Modern slavery in global supply chains remains a critical concern, prompting governments in countries such as the UK, Australia, and Canada to introduce corporate transparency legislation, including Modern Slavery Acts. However, the growing volume of compliance reports has made manual analysis increasingly impractical. This challenge is compounded by the fact that many government agencies and NGOs responsible for assessing these statements operate in resource-constrained environments, limiting their ability to deploy large-scale language models. To address both issues, we present a novel AI framework for cross-jurisdictional compliance analysis. Our approach integrates four specialised teacher models, each trained using contrastive learning, prompt engineering, pseudo-labelling, and context-enhanced learning, which are distilled into a single lightweight, computationally efficient student model. This design enhances generalisability across legal frameworks while remaining affordable to deploy in low-resource settings. Experimental evaluations demonstrate that our method achieves higher accuracy and efficiency than existing approaches, offering a scalable, accessible solution for regulators and other stakeholders.

Modern Slavery Acts mandate that corporations disclose their efforts to combat modern slavery, aiming to enhance transparency and strengthen practices for its eradication. However, verifying these statements remains challenging due to their complex, diversified language and the sheer number of statements that must be reviewed. The development of NLP tools to assist in this task is also difficult due to a scarcity of annotated data. Furthermore, as modern slavery transparency legislation has been introduced in several countries, the generalizability of such tools across legal jurisdictions must be studied. To address these challenges, we work with domain experts to make two key contributions. First, we present AIMS.uk and AIMS.ca, newly annotated datasets from the UK and Canada to enable cross-jurisdictional evaluation. Second, we introduce AIMSCheck, an end-to-end framework for compliance validation. AIMSCheck decomposes the compliance assessment task into three levels, enhancing interpretability and practical applicability. Our experiments show that models trained on an Australian dataset generalize well across UK and Canadian jurisdictions, demonstrating the potential for broader application in compliance monitoring. We release the benchmark datasets and AIMSCheck to the public to advance AI-adoption in compliance assessment and drive further research in this field.

Despite over a decade of legislative efforts to address modern slavery in the supply chains of large corporations, the effectiveness of government oversight remains hampered by the challenge of scrutinizing thousands of statements annually. While Large Language Models (LLMs) can be considered a well established solution for the automatic analysis and summarization of documents, recognizing concrete modern slavery countermeasures taken by companies and differentiating those from vague claims remains a challenging task. To help evaluate and fine-tune LLMs for the assessment of corporate statements, we introduce a dataset composed of 5,731 modern slavery statements taken from the Australian Modern Slavery Register and annotated at the sentence level. This paper details the construction steps for the dataset that include the careful design of annotation specifications, the selection and preprocessing of statements, and the creation of high-quality annotation subsets for effective model evaluations. To demonstrate our dataset's utility, we propose a machine learning methodology for the detection of sentences relevant to mandatory reporting requirements set by the Australian Modern Slavery Act. We then follow this methodology to benchmark modern language models under zero-shot and supervised learning settings.

OBJECTIVE: The Australian Cancer Atlas (ACA) aims to provide small-area estimates of cancer incidence and survival in Australia to help identify and address geographical health disparities. We report on the 21-month user-centered design study to visualize the data, in particular, the visualization of the estimate uncertainty for multiple audiences. MATERIALS AND METHODS: The preliminary phases included a scoping study, literature review, and target audience focus groups. Several methods were used to reach the wide target audience. The design and development stage included digital prototyping in parallel with Bayesian model development. Feedback was sought from multiple workshops, audience focus groups, and regular meetings throughout with an expert external advisory group. RESULTS: The initial scoping identified 4 target audience groups: the general public, researchers, health practitioners, and policy makers. These target groups were consulted throughout the project to ensure the developed model and uncertainty visualizations were effective for communication. In this paper, we detail ACA features and design iterations, including the 3 complementary ways in which uncertainty is communicated: the wave plot, the v-plot, and color transparency. DISCUSSION: We reflect on the methods, design iterations, decision-making process, and document lessons learned for future atlases. CONCLUSION: The ACA has been hugely successful since launching in 2018. It has received over 62 000 individual users from over 100 countries and across all target audiences. It has been replicated in other countries and the second version of the ACA was launched in May 2024. This paper provides rich documentation for future projects.

Fibrosis, a pathological increase in extracellular matrix proteins, is a significant health issue that hinders the function of many organs in the body, in some cases fatally. In the heart, fibrosis impacts on electrical propagation in a complex and poorly predictable fashion, potentially serving as a substrate for dangerous arrhythmias. Individual risk depends on the spatial manifestation of fibrotic tissue, and learning the spatial arrangement on the fine scale in order to predict these impacts still relies upon invasive ex vivo procedures. As a result, the effects of spatial variability on the symptomatic impact of cardiac fibrosis remain poorly understood. In this work, we address the issue of availability of such imaging data via a computational methodology for generating new realisations of cardiac fibrosis microstructure. Using the Perlin noise technique from computer graphics, together with an automated calibration process that requires only a single training image, we demonstrate successful capture of collagen texturing in four types of fibrosis microstructure observed in histological sections. We then use this generator to quantitatively analyse the conductive properties of these different types of cardiac fibrosis, as well as produce three-dimensional realisations of histologically-observed patterning. Owing to the generator's flexibility and automated calibration process, we also anticipate that it might be useful in producing additional realisations of other physiological structures.

Inference on modern Bayesian Neural Networks (BNNs) often relies on a variational inference treatment, imposing violated assumptions of independence and the form of the posterior. Traditional MCMC approaches avoid these assumptions at the cost of increased computation due to its incompatibility to subsampling of the likelihood. New Piecewise Deterministic Markov Process (PDMP) samplers permit subsampling, though introduce a model-specific inhomogenous Poisson Process (IPPs) which is difficult to sample from. This work introduces a new generic and adaptive thinning scheme for sampling from these IPPs, and demonstrates how this approach can accelerate the application of PDMPs for inference in BNNs. Experimentation illustrates how inference with these methods is computationally feasible, can improve predictive accuracy, MCMC mixing performance, and provide informative uncertainty measurements when compared against other approximate inference schemes.

Nonnegative matrix factorization (NMF) is a powerful tool for parameter estimation applied in numerous robotics applications, such as path planning, motion trajectory prediction, and motion intention detection. In particular, NMF has been successfully used to extract simplified and organized movement primitives from myoelectric signal (MES) for robust control of multi-degree of freedom humanoid robots. However, MES is typically contaminated by complex noise sources. The system performance often degrades due to the simplified Gaussian assumption of the noise distribution in existing NMF methods. Furthermore, most existing NMF models are unable to automatically determine the rank of the latent matrices. To address these issues, this article presents a hybrid variational Bayesian Gaussian mixture and NMF (GMNMF) model with a finite Gaussian mixture model adopted to fit the mixed noise density function of MES. In addition, the automatic relevant determination criterion is applied to automatically infer the number of movement primitives. The coordinate descent update rules for the proposed model are formulated by mean-field variational Bayesian inference. We assess the model performance on five synthetic noise distribution functions and an experimental MES dataset to perform six wrist movements. The results demonstrate that GMNMF yields low error and high robustness in extracting the movement primitives over four competitive methods for robust cybernetic control.

Extracting low-rank and/or sparse structures using matrix factorization techniques has been extensively studied in the machine learning community. Kernelized matrix factorization (KMF) is a powerful tool to incorporate side information into the low-rank approximation model, which has been applied to solve the problems of data mining, recommender systems, image restoration, and machine vision. However, most existing KMF models rely on specifying the rows and columns of the data matrix through a Gaussian process prior and have to tune manually the rank. There are also computational issues of existing models based on regularization or the Markov chain Monte Carlo. In this article, we develop a hierarchical kernelized sparse Bayesian matrix factorization (KSBMF) model to integrate side information. The KSBMF automatically infers the parameters and latent variables including the reduced rank using the variational Bayesian inference. In addition, the model simultaneously achieves low-rankness through sparse Bayesian learning and columnwise sparsity through an enforced constraint on latent factor matrices. We further connect the KSBMF with the nonlocal image processing framework to develop two algorithms for image denoising and inpainting. Experimental results demonstrate that KSBMF outperforms the state-of-the-art approaches for these image-restoration tasks under various levels of corruption.

The Banana Bunchy Top Virus (BBTV) is one of the most economically important vector-borne banana diseases throughout the Asia-Pacific Basin and presents a significant challenge to the agricultural sector. Current models of BBTV are largely deterministic, limited by an incomplete understanding of interactions in complex natural systems, and the appropriate identification of parameters. A stochastic network-based Susceptible-Infected-Susceptible model has been created which simulates the spread of BBTV across the subsections of a banana plantation, parameterising nodal recovery, neighbouring and distant infectivity across summer and winter. Findings from posterior results achieved through Markov Chain Monte Carlo approach to approximate Bayesian computation suggest seasonality in all parameters, which are influenced by correlated changes in inspection accuracy, temperatures and aphid activity. This paper demonstrates how the model may be used for monitoring and forecasting of various disease management strategies to support policy-level decision making.

Singular value thresholding (SVT)- or nuclear norm minimization (NNM)-based nonlocal image denoising methods often rely on the precise estimation of the noise variance. However, most existing methods either assume that the noise variance is known or require an extra step to estimate it. Under the iterative regularization framework, the error in the noise variance estimate propagates and accumulates with each iteration, ultimately degrading the overall denoising performance. In addition, the essence of these methods is still least squares estimation, which can cause a very high mean-squared error (MSE) and is inadequate for handling missing data or outliers. In order to address these deficiencies, we present a hybrid denoising model based on variational Bayesian inference and Stein's unbiased risk estimator (SURE), which consists of two complementary steps. In the first step, the variational Bayesian SVT performs a low-rank approximation of the nonlocal image patch matrix to simultaneously remove the noise and estimate the noise variance. In the second step, we modify the conventional SURE full-rank SVT and its divergence formulas for rank-reduced eigen-triplets to remove the residual artifacts. The proposed hybrid BSSVT method achieves better performance in recovering the true image compared with state-of-the-art methods.

Fuzzy entropy (FuzzyEn), which employs the fuzzy probability to characterize the similarity between vectors, is a robust nonlinear statistic to quantify the complexity or regularity of nonlinear time series. The aim of this study is to investigate the statistical properties of FuzzyEn and improve the subspace denoising technique using FuzzyEn. We first show the asymptotic normality of FuzzyEn and derive its variance for finite sample behavior. We then analyze the two pending and fundamental issues in subspace denoising, i.e., depending on the so-called “noise floor” and the unaltered noise existing in signal subspace, from the point of view of fuzzy logic. A FuzzyEn-assisted subspace iterative soft threshold (FESIST) denoising method, which can effectively overcome the deficiency in the existing subspace filtering (SSF) techniques, is presented. The effectiveness of the method is first demonstrated on two synthetic chaotic series and then tested on real biological signals. The results demonstrate the superiority of the proposed method over existing SSF techniques, as well as the empirical mode decomposition and wavelet decomposition approaches.

Due to advancements in computational ability, enhanced technology and a reduction in the price of genotyping, more data are being generated for understanding genetic associations with diseases and disorders. However, with the availability of large data sets comes the inherent challenges of new methods of statistical analysis and modeling. Considering a complex phenotype may be the effect of a combination of multiple loci, various statistical methods have been developed for identifying genetic epistasis effects. Among these methods, logic regression (LR) is an intriguing approach incorporating tree-like structures. Various methods have built on the original LR to improve different aspects of the model. In this study, we review four variations of LR, namely Logic Feature Selection, Monte Carlo Logic Regression, Genetic Programming for Association Studies, and Modified Logic Regression-Gene Expression Programming, and investigate the performance of each method using simulated and real genotype data. We contrast these with another tree-like approach, namely Random Forests, and a Bayesian logistic regression with stochastic search variable selection.

MOTIVATION: Gene expression data offer a large number of potentially useful predictors for the classification of tissue samples into classes, such as diseased and non-diseased. The predictive error rate of classifiers can be estimated using methods such as cross-validation. We have investigated issues of interpretation and potential bias in the reporting of error rate estimates. The issues considered here are optimization and selection biases, sampling effects, measures of misclassification rate, baseline error rates, two-level external cross-validation and a novel proposal for detection of bias using the permutation mean. RESULTS: Reporting an optimal estimated error rate incurs an optimization bias. Downward bias of 3-5% was found in an existing study of classification based on gene expression data and may be endemic in similar studies. Using a simulated non-informative dataset and two example datasets from existing studies, we show how bias can be detected through the use of label permutations and avoided using two-level external cross-validation. Some studies avoid optimization bias by using single-level cross-validation and a test set, but error rates can be more accurately estimated via two-level cross-validation. In addition to estimating the simple overall error rate, we recommend reporting class error rates plus where possible the conditional risk incorporating prior class probabilities and a misclassification cost matrix. We also describe baseline error rates derived from three trivial classifiers which ignore the predictors. AVAILABILITY: R code which implements two-level external cross-validation with the PAMR package, experiment code, dataset details and additional figures are freely available for non-commercial use from http://www.maths.qut.edu.au/profiles/wood/permr.jsp