Search

To solve the problem of feature selection and error correction after mode decomposition and improve the ability of power load forecasting models to capture complex time series information, a two-stage short-term power load forecasting method based on recursive feature elimination with a cross validation (RFECV) algorithm and time convolution network–efficient channel attention mechanism–long short-term memory network (TCN–ECA–LSTM) is presented. First, the load sequence is decomposed into a relatively stable set of modal components using variational mode decomposition. Then, the RFECV-based method filters the feature set of each modal component to construct the best feature set. Finally, a two-stage prediction model based on TCN–ECA–LSTM is established. The first stage predicts each modal component and the second stage reconstructs the load forecast based on the predicted value of the previous stage. This paper takes actual data from New South Wales, Australia, as an example, and the results show that the method proposed in this paper can build the feature set reliably and efficiently and has a higher accuracy than the conventional prediction model. [ABSTRACT FROM AUTHOR]

This paper formulates a control problem for systems that are affected by uncertain inputs and are vulnerable to risks as a chance-constrained optimization problem (CCP) with two chance-constraints (CCs). The first CC encompasses requirements of the normal operations of the system, whereas the second CC ensures the avoidance of risks associated with rare events. CCPs are in general difficult to solve, and this paper proposes a scenario-based optimization, testing, and improving algorithm to find approximate solutions to such problems within a stochastic model predictive control setting in a computationally cheap manner. The proposed approach is applied to a river control problem with flood avoidance, and the controller performed well in realistic simulations of the upper part of Murray River in Australia. [ABSTRACT FROM AUTHOR]

Simple Summary: Breast cancer is one of the leading causes of cancer-related death in women. The early detection of breast cancer with screening mammograms plays a pivotal role in reducing mortality rates. Although population-based double-reading screening mammograms have reduced mortality by over 31% in women with breast cancer in Europe, continuing this program is difficult due to the shortage of radiologists. Artificial intelligence (AI) is an emerging technology that has provided promising results in medical imaging for disease detection. This study investigates the performance of AI models on an Australian mammographic database, demonstrating how transfer learning from a USA mammographic database to an Australian one, contrast enhancement on mammographic images and the quality of training data according to radiologists' concordance can improve breast cancer diagnosis. Our proposed methodology offers a more efficacious approach for AI to contribute to radiologists' decision making when interpreting mammography images. This paper investigates the adaptability of four state-of-the-art artificial intelligence (AI) models to the Australian mammographic context through transfer learning, explores the impact of image enhancement on model performance and analyses the relationship between AI outputs and histopathological features for clinical relevance and accuracy assessment. A total of 1712 screening mammograms (n = 856 cancer cases and n = 856 matched normal cases) were used in this study. The 856 cases with cancer lesions were annotated by two expert radiologists and the level of concordance between their annotations was used to establish two sets: a 'high-concordances subset' with 99% agreement of cancer location and an 'entire dataset' with all cases included. The area under the receiver operating characteristic curve (AUC) was used to evaluate the performance of Globally aware Multiple Instance Classifier (GMIC), Global-Local Activation Maps (GLAM), I&H and End2End AI models, both in the pretrained and transfer learning modes, with and without applying the Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm. The four AI models with and without transfer learning in the high-concordance subset outperformed those in the entire dataset. Applying the CLAHE algorithm to mammograms improved the performance of the AI models. In the high-concordance subset with the transfer learning and CLAHE algorithm applied, the AUC of the GMIC model was highest (0.912), followed by the GLAM model (0.909), I&H (0.893) and End2End (0.875). There were significant differences (p < 0.05) in the performances of the four AI models between the high-concordance subset and the entire dataset. The AI models demonstrated significant differences in malignancy probability concerning different tumour size categories in mammograms. The performance of AI models was affected by several factors such as concordance classification, image enhancement and transfer learning. Mammograms with a strong concordance with radiologists' annotations, applying image enhancement and transfer learning could enhance the accuracy of AI models. [ABSTRACT FROM AUTHOR]

Background: Developmental language disorder (DLD) is one of the most common neurodevelopmental conditions. Due to variable rates of language growth in children under 5 years, the early identification of children with DLD is challenging. Early indicators are often outlined by speech pathology regulatory bodies and other developmental services as evidence to empower caregivers in the early identification of DLD. Aims: To test the predictive relationship between parent‐reported early indicators and the likelihood of children meeting diagnostic criteria for DLD at 10 years of age as determined by standardized assessment measures in a population‐based sample. Methods: Data were leveraged from the prospective Raine Study (n = 1626 second‐generation children: n = 104 with DLD; n = 1522 without DLD). These data were transformed into 11 predictor variables that reflect well‐established early indicators of DLD from birth to 3 years, including if the child does not smile or interact with others, does not babble, makes only a few sounds, does not understand what others say, says only a few words, says words that are not easily understood, and does not combine words or put words together to make sentences. Family history (mother and father) of speech and language difficulties were also included as variables. Regression analyses were planned to explore the predictive relationship between this set of early indicator variables and likelihood of meeting DLD diagnostic criteria at 10 years. Results: No single parent‐reported indicator uniquely accounted for a significant proportion of children with DLD at 10 years of age. Further analyses, including bivariate analyses testing the predictive power of a cumulative risk index of combined predictors (odds ratio (OR) = 0.95, confidence interval (CI) = 0.85–1.09, p = 0.447) and the moderating effect of sex (OR = 0.89, CI = 0.59–1.32, p = 0.563) were also non‐significant. Conclusions: Parent reports of early indicators of DLD are well‐intentioned and widely used. However, data from the Raine Study cohort suggest potential retrospective reporting bias in previous studies. We note that missing data for some indicators may have influenced the results. Implications for the impact of using early indicators as evidence to inform early identification of DLD are discussed. WHAT THIS PAPER ADDS: What is already known on the subject: DLD is a relatively common childhood condition; however, children with DLD are under‐identified and under‐served. Individual variability in early childhood makes identification of children at risk of DLD challenging. A range of 'red flags' in communication development are promoted through speech pathology regulatory bodies and developmental services to assist parents to identify if their child should access services. What this paper adds to the existing knowledge: No one parent‐reported early indicator, family history or a cumulation of indicators predicted DLD at 10 years in the Raine study. Sex (specifically, being male) did not moderate an increased risk of DLD at 10 years in the Raine study. Previous studies reporting on clinical samples may be at risk of retrospective reporting bias. What are the potential or actual clinical implications of this work?: The broad dissemination and use of 'red flags' is well‐intentioned; however, demonstrating 'red flags' alone may not reliably identify those who are at later risk of DLD. Findings from the literature suggest that parent concern may be complemented with assessment of linguistic behaviours to increase the likelihood of identifying those who at risk of DLD. Approaches to identification and assessment should be considered alongside evaluation of functional impact to inform participation‐based interventions. [ABSTRACT FROM AUTHOR]

This paper presents the development and evaluation of short-term traffic prediction models using unidirectional and bidirectional deep learning long short-term memory (LSTM) neural networks. The unidirectional LSTM (Uni-LSTM) model provides high performance through its ability to recognize longer sequences of traffic time series data. In this work, Uni-LSTM is extended to bidirectional LSTM (BiLSTM) networks which train the input data twice through forward and backward directions. The paper presents a comparative evaluation of the two models for short-term speed and traffic flow prediction using a common dataset of field observations collected from multiple freeways in Australia. The results showed BiLSTM performed better for variable prediction horizons for both speed and flow. Stacked and mixed Uni-LSTM and BiLSTM models were also investigated for 15-minute prediction horizons resulting in improved accuracy when using 4-layer BiLSTM networks. The optimized 4-layer BiLSTM model was then calibrated and validated for multiple prediction horizons using data from three different freeways. The validation results showed a high degree of prediction accuracy exceeding 90% for speeds up to 60-minute prediction horizons. For flow, the model achieved accuracies above 90% for 5- and 10-minute prediction horizons and more than 80% accuracy for 15- and 30-minute prediction horizons. These findings extend the set of AI models available for road operators and provide them with confidence in applying robust models that have been tested and evaluated on different freeways in Australia. [ABSTRACT FROM AUTHOR]

The dry weight of biomass to be consumed by fire in the wildland – urban interface (WUI) plays an important role in the spread of fire inside the WUI. In this paper, we present a model of grassland fire spread based on fuel load. The herbaceous stratum is represented by a heterogeneous fuel layer, with characteristics close to the real one. Fire propagation is simulated by using a two-phase model. Thirteen fire experiments in eastern Australia were used to test the predictive capacity of the model. The rates of spread are on the whole relatively well predicted. Using the fuel layer model to simulate fire spread, we tested how fuel load affects fire behavior. The results show that the fire spread rate does not systematically decrease with the increasing of fuel load. However, there may be a critical fuel load for rapid rate of spread, below or above which the rate of spread decreases. [ABSTRACT FROM AUTHOR]

Fires in buildings are significant public safety hazards and can result in fatalities and substantial financial losses. Studies have shown that the socioeconomic makeup of a region can impact the occurrence of building fires. However, existing models based on the classical stepwise regression procedure have limitations. This paper proposes a more accurate predictive model of building fire rates using a set of socioeconomic variables. To improve the model's forecasting ability, a backward elimination by robust final predictor error (RFPE) criterion is introduced. The proposed approach is applied to census and fire incident data from the South East Queensland region of Australia. A cross-validation procedure is used to assess the model's accuracy, and comparative analyses are conducted using other elimination criteria such as p-value, Akaike's information criterion (AIC), Bayesian information criterion (BIC), and predicted residual error sum of squares (PRESS). The results demonstrate that the RFPE criterion is a more accurate predictive model based on several goodness-of-fit measures. Overall, the RFPE equation was found to be a suitable criterion for the backward elimination procedure in the socioeconomic modeling of building fires. [ABSTRACT FROM AUTHOR]

Beef production drives a significant proportion of Australia's agricultural economy, representing AUD11 billion in agricultural production value annually. The profitability of cattle farms across seasons varies greatly and is particularly influenced by weather and associated uncertainty through pasture growth. Furthermore, producers must be careful in managing stocking rates to avoid overgrazing which has a significant environmental and economic impact. Predictive modelling of pasture and cattle liveweight can help producers to better manage this difficult balancing act. In this paper, we integrate a model for pasture growth and cattle weight gain to formulate predictions of liveweight production volume and pasture biomass. Monte‐Carlo simulation was used to understand the impact of uncertainty in model inputs relating to weather. Through such an approach, a distribution of possible pasture outcomes and beef production is formed which can be inspected to determine, for example expected production volume and risk of overgrazing. The methodology is demonstrated and validated through application to case study data sourced from Australian beef producers. Results demonstrate that it is possible to obtain reasonable predictions of liveweight gain and highlight the importance of considering the associated uncertainty. The accuracy of the proposed models has been examined by calculating statistical parameters MSE, MAE and R2. This approach can provide insight into the distribution of possible production outcomes given the long‐term rainfall outlook. The use of such predictive models and simulations by producers will lead to better‐informed planning of stocking rates, with benefits to productivity and sustainable utilisation of pasture. [ABSTRACT FROM AUTHOR]

Climate change is impacting people's lives, with management of water resources and food security being major concerns for the future of many countries. In this paper, future water availability, crop water needs, yields, market costs and returns of current crops in a case study area in Australia are evaluated under future climatic conditions. The predictive methods on which the work is based have the advantage of being robust—they are able to simultaneously consider many climate change models—giving greater confidence in determining what the future will hold in this regard. The results indicate business as usual, in terms of the quantity and types of crops that can be grown presently, will not be sustainable in the medium and long term future. Instead, modelling indicates that changes in production and land use to maximise revenue per megalitre of water will be needed to adapt to future conditions and deliver climate-smart agriculture. [ABSTRACT FROM AUTHOR]

Australia faces a dryness disaster whose impact may be mitigated by rainfall prediction. Being an incredibly challenging task, yet accurate prediction of rainfall plays an enormous role in policy making, decision making and organizing sustainable water resource systems. The ability to accurately predict rainfall patterns empowers civilizations. Though short-term rainfall predictions are provided by meteorological systems, long-term prediction of rainfall is challenging and has a lot of factors that lead to uncertainty. Historically, various researchers have experimented with several machine learning techniques in rainfall prediction with given weather conditions. However, in places like Australia where the climate is variable, finding the best method to model the complex rainfall process is a major challenge. The aim of this paper is to: (a) predict rainfall using machine learning algorithms and comparing the performance of different models. (b) Develop an optimized neural network and develop a prediction model using the neural network (c) to do a comparative study of new and existing prediction techniques using Australian rainfall data. In this paper, rainfall data collected over a span of ten years from 2007 to 2017, with the input from 26 geographically diverse locations have been used to develop the predictive models. The data was divided into training and testing sets for validation purposes. The results show that both traditional and neural network-based machine learning models can predict rainfall with more precision. [ABSTRACT FROM AUTHOR]

The objective of this paper is to assess whether existing pavement temperature prediction algorithms can be used to reliably determine Performance Grade (PG) design temperatures for Australian asphalt pavements. The results show good agreement between internationally and locally developed pavement temperature algorithms for the prediction of high pavement design temperature. There is more variability between models in the prediction of low pavement design temperature. The paper also provides a set of PG grading results for a range of Australian asphalt binders. The findings indicate that for a given design situation harder bitumen, ormore highly modified binder would be specified in Australia than in jurisdictions using the PG system. [ABSTRACT FROM AUTHOR]

Forecasting solar radiation for a given region is an emerging field of study. It will help to identify the places for installing large-scale photovoltaic-systems, designing energy-efficient buildings and energy estimation. The different machine learning kernel-based approaches for prediction problems uses either a local or global kernel. These models can provide either strong training capability or good generalization performance. In this paper, a new hybrid kernel is proposed using the combination of a local and global kernel. A novel algorithm Hybrid Kernel-based Extreme Learning Machine is proposed for predictive modelling of Incident Solar Radiation (ISR) time series using new hybrid kernel. The proposed algorithm uses the surface, atmospheric, cloud properties obtained from the MODIS instrument and observed ISR at time t – 1 to predict ISR at time t. This study is conducted for 41 diverse sites of Australia for the period of 2012–2015. Further, the proposed model is experimented with other time series datasets to prove its efficacy. It is shown that the proposed methodology outperforms five other benchmarking methods in terms of MAE and Willmott's Index (WI). Therefore, the suggested approach can be used for modelling solar energy at a national scale using remotely-sensed satellite footprints. [ABSTRACT FROM AUTHOR]

The conditional autoregressive approach is popular to analyse data with geocoded boundary. However, spatial prediction is often challenging when observed data are sparse. It becomes more challenging in predicting areal units with different areal boundaries. Hence, this paper develops a spatial generalised linear model for spatial predictions using data from spatially misaligned sparse locations. A spatial basis function associated with the conditional autoregressive models and the kriging method is considered. The proposed model demonstrates its better predictive performance through a simulation study and then is applied to understand the spatial pattern of undecided voting preferences in Australia. [ABSTRACT FROM AUTHOR]

Background: Artificial intelligence has the potential to innovate current practices used to detect the imminent risk of suicide and to address shortcomings in traditional assessment methods. Objective: In this paper, we sought to automatically classify short segments (40 milliseconds) of speech according to low versus imminent risk of suicide in a large number (n=281) of telephone calls made to 2 telehealth counselling services in Australia. Methods: A total of 281 help line telephone call recordings sourced from On The Line, Australia (n=266, 94.7%) and 000 Emergency services, Canberra (n=15, 5.3%) were included in this study. Imminent risk of suicide was coded for when callers affirmed intent, plan, and the availability of means; level of risk was assessed by the responding counsellor and reassessed by a team of clinical researchers using the Columbia Suicide Severity Rating Scale (=5/6). Low risk of suicide was coded for in an absence of intent, plan, and means and via Columbia suicide Severity Scale Ratings (=1/2). Preprocessing involved normalization and pre-emphasis of voice signals, while voice biometrics were extracted using the statistical language r. Candidate predictors were identified using Lasso regression. Each voice biomarker was assessed as a predictor of suicide risk using a generalized additive mixed effects model with splines to account for nonlinearity. Finally, a component-wise gradient boosting model was used to classify each call recording based on precoded suicide risk ratings. Results: A total of 77 imminent-risk calls were compared with 204 low-risk calls. Moreover, 36 voice biomarkers were extracted from each speech frame. Caller sex was a significant moderating factor (β=-.84, 95% CI -0.85, -0.84; t=6.59, P<.001). Candidate biomarkers were reduced to 11 primary markers, with distinct models developed for men and women. Using leave-one-out cross-validation, ensuring that the speech frames of no single caller featured in both training and test data sets simultaneously, an area under the precision or recall curve of 0.985 was achieved (95% CI 0.97, 1.0). The gamboost classification model correctly classified 469,332/470,032 (99.85%) speech frames. Conclusions: This study demonstrates an objective, efficient, and economical assessment of imminent suicide risk in an ecologically valid setting with potential applications to real-time assessment and response. [ABSTRACT FROM AUTHOR]

Background: Previous research has raised substantial concerns regarding the validity of the International Statistical Classification of Diseases and Related Health Problems (ICD) codes (ICD-10 I05–I09) for rheumatic heart disease (RHD) due to likely misclassification of non-rheumatic valvular disease (non-rheumatic VHD) as RHD. There is currently no validated, quantitative approach for reliable case ascertainment of RHD in administrative hospital data. Methods: A comprehensive dataset of validated Australian RHD cases was compiled and linked to inpatient hospital records with an RHD ICD code (2000– 2018, n=7555). A prediction model was developed based on a generalized linear mixed model structure considering an extensive range of demographic and clinical variables. It was validated internally using randomly selected cross-validation samples and externally. Conditional optimal probability cutpoints were calculated, maximising discrimination separately for high-risk versus low-risk populations. Results: The proposed model reduced the false-positive rate (FPR) from acute rheumatic fever (ARF) cases misclassified as RHD from 0.59 to 0.27; similarly for non-rheumatic VHD from 0.77 to 0.22. Overall, the model achieved strong discriminant capacity (AUC: 0.93) and maintained a similar robust performance during external validation (AUC: 0.88). It can also be used when only basic demographic and diagnosis data are available. Conclusion: This paper is the first to show that not only misclassification of non-rheumatic VHD but also of ARF as RHD yields substantial FPRs. Both sources of bias can be successfully addressed with the proposed model which provides an effective solution for reliable RHD case ascertainment from hospital data for epidemiological disease monitoring and policy evaluation. [ABSTRACT FROM AUTHOR]

Accurate and reliable low-voltage load forecasting is critical to optimal operation and control of distribution network and smart grid. However, compared to traditional regional load forecasting at high-voltage level, it faces tough challenges due to the inherent high uncertainty of the low-capacity load and distributed renewable energy integrated in the demand side. This paper proposes a novel hybrid ensemble deep learning (HEDL) approach for deterministic and probabilistic low-voltage load forecasting. The deep belief network (DBN) is applied to low-voltage load point prediction with the strong ability of approximating nonlinear mapping. A series of ensemble learning methods including bagging and boosting variants are introduced to improve the regression ability of DBN. In addition, the differencing transformation technique is utilized to ensure the stationarity of load time series for the application bagging and boosting methods. On the basis of the integrated thought of ensemble learning, a new hybrid ensemble algorithm is developed via integrating multiple separate ensemble methods. Considering the diversity in various ensemble algorithms, an effective K nearest neighbor classification method is utilized to adaptively determine the weights of sub-models. Furthermore, HEDL based probabilistic forecasting is proposed by taking advantage of the inherent resample idea in bagging and boosting. The effectiveness of the HEDL method for both deterministic and probabilistic forecasting has been systematically verified based on realistic load data from East China and Australia, indicating its promising prospective for practical applications in distribution networks. [ABSTRACT FROM AUTHOR]

The emergence of many strains of the coronavirus, including the latest omicron strain, which is spreading at a very high speed, is leading to the World Health Organization's (WHO) concern about the creation of this new mutation. Therefore, there is a strong motivation for modeling and predicting COVID-19 to control the number of cases of the disease. The proposed system for predicting the number of cases of COVID-19 can help governments take precautions to prevent the spread of the disease. In this paper, a statistical logistic growth model was employed to predict the spread of COVID-19 in Australia and Brazil. The datasets were collected from the surveillance systems in Australia and Brazil from March 13, 2020, to December 12, 2021, for 641 days. This proposed method used a tested logistic growth model for the complex spread of COVID-19 and forecasted future values within a time interval of six days. The results of the predicted, cumulative, confirmed cases indicate the robustness and effectiveness of the proposed system, which was categorized by time-dependent dynamics. The coefficient of determination (R) metric was used to evaluate the model to predict COVID-19, and the proposed system scored the highest correlation ( R 2 = 99 %). The proposed system has the potential to contribute to public health by making decisions about how to prevent the spread of COVID-19. [ABSTRACT FROM AUTHOR]

The corrosion of steel due to chloride ingress is one of the major causes of deterioration of reinforced concrete structures. In order to ensure a structure achieves the design life specified, predictive modelling is employed. To undertake this modelling, details are required on a number of variables; however, each of these variables has a level of uncertainty which can affect the reliability of the model. To address these issues, this paper reports the analysis of data taken from four distinct elements on a port structure, in Australia, constructed in three phases between 1926 and 1985, using both pre-cast and cast in situ techniques. The cover depth, surface chloride concentration and chloride diffusion coefficient were determined for different elements on the structure, with a total of 244 data points obtained. The data was analysed to identify the statistical distributions and probability density functions produced. A novel analytical model was developed based on the solutions to Fick's equation. The results showed that both surface chloride and the diffusion coefficient were positively skewed with no significant variation in the sensitivity. It was also found that controlling the diffusion coefficient has a more influential effect than increasing the cover. [ABSTRACT FROM AUTHOR]

Purpose – Ethnographic studies of cyber attacks typically aim to explain a particular profile of attackers in qualitative terms. The purpose of this paper is to formalise some of the approaches to build a Cyber Attacker Model Profile (CAMP) that can be used to characterise and predict cyber attacks. Design/methodology/approach – The paper builds a model using social and economic independent or predictive variables from several eastern European countries and benchmarks indicators of cybercrime within the Australian financial services system. Findings – The paper found a very strong link between perceived corruption and GDP in two distinct groups of countries – corruption in Russia was closely linked to the GDP of Belarus, Moldova and Russia, while corruption in Lithuania was linked to GDP in Estonia, Latvia, Lithuania and Ukraine. At the same time corruption in Russia and Ukraine were also closely linked. These results support previous research that indicates a strong link between been legitimate economy and the black economy in many countries of Eastern Europe and the Baltic states. The results of the regression analysis suggest that a highly skilled workforce which is mobile and working in an environment of high perceived corruption in the target countries is related to increases in cybercrime even within Australia. It is important to note that the data used for the dependent and independent variables were gathered over a seven year time period, which included large economic shocks such as the global financial crisis. Originality/value – This is the first paper to use a modelling approach to directly show the relationship between various social, economic and demographic factors in the Baltic states and Eastern Europe, and the level of card skimming and card not present fraud in Australia. [ABSTRACT FROM AUTHOR]

Accurate rainfall prediction is a challenging task. It is especially challenging in Australia where the climate is highly variable. Australia’s climatic zones range from high rainfall tropical regions in the north to the driest desert region in the interior. The performance of prediction models may vary depending on climatic conditions. It is, therefore, important to assess and compare the performance of these models in different climatic zones. This paper examines the performance of data driven models such as the support vector machines for regression, the multiple linear regression, the k-nearest neighbors and the artificial neural networks for monthly rainfall prediction in Australia depending on climatic conditions. Rainfall data with five meteorological variables over the period of 1970–2014 from 24 geographically diverse weather stations are used for this purpose. The prediction performance of each model was evaluated by comparing observed and predicted rainfall using various measures for prediction accuracy. [ABSTRACT FROM AUTHOR]

This paper sets up and estimates a structural model of Australia as a small open economy using Bayesian techniques. Unlike other recent studies, the paper shows that a small micro-founded model can capture the open economy dimensions quite well. Specifically, the model attributes a substantial fraction of the volatility of domestic output and inflation to foreign disturbances, close to what is suggested by unrestricted VAR studies. The paper also investigates the effects of various exogenous shocks on the Australian economy. [ABSTRACT FROM AUTHOR]

Aim: To develop and internally validate risk prediction models for subsequent clinical deterioration, unplanned ICU admission and death among ward patients following medical emergency team (MET) review. Design: A retrospective cohort study of 1500 patients who remained on a general ward following MET review at an Australian quaternary hospital. Method: Logistic regression was used to model (1) subsequent MET review within 48 h, (2) unplanned ICU admission within 48 h and (3) hospital mortality. Models included demographic, clinical and illness severity variables. Model performance was evaluated using discrimination and calibration with optimism‐corrected bootstrapped estimates. Findings are reported using the TRIPOD guideline for multivariable prediction models for prognosis or diagnosis. There was no patient or public involvement in the development and conduct of this study. Results: Within 48 h of index MET review, 8.3% (n = 125) of patients had a subsequent MET review, 7.2% (n = 108) had an unplanned ICU admission and in‐hospital mortality was 16% (n = 240). From clinically preselected predictors, models retained age, sex, comorbidity, resuscitation limitation, acuity‐dependency profile, MET activation triggers and whether the patient was within 24 h of hospital admission, ICU discharge or surgery. Models for subsequent MET review, unplanned ICU admission, and death had adequate accuracy in development and bootstrapped validation samples. Conclusion: Patients requiring MET review demonstrate complex clinical characteristics and the majority remain on the ward after review for deterioration. A risk score could be used to identify patients at risk of poor outcomes after MET review and support general ward clinical decision‐making. Relevance to clinical practice: Our risk calculator estimates risk for patient outcomes following MET review using clinical data available at the bedside. Future validation and implementation could support evidence‐informed team communication and patient placement decisions. [ABSTRACT FROM AUTHOR]

Prediction of true classes of surficial and deep earth materials using multivariate spatial data is a common challenge for geoscience modelers. Most geological processes leave a footprint that can be explored by geochemical data analysis. These footprints are normally complex statistical and spatial patterns buried deep in the high-dimensional compositional space. This paper proposes a spatial predictive model for classification of surficial and deep earth materials derived from the geochemical composition of surface regolith. The model is based on a combination of geostatistical simulation and machine learning approaches. A random forest predictive model is trained, and features are ranked based on their contribution to the predictive model. To generate potential and uncertainty maps, compositional data are simulated at unsampled locations via a chain of transformations (isometric log-ratio transformation followed by the flow anamorphosis) and geostatistical simulation. The simulated results are subsequently back-transformed to the original compositional space. The trained predictive model is used to estimate the probability of classes for simulated compositions. The proposed approach is illustrated through two case studies. In the first case study, the major crustal blocks of the Australian continent are predicted from the surface regolith geochemistry of the National Geochemical Survey of Australia project. The aim of the second case study is to discover the superficial deposits (peat) from the regional-scale soil geochemical data of the Tellus Project. The accuracy of the results in these two case studies confirms the usefulness of the proposed method for geological class prediction and geological process discovery. [ABSTRACT FROM AUTHOR]

Short‐term load forecasting is essential to power systems management. However, most existing forecasting methods fail to fully consider how to rationally integrate the intrinsic time‐related dimensions of electric load data and the decomposition methods into machine learning models so that their prediction accuracy and robustness still have much room for improvement. To solve this problem, this paper proposes a decomposition‐based multi‐time dimension long short‐term memory (DB‐MTD‐LSTM) model for short‐term electric load forecasting (STELF). In DB‐MTD‐LSTM, empirical mode decomposition with adaptive noise (CEEMDAN) is first introduced to smooth non‐linear non‐stationary electric load data and constrain the modal aliasing or noise of decomposed electric load data in the traditional decomposed method. A joint relevant time dimensions method (JRTDM) is then developed using autocorrelation analysis to rationally extract the temporal characteristics of decomposed data in multiple time dimensions. An improved LSTM called MTD‐LSTM is developed by combining JRTDM with LSTM, which can effectively apply multi‐dimensional time characteristics of the decomposed load to improve the predictive accuracy and robustness. Several datasets from Australia and China are performed to check the predictive performance of DB‐MTD‐LSTM. Experimental results verify that DB‐MTD‐LSTM has better predictive accuracy and satisfactory robustness compared with state‐of‐the‐art and conventional predictive models. [ABSTRACT FROM AUTHOR]

As more and more photovoltaic (PV) systems are integrated into the grid, the intelligent operation of the grid system is facing significant challenges. Therefore, accurately forecasting PV power output at various time scales is particularly urgent. To meet this demand, this paper proposes an LSTM-Informer model based on an improved Stacking ensemble algorithm (ISt-LSTM-Informer). The proposed model improves the k-fold cross validation in the traditional Stacking algorithm to a time-series cross validation for integrating time-series forecasting models. Simultaneously, it utilizes long short-term memory (LSTM) and Informer as the base models. By integrating the advantages of the two base models, the ISt-LSTM-Informer achieves accurate short and medium-term PV power forecasting. To validate the effectiveness of the model, a historical dataset from a PV system located in Uluru, Australia, is used for various types of experiments. Among them, comparative experiments validate the superiority of the model. Compared with five other methods, the ISt-LSTM-Informer obtains 21 optimal results for the four evaluation metrics of RMSE, MAE, MAPE, and R 2 across eight forecasting time scales. In addition, different combinations of base models are conducted to verify the advantages of the Stacking ensemble algorithm and the two base models, respectively. • A novel multi-timescale photovoltaic power forecasting model is proposed. • Time-series cross validation is introduced into the Stacking algorithm. • LSTM and Informer are utilized as the base models of the Stacking algorithm. • Various methods are compared to verify the proposed model's effectiveness. • The model's predictive accuracy is illustrated through various visualization methods. [ABSTRACT FROM AUTHOR]

Understanding and projecting drought, especially in the face of climate change, is crucial for assessing its impending risks. However, the causes of drought are multifaceted. As the environmental research paradigm pivots towards machine learning (ML) for predictions, our investigation contrasted multiple ML techniques to simulate the Standardized Precipitation Evapotranspiration Index (SPEI) from 2009 to 2022, utilizing various potential evapotranspiration (PET) methods. Our primary focus was Australia, the world's driest inhabited continent. Given the challenges with ML model interpretation, SHAP (SHapley Additive exPlanations) values were employed to decipher SPEI variations and to gauge the relative importance of precipitation (Prec) and PET in six key Australian cities. Our findings revealed that while different PET methods resulted in distinct mean values, their trends remained consistent. Post the Millennium Drought, Australia experienced several drought events. SPEI discrepancies based on PET methods were minimal in humid regions like Brisbane and Darwin. However, for arid cities, the Priestley–Taylor equation-driven SPEI differed notably from other methods. Ridge regression was the most adept at mirroring SPEI changes among the assessed ML models. Furthermore, the SHAP explainer discerned that PET-related climate variables had a greater impact on SPEI in drier cities, whereas in humid cities, Prec was more influential. Notably, the research emphasised CO2′s role in influencing drought dynamics in humid cities. These insights are invaluable for enhancing drought mitigation strategies and refining predictive models. Such revelations are crucial for stakeholders aiming to improve drought prediction and management, especially in drought-prone regions like Australia. [ABSTRACT FROM AUTHOR]

Background: Operating rooms (ORs) are one of the costliest units in a hospital, therefore the cumulative consequences of any kind of inefficiency in OR management lead to a significant loss of revenue for the hospital, staff dissatisfaction, and patient care disruption. One of the possible solutions to improving OR efficiency is knowing a reliable estimate of the duration of operations. The literature suggests that the current methods used in hospitals, e.g., a surgeon's estimate for the given surgery or taking the average of only five previous records of the same procedure, have room for improvement. Methods: We used over 4 years of elective surgery records (n = 52,171) from one of the major metropolitan hospitals in Australia. We developed robust Machine Learning (ML) approaches to provide a more accurate prediction of operation duration, especially in the absence of surgeon's estimation. Individual patient characteristics and historic surgery information attributed to medical records were used to train predictive models. A wide range of algorithms such as Extreme Gradient Boosting (XGBoost) and Random Forest (RF) were tested for predicting operation duration. Results: The results show that the XGBoost model provided statistically significantly less error than other compared ML models. The XGBoost model also reduced the total absolute error by 6854 min (i.e., about 114 h) compared to the current hospital methods. Conclusion: The results indicate the potential of using ML methods for reaching a more accurate estimation of operation duration compared to current methods used in the hospital. In addition, using a set of realistic features in the ML models that are available at the point of OR scheduling enabled the potential deployment of the proposed approach. [ABSTRACT FROM AUTHOR]

The term ‘hydrologic non-stationarity’ has been used to describe many things, ranging from different climate-runoff relationships evident in different periods within a long hydroclimate time series to changes in hydroclimate characteristics and dominant hydrological processes in an increasingly warmer and higher CO 2 world. This paper presents several examples of observed ‘hydrologic non-stationarity’ in far south-eastern Australia exposed by the prolonged 1997–2009 “Millennium” drought, focussing on the implications of this hydrologic non-stationarity on hydrological modelling and prediction. The runoff decline during the drought was unprecedented in the instrumental historical record. It was caused not only by the lower annual rainfall, but also by changes in other climate characteristics (lack of any high rainfall years, change in rainfall seasonality and higher temperatures) and dominant hydrological processes (reduced surface–groundwater connection and farm dams intercepting proportionally more water during dry periods). Hydrological models developed and calibrated against pre-1997 data cannot predict adequately the flow volumes and runoff characteristics during the drought. However, as the Millennium drought has exposed these extreme conditions, models can now be developed and calibrated to represent these, as well other conditions observed in the instrumental historical records (i.e., hydrologic non-stationarity that has already been observed). Such models should be able to satisfactorily predict the near-term runoff which will be influenced mainly by the rainfall inputs. However, further into the future, runoff will be increasingly influenced by higher temperatures and changed ecohydrological processes under higher CO 2. Reliably modelling these is difficult because of the complex interactions and feedbacks between many variables and processes in a future environment not seen in the past (i.e., hydrologic non-stationarity that has not been observed). [ABSTRACT FROM AUTHOR]

• Mutual information is effective to analyze dependence of foF2 on R 12 and F10.7 12. • Dependence of foF2 on R 12 and F10.7 12 differ in different solar activity years. • Mutual information provides an effective selection of inputs for foF2 prediction. This paper analyzes the dependence of the ionospheric F2 layer critical frequency, f oF2, on two widely used solar activity indices (12-month running mean of the sunspot number (R 12) and the solar radio flux of 10.7 cm wavelength (F10.7 12)) by using mutual information method at the ionospheric station of Darwin (geographic 12.4°S, 131.5°E) in Australia. The results show that the f oF2 have different responses to R 12 and F10.7 12 in different solar activity years. In the high and low solar activity years, the f oF2 is more dependent on R 12 rather than F10.7 12. In the moderate solar activity years, the f oF2 is more dependent on F10.7 12 rather than R 12. We further verify the effectiveness of the mutual information on the selection of the solar activity index by developing the prediction models of the f oF2. Additionally, the results are compared against the International Reference Ionosphere (IRI) model. The data of training period used in the model is from 1998 to 2015, except 2000, 2009 and 2013. Data for 2000, 2009 and 2013 are used to validate the prediction accuracy, for high, low and moderate solar activity years, respectively. The results demonstrate that the favorable prediction results can be obtained when the solar activity index with large mutual information is used as the input variable of the fo F2 prediction model. The proposed method not only can quantitatively analyze the nonlinear relationship between the fo F2 and solar activity indices but also provides an effective way of selecting the solar activity indices for the fo F2 prediction. [ABSTRACT FROM AUTHOR]

This paper introduces a novel model for predicting the performance and conducting sensitivity analysis of design parameters in two-body point absorber wave energy converters. The key novelty lies in the examination of design parameter sensitivity and their interaction effects on performance. The model utilizes the response surface method (RSM) in conjunction with central composite design to establish analytical equations for efficiently predicting the resonance frequency and peak generated power of the two-body wave energy converters based on geometric parameters and wave height. This eliminates the need for complex analytical solutions and boundary element simulations. The accuracy and reliability of the RSM prediction models are validated through state-of-the-art numerical simulations and analysis of variance (ANOVA). Using these RSM prediction models, the study proceeds to design and optimize two-body point absorbers for locations along the coastlines of the six Australian states, focusing on two objectives: maximizing peak output power and maximizing the power-to-weight ratio at each location. By incorporating the second optimization target, it is observed that impressive power output with smaller device dimensions or a higher power-to-weight ratio can be achieved across all six Australian states. The developed response surface method prediction model is a versatile mathematical framework applicable to all two-body point absorber wave energy converters and can be adapted for optimizing other types of wave energy converters with expansive search spaces. Australia was selected as a case study due to its abundant wave energy density along its southern shorelines. Notably, no similar studies addressing these specific aspects have been reported in the literature, making this work the first of its kind. • The performance prediction models of two body wave energy converters have been developed from design parameters. • The prediction models are validated against numerical simulations and the analysis of variance (ANOVA). • The sensitivity of design parameters and their interactions has been analyzed and disclosed. • The optimal dimensions for the maximum power and maximum power to weight ratio are derived for all the Australian seas. [ABSTRACT FROM AUTHOR]

Although consensual sending of sexts between adolescents is considered developmentally appropriate, it may also entail a range of negative consequences. Current sexting research lacks a comprehensive theoretical framework identifying a range of risk and protective factors underpinning adolescent consensual sending of sexts across individual, interpersonal, and distal levels. Further, there is a lack of systematic evaluation of how the importance of these factors may vary across adolescent age. This study investigated the utility of the Social Development Model to predict a range of risk and protective factors across individual, family, peer, school, and community-level factors. The sample included 1302 teenagers from Victoria, Australia (Mage = 14.54, SD = 1.14, 50.8% girls). Results indicated that 146 (11.7%) participants sent a sext (76 boys and 70 girls). Logistic regression analyses revealed that the Social Development Model accounted for 45.8% of variance in sexting, with greater likelihood of sending sexts being associated with older age, prior sexual activity, school sector, physical activity, lifetime substance use, greater depressive symptoms, sensation seeking, and perceived substance availability in the community. Multigroup analyses revealed that lifetime substance use was associated with a greater likelihood of sending sexts among younger teens. Among older adolescents, adaptive coping was associated with reduced engagement in sexting, while higher parental overcontrol and family conflict increased the odds of sending sexts. Overall, sexting is associated with a range of modifiable factors potentially amenable to intervention. [ABSTRACT FROM AUTHOR]

Background: The term 'pandemic paranoia' has been coined to refer to heightened levels of mistrust and suspicion towards other people specifically due to the COVID-19 pandemic. In this study, we examine the international prevalence of pandemic paranoia in the general population and its associated sociodemographic profile. Methods: A representative international sample of general population adults (N = 2510) from five sites (USA N = 535, Germany N = 516, UK N = 512, Australia N = 502 and Hong Kong N = 445) were recruited using stratified quota sampling (for age, sex, educational attainment) and completed the Pandemic Paranoia Scale (PPS). Results: The overall prevalence rate of pandemic paranoia was 19%, and was highest in Australia and lowest in Germany. On the subscales of the PPS, prevalence was 11% for persecutory threat, 29% for paranoid conspiracy and 37% for interpersonal mistrust. Site and general paranoia significantly predicted pandemic paranoia. Sociodemographic variables (lower age, higher population size and income, being male, employed and no migrant status) explained additional variance and significantly improved prediction of pandemic paranoia. Conclusions: Pandemic paranoia was relatively common in a representative sample of the general population across five international sites. Sociodemographic variables explained a small but significant amount of the variance in pandemic paranoia. [ABSTRACT FROM AUTHOR]

Objectives Damage accrual in SSc can be tracked using the Scleroderma Clinical Trials Consortium Damage Index (DI). Our goal was to develop a prediction model for damage accrual in SSc patients with early disease. Methods Using patients with <2 years disease duration from Canada and Australia as a derivation cohort, and from the Netherlands as a validation cohort, we used group-based trajectory modelling (GBTM) to determine 'good' and 'bad' latent damage trajectories. We developed a prediction model from this analysis and applied it to patients from derivation and validation cohorts. We plotted the actual DI trajectories of the patients predicted to be in 'good' or 'bad' groups. Results We found that the actual trajectories of damage accumulation for lcSSc and dcSSc were very different, so we studied each subset separately. GBTM found two distinct trajectories in lcSSc and three in dcSSc. We collapsed the two worse trajectories in the dcSSc into one group and developed a prediction model for inclusion in either 'good' or 'bad' trajectories. The performance of models using only baseline DI and sex was excellent with ROC AUC of 0.9313 for lcSSc and 0.9027 for dcSSc. Using this model, we determined whether patients would fall into 'good' or 'bad' trajectory groups and then plotted their actual trajectories which showed clear differences between the predicted 'good' and 'bad' cases in both derivation and validation cohorts. Conclusions A simple model using only cutaneous subset, baseline DI and sex can predict damage accumulation in early SSc. [ABSTRACT FROM AUTHOR]

Frailty is a biological syndrome that is associated with increased risks of morbidity and mortality. To assess the value of interventions to prevent or manage frailty, all important impacts on costs and outcomes should be estimated. The aim of this study is to describe the development and validation of an individual-based state transition model that predicts the incidence and progression of frailty and frailty-related events over the remaining lifetime of older Australians. An individual-based state transition simulation model comprising integrated sub models that represent the occurrence of seven events (mortality, hip fracture, falls, admission to hospital, delirium, physical disability, and transitioning to residential care) was developed. The initial parameterisation used data from the Survey of Health, Ageing, and Retirement in Europe (SHARE). The model was then calibrated for an Australian population using data from the Household, Income and Labour Dynamics in Australia (HILDA) Survey. The simulation model established internal validity with respect to predicting outcomes at 24 months for the SHARE population. Calibration was required to predict longer terms outcomes at 48 months in the SHARE and HILDA data. Using probabilistic calibration methods, over 1,000 sampled sets of input parameter met the convergence criteria across six external calibration targets. The developed model provides a tool for predicting frailty and frailty-related events in a representative community dwelling Australian population aged over 65 years and provides the basis for economic evaluation of frailty-focussed interventions. Calibration to outcomes observed over an extended time horizon would improve model validity. [ABSTRACT FROM AUTHOR]

Ross River virus (RRV) disease is one of the most epidemiological mosquito-borne diseases in Australia. Its major consequences on public health require building a precise and accurate model for predicting any forthcoming outbreaks. Several models have been developed by machine learning (ML) researchers, and many studies have been published as a result. Later, deep learning models have been introduced and shown tremendous success in forecasting, mainly the long short-term memory (LSTM), which performs significantly better than the traditional machine learning approaches. There are four common problems that previously developed models need to solve. They are exploding gradient, vanishing gradient, uncertainty and parameter bias. LSTM has already solved the first two problems, i.e. exploding and vanishing gradient problems, and the remaining two are overcome by n -LSTM. However, developing a prediction model for the RRV disease is a challenging task because it presents a wide range of symptoms, and there needs to be more accurate information available on the disease. To address these challenges, we propose a data-driven ensemble deep learning model using multi-networks of LSTM neural network for RRV disease forecasting in Australia. Data is collected between 1993 and 2020 from the Health Department of the Government of Australia. Data from 1993 to 2016 is taken to train the model, while the data of 2016–2020 is used as a test dataset. Previous research has demonstrated the efficacy of both ARIMA and exponential smoothing techniques in the field of time-series forecasting. As a result, our study sought to evaluate the performance of our proposed model in comparison to these established parametric methods, including ARIMA and ARMA, as well as the more recent deep learning approaches such as encoder–decoder and attention mechanism models. The results show that n -LSTM achieves higher accuracy and has a less mean-square error. We have also discussed the comparison of the models in detail. Such forecasting gives an insight into being well prepared and handling the situation of the outbreak. [ABSTRACT FROM AUTHOR]

• Formulate the logistic regression model with minimum classification error function. • Adopt classification maximum likelihood criterion to infer label information. • Compare results of the proposed model with others and show the effectiveness. • Investigate the most significant contributing factors to hit-and-run crashes. • Conduct sensitivity analysis of related parameters. • Provide implications for policies and counter-measures for hit-and-run crashes. Hit-and-run crashes not only degrade the morality, but also result in delays of medical services provided to victims. However, class imbalance problem exists as the number of hit-and-run crashes is much smaller than that of non-hit-and-run crashes. The missing label problem also exists in the crash analysis due to reasons like data barrier such that the information hidden in the unlabelled samples has not been effectively utilised. In this paper, a cost-sensitive semi-supervised logistic regression (CS3LR) model is proposed for hit-and-run analysis, in order to tackle class-imbalanced data distribution and missing label problem, based on the crash dataset of Victorian, Australia (2013–2019). By performing label estimation with logistic regression jointly utilising both labelled and unlabelled data with pseudo labels in a well-designed cost-sensitive semi-supervised maximum likelihood framework, the proposed model can obtain an unbiased likelihood parameter for hit-and-run prediction and analysis. Comparing the experimental results of CS3LR model with two logistic regression models and seven machine learning methods, better performance of CS3LR model is demonstrated. The most significant contributing factors to hit-and-run crashes extracted by CS3LR with only 10% labelled data show a high degree of consistency with the true contributing factors obtained by the supervised cost-sensitive logistic regression with complete hit-and-run labels. The effects of class-weighted ratio and hyper-parameter λ on the performance of hit-and-run crash prediction model have also been analysed. The results can further provide recommendations and implications on the policies and counter-measures for preventing hit-and-run collisions and crimes. The methodology proposed in this paper can also be employed to analyse crash data with other types of missing labels, such as crash severity. [ABSTRACT FROM AUTHOR]

Bayesian networks (BNs) are increasingly being used to model complex coastal processes due to their ability to integrate non-linear systems, their transparent probabilistic framework, and low computational cost. A BN may be suited to descriptive or predictive application. Descriptive BNs are highly calibrated models that are useful for better understanding the physics and causal relationships driving a system. Predictive BNs are generalisations of a system that have skill at predicting outside of the training domain. The predictive and descriptive usefulness of a BN depends on its complexity and the amount of data available to train it, but there is often a trade-off; higher descriptive skill comes at the cost of reduced predictive skill. To demonstrate the differences between predictive and descriptive BNs in a coastal engineering context, a BN to predict shoreline recession caused by coastal storm events is developed and tested using an extensive 10-year dataset incorporating 137 individual storms events monitored at Narrabeen-Collaroy Beach, Australia. A parsimonious approach to BN development is used to separately determine the optimum predictive and descriptive BNs for this dataset. Results show that for this dataset two quite different BNs can be developed: one that is optimized to achieve the highest predictive skill, and a second network that is optimized to maximize descriptive skill. The optimum predictive BN is found to comprise 3 nodes (variables) and can predict the shoreline recession caused by unseen storm events with a skill of 65%. The optimum descriptive BN is composed of 5 nodes and can reproduce 88% of the training dataset, but with more limited predictive capabilities. The uses and limitations of these two different approaches to BN formulation are illustrated with example applications to coastal process modelling. It is anticipated that the insights provided in this paper will help to clarify the further development of Bayesian Networks applied to coastal modelling. [ABSTRACT FROM AUTHOR]

Objective: To develop and internally validate risk prediction models for adolescent onset and persistence of eating disorders. Methods: N = 963 Australian adolescents (11–19 years) in the EveryBODY Study cohort completed online surveys in 2018 and 2019. Models were built to predict 12‐month risk of (1) onset, and (2) persistence of a DSM‐5 eating disorder. Results: Onset Model. Of the n = 687 adolescents without an eating disorder at baseline, 16.9% were identified with an eating disorder after 12 months. The prediction model was based on evidence‐based risk factors for eating disorder onset available within the dataset (sex, body mass index percentile, strict weight loss dieting, history of bullying, psychological distress, weight/shape concerns). This model showed fair discriminative performance (mean AUC =.75). The most important factors were psychological distress, weight and shape concerns, and female sex. Diagnostic Persistence Model. Of the n = 276 adolescents with an eating disorder at baseline, 74.6% were identified as continuing to meet criteria for an eating disorder after 12 months. The prediction model for diagnostic persistence was based on available evidence‐based risk factors for eating disorder persistence (purging, distress, social impairment). This model showed poor discriminative performance (mean AUC =.65). The most important factors were psychological distress and self‐induced vomiting for weight control. Discussion: We found preliminary evidence for the utility of a parsimonious model for 12‐month onset of an eating disorder among adolescents in the community. Future research should include additional evidence‐based risk factors and validate models beyond the original sample. Public Significance: This study demonstrated the feasibility of developing parsimonious and accurate models for the prediction of future onset of an eating disorder among adolescents. The most important predictors in this model included psychological distress and weight and shape concerns. This study has laid the ground work for future research to build and test more accurate prediction models in diverse samples, prior to translation into a clinical tool for use in real world settings to aid decisions about referral to early intervention. [ABSTRACT FROM AUTHOR]

Fire behaviour and spread predictions guides suppression strategies and public warnings during wildfires. The scientific understanding of fire behaviour forms the core of these predictions, but is incomplete, and expert judgement and experience are required to augment the evidence based knowledge. Amicus is a new decision support system that implements contemporary, published and operationalised bushfire behaviour models (e.g. rate of spread, flame height, fireline intensity, spotting distance) in the Australian bushfire context. It enables the inclusion of expert judgement and local knowledge, allows users to analyse temporal trends and uncertainty in inputs, and facilitates reliable and practical predictions. This paper provides a comprehensive overview of Amicus, including its operation and functionality, identifies the boundaries of the current understanding of fire science, discusses the major limitations in existing knowledge, and provides a framework for allowing deterministic and anecdotal/local knowledge to be incorporated into formal fire behaviour predictions. [ABSTRACT FROM AUTHOR]

The measurement of functional outcomes following severe trauma has been widely recognised as a priority for countries with developed trauma systems. In this respect, the Functional Capacity Index (FCI), a multi-attribute index which has been incorporated into the most recent Abbreviated Injury Scale (AIS) dictionary, is potentially attractive as it offers 12-month functional outcome predictions for patients captured by existing AIS-coded datasets. This review paper outlines the development, construction and validation of the predictive form of the FCI (termed the pFCI), the modifications made which produced the currently available 'revised' pFCI, and the extent to which the revised pFCI has been validated and used. The original pFCI performed poorly in validation studies. The revised pFCI does not address many of the identified limitations of the original version, and despite the ready availability of a truncated version in the AIS dictionary, it has only been used in a handful of studies since its introduction several years ago. Additionally, there is little evidence for its validity. It is suggested that the pFCI should be better validated, whether in the narrow population group of young, healthy individuals for which it was developed, or in the wider population of severely injured patients. Methods for accounting for the presence of multiple injures (of which two have currently been used) should also be evaluated. Many factors other than anatomical injury are known to affect functional outcomes following trauma. However, it is intuitive that any model which attempts to predict the ongoing morbidity burden in a trauma population should consider the effects of the injuries sustained. Although the revised pFCI potentially offers a low-cost assessment of likely functional limitations resulting from anatomical injury, it must be more rigorously evaluated before more comprehensive predictive tools can be developed from it. [ABSTRACT FROM AUTHOR]

Cast iron was the dominant material for buried pipes for water networks prior to the 1970s in Australia and overseas. At present, many water utilities still have a significant amount of ageing cast iron pipes. Cast iron is a brittle material and when large diameter cast iron pipes (diameters above 300 mm) further deteriorate, the consequences of failure can be substantial. Focusing on the likelihood of failure to assist risk assessment, this paper examines the performance of large-diameter cast iron pipes using probabilistic analysis, incorporating uncertainties of governing variables. Finite element analysis is first conducted to study the physical mechanism of buried pipes subjected to complex environmental conditions. The deterioration of cast iron pipes due to corrosion is considered on the basis of recent research. The uncertainties of governing variables, such as the physical properties of soil, cast iron, water pressure and corrosion patterns, in pipe failure risk assessment are considered. Using probabilistic physical modelling, the lifetime probability of failure is derived and a time-dependent sensitivity analysis is presented. The results of this probabilistic physical modelling are compared with cohorts of failure data from two Australian water utilities to examine the underlying trends from both physical modelling and statistical analysis. [ABSTRACT FROM AUTHOR]

Background: The purpose of the study was to explore, analyse, and describe the patterns of public dental service utilisation among the refugee populations in Victoria, Australia, and determine their predictors at the individual and contextual levels. Methods: Data on the refugees who attended Victorian public dental services between July 2016 to June 2020 was gathered from the Dental Health Program dataset. Latent profile analysis was used to identify discrete groups among the refugee clientele with similar mean utilisation patterns across six indicator variables describing the attributes of dental services received and the site of care provision, over the study period. Multilevel multinomial logistic regression analysis was performed to examine the individual and contextual level correlates of the identified utilisation patterns. Results: Six distinct profiles of public dental service utilisation were identified among the study population (n = 25,542). The largest group comprised refugees predominantly using restorative services under general course of care (38.10%), followed by extraction services under emergency course of care (23.50%). Only a small proportion were estimated as having a higher mean utilisation of preventive services under general course of care (9.10%). Multilevel analysis revealed that the following variables had a significant association with refugee utilisation pattern: at the individual-level – demographic and ethnic attributes including age, gender, region of birth, preferred language for communication, use of language interpreter services, and type of eligibility card; at the contextual-level – characteristics of refugees' neighbourhood of residence including urbanicity, socioeconomic disadvantage, delivery of Refugee Health Program at the community health centres, and spatial accessibility to public dental services via driving and public transit modes of travel. Conclusions: The study represents a significant step towards the development of an evidence-based knowledge around public dental service utilisation among Victorian refugees. Overall, the study findings reiterate the critical need for targeted strategies to promote the importance of routine dental visits, oral disease prevention, and timely intervention among refugee groups. [ABSTRACT FROM AUTHOR]

Aim: First, to identify which aspects of missed care accurately define the integration of care and context of care dimensions of the Fundamentals of Care Framework. Second, to test the Framework for validity and reliability and lastly, to explore how leadership influences care integration. Design: A non‐experimental research design using self‐audit data collected information about variations in nursing care as exemplars for dimensions of the Framework. Methods: A multi‐variate approach using path analysis was used to apply the consensus scores of 3079 Australian residential care nurses and carers to define the dimensions of the Framework. Results/Findings In the Australian residential care setting, the factors that define both the contexts of care and the integration of care dimensions constructs are now empirically established. The most direct predictor for the integration of care dimension arises from both the leadership and resource allocation variables, while the remaining context of care factors have indirect but significant effects. The integration of psychosocial care in the residential care sector is not influenced by any of the Framework's context‐based factors. Conclusion: The component variables of the Framework show both good reliability and convergent validity. These findings confirm a predictive relationship exists between the elements of the context of care and the different types of nursing activities that form the integration of the care dimension, including organizational leadership. [ABSTRACT FROM AUTHOR]

Older people prefer to remain living in their own home for as long as possible; however, many require support to do so through health and other care services provided in the home. This study aimed to explore the trends in usage of a home-based care service by older people in metropolitan Melbourne and factors associated with unplanned hospitalisations. This longitudinal study analysed episodes of home-based care for people aged ≥65 years between 2006 and 2015. An episode of care was defined as the period of time during which the home care services were provided to the client. Care episodes culminated in a planned discharge from the service or an unplanned hospitalisation. Descriptive statistics and multivariable logistic regression were utilised to investigate the characteristics associated with unplanned hospitalisations. Utilisation of home-based care services over the 10-year period showed an increasing rate of use by people aged ≥85 years and a reduced usage rate by females aged 70–84 years and males 75–79 years old. Of 170,001 episodes of care, 43,608 (25.7%) resulted in an unplanned hospitalisation. Home-based care delivered to people aged ≥85 years showed an increasing rate of episodes ending in an unplanned transfer to the hospital. Between 2006 and 2015, individuals aged 85–89 years displayed a rate increase of 18.7% in episodes ending in an unplanned hospitalisation; for those aged ≥90 years, the rate rise was 43.6%. Factors associated with an unplanned hospitalisation included advancing age, male gender, living alone, cognitive dysfunction, and the complexity of medical issues. Health policy has focussed on providing services to enable older people to remain in their own home. The increasing rate of unplanned hospitalisations for community-dwellers aged ≥85 years suggests more support is required to enable ageing in place. [ABSTRACT FROM AUTHOR]

It is critically meaningful to accurately predict the ionospheric F2 layer critical frequency (foF2), which greatly limits the efficiency of communications, radar, and navigation systems. This paper introduced the entropy weight method to develop the combination prediction model (CPM) for long-term foF2 at Darwin (12.4° S, 131.5° E) in Australia. The weight coefficient of each individual model in the CPM is determined by using the entropy weight method after completing the simulation of the individual model in the calibration period. We analyzed two sets of data to validate the method used in this study: One set is from 2000 and 2009, which are included in the calibration period (1998–2016), and the other set is outside the calibration cycle (from 1997 and 2017). To examine the performance, the root mean square error (RMSE) of the observed monthly median foF2 value, the proposed CPM, the Union Radio Scientifique Internationale (URSI), and the International Radio Consultative Committee (CCIR) are compared. The yearly RMSE average values calculated from CPM were less than those calculated from URSI and CCIR in 1997, 2000, 2009, and 2017. In 2000 and 2009, the average percentage improvement between CPM and URSI is 9.01%, and the average percentage improvement between CPM and CCIR is 13.04%. Beyond the calibration period, the average percentage improvement between CPM and URSI is 13.2%, and the average percentage improvement between CPM and CCIR is 12.6%. The prediction results demonstrated that the proposed CPM has higher precision of prediction and stability than that of the URSI and CCIR, both within the calibration period and outside the calibration period. [ABSTRACT FROM AUTHOR]

Juvenile populations face a substantial risk of emotional, physical, and psychological harm as a result of bullying and cyberbullying experiences. As a result, there is a need to assess the situational and individual factors contributing to the risk of bullying victimization. There is, however, little research examining cyberbullying victimization using frequency-based measures of victimization. To address this gap in the literature, this study utilized a sample of over 37,000 youth from South Australia to explore the risk factors associated with cyberbullying victimization through a routine activities framework while controlling for verbal, social, and physical bullying. The findings noted partial support for the routine activities theory framework to account for cyberbullying victimization. Additionally, the study found differences in cyberbullying risk factors relative to the frequency with which it was reported, as well as the role of school support from peers and adults in increasing risks. [ABSTRACT FROM AUTHOR]

Carrying a laser Doppler instrument, the Aeolus satellite was launched in 2018, becoming the first mission for atmospheric wind profile measurements from space. Before utilizing the Aeolus winds for different applications, evaluating their data quality is essential. With the help of ground-based wind profiling radar measurements and the European Centre for Medium-Range Weather Forecasts (ECMWF) model equivalents, this study quantifies the error characteristics of Aeolus L2B (baseline-11) near-real-time horizontal line-of-sight winds across Australia during October 2020–March 2021 by using both inter-comparison and triple collocation analysis. The results of the inter-comparison analysis indicate that both Rayleigh-clear winds and Mie-cloudy winds are in good agreement with the ground-based radar measurements with overall absolute mean biases smaller than 0.7 m s -1 and correlation coefficients larger than or equal to 0.9. Moreover, assuming the radar measurements as the reference data set, Mie-cloudy winds are shown to be more precise than Rayleigh-clear winds with an overall random error of 4.14 and 5.81 m s -1 , respectively. Similar results were also found from triple collocation analysis, with error standard deviations of 5.61 and 3.50 m s -1 for Rayleigh-clear winds and Mie-cloudy winds. In addition, the Mie channel is shown to be more capable of capturing the wind in the planetary boundary layer (< 1500 m). The findings of this study demonstrate the good performance of space-borne Doppler lidar for wind profiling and provide valuable information for data assimilation in numerical weather prediction. [ABSTRACT FROM AUTHOR]

• A spatial mode-based calibration model is developed to post-process short-term forecasts of precipitation fields. • The calibration model directly embeds spatial structure into calibrated ensemble forecasts. • Calibrated ensemble forecasts are shown to be of high quality at both grid-cell and basin scales. Statistical calibration of precipitation forecasts from numerical weather prediction (NWP) models is routinely performed grid-cell by grid-cell, aiming to produce accurate and reliable ensemble forecasts for precipitation fields. Calibrated ensemble members from different grid-cells are then connected using ensemble reordering to form spatially structured ensemble forecasts. However, ensemble reordering approaches, such as the well-known Schaake shuffle method, are often criticized for not considering real physical atmospheric states of precipitation events. In this paper, we propose a spatial mode-based calibration (SMoC) model for post-processing forecast precipitation fields and producing ensemble forecasts with an inbuilt spatial structure, so that ensemble reordering is not required. The SMoC model is developed based on spatial modes derived from empirical orthogonal function (EOF) analyses of precipitation fields and linear regressions of derived EOF expansion coefficients of the first few dominant modes. Unlike conventional calibration models that are applied to forecast grid-cells individually, SMoC is applied to the whole forecast fields, and the spatial structure is inherently present in calibrated ensemble forecasts. There is therefore no need to rely on ensemble reordering for spatial reconstruction. The performance of SMoC is evaluated by applying it to NWP forecasts of substantive precipitation events over the Brisbane drainage basin in eastern Australia. Cross-validated results show that SMoC calibrated forecasts are of high quality at both grid-cell and basin scales. The spatial structure of precipitation is found to be well embedded in the ensemble members of the calibrated forecasts for the basin. [ABSTRACT FROM AUTHOR]

In low-to-moderate seismicity (intraplate) regions where locally recorded strong motion data are too scare for conventional regression analysis, stochastic simulations based on seismological modelling have often been used to predict ground motions of future earthquakes. This modelling methodology has been practised in Central and Eastern North America (CENA) for decades. It is cautioned that ground motion prediction equations (GMPE) that have been developed for use in CENA might not always be suited for use in another intraplate region because of differences in the crustal structure. This paper introduces a regionally adjustable GMPE, known as the component attenuation model (CAM), by which a diversity of crustal conditions can be covered in one model. Input parameters into CAM have been configured in the same manner as a seismological model, as both types of models are based on decoupling the spectral properties of earthquake ground motions into a generic source factor and a regionally specific path factor (including anelastic and geometric attenuation factors) along with a crustal factor. Unlike seismological modelling, CAM is essentially a GMPE that can be adapted readily for use in different regions (or different areas within a region) without the need of undertaking any stochastic simulations, providing that parameters characterising the crustal structure have been identified. In addressing the challenge of validating a GMPE for use in an area where instrumental data are scarce, modified Mercalli intensity (MMI) data inferred from peak ground velocity values predicted by CAM are compared with records of MMI of past earthquake events, as reported in historical archives. South-Eastern Australia (SEA) and South-Eastern China (SEC) are the two study regions used in this article for demonstrating the viability of CAM as a ground motion prediction tool in an intraplate environment. [ABSTRACT FROM AUTHOR]

• The LSTM method is proposed to construct the LUBE approach-based prediction interval for wind power forecast. • An innovative fuzzy approach is suggested to adjust the prediction interval coverage probability. • CDOA is applied to achieve the most optimal prediction intervals. This paper proposes a novel deep learning method based on lower-upper-bound-estimation (LUBE) and long short-term memory (LSTM) models to capture the uncertainty effects in the power generation of wind turbines. The LUBE model deploys the prediction interval concept as well as the LSTM approach to make a robust and resilient model. The LSTM approach is applied to construct the optimal prediction intervals with an appropriate upper bound and lower bound with a certain confidence level. In addition, the fuzzy set theory is proposed in the model to let adjust LSTM parameters based on the decision maker's ideas. This approach empowers operators to satisfy both coverage probability and width indicators of prediction intervals to achieve the optimal solution. The collective decision optimization algorithm is introduced to provide more flexibility in tuning the LSTM parameters. The efficiency and quality of the proposed scheme are studied using some datasets gathered from the Australia wind farms. [Display omitted] [ABSTRACT FROM AUTHOR]