Regression is a fundamental prediction task common in data-centric engineering applications that involves learning mappings between continuous variables. In many engineering applications (e.g., structural health monitoring), feature-label pairs used to learn such mappings are of limited availability, which hinders the effectiveness of traditional supervised machine learning approaches. This paper proposes a methodology for overcoming the issue of data scarcity by combining active learning (AL) for regression with hierarchical Bayesian modeling. AL is an approach for preferentially acquiring feature-label pairs in a resource-efficient manner. In particular, the current work adopts a risk-informed approach that leverages contextual information associated with regression-based engineering decision-making tasks (e.g., inspection and maintenance). Hierarchical Bayesian modeling allow multiple related regression tasks to be learned over a population, capturing local and global effects. The information sharing facilitated by this modeling approach means that information acquired for one engineering system can improve predictive performance across the population. The proposed methodology is demonstrated using an experimental case study. Specifically, multiple regressions are performed over a population of machining tools, where the quantity of interest is the surface roughness of the workpieces. An inspection and maintenance decision process is defined using these regression tasks, which is in turn used to construct the active-learning algorithm. The novel methodology proposed is benchmarked against an uninformed approach to label acquisition and independent modeling of the regression tasks. It is shown that the proposed approach has superior performance in terms of expected cost—maintaining predictive performance while reducing the number of inspections required.

In practice, nondestructive testing (NDT) procedures tend to consider experiments (and their respective models) as distinct, conducted in isolation, and associated with independent data. In contrast, this work looks to capture the interdependencies between acoustic emission (AE) experiments (as meta-models) and then use the resulting functions to predict the model hyperparameters for previously unobserved systems. We utilize a Bayesian multilevel approach (similar to deep Gaussian Processes) where a higher-level meta-model captures the inter-task relationships. Our key contribution is how knowledge of the experimental campaign can be encoded between tasks as well as within tasks. We present an example of AE time-of-arrival mapping for source localization, to illustrate how multilevel models naturally lend themselves to representing aggregate systems in engineering. We constrain the meta-model based on domain knowledge, then use the inter-task functions for transfer learning, predicting hyperparameters for models of previously unobserved experiments (for a specific design).

Background: Intravenous Immunoglobulin (IVIg) use for Central Nervous System (CNS) conditions has increased over the last decade. In many CNS disorders, robust evidence for IVIg efficacy is still lacking. Building on the success of the British Columbia (BC) Neuromuscular IVIg utilization initiative, Guidelines for IVIg use in CNS conditions were developed. A provincial screening program was launched in 2023. Methods: For CNS IVIg, requests, diagnosis, dosing, consultation letters and treatment questionnaires were reviewed. Patient management was compared to provincial guidelines. A letter was sent to the ordering physician with the results of the review and treatment recommendations when management differed significantly from guidelines. Review of the first year’s cases was conducted. Results: Over the first 11 months of the program, 79 IVIg renewal requests were reviewed. The most common diagnoses were antibody mediated autoimmune encephalitis, severe drug resistant non-surgical epilepsy and Susac’s syndrome. Recommendations included dose reduction, discontinuation of IVIg, or initiation of alternative therapies for many of the requests. Conclusions: IVIg may be effective in the management of some CNS inflammatory conditions. A physician-led utilization program in BC with targeted education to ordering physicians promotes best practice. Review of year one data will inform a quality improvement cycle to optimize the guidelines.

Australian Aboriginal and Torres Strait Islander peoples are disproportionately affected by diet-related disease such as type 2 diabetes, the rate of which is 20 fold higher than that of non-Indigenous young Australians(1). Before colonisation, Gomeroi and other First Nations people harvested, threshed and ground native grass seeds with water into a paste before cooking(2). The introduction of white refined flour has meant that time-consuming grass seed processing has mainly ceased, and native grains are no longer eaten habitually. The aim of this study was to determine the effect of 10% incorporation of two native grain flours on postprandial blood glucose response and Glycemic Index (GI). Five male and five female subjects, with a mean age of 30 ± 0.9 and BMI of 21.6 ± 0.4 and normoglycemic, participated in GI testing of three flour + water pancake compositions matched for available carbohydrate: 100% wheat (Wheat) and 90% wheat:10% native grains (Native_a and Native_b). Effect on satiety was determined using subjective ratings of hunger/fullness over the time course of the GI testing. In comparison to the plain flour pancake, replacing 10% plain wheat flour with Native_b flour significantly reduced the GI by 28.8% from 73 ± 5 to 48 ± 5, having a profound effect on postprandial blood glucose levels in 9 of 10 subjects (p<0.05, paired t-test). The GI of 10% Native_a flour pancake was not different from 100% wheat flour pancake (75 ± 5). Satiety tended to be greater when native grains were incorporated but this study was not powered to detect effect on satiety. In conclusion, replacing only 10% of plain wheat flour with Native_b flour was sufficient to significantly reduce the blood glycemic response to the pancake. This replacement could be easily implemented for prevention and treatment of type 2 diabetes. For Aboriginal people with access to grain Country, the nutritional health benefits associated with eating native grains, as well as the cultural benefits of caring for Country, will have a direct transformational impact on local communities. Our vision is to revitalise Gomeroi grains and to guide a sustainable Indigenous-led industry to heal Country and people through co-designed research.

Despite the growing availability of sensing and data in general, we remain unable to fully characterize many in-service engineering systems and structures from a purely data-driven approach. The vast data and resources available to capture human activity are unmatched in our engineered world, and, even in cases where data could be referred to as “big,” they will rarely hold information across operational windows or life spans. This paper pursues the combination of machine learning technology and physics-based reasoning to enhance our ability to make predictive models with limited data. By explicitly linking the physics-based view of stochastic processes with a data-based regression approach, a derivation path for a spectrum of possible Gaussian process models is introduced and used to highlight how and where different levels of expert knowledge of a system is likely best exploited. Each of the models highlighted in the spectrum have been explored in different ways across communities; novel examples in a structural assessment context here demonstrate how these approaches can significantly reduce reliance on expensive data collection. The increased interpretability of the models shown is another important consideration and benefit in this context.

We describe the design, validation, and commissioning of a new correlator termed ‘MWAX’ for the Murchison Widefield Array (MWA) low-frequency radio telescope. MWAX replaces an earlier generation MWA correlator, extending correlation capabilities and providing greater flexibility, scalability, and maintainability. MWAX is designed to exploit current and future Phase II/III upgrades to MWA infrastructure, most notably the simultaneous correlation of all 256 of the MWA’s antenna tiles (and potentially more in future). MWAX is a fully software-programmable correlator based around an ethernet multicast architecture. At its core is a cluster of 24 high-performance GPU-enabled commercial-off-the-shelf compute servers that together process in real-time up to 24 coarse channels of 1.28 MHz bandwidth each. The system is highly flexible and scalable in terms of the number of antenna tiles and number of coarse channels to be correlated, and it offers a wide range of frequency/time resolution combinations to users. We conclude with a roadmap of future enhancements and extensions that we anticipate will be progressively rolled out over time.

Background: Intravenous immunoglobulin (IVIG) may benefit many inflammatory central nervous system (CNS) disorders based on multiple immunomodulatory effects. IVIg is being used in inflammatory CNS conditions however robust evidence and guidelines are lacking in many disorders. Over the last 5 years, the percentage of IVIg used for CNS indications within neurology almost doubled in British Columbia (BC), Canada. Clear local guidelines may guide rational use. Methods: Consensus guidelines for IVIG use for CNS indications were developed by a panel of subspecialty neurologists and the Provincial Blood Coordinating Office, informed by focused literature review. Guidelines were structured similarly to existing BC peripheral nervous system guidelines and Australian Consensus Guidelines. Utilization and efficacy will be monitored provincewide on an ongoing basis. Results: Categories of conditions for Conditionally Approved (N=11) and Exceptional Circumstance Use (N=5) were created based on level of evidence for efficacy. Dosing and monitoring recommendations were made and outcomes measures defined. Rationale for Not Indicated conditions (N=2) was included. Guidelines were distributed to BC neurologists for feedback. This system will be re-evaluated after 1 year. Conclusions: IVIG use in CNS inflammatory conditions has an emerging role. Guidelines for use and monitoring of outcomes will help improve resource utilization and provide further evidence regarding effectiveness.

Background: Intravenous immunoglobulin (IVIG) may benefit many inflammatory central nervous system (CNS) disorders based on multiple immunomodulatory effects. IVIG is being used in inflammatory CNS conditions however robust evidence and guidelines are lacking in many disorders. Over the last 5 years, the percentage of IVIG used for CNS indications within neurology almost doubled in British Columbia (BC), Canada. Clear local guidelines may guide rational use. Methods: Consensus guidelines for IVIG use for CNS indications were developed by a panel of subspecialty neurologists and the Provincial Blood Coordinating Office, informed by focused literature review. Guidelines were structured similarly to existing BC peripheral nervous system guidelines and Australian Consensus Guidelines. Utilization and efficacy will be monitored provincewide on an ongoing basis. Results: Categories of conditions for Possible Indication (N=11) and Exceptional Circumstance Use (N=4) were created based on level of evidence for efficacy. Dosing and monitoring recommendations were made and outcomes measures defined. Rationale for Not Indicated conditions (N=3) was included. Guidelines will be distributed to BC neurologists for feedback and re-evaluated after 1 year. Conclusions: IVIG use in CNS inflammatory conditions has an emerging role. Guidelines for use and monitoring of outcomes will help improve resource utilization and provide further evidence regarding effectiveness.

The liver is a key metabolic organ that undertakes a multitude of physiological processes over the course of a day, including intrahepatic lipid and glucose metabolism which plays a key role in the regulation of systemic lipid and glucose concentrations. It serves as an intermediary organ between exogenous (dietary) and endogenous energy supply to extrahepatic organs. Thus, perturbations in hepatic metabolism can impact widely on metabolic disease risk. For example, the accumulation of intra-hepatocellular TAG (IHTG), for which adiposity is almost invariably a causative factor may result in dysregulation of metabolic pathways. Accumulation of IHTG is likely due to an imbalance between fatty acid delivery, synthesis and removal (via oxidation or export as TAG) from the liver; insulin plays a key role in all of these processes.

We present the first Southern-Hemisphere all-sky imager and radio-transient monitoring system implemented on two prototype stations of the low-frequency component of the Square Kilometre Array (SKA-Low). Since its deployment, the system has been used for real-time monitoring of the recorded commissioning data. Additionally, a transient searching algorithm has been executed on the resulting all-sky images. It uses a difference imaging technique to enable identification of a wide variety of transient classes, ranging from human-made radio-frequency interference to genuine astrophysical events. Observations at the frequency 159.375 MHz and higher in a single coarse channel ($\approx$0.926 MHz) were made with 2 s time resolution, and multiple nights were analysed generating thousands of images. Despite having modest sensitivity ($\sim$ few Jy beam–1), using a single coarse channel and 2-s imaging, the system was able to detect multiple bright transients from PSR B0950+08, proving that it can be used to detect bright transients of an astrophysical origin. The unusual, extreme activity of the pulsar PSR B0950+08 (maximum flux density $\sim$155 Jy beam–1) was initially detected in a ‘blind’ search in the 2020 April 10/11 data and later assigned to this specific pulsar. The limitations of our data, however, prevent us from making firm conclusions of the effect being due to a combination of refractive and diffractive scintillation or intrinsic emission mechanisms. The system can routinely collect data over many days without interruptions; the large amount of recorded data at 159.375 and 229.6875 MHz allowed us to determine a preliminary transient surface density upper limit of $1.32 \times 10^{-9} \text{deg}^{-2}$ for a timescale and limiting flux density of 2 s and 42 Jy, respectively. In the future, we plan to extend the observing bandwidth to tens of MHz and improve time resolution to tens of milliseconds in order to increase the sensitivity and enable detections of fast radio bursts below 300 MHz.

A new high time resolution observing mode for the Murchison Widefield Array (MWA) is described, enabling full polarimetric observations with up to $30.72\,$MHz of bandwidth and a time resolution of ${\sim}$$0.8\,\upmu$s. This mode makes use of a polyphase synthesis filter to ‘undo’ the polyphase analysis filter stage of the standard MWA’s Voltage Capture System observing mode. Sources of potential error in the reconstruction of the high time resolution data are identified and quantified, with the $S/N$ loss induced by the back-to-back system not exceeding $-0.65\,$dB for typical noise-dominated samples. The system is further verified by observing three pulsars with known structure on microsecond timescales.

At Guy's King's and St Thomas’ School of Medicine, a unique initiative is the Psychiatry Early Experience Programme (PEEP), which allows students to shadow psychiatry trainees at work several times a year. The students’ attitudes towards psychiatry and the scheme are regularly assessed and initial results are already available.

The Murchison Widefield Array (MWA) is an open access telescope dedicated to studying the low-frequency (80–300 MHz) southern sky. Since beginning operations in mid-2013, the MWA has opened a new observational window in the southern hemisphere enabling many science areas. The driving science objectives of the original design were to observe 21 cm radiation from the Epoch of Reionisation (EoR), explore the radio time domain, perform Galactic and extragalactic surveys, and monitor solar, heliospheric, and ionospheric phenomena. All together $60+$ programs recorded 20 000 h producing 146 papers to date. In 2016, the telescope underwent a major upgrade resulting in alternating compact and extended configurations. Other upgrades, including digital back-ends and a rapid-response triggering system, have been developed since the original array was commissioned. In this paper, we review the major results from the prior operation of the MWA and then discuss the new science paths enabled by the improved capabilities. We group these science opportunities by the four original science themes but also include ideas for directions outside these categories.