A total of 326 SNPs were investigated in a discovery dataset of 1343 MS cases and 1379 healthy controls of European ancestry using a multi-analytical strategy. Random Forests, a supervised machine-learning algorithm, identified eight intronic SNPs within the corticotrophin-releasing hormone receptor 1 or CRHR1 locus on 17q21.31 as important predictors of MS. On the basis of univariate analyses, six CRHR1 variants were associated with decreased risk for disease following a conservative correction for multiple tests. Independent replication was observed for CRHR1 in a large meta-analysis comprising 2624 MS cases and 7220 healthy controls of European ancestry. Results from a combined meta-analysis of all 3967 MS cases and 8599 controls provide strong evidence for the involvement of CRHR1 in MS. The strongest association was observed for rs242936 (OR = 0.82, 95% CI = 0.74-0.90, P = 9.7 × 10-5). Replicated CRHR1 variants appear to exist on a single associated haplotype. Further investigation of mechanisms involved in HPA axis regulation and response to stress in MS pathogenesis is warranted. © The Author 2010. Published by Oxford University Press. All rights reserved.

Cognitive shifts related to interactive information retrieval

Purpose – Interactive information retrieval (IR) involves many human cognitive shifts at different information behaviour levels. Cognitive science defines a cognitive shift or shift in cognitive focus as triggered by the brain's response and change due to some external force. This paper aims to provide an explication of the concept of “cognitive shift” and then report results from a study replicating Spink's study of cognitive shifts during interactive IR. This work aims to generate promising insights into aspects of cognitive shifts during interactive IR and a new IR evaluation measure – information problem shift. Design/methodology/approach – The study participants (n=9) conducted an online search on an in-depth personal medical information problem. Data analysed included the pre- and post-search questionnaires completed by each study participant. Implications for web services and further research are discussed. Findings – Key findings replicated the results in Spink's study, including: all study participants reported some level of cognitive shift in their information problem, information seeking and personal knowledge due to their search interaction; and different study participants reported different levels of cognitive shift. Some study participants reported major cognitive shifts in various user-based variables such as information problem or information-seeking stage. Unlike Spink's study, no participant experienced a negative shift in their information problem stage or level of information problem understanding. Originality/value – This study builds on the previous study by Spink using a different dataset. The paper provides valuable insights for further research into cognitive shifts during interactive IR.

A people-to-people recommendation system using Tensor Space Models

Existing recommendation systems often recommend products to users by capturing the item-to-item and user-to-user similarity measures. These types of recommendation systems become inefficient in people-to-people networks for people to people recommendation that require two way relationship. Also, existing recommendation methods use traditional two dimensional models to find inter relationships between alike users and items. It is not efficient enough to model the people-to-people network with two-dimensional models as the latent correlations between the people and their attributes are not utilized. In this paper, we propose a novel tensor decomposition-based recommendation method for recommending people-to-people based on users profiles and their interactions. The people-to-people network data is multi-dimensional data which when modeled using vector based methods tend to result in information loss as they capture either the interactions or the attributes of the users but not both the information. This paper utilizes tensor models that have the ability to correlate and find latent relationships between similar users based on both information, user interactions and user attributes, in order to generate recommendations. Empirical analysis is conducted on a real-life online dating dataset. As demonstrated in results, the use of tensor modeling and decomposition has enabled the identification of latent correlations between people based on their attributes and interactions in the network and quality recommendations have been derived using the 'alike' users concept.

A recommendation method for online dating networks based on social relations and demographic information

A new relationship type of social networks - online dating - are gaining popularity. With a large member base, users of a dating network are overloaded with choices about their ideal partners. Recommendation methods can be utilized to overcome this problem. However, traditional recommendation methods do not work effectively for online dating networks where the dataset is sparse and large, and a two-way matching is required. This paper applies social networking concepts to solve the problem of developing a recommendation method for online dating networks. We propose a method by using clustering, SimRank and adapted SimRank algorithms to recommend matching candidates. Empirical results show that the proposed method can achieve nearly double the performance of the traditional collaborative filtering and common neighbor methods of recommendation.

Naming and claiming workplace sexual harassment in Australia

The persistence of sexual harassment in the workplace and the fact such behaviour remains significantly unreported suggest that legal definitions of sexual harassment may not be well understood. In this paper we explore the naming and claiming of sexual harassment in Australian workplaces, drawing on a unique dataset from a national sexual harassment prevalence survey. We compare a group of individuals who stated they had been sexually harassed according to a legal definition with a group who denied having experienced sexual harassment according to this definition but who went on to report sexually harassing behaviours. The study offers important insights into how workplace sexual harassment comes to be defined and understood in the Australian community, as well as some possible explanations for persistently low rates of formal complaints.

Feature-based visual odometry and featureless place recognition for SLAM in 2.5D environments

In this paper we present a novel algorithm for localization during navigation that performs matching over local image sequences. Instead of calculating the single location most likely to correspond to a current visual scene, the approach finds candidate matching locations within every section (subroute) of all learned routes. Through this approach, we reduce the demands upon the image processing front-end, requiring it to only be able to correctly pick the best matching image from within a short local image sequence, rather than globally. We applied this algorithm to a challenging downhill mountain biking visual dataset where there was significant perceptual or environment change between repeated traverses of the environment, and compared performance to applying the feature-based algorithm FAB-MAP. The results demonstrate the potential for localization using visual sequences, even when there are no visual features that can be reliably detected.

Outdoor simultaneous localisation and mapping using RatSLAM

In this paper an existing method for indoor Simultaneous Localisation and Mapping (SLAM) is extended to operate in large outdoor environments using an omnidirectional camera as its principal external sensor. The method, RatSLAM, is based upon computational models of the area in the rat brain that maintains the rodent’s idea of its position in the world. The system uses the visual appearance of different locations to build hybrid spatial-topological maps of places it has experienced that facilitate relocalisation and path planning. A large dataset was acquired from a dynamic campus environment and used to verify the system’s ability to construct representations of the world and simultaneously use these representations to maintain localisation.

An exploration of feature detector performance in the thermal-infrared modality

Thermal-infrared images have superior statistical properties compared with visible-spectrum images in many low-light or no-light scenarios. However, a detailed understanding of feature detector performance in the thermal modality lags behind that of the visible modality. To address this, the first comprehensive study on feature detector performance on thermal-infrared images is conducted. A dataset is presented which explores a total of ten different environments with a range of statistical properties. An investigation is conducted into the effects of several digital and physical image transformations on detector repeatability in these environments. The effect of non-uniformity noise, unique to the thermal modality, is analyzed. The accumulation of sensor non-uniformities beyond the minimum possible level was found to have only a small negative effect. A limiting of feature counts was found to improve the repeatability performance of several detectors. Most other image transformations had predictable effects on feature stability. The best-performing detector varied considerably depending on the nature of the scene and the test.