Search

In this paper, 1,538 papers retrieved with the keywords "sports artificial intelligence (AI)" on the Web of Science database since 2007 were taken as the data source, and the Cite Space V software was used to visualize and analyze them. A visual knowledge graph was used to streamline the countries, institutions and authors conducting sports AI research, discipline distribution, research hotspots and development trends in the past 15 years. Subsequently, its development direction and research progress were discussed. Sports AI was widely distributed, with the US, China and the UK leading the way. The most prolific authors and teams in research on sports AI were concentrated in American universities. Their main research direction is to develop and improve smart wearable devices based on machine learning and deep learning technologies for different groups of people. Research on sports AI involved multiple disciplines, which mainly applied and referred to research methodologies and theories on engineering, computer science and sports science. It could be seen from the frequency and centrality of keywords that in the current field of sports AI, machine learning is the main direction, artificial neural networks is the main algorithm, and practical and empirical research based on data mining is the focus. The research hotspots were divided into three major clusters: physical health promotion, sports injury prevention and control, and athletic performance enhancement. How to introduce intelligent technology into sports for a perfect integration still has an arduous and long way to go. Future development requires joint efforts and participation of scientific researchers, professionals and common people. [ABSTRACT FROM AUTHOR]

Across the globe, governments are developing policies and strategies to reduce carbon emissions to address climate change. Monitoring the impact of governments' carbon reduction policies can significantly enhance our ability to combat climate change and meet emissions reduction targets. One promising area in this regard is the role of artificial intelligence (AI) in carbon reduction policy and strategy monitoring. While researchers have explored applications of AI on data from various sources, including sensors, satellites, and social media, to identify areas for carbon emissions reduction, AI applications in tracking the effect of governments' carbon reduction plans have been limited. This study presents an AI framework based on long short-term memory (LSTM) and statistical process control (SPC) for the monitoring of variations in carbon emissions, using UK annual CO2 emission (per capita) data, covering a period between 1750 and 2021. This paper used LSTM to develop a surrogate model for the UK's carbon emissions characteristics and behaviours. As observed in our experiments, LSTM has better predictive abilities than ARIMA, Exponential Smoothing and feedforward artificial neural networks (ANN) in predicting CO2 emissions on a yearly prediction horizon. Using the deviation of the recorded emission data from the surrogate process, the variations and trends in these behaviours are then analysed using SPC, specifically Shewhart individual/moving range control charts. The result shows several assignable variations between the mid-1990s and 2021, which correlate with some notable UK government commitments to lower carbon emissions within this period. The framework presented in this paper can help identify periods of significant deviations from a country's normal CO2 emissions, which can potentially result from the government's carbon reduction policies or activities that can alter the amount of CO2 emissions. [ABSTRACT FROM AUTHOR]

Nowadays, the load monitoring system is an important element in smart buildings to reduce energy consumption. Nonintrusive load monitoring (NILM) is utilized to determine the power consumption of each appliance in smart homes. The main problem of NILM is how to separate each appliance's power from the signal of aggregated consumption. In this regard, this paper presents a combination between particle swarm optimization (PSO) and artificial neural networks (ANNs) to identify electrical appliances for demand‐side management. ANN is applied in NILM as a load identification task, and PSO is used to train the ANN algorithm. This combination enhances the NILM technique's accuracy, which is further verified by experiments on different datasets like Reference Energy Disaggregation Dataset, UK Domestic Appliance‐Level ElectricityUK‐DALE, and Indian data for Ambient Water and electricity Sensing. The high accuracy of the proposed algorithm is verified by comparisons with state of the art methods. Compared with other approaches, the total mean absolute error has decreased from 39.3566 to 18.607. Also, the normalized root mean square error (NRMSE) method has been used to compare the measured and predicted results. The NRMSE is in the range of 1.719%–16.514%, which means perfect consistency. This demonstrates the effectiveness of the proposed approach for home energy management. Furthermore, customer behavior has been studied, considering energy costs during day hours. [ABSTRACT FROM AUTHOR]

Introduction: Postoperative complications affect up to 15% of surgical patients constituting a major part of the overall disease burden in a modern healthcare system. While several surgical risk calculators have been developed, none have so far been shown to decrease the associated mortality and morbidity. Combining deep neural networks and genomics with the already established clinical predictors may hold promise for improvement. Methods: The UK Biobank was utilized to build linear and deep learning models for the prediction of surgery relevant outcomes. An initial GWAS for the relevant outcomes was initially conducted to select the Single Nucleotide Polymorphisms for inclusion in the models. Model performance was assessed with Receiver Operator Characteristics of the Area Under the Curve and optimum precision and recall. Feature importance was assessed with SHapley Additive exPlanations. Results: Models were generated for atrial fibrillation, venous thromboembolism and pneumonia as genetics only, clinical features only and a combined model. For venous thromboembolism, the ROC-AUCs were 60.1% [59.6%-60.4%], 63.4% [63.2%-63.4%] and 66.6% [66.2%-66.9%] for the linear models and 51.5% [49.4%-53.4%], 63.2% [61.2%-65.0%] and 62.6% [60.7%-64.5%] for the deep learning SNP, clinical and combined models, respectively. For atrial fibrillation, the ROC-AUCs were 60.3% [60.0%-60.4%], 78.7% [78.7%-78.7%] and 80.0% [79.9%-80.0%] for the linear models and 59.4% [58.2%-60.9%], 78.8% [77.8%-79.8%] and 79.8% [78.8%-80.9%] for the deep learning SNP, clinical and combined models, respectively. For pneumonia, the ROC-AUCs were 50.1% [49.6%-50.6%], 69.2% [69.1%-69.2%] and 68.4% [68.0%-68.5%] for the linear models and 51.0% [49.7%-52.4%], 69.7% [.5%-70.8%] and 69.7% [68.6%-70.8%] for the deep learning SNP, clinical and combined models, respectively. Conclusion: In this report we presented linear and deep learning predictive models for surgery relevant outcomes. Overall, predictability was similar between linear and deep learning models and inclusion of genetics seemed to improve accuracy. [ABSTRACT FROM AUTHOR]

Utilizing received signal strength indicators (RSSIs) is one of the most widely used cost-effective techniques for the localization and tracking of mobile targets using wireless sensor networks (WSNs). Significant estimation errors in target localization are caused by the noise variability in received signal strength indicator (RSSI) readings, particularly in indoor environments. In this paper, a new method is proposed based on a Nomadic People Optimizer (NPO) and Artificial Neural Network (ANN) to overcome the weaknesses of the traditional method, which is called NPO+ANN algorithm to improve the accuracy of target localization and tracking. This study presents a novel method for estimating the initial location of a single target moving in a 2-D space within a wireless sensor network (WSN) that combines hybrid NPO+ANN as a substitute for the common RSSI-based method. The Unscented Kalman Filter (UKF) is then used to improve and fine-tune these preliminary estimations to increase target localization accuracy, the research suggests NPO+ANN+UKF. The simulation outcome validates the NPO+ANN+UK architecture's capability for solving the real-time target tracking issue in WSN utilizing RSSI. The NPO+ANN+UKF provides a remarkable improvement of 98.2%, and 88% over the traditional RSSI, and NPO+ANN, respectively. [ABSTRACT FROM AUTHOR]

A variant of membrane computing models called Spiking Neural P systems (SNP systems) closely mimics the structure and behavior of biological neurons. As third-generation neural networks, SNP systems have flexible architectures allowing the design of bio-inspired machine learning algorithms. This paper proposes Modular Spiking Neural P (MSNP) systems to solve image classification problems, a novel SNP system to be applied in scenarios where hundreds or even thousands of different classes are considered. A main issue to face in such situations is related to the structural complexity of the network. MSNP systems devised in this work allow to approach the general classification problem by dividing it in smaller parts, that are then faced by single entities of the network. As a benchmark dataset, the Oxford Flowers 102 dataset is considered, consisting of more than 8000 pictures of flowers belonging to the 102 species commonly found in the UK. These classes sometimes present large variations within them, may be also very similar to one another, and different images of the same subject may differ a lot. The work describes the architecture of the MSNP system, based on modules focusing on a specific class, their training phase, and the evaluation of the model both concerning result accuracy as well as energy consumption. Experimental results on image classification problems show that the model achieves good results, but is strongly connected to image quality, mainly depending on the frequency of images, remarkable changes of pose, images not centered, and subject mostly not shown. [ABSTRACT FROM AUTHOR]

Rainfall-runoff (R-R) modelling is used to study the runoff generation of a catchment. The quantity or rate of change measure of the hydrological variable, called runoff, is important for environmental scientists to accomplish water-related planning and design. This paper proposes (i) an integrated model namely EO-ELM (an integration of equilibrium optimizer (EO) and extreme learning machine (ELM)) and (ii) a deep neural network (DNN) for one day-ahead R-R modelling. The proposed R-R models are validated at two different benchmark stations of the catchments, namely river Teifi at Glanteifi and river Fal at Tregony in the UK. Firstly, a partial autocorrelation function (PACF) is used for optimal number of lag inputs to deploy the proposed models. Six other well-known machine learning models, called ELM, kernel ELM (KELM), and particle swarm optimization-based ELM (PSO-ELM), support vector regression (SVR), artificial neural network (ANN) and gradient boosting machine (GBM) are utilized to validate the two proposed models in terms of prediction efficiency. Furthermore, to increase the performance of the proposed models, paper utilizes a discrete wavelet-based data pre-processing technique is applied in rainfall and runoff data. The performance of wavelet-based EO-ELM and DNN are compared with wavelet-based ELM (WELM), KELM (WKELM), PSO-ELM (WPSO-ELM), SVR (WSVR), ANN (WANN) and GBM (WGBM). An uncertainty analysis and two-tailed t-test are carried out to ensure the trustworthiness and efficacy of the proposed models. The experimental results for two different time series datasets show that the EO-ELM performs better in an optimal number of lags than the others. In the case of wavelet-based daily R-R modelling, proposed models performed better and showed robustness compared to other models used. Therefore, this paper shows the efficient applicability of EO-ELM and DNN in R-R modelling that may be used in the hydrological modelling field. [ABSTRACT FROM AUTHOR]

Numerous Artificial Intelligence (AI) solutions are available for achieving thermal comfort. They were either trained with limited datasets or using personalized training with limited field studies. This work assessed the model that used the ASHRAE multiple databases as the shallow supervised learning dataset for an Artificial Neural Network (ANN) based controller suitable for the residential dwellings' node. The learning accuracy can be increased to 96.1%. This paper presented the field studies to show the model performances for the common UK dwellings: the prior 1970s, the new, modular, refurbished, and the use of new materials to improve indoor thermal performance. The result shows that the model was able to perform in different environments and able to acknowledge adaptive human comfort. This was shown by the ability to represent 98.90% of the ASHRAE Standard 55 data, 6.06% improvement from the previous research. As a result, the broader comfort zone acknowledgement can lead to energy saving whilst maintaining comfort by the possibility of lowering the temperature set point. This study also proves that further energy savings can be acquired from the occupants' presence, scheduling, and activities. These factors can increase the comfort probability to more than 10%. [Display omitted] • This paper addresses the gap between the physiology and the psychology thermal comfort approach, dominated by AI solutions. • The work shows a wider comfort zone which has been identified to become progressively narrower over the past several decades. • The field studies represent major UK-dwelling cases that weren't addressed in the previous Artificial Intelligence approach. • The occupant presence and scheduling can contribute to more than a 10% increase in comfort which impacts energy saving. • This work highlights the possibility of achieving indoor thermal comfort with less energy for more sustainable dwellings. [ABSTRACT FROM AUTHOR]

• Trapping indices stabilization is lagged as injection period is active. • Greater CO 2 cumulative volume occurs as reservoir pressure is far from caprock fracture pressure. • Larger closures will require pressure management-based brine production to reach theoretical storage capacity. • ML-based CO 2 storage modelling preliminary de-risked saline aquifers lacking numerical models. This paper presents a machine learning (ML) model designed to speed up the appraisal of geologic CO 2 storage sites by predicting the effectiveness in trapping and accommodating CO 2 in saline aquifers. Considering the urgency of de-risking as much geologic CO 2 storage resources as possible to help with CO 2 emission reduction Paris' goal, ML-based reservoir modelling has been documented as proper tool when a faster, good approximate, and less expensive approach is needed to surrogate multiple assessments of storage sites traditionally performed by long-timeframe and multi-stage geologic CO 2 storage numerical modelling approach. In this paper, a case study is presented. It consisted of a dataset comprised of six geologic aquifer parameters (CO 2 residual saturation, horizontal permeability, vertical to horizontal permeability ratio, porosity, brine salinity, and CO 2 flow rate) and elapsed time as input data, and as output data the CO 2 trapping mechanism indices (Solubility Trapping Index, Residual Trapping Index, and Structural Trapping Index) along with the dynamic storage capacity (CO 2 injected volume). Such dataset was used to train and test the artificial neural network (ANN) model. The dataset was generated from thousands of post-processed numerical realizations at several injection periods by applying design of experiment using a synthetic aquifer model derived from the Bunter Sandstone Closure 36 aquifer numerical model, from the Southern North Sea. The ANN architecture designed in Python consisted of 3 hidden layers and 40 nodes and its performance was assessed using the coefficient of determination (R2) and root mean squared error (RMSE). The ANN performance showed accuracies (R2) for training and testing with 96% and 95% of precision respectively. Practical application of the ANN model was successfully implemented to CO 2 storage aquifer sites selected from CO2Stored® database which lacking numerical models (Bunter Closure 3, 9, 35, and 40), obtaining at the end of 100-years injection case a Structural, Residual, and Solubility Trapping Index averaging 83%, 11%, and 6% respectively, with low variation coefficient indicating that trapping indices were predicted properly because aquifers selected for ANN model application have similar structures (dome-like shape) and reservoir properties. In addition, CO 2 injected volume predictions for 100-years injection case were ranging from 397 to 456 million ton (Mt) totalling 2.1 giga ton (Gt) of potential storage capacity which represents 70% of total theoretical volumetric capacity. These results show the significant impact to accelerate geologic CO 2 storage sites assessment by implementing ML-based modelling to preliminary de-risking groups of saline aquifers and reasonably consider them technically feasible CO 2 storage sites in UK. [ABSTRACT FROM AUTHOR]

This paper presents a systematic investigation into modelling capacities of three conventional data-driven modelling techniques, namely, wavelet-based artificial neural network (WANN), support vector regression (SVR) and deep belief network (DBN) for multi-step ahead stream flow forecasting. To evaluate the effectiveness of these modelling techniques, hydro-meteorological hourly datasets from three case-study rivers located in the UK have been used. A heuristic performance analysis of the modelling schemes has been conducted by systematically analysing the key statistics that measure magnitude, scatter and density of model errors. Finally, for each of the modelling techniques, the performance deterioration rate in time was estimated. The results show that the SVR model can forecast quite accurately up to one to two hours ahead but its performance deteriorates gradually from three hours onwards. Further it has been found that the WANN model performs better when the overall non-linearity of the system increases, whereas the DBN model appeared to show consistently poor predictive capabilities when compared to the other models presented herein. The authors conclude by stating that, for any selected model, it is possible to use an identical model structure for up to two steps ahead forecasting. Models need to be re-configured beyond that limit. [ABSTRACT FROM AUTHOR]

Water demand forecasting is an essential task for water utilities, with increasing importance due to future societal and environmental changes. This paper suggests a new methodology for water demand forecasting, based on model stacking and bias correction that predicts daily demands for groups of ~120 properties. This methodology is compared to a number of models (Artificial Neural Networks – ANNs, Generalised Linear Models – GLMs, Random Forests – RFs, Gradient Boosting Machines – GBMs, Extreme Gradient Boosting – XGBoost, and Deep Neural Networks – DNNs), using real consumption data from the UK, collected at 15–30 minute intervals from 1,793 properties. Results show that the newly proposed stacked model that comprises of RFs, GBMs, DNNs, and GLMs consistently outperformed other water demand forecasting techniques (peak R2 = 74.1%). The stacked model's accuracy on peak consumption days further improved by applying a bias correction method on the model's output. [ABSTRACT FROM AUTHOR]

Purpose: This study examines the effectiveness of automatic speech recognition (ASR) for individuals with speech disorders, addressing the gap in performance between read and conversational ASR. We analyze the factors influencing this disparity and the effect of speech mode-specific training on ASR accuracy. Method: Recordings of read and conversational speech from 27 individuals with various speech disorders were analyzed using both (a) one speaker-independent ASR system trained and optimized for typical speech and (b) multiple ASR models that were personalized to the speech of the participants with disordered speech. Word error rates were calculated for each speech model, read versus conversational, and subject. Linear mixed-effects models were used to assess the impact of speech mode and disorder severity on ASR accuracy. We investigated nine variables, classified as technical, linguistic, or speech impairment factors, for their potential influence on the performance gap. Results: We found a significant performance gap between read and conversational speech in both personalized and unadapted ASR models. Speech impairment severity notably impacted recognition accuracy in unadapted models for both speech modes and in personalized models for read speech. Linguistic attributes of utterances were the most influential on accuracy, though atypical speech characteristics also played a role. Including conversational speech samples in model training notably improved recognition accuracy. Conclusions: We observed a significant performance gap in ASR accuracy between read and conversational speech for individuals with speech disorders. This gap was largely due to the linguistic complexity and unique characteristics of speech disorders in conversational speech. Training personalized ASR models using conversational speech significantly improved recognition accuracy, demonstrating the importance of domain-specific training and highlighting the need for further research into ASR systems capable of handling disordered conversational speech effectively. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of this paper is to present an approach to address the overfitting and collinearity problems that frequently occur in predictive cost estimating models for construction practice. A case study, modeling the cost of preliminaries is proposed to test the robustness of this approach. Design/methodology/approach: A hybrid approach is developed based on the Akaike information criterion (AIC) and principal component regression (PCR). Cost information for a sample of 204 UK school building projects is collected involving elemental items, contingencies (risk) and the contractors' preliminaries. An application to estimate the cost of preliminaries for construction projects demonstrates the method and tests its effectiveness in comparison with such competing models as: alternative regression models, three artificial neural network data mining techniques, case-based reasoning and support vector machines. Findings: The experimental results show that the AIC–PCR approach provides a good predictive accuracy compared with the alternatives used, and is a promising alternative to avoid overfitting and collinearity. Originality/value: This is the first time an approach integrating the AIC and PCR has been developed to offer an improvement on existing methods for estimating construction project Preliminaries. The hybrid approach not only reduces the risk of overfitting and collinearity, but also results in better predictability compared with the commonly used stepwise regression. [ABSTRACT FROM AUTHOR]

This paper presents an adaptive control system for coordinated metro operations with flexible train composition by using a multi-agent deep reinforcement learning (MADRL) approach. The control problem is formulated as a Markov decision process (MDP) with multiple agents regulating different service lines in a metro network with passenger transfer. To ensure the overall computational effectiveness and stability of the control system, we adopt an actor–critic reinforcement learning framework in which each control agent is associated with a critic function for estimating future system states and an actor function deriving local operational decisions. The critics and actors in the MADRL are represented by multi-layer artificial neural networks (ANNs). A multi-agent deep deterministic policy gradient (MADDPG) algorithm is developed for training the actor and critic ANNs through successive simulated transitions over the entire metro network. The developed framework is tested with a real-world scenario in Bakerloo and Victoria Lines of London Underground, UK. Experiment results demonstrate that the proposed method can outperform previous centralized optimization and distributed control approaches in terms of solution quality and performance achieved. Further analysis shows the merits of MADRL for coordinated service regulation with flexible train composition. This study contributes to real-time coordinated metro network services with flexible train composition and advanced optimization techniques. • An adaptive rail transit control system with passengers' transfers and flexible train composition. • A novel modeling and optimization framework based on multi-agent deep reinforcement learning. • A computational framework with 'decentralized execution and centralized training' for effectiveness and stability. • Case study demonstrating the system efficiency and computational effectiveness of proposed algorithm over previous methods. [ABSTRACT FROM AUTHOR]

In recent years, the utility of polygenic risk scores (PRS) in forecasting disease susceptibility from genome-wide association studies (GWAS) results has been widely recognised. Yet, these models face limitations due to overfitting and the potential overestimation of effect sizes in correlated variants. To surmount these obstacles, we devised the Stacked Neural Network Polygenic Risk Score (SNPRS). This novel approach synthesises outputs from multiple neural network models, each calibrated using genetic variants chosen based on diverse p-value thresholds. By doing so, SNPRS captures a broader array of genetic variants, enabling a more nuanced interpretation of the combined effects of these variants. We assessed the efficacy of SNPRS using the UK Biobank data, focusing on the genetic risks associated with breast and prostate cancers, as well as quantitative traits like height and BMI. We also extended our analysis to the Korea Genome and Epidemiology Study (KoGES) dataset. Impressively, our results indicate that SNPRS surpasses traditional PRS models and an isolated deep neural network in terms of accuracy, highlighting its promise in refining the efficacy and relevance of PRS in genetic studies. [ABSTRACT FROM AUTHOR]

There are global efforts to deploy Electric Vehicles (EVs) because of the role they promise to play in energy transition. These efforts underscore the e-mobility paradigm, representing an interplay between renewable energy resources, smart technologies, and networked transportation. However, there are concerns that these initiatives could burden the electricity grid due to increased demand. Hence, the need for accurate short-term load forecasting is pivotal for the efficient planning, operation, and control of the grid and associated power systems. This study presents robust models for forecasting half-hourly and hourly loads in the UK's power system. The work leverages machine learning techniques such as Support Vector Regression (SVR), Artificial Neural Networks (ANN), and Gaussian Process Regression (GPR) to develop robust prediction models using the net imports dataset from 2010 to 2020. The models were evaluated based on metrics like Root Mean Square Error (RMSE), Mean Absolute Prediction Error (MAPE), Mean Absolute Deviation (MAD), and the Correlation of Determination (R2). For half-hourly forecasts, SVR performed best with an R-value of 99.85%, followed closely by GPR and ANN. But, for hourly forecasts, ANN led with an R-value of 99.71%. The findings affirm the reliability and precision of machine learning methods in short-term load forecasting, particularly highlighting the superior accuracy of the SVR model for half-hourly forecasts and the ANN model for hourly forecasts. [ABSTRACT FROM AUTHOR]

Wearable inertial measurement units (IMUs) are being used to quantify gait characteristics that are associated with increased fall risk, but the current limitation is the lack of contextual information that would clarify IMU data. Use of wearable video-based cameras would provide a comprehensive understanding of an individual's habitual fall risk, adding context to clarify abnormal IMU data. Generally, there is taboo when suggesting the use of wearable cameras to capture real-world video, clinical and patient apprehension due to ethical and privacy concerns. This perspective proposes that routine use of wearable cameras could be realized within digital medicine through AI-based computer vision models to obfuscate/blur/shade sensitive information while preserving helpful contextual information for a comprehensive patient assessment. Specifically, no person sees the raw video data to understand context, rather AI interprets the raw video data first to blur sensitive objects and uphold privacy. That may be more routinely achieved than one imagines as contemporary resources exist. Here, to showcase/display the potential an exemplar model is suggested via off-the-shelf methods to detect and blur sensitive objects (e.g., people) with an accuracy of 88%. Here, the benefit of the proposed approach includes a more comprehensive understanding of an individual's free-living fall risk (from free-living IMU-based gait) without compromising privacy. More generally, the video and AI approach could be used beyond fall risk to better inform habitual experiences and challenges across a range of clinical cohorts. Medicine is becoming more receptive to wearables as a helpful toolbox, camera-based devices should be plausible instruments. [ABSTRACT FROM AUTHOR]

• A novel model of loop metro service driven by stochastic demand of general distribution. • A Markov decision process for optimal schedule with circulation of limited rolling stock. • An actor-critic deep reinforcement learning framework with an off-policy training algorithm. • A case study demonstrating the efficiency and robustness of the proposed control system. This paper presents a novel actor-critic deep reinforcement learning approach for metro train scheduling with circulation of limited rolling stock. The scheduling problem is modeled as a Markov decision process driven by stochastic passenger demand. As in most dynamic optimization problems, the complexity of the scheduling process grows exponentially with the amount of states, decisions, and uncertainties involved. This study aims to address this 'curses of dimensionality' issue by adopting an actor-critic deep reinforcement learning solution framework. The framework simplifies the evaluation and searching process for potential optimal solutions by parameterizing the original state and decision spaces with the use of artificial neural networks. A deep deterministic policy gradient algorithm is developed for training the artificial neural networks via simulated system transitions before the actor-critic agent can be applied for online schedule control. The proposed approach is tested with a real-world scenario configured with data collected from the Victoria Line of London Underground, UK. Experiment results illustrate the advantages of the proposed method over a range of established meta-heuristics in terms of computing time, system efficiency, and robustness under different stochastic environments. This study innovates urban transit operations with state-of-the-art computer science and dynamic optimization techniques. [ABSTRACT FROM AUTHOR]

Multiphase flowmeters are important to monitor oil wells, as they allow operators to obtain a real-time estimate of the production. However, due to its high installation cost, uncertainty, and reading errors, the oil and gas industry started to invest in virtual meters, mathematical models that can obtain the oil and gas flow forecast using the instrumentation already available in the well, such as pressure and temperature sensors. The purpose of this article is to develop a virtual multiphase flow predictor using artificial intelligence models such as Long Short-Term Memory (LSTM), Gate Recurrent Units (GRU), Multi-Layer Perceptron (MLP) neural networks and deep learning. As input data, this paper uses a public database available on the Oil and Gas Authority (UK) to train the models and demonstrate the possibility of predicting multiphase flow with a reasonable error margin, proving that the method is efficient in estimating well production rates. • In the oil industry, it is important to measure the production from each well. • A Virtual Meter is a low-cost alternative. It can measure multiphase flow without any additional equipment. • This paper proposes a Virtual Meter using neural networks such as MLP, LSTM, GRU and deep learning combinations. • Prediction performance was evaluated using the Oil and Gas Authority (OGA) public database and it shows promising results. • Experiments using a combination of multiple layers shows this type of prediction takes advantage of deep learning techniques. [ABSTRACT FROM AUTHOR]

Highway safety researchers focus on crash injury severity, utilizing deep learning--specifically, deep neural networks (DNN), deep convolutional neural networks (D-CNN), and deep recurrent neural networks (D-RNN)--as the preferred method for modeling accident severity. Deep learning's strength lies in handling intricate relationships within extensive datasets, making it popular for accident severity level (ASL) prediction and classification. Despite prior success, there is a need for an efficient system recognizing ASL in diverse road conditions. To address this, we present an innovative Accident Severity Level Prediction Deep Learning (ASLP-DL) framework, incorporating DNN, D-CNN, and D-RNN models fine-tuned through iterative hyperparameter selection with Stochastic Gradient Descent. The framework optimizes hidden layers and integrates data augmentation, Gaussian noise, and dropout regularization for improved generalization. Sensitivity and factor contribution analyses identify influential predictors. Evaluated on three diverse crash record databases--NCDB 2018-2019, UK 2015-2020, and US 2016-2021--the D-RNN model excels with an ACC score of 89.0281%, a Roc Area of 0.751, an F-estimate of 0.941, and a Kappa score of 0.0629 over the NCDB dataset. The proposed framework consistently outperforms traditional methods, existing machine learning, and deep learning techniques. [ABSTRACT FROM AUTHOR]

The urban morphology is characterised by self-organisation where interactions of multiple agents produce emerging patterns on the urban form. Port-urban relationship added to the complexity of port cities' urban form. Most urban cellular automata (CA) models simulate land-use evolution through transition rules representing multi-factored local interactions. However, calibration of CA-based urban land use and transport interaction (LUTI) models often utilise manual methods due to complexity of the process. This limits insights on urban interactions to a few explored settlements and prevents applications for planning and assessment of transport policies in other contexts. This paper, therefore, addresses three main points. The paper (i) demonstrates an improved method for the calibration of CA-based LUTI models, (ii) contributes to a better understanding of the urban dynamics in port city systems by quantifying generalizable interactions from a wide range of port-urban settlements, and (iii) illustrates how the use of these interactions in a simulation model can allow long-term impact predictions of planning interventions. These were done by formulating a model in a similar structure as a neural network model to enable automatic calibration using an application of the gradient-descent algorithm. The model was then used to quantify the dynamics between land-use, geographic, and transport factors in 46 port-based and 10 non-port settlements across Great Britain, thus enabling cross-sectional analysis. Cluster analysis of the calibrated interactions in the study areas was conducted to examine the variations of these interactions. This produced two main groups. In the first group, consisting larger settlements, connections between ports and other urban activities were weaker than in the second group which consisted of smaller port-settlements. Overall, the findings of the research are consistent with existing evidence in the port-cities literature but go further in quantifying the interaction between urban agents within port-urban systems of various sizes and types. These quantified interactions will enable planners to better predict the longer-term consequences of their interventions. • This paper improved calibration process of urban model using optimization method from machine learning • The improved process allowed examination of wide range of port cities to counter the current trend of case-specific studies • Quantified interactions from wide range of port cities provide insights of the different land use behaviour in different types of port cities • Port-urban interactions in smaller urban areas with port are stronger thn in most other port cities • Interactions quantified in the study can be used in simulation to predict future port city urban form [ABSTRACT FROM AUTHOR]

• An algorithm to automatically detect motion artefacts in cardiac MR short axis images. • Use of k-space corruption to generate realistic motion artefacts to address data imbalance. • Training of a spatio-temporal convolutional neural network using curriculum learning. • Detailed comparison against a range of machine learning methods. • An area under ROC curve of 0.89 is achieved. Good quality of medical images is a prerequisite for the success of subsequent image analysis pipelines. Quality assessment of medical images is therefore an essential activity and for large population studies such as the UK Biobank (UKBB), manual identification of artefacts such as those caused by unanticipated motion is tedious and time-consuming. Therefore, there is an urgent need for automatic image quality assessment techniques. In this paper, we propose a method to automatically detect the presence of motion-related artefacts in cardiac magnetic resonance (CMR) cine images. We compare two deep learning architectures to classify poor quality CMR images: 1) 3D spatio-temporal Convolutional Neural Networks (3D-CNN), 2) Long-term Recurrent Convolutional Network (LRCN). Though in real clinical setup motion artefacts are common, high-quality imaging of UKBB, which comprises cross-sectional population data of volunteers who do not necessarily have health problems creates a highly imbalanced classification problem. Due to the high number of good quality images compared to the relatively low number of images with motion artefacts, we propose a novel data augmentation scheme based on synthetic artefact creation in k-space. We also investigate a learning approach using a predetermined curriculum based on synthetic artefact severity. We evaluate our pipeline on a subset of the UK Biobank data set consisting of 3510 CMR images. The LRCN architecture outperformed the 3D-CNN architecture and was able to detect 2D+time short axis images with motion artefacts in less than 1ms with high recall. We compare our approach to a range of state-of-the-art quality assessment methods. The novel data augmentation and curriculum learning approaches both improved classification performance achieving overall area under the ROC curve of 0.89. [ABSTRACT FROM AUTHOR]

This paper investigates the influence of incorporating spatiotemporal wind data on the performance of wind forecasting neural networks. While previous studies have shown that including spatial data enhances the accuracy of such models, limited research has explored the impact of different spatial and temporal scales of input wind data on the learnability of neural network models. In this study, convolutional neural networks (CNNs) are employed and trained using various scales of spatiotemporal wind data. The research demonstrates that using spatiotemporally correlated data from the surrounding area and past time steps for training a CNN favorably affects the predictive performance of the model. The study proposes correlation analyses, including autocorrelation and Pearson correlation analyses, to unveil the influence of spatiotemporal wind characteristics on the predictive performance of different CNN models. The spatiotemporal correlations and performances of CNN models are investigated in three regions: Korea, the USA, and the UK. The findings reveal that regions with smaller deviations of autocorrelation coefficients (ACC) are more favorable for CNNs to learn the regional and seasonal wind characteristics. Specifically, the regions of Korea, the USA, and the UK exhibit maximum standard deviations of ACCs of 0.100, 0.043, and 0.023, respectively. The CNNs wind prediction performances follow the reverse order of the regions: UK, USA, and Korea. This highlights the significant impact of regional and seasonal wind conditions on the performance of the prediction models. [Display omitted] • 3D CNN-based wind velocity prediction. • Estimation of CNN learnability through spatiotemporal wind correlation analysis. • Discovery of influence of local geometric and seasonal wind on CNN prediction. • The proposed correlation analysis can aid in selecting yaw-control wind farm sites. [ABSTRACT FROM AUTHOR]

Breast cancer is one of the deadly cancer types that causes high mortality among women globally. Meanwhile, Deep Learning (DL) emerges as the most frequently utilized and rapidly developing branch of classical machine learning. The study examines a modern Computer-Aided Diagnosis (CAD) framework that uses DL to extract features and classify them for aiding radiologists in breast cancer diagnosis. This is accomplished through four distinct experimentations aimed at identifying the most optimal method of effective classification. Here, the first uses Deep CNNs that are pre-trained, such as AlexNet, GoogleNet, ResNet50, and Dense-Net121. The second is based on experiments using Deep CNNs to extract features and applying them onto a Support Vector Machine algorithm using three different kernels. The next one involves the fusion of different deep features for demonstrating the classification improvement by fusion of these deep features. The final experiment involves Principal Component Analysis (PCA) for reducing the computational cost and for decreasing the larger feature vectors created during fusion. The abovesaid experimentations are carried out in two different mammogram datasets namely MIAS and INbreast. The classification accuracy attained for both datasets through the fuzing of deep features (97.93% for MIAS and 96.646% for INbreast) is the highest compared with the state-of-the-art frameworks. In contrast, the classification performance did not enhance while applying the PCA on combined deep features; but the decrease in execution time provides a reduced computational cost. Abbreviations: CAD: Computer Aided Diagnosis; CNN: Convolution Neural Network; CSI: Classification Success Index; DCNN: Deep Convolution Neural Network; DICOM: Digital Imaging and Communications in Medicine; DL: Deep Learning; FC layer: Fully Connected layer; FFDM: Full-Field Digital Mammograms; FN: False Negative; FP: False Positive; ICSI: Individual Classification Success Index; MIAS: Mammographic Image Analysis Society; ML: Machine Learning; MLO: Medio-Lateral Oblique; PCA: Principal Component Analysis; PGM: Portable Gray Map; PPV: Positive Predictive Value; RBF: Radial Basis Function; SGDM: Stochastic Gradient Descent with Momentum; SVM: Support Vector Machine; TN: True Negative; TP: True Positive; TPR: True Positive Rate; UK: United Kingdom [ABSTRACT FROM AUTHOR]

Predicting emergence from prolonged disorders of consciousness (PDOC) is important for planning care and treatment. We used machine learning to examine which variables from routine clinical data on admission to specialist rehabilitation units best predict emergence by discharge. A multicentre national cohort analysis of prospectively collected clinical data from the UK Rehabilitation Outcomes (UKROC) database 2010–2018. Patients (n = 1170) were operationally defined as "still in PDOC" or "emerged" by their total UK Functional Assessment Measure (FIM + FAM) discharge score. Variables included: Age, aetiology, length of stay, time since onset, and all items of the Neurological Impairment Scale, Rehabilitation Complexity Scale, Northwick Park Dependency Scale, and the Patient Categorisation Tool. After filtering, prediction of emergence was explored using four techniques: binary logistic regression, linear discriminant analysis, artificial neural networks, and rule induction. Triangulation through these techniques consistently identified characteristics associated with emergence from PDOC. More severe motor impairment, complex disability, medical and behavioural instability, and anoxic aetiology were predictive of non-emergence, whereas those with less severe motor impairment, agitated behaviour and complex disability were predictive of emergence. This initial exploration demonstrates the potential opportunities to enhance prediction of outcome using machine learning techniques to explore routinely collected clinical data. Predicting emergence from prolonged disorders of consciousness is important for planning care and treatment. Few evidence-based criteria exist for aiding clinical decision-making and existing criteria are mostly based upon acute admission data. Whilst acknowledging the limitations of using proxy data for diagnosis of emergence, this study suggests that key items from the UKROC dataset, routinely collected on admission to specialist rehabilitation some months post injury, may help to predict those patients who are more (or less) likely to regain consciousness. Machine learning can help to enhance our understanding of the best predictors of outcome and thus assist with clinical decision-making in PDOC. [ABSTRACT FROM AUTHOR]

• A novel deep CNN architecture is proposed for jointly learning the expert consensus label and the annotator's label. The proposed architecture (Fig. 1) consists of two coupled CNNs where one estimates the expert consensus label probabilities and the other models the characteristics of individual annotators (e.g., tendency to over-segmentation, mix-up between different classes, etc) by estimating the pixel-wise confusion matrices (CMs) on a per image basis. Unlike STAPLE [25] and its variants, our method models, and disentangles with deep neural networks, the complex mappings from the input images to the annotator behaviours and to the expert consensus label. • The parameters of our CNNs are "global variables" that are optimised across different image samples; this enables the model to disentangle robustly the annotators' mistakes and the expert consensus label based on correlations between similar image samples, even when the number of available annotations is small per image (e.g., a single annotation per image). In contrast, this would not be possible with STAPLE [25] and its variants [5,8] where the annotators' parameters are estimated on every target image separately. • This paper extends the preliminary version of our method presented at the NeurIPS Thirty-fourth Annual Conference on Neural Information Processing Systems [30] , by extensively evaluating our model on a new created real-world multiple sclerosis lesion dataset (QSMSC at UCL: Queen Square Multiple Sclerosis Center at UCL, UK). This dataset is generated with manual segmentations from 4 different annotators (3 radiologists with different level skills and 1 expert to generate the expert consensus label). Additionally, we presented a comprehensive discussion about our model's potential applications (e.g., estimate annotator's quality and annotation's quality), the future works we are going to explore, and the potential limitations of our model. [Display omitted] Supervised machine learning methods have been widely developed for segmentation tasks in recent years. However, the quality of labels has high impact on the predictive performance of these algorithms. This issue is particularly acute in the medical image domain, where both the cost of annotation and the inter-observer variability are high. Different human experts contribute estimates of the "actual" segmentation labels in a typical label acquisition process, influenced by their personal biases and competency levels. The performance of automatic segmentation algorithms is limited when these noisy labels are used as the expert consensus label. In this work, we use two coupled CNNs to jointly learn, from purely noisy observations alone, the reliability of individual annotators and the expert consensus label distributions. The separation of the two is achieved by maximally describing the annotator's "unreliable behavior" (we call it "maximally unreliable") while achieving high fidelity with the noisy training data. We first create a toy segmentation dataset using MNIST and investigate the properties of the proposed algorithm. We then use three public medical imaging segmentation datasets to demonstrate our method's efficacy, including both simulated (where necessary) and real-world annotations: 1) ISBI2015 (multiple-sclerosis lesions); 2) BraTS (brain tumors); 3) LIDC-IDRI (lung abnormalities). Finally, we create a real-world multiple sclerosis lesion dataset (QSMSC at UCL: Queen Square Multiple Sclerosis Center at UCL, UK) with manual segmentations from 4 different annotators (3 radiologists with different level skills and 1 expert to generate the expert consensus label). In all datasets, our method consistently outperforms competing methods and relevant baselines, especially when the number of annotations is small and the amount of disagreement is large. The studies also reveal that the system is capable of capturing the complicated spatial characteristics of annotators' mistakes. [ABSTRACT FROM AUTHOR]

The wellbore stability is an important issue in the drilling operation. Wellbore instability can interrupt the drilling and waste lots of time and money. The drilling mud is used to keep up the stability of the wellbore. Therefore, selecting the proper mud weight is an important issue in the drilling industry. The goal of this research is presenting an efficient mud weight estimator using deep learning techniques. To obtain this goal, a relatively big dataset (contained more than half-million samples) has been compiled from 116 wells of two fields in the United Kingdom and Norway. Our main contributions are assembling this large dataset, and applying the deep learning techniques to obtain efficient mud weight estimators. Our estimator is an artificial neural network with five hidden layers and 256 nodes in each layer that is able to estimate the mud weight for new wells and depths with the mean absolute error (MAE) of less than ±0.04 pound per gallon (ppg). In various experiments, the presented model has been challenged and the real-world conditions have been simulated. The results have shown that our model can be reliable and efficient in the real world. [ABSTRACT FROM AUTHOR]

Aim: Lower gastrointestinal (GI) diagnostics have been facing relentless capacity constraints for many years, even before the COVID‐19 era. Restrictions from the COVID pandemic have resulted in a significant backlog in lower GI diagnostics. Given recent developments in deep neural networks (DNNs) and the application of artificial intelligence (AI) in endoscopy, automating capsule video analysis is now within reach. Comparable to the efficiency and accuracy of AI applications in small bowel capsule endoscopy, AI in colon capsule analysis will also improve the efficiency of video reading and address the relentless demand on lower GI services. The aim of the CESCAIL study is to determine the feasibility, accuracy and productivity of AI‐enabled analysis tools (AiSPEED) for polyp detection compared with the 'gold standard': a conventional care pathway with clinician analysis. Method: This multi‐centre, diagnostic accuracy study aims to recruit 674 participants retrospectively and prospectively from centres conducting colon capsule endoscopy (CCE) as part of their standard care pathway. After the study participants have undergone CCE, the colon capsule videos will be uploaded onto two different pathways: AI‐enabled video analysis and the gold standard conventional clinician analysis pathway. The reports generated from both pathways will be compared for accuracy (sensitivity and specificity). The reading time can only be compared in the prospective cohort. In addition to validating the AI tool, this study will also provide observational data concerning its use to assess the pathway execution in real‐world performance. Results: The study is currently recruiting participants at multiple centres within the United Kingdom and is at the stage of collecting data. Conclusion: This standard diagnostic accuracy study carries no additional risk to patients as it does not affect the standard care pathway, and hence patient care remains unaffected. [ABSTRACT FROM AUTHOR]

• BP-ANN was applied to model the factors of older female and male driver accidents. • Models have greater accuracy and define the proportional contribution of errors. • 95,092 accident records in West Midlands during 2006-2016 were analysed. • Vital causes are journey purpose, lighting, pedestrian crossing & extreme weather. • Decline in abilities & cut-off of public transport make older people reliant on car. Older people are vulnerable road users with higher rate of casualties in traffic accidents. The commonly cited causes of accidents for older people are poor attention and decision making at critical locations of road, poor visibility in extreme weather, poor road surface condition and unpredictability of other road users, particularly young drivers. Female drivers are often labelled as being precarious drivers and having higher accident risk comparing to male drivers. This paper applies Backpropagation - Artificial Neural Network (BP-ANN) with a Generalized Delta Rule (GDR) learning algorithm to model the factors affecting traffic accidents of both older female and male drivers. The BP-ANN can construct the causation model of traffic accidents with greater accuracy and define the proportion of errors contributed by each factor to traffic accidents. This paper studies a total of 95,092 accident records in West Midlands of the United Kingdom during the period of 2006 to 2016. This paper determines journey purpose, lighting condition, pedestrian crossing with physical interventions, complex roadway geometry, extreme weather and time severity as the most significant factors of older driver accidents. The accident risk of older drivers can be improved by providing accessible routes, affordable, reliable and convenient public transport, timely warning of unexpected situations and changes in roadway geometry; increasing use of assistive technology in cars, driverless cars and encouraging active transports into sociable activities. The findings help the transport authorities and city councils to develop strategies and measures promoting public and active transports to ensuring the safety of older drivers. [ABSTRACT FROM AUTHOR]

Volatility plays a crucial role in financial markets and accurate prediction of the stock price indices is of high interest. In multivariate time series, Dynamic Conditional Correlation (DCC)-Generalized Autoregressive Conditional Heteroscedastic (GARCH) is used to model and forecast the volatility (risk) and co-movement between stock prices data. We propose multivariate artificial neural networks (MANNs) hybridized with the DCC-GARCH model to forecast the volatility of stock prices and to examine the time-varying correlation. The daily share price data of five stock markets: S&P 500 (USA), FTSE-100 (UK), KSE-100 (Pakistan), Malaysia (KLSE) and BSESN (India) covering the period from 1st, January 2013 to 17th, March 2020 are considered for empirical analysis. Moreover, the hybrid models of MANNs and DCC-GARCH are developed in two ways: (i) MANNs is provided as an input to DCC-GARCH (1,1) producing a hybrid model of DCC-GARCH(1,1)-MANNs and (ii) DCC-GARCH(1,1) model is set as an input to MANNs resulting hybrid model of MANNs-DCC-GARCH(1,1). Furthermore, the performances of the proposed models are compared with single models via the root mean square (RMSE), mean absolute error (MAE) and relative mean absolute error (RMAE). The empirical results show that DCC-GARCH (1,1)-MANNs, a parametric model, outperforms both in-sample and out-sample forecasts and helps to examine the time-varying correlation and also provides volatility forecast as well, whereas the hybrid model MANNs-DCC-GARCH (1,1) provides forecast only. Therefore, the hybrid model of DCC-GARCH (1,1)-MANNs is found suitable as compared to MANNs-DCC-GARCH(1,1) to model and forecast the stock price indices under consideration. [ABSTRACT FROM AUTHOR]

As the access to consumption data available in household smart meters is now very common in several developed countries, this kind of information is assuming a providential role for different players in the energy sector. The proposed study was applied to data available from the Smart Meter Energy Consumption Data in the London Households dataset, provided by UK Power Networks, containing half-hourly readings from an original sample of 5567 households (71 households were hereby carefully selected after a justified filtering process). The main aim is to forecast the day—ahead load profile, based only on previous load values and some auxiliary variables. During this research different forecasting models are applied, tested and compared to allow comprehensive analyses integrating forecasting accuracy, processing times and the interpretation of the most influential features in each case. The selected models are based on Multivariate Adaptive Regression Splines, Random Forests and Artificial Neural Networks, and the accuracies resulted from each model are compared and confronted with a baseline (Naïve model). The different forecasting approaches being evaluated have been revealed to be effective, ensuring a mean reduction of 15% in Mean Absolute Error when compared to the baseline. Artificial Neural Networks proved to be the most accurate model for a major part of the residential consumers. [ABSTRACT FROM AUTHOR]

Disinformation attacks that make use of social media platforms, e.g., the attacks orchestrated by the Russian "Internet Research Agency" during the 2016 U.S. Presidential election campaign and the 2016 Brexit referendum in the UK, have led to increasing demands from governmental agencies for AI tools that are capable of identifying such attacks in their earliest stages, rather than responding to them in retrospect. This research undertaken on behalf of the Canadian Armed Forces and Department of National Defence. Our ultimate objective is the development of an integrated set of machine-learning algorithms which will mobilize artificial intelligence to identify hostile disinformation activities in "near-real-time." Employing The Dark Crawler, the Posit Toolkit, TensorFlow (Deep Neural Networks), plus the Random Forest classifier and short-text classification programs known as LibShortText and LibLinear, we have analysed a wide sample of social media posts that exemplify the "fake news" that was disseminated by Russia's Internet Research Agency, comparing them to "real news" posts in order to develop an automated means of classification. [ABSTRACT FROM AUTHOR]

Motivation Medical images can provide rich information about diseases and their biology. However, investigating their association with genetic variation requires non-standard methods. We propose transferGWAS , a novel approach to perform genome-wide association studies directly on full medical images. First, we learn semantically meaningful representations of the images based on a transfer learning task, during which a deep neural network is trained on independent but similar data. Then, we perform genetic association tests with these representations. Results We validate the type I error rates and power of transferGWAS in simulation studies of synthetic images. Then we apply transferGWAS in a genome-wide association study of retinal fundus images from the UK Biobank. This first-of-a-kind GWAS of full imaging data yielded 60 genomic regions associated with retinal fundus images, of which 7 are novel candidate loci for eye-related traits and diseases. Availability and implementation Our method is implemented in Python and available at https://github.com/mkirchler/transferGWAS/. Supplementary information Supplementary data are available at Bioinformatics online. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of this study is to explore the link between information systems (IS) capabilities, supplier integration and cost performance in the service context. Specifically, it empirically investigates how supplier integration meditates the relationship between three dimensions of IS capabilities and cost performance in service firms. Design/methodology/approach: A survey of 156 UK service firms was conducted and the data analyzed to determine the role of supplier integration in mediating the effects of IS capabilities on firms' cost performance. The research model was tested using structural equation modeling (SEM), and the neural network model was used to rank the relative influence of significant predictors obtained from SEM. Findings: The results confirmed that supplier integration fully mediates the effects of information technology (IT) for supply chain activities and flexible IT infrastructure on cost performance and partially mediates the effect of operations manager's IT knowledge on cost performance. The results showed that operations manager's IT knowledge is the strongest predictor of supplier integration. Originality/value: This study takes a step toward quelling concerns about the business value of IS, contributing to the development and validation of the measurement of IS capabilities in the service operations context. Additionally, it adds to the emerging body of literature linking supplier integration to the operational performance of service firms. [ABSTRACT FROM AUTHOR]

(1) Background: Coronavirus disease 2019 (COVID-19) is a dominant, rapidly spreading respiratory disease. However, the factors influencing COVID-19 mortality still have not been confirmed. The pathogenesis of COVID-19 is unknown, and relevant mortality predictors are lacking. This study aimed to investigate COVID-19 mortality in patients with pre-existing health conditions and to examine the association between COVID-19 mortality and other morbidities. (2) Methods: De-identified data from 113,882, including 14,877 COVID-19 patients, were collected from the UK Biobank. Different types of data, such as disease history and lifestyle factors, from the COVID-19 patients, were input into the following three machine learning models: Deep Neural Networks (DNN), Random Forest Classifier (RF), eXtreme Gradient Boosting classifier (XGB) and Support Vector Machine (SVM). The Area under the Curve (AUC) was used to measure the experiment result as a performance metric. (3) Results: Data from 14,876 COVID-19 patients were input into the machine learning model for risk-level mortality prediction, with the predicted risk level ranging from 0 to 1. Of the three models used in the experiment, the RF model achieved the best result, with an AUC value of 0.86 (95% CI 0.84–0.88). (4) Conclusions: A risk-level prediction model for COVID-19 mortality was developed. Age, lifestyle, illness, income, and family disease history were identified as important predictors of COVID-19 mortality. The identified factors were related to COVID-19 mortality. [ABSTRACT FROM AUTHOR]

Complex network analyses have provided clues to improve power-grid stability with the help of numerical models. The high computational cost of numerical simulations, however, has inhibited the approach, especially when it deals with the dynamic properties of power grids such as frequency synchronization. In this study, we investigate machine learning techniques to estimate the stability of power-grid synchronization. We test three different machine learning algorithms—random forest, support vector machine, and artificial neural network—training them with two different types of synthetic power grids consisting of homogeneous and heterogeneous input-power distribution, respectively. We find that the three machine learning models better predict the synchronization stability of power-grid nodes when they are trained with the heterogeneous input-power distribution rather than the homogeneous one. With the real-world power grids of Great Britain, Spain, France, and Germany, we also demonstrate that the machine learning algorithms trained on synthetic power grids are transferable to the stability prediction of the real-world power grids, which implies the prospective applicability of machine learning techniques on power-grid studies. [ABSTRACT FROM AUTHOR]

This study appraises different types of conventional (e.g., GRNN, RBNN, & MLPNN) and modern neural networks (e.g., integrative, inclusive, hybrid, & recurrent) in forecasting daily flow in the Thames River located in the United Kingdom. The models are mathematically, statistically, and diagnostically compared based on the forecasted results for ten different time-series assortments. The results indicate that all the neural network models acceptably forecasted the daily flow rate, with mean values of R2 > 0.92 and RMSE < 18.6 m3/s. Despite the fact that the integrative neural network models slightly acted better in forecasting flow rate (mean values of R2 > 0.94 and RMSE < 15.3 m3/s), they were not as computationally effective as the other applied models. [ABSTRACT FROM AUTHOR]

A major goal of neuroimaging studies is to develop predictive models to analyze the relationship between whole brain functional connectivity patterns and behavioural traits. However, there is no single widely-accepted standard pipeline for analyzing functional connectivity. The common procedure for designing functional connectivity based predictive models entails three main steps: parcellating the brain, estimating the interaction between defined parcels, and lastly, using these integrated associations between brain parcels as features fed to a classifier for predicting non-imaging variables e.g., behavioural traits, demographics, emotional measures, etc. There are also additional considerations when using correlation-based measures of functional connectivity, resulting in three supplementary steps: utilising Riemannian geometry tangent space parameterization to preserve the geometry of functional connectivity; penalizing the connectivity estimates with shrinkage approaches to handle challenges related to short time-series (and noisy) data; and removing confounding variables from brain-behaviour data. These six steps are contingent on each-other, and to optimise a general framework one should ideally examine these various methods simultaneously. In this paper, we investigated strengths and short-comings, both independently and jointly, of the following measures: parcellation techniques of four kinds (categorized further depending upon number of parcels), five measures of functional connectivity, the decision of staying in the ambient space of connectivity matrices or in tangent space, the choice of applying shrinkage estimators, six alternative techniques for handling confounds and finally four novel classifiers/predictors. For performance evaluation, we have selected two of the largest datasets, UK Biobank and the Human Connectome Project resting state fMRI data, and have run more than 9000 different pipeline variants on a total of ∼ 14000 individuals to determine the optimum pipeline. For independent performance validation, we have run some best-performing pipeline variants on ABIDE and ACPI datasets (∼ 1000 subjects) to evaluate the generalisability of proposed network modelling methods. Image 1 [ABSTRACT FROM AUTHOR]

We take up the problem of forecasting the amount of money to be withdrawn from automated teller machines (ATM). We compare the performances of eleven different algorithms from four different research areas on two different datasets. The exploited algorithms are fuzzy time series, multiple linear regression, artificial neural network, autoregressive integrated moving average, gaussian process regression, support vector regression, long-short term memory, simultaneous perturbation stochastic approximation, migrating birds optimization, differential evolution, and particle swarm optimization. The first dataset is very volatile and is obtained from a Turkish bank whereas the more stationary second dataset is obtained from a UK bank which was used in competitions previously. We use mean absolute deviation (MAD) to compare the algorithms since it provides a universal comparison ability independent of the magnitude of the data. The results show that support vector regression (SVR) performs the best on both data sets with a very short run time. [ABSTRACT FROM AUTHOR]

Background: Estimation of the risk of malignancy in pulmonary nodules detected by CT is central in clinical management. The use of artificial intelligence (AI) offers an opportunity to improve risk prediction. Here we compare the performance of an AI algorithm, the lung cancer prediction convolutional neural network (LCP-CNN), with that of the Brock University model, recommended in UK guidelines.Methods: A dataset of incidentally detected pulmonary nodules measuring 5-15 mm was collected retrospectively from three UK hospitals for use in a validation study. Ground truth diagnosis for each nodule was based on histology (required for any cancer), resolution, stability or (for pulmonary lymph nodes only) expert opinion. There were 1397 nodules in 1187 patients, of which 234 nodules in 229 (19.3%) patients were cancer. Model discrimination and performance statistics at predefined score thresholds were compared between the Brock model and the LCP-CNN.Results: The area under the curve for LCP-CNN was 89.6% (95% CI 87.6 to 91.5), compared with 86.8% (95% CI 84.3 to 89.1) for the Brock model (p≤0.005). Using the LCP-CNN, we found that 24.5% of nodules scored below the lowest cancer nodule score, compared with 10.9% using the Brock score. Using the predefined thresholds, we found that the LCP-CNN gave one false negative (0.4% of cancers), whereas the Brock model gave six (2.5%), while specificity statistics were similar between the two models.Conclusion: The LCP-CNN score has better discrimination and allows a larger proportion of benign nodules to be identified without missing cancers than the Brock model. This has the potential to substantially reduce the proportion of surveillance CT scans required and thus save significant resources. [ABSTRACT FROM AUTHOR]

Motivation Implicit solvent models play an important role in describing the thermodynamics and the dynamics of biomolecular systems. Key to an efficient use of these models is the computation of generalized Born (GB) radii, which is accomplished by algorithms based on the electrostatics of inhomogeneous dielectric media. The speed and accuracy of such computations are still an issue especially for their intensive use in classical molecular dynamics. Here, we propose an alternative approach that encodes the physics of the phenomena and the chemical structure of the molecules in model parameters which are learned from examples. Results GB radii have been computed using (i) a linear model and (ii) a neural network. The input is the element, the histogram of counts of neighbouring atoms, divided by atom element, within 16 Å. Linear models are ca. 8 times faster than the most widely used reference method and the accuracy is higher with correlation coefficient with the inverse of 'perfect' GB radii of 0.94 versus 0.80 of the reference method. Neural networks further improve the accuracy of the predictions with correlation coefficient with 'perfect' GB radii of 0.97 and ca. 20% smaller root mean square error. Availability and implementation We provide a C program implementing the computation using the linear model, including the coefficients appropriate for the set of Bondi radii, as Supplementary Material. We also provide a Python implementation of the neural network model with parameter and example files in the Supplementary Material as well. Supplementary information Supplementary data are available at Bioinformatics online. [ABSTRACT FROM AUTHOR]

Background. Fasciola hepatica and F. gigantica cause fascioliasis in both humans and livestock. Some adult specimens of Fasciola sp. referred to as "intermediate forms" based on their genetic traits, are also frequently reported. Simple morphological criteria are unreliable for their specific identification. In previous studies, promising phenotypic identification scores were obtained using morphometrics based on linear measurements (distances, angles, curves) between anatomical features. Such an approach is commonly termed "traditional" morphometrics, as opposed to "modern" morphometrics, which is based on the coordinates of anatomical points. Methods. Here, we explored the possible improvements that modern methods of morphometrics, including landmark-based and outline-based approaches, could bring to solving the problem of the non-molecular identification of these parasites. F. gigantica and Fasciola intermediate forms suitable for morphometric characterization were selected from Thai strains following their molecular identification. Specimens of F. hepatica were obtained from the Liverpool School of Tropical Medicine (UK). Using these three taxa, we tested the taxonomic signal embedded in traditional linear measurements versus the coordinates of anatomical points (landmark- and outlinebased approaches). Various statistical techniques of validated reclassification were used, based on either the shortest Mahalanobis distance, the maximum likelihood, or the artificial neural network method. Results. Our results revealed that both traditional and modern morphometric approaches can help in the morphological identification of Fasciola sp. We showed that the accuracy of the traditional approach could be improved by selecting a subset of characters among the most contributive ones. The influence of size on discrimination by shape was much more important in traditional than in modern analyses. In our study, the modern approach provided different results according to the type of data: satisfactory when using pseudolandmarks (outlines), less satisfactory when using landmarks. The different reclassification methods provided approximately similar scores, with a special mention to the neural network, which allowed improvements in accuracy by combining data from both morphometric approaches. Conclusion. We conclude that morphometrics, whether traditional or modern, represent a valuable tool to assist in Fasciola species recognition. The general level of accuracy is comparable among the various methods, but their demands on skills and time differ. Based on the outline method, our study could provide the first description of the shape differences between species, highlighting the more globular contours of the intermediate forms. [ABSTRACT FROM AUTHOR]

The purpose of the current investigation was to describe how the artificial neural networks (ANNs) can be used to interpret student performance on cognitive diagnostic assessments (CDAs) and evaluate the performances of ANNs using simulation results. CDAs are designed to measure student performance on problem-solving tasks and provide useful diagnostic information about cognitive skill acquisition. But for CDA to realise its potential as a formative testing method, substantial progress must be made in the development of cognitive models that characterise students’ knowledge structures and processes skills, the construction of high-quality test items that precisely measure the nature of the knowledge and skills as specified in the cognitive models, as well as the advancement of psychometric techniques that allow us to accurately interpret student performance. The current investigation focuses on the third component as we examine the use of ANNs as a powerful nonparametric statistical method for diagnostic classification. [ABSTRACT FROM AUTHOR]

Nicotine consumption is considered a major health problem, where many of those who wish to quit smoking relapse. The problem is that overtime smoking as behaviour is changing into a habit, in which it is connected to internal (e.g., nicotine level, craving) and external (action, time, location) triggers. Smoking cessation apps have proved their efficiency to support smoking who wish to quit smoking. However, still, these applications suffer from several drawbacks, where they are highly relying on the user to initiate the intervention by submitting the factor the causes the urge to smoke. This research describes the creation of a combined Control Theory and deep learning model that can learn the smoker's daily routine and predict smoking events. The model's structure combines a Control Theory model of smoking with a 1D-CNN classifier to adapt to individual differences between smokers and predict smoking events based on motion and geolocation values collected using a mobile device. Data were collected from 5 participants in the UK, and analysed and tested on 3 different machine learning model (SVM, Decision tree, and 1D-CNN), 1D-CNN has proved it's efficiency over the three methods with average overall accuracy 86.6%. The average MSE of forecasting the nicotine level was (0.04) in the weekdays, and (0.03) in the weekends. The model has proved its ability to predict the smoking event accurately when the participant is well engaged with the app. [ABSTRACT FROM AUTHOR]

We develop a method based on computer vision and a hierarchical multilevel model to derive an Urban Street Tree Vegetation Index which aims to quantify the amount of vegetation visible from the point of view of a pedestrian. Our approach unfolds in two steps. First, areas of vegetation are detected within street-level imagery using a state-of-the-art deep neural network model. Second, information is combined from several images to derive an aggregated indicator at the area level using a hierarchical multilevel model. The comparative performance of our proposed approach is demonstrated against a widely used image segmentation technique based on a pre-labelled dataset. The approach is deployed to a real-world scenario for the city of Cardiff, Wales, using Google Street View imagery. Based on more than 200,000 street-level images, an urban tree street-level indicator is derived to measure the spatial distribution of tree cover, accounting for the presence of obstructing objects present in images at the Lower Layer Super Output Area (LSOA) level, corresponding to the most commonly used administrative areas for policy-making in the United Kingdom. The results show a high degree of correspondence between our tree street-level score and aerial tree cover estimates. They also evidence more accurate estimates at a pedestrian perspective from our tree score by more appropriately capturing tree cover in areas with large burial, woodland, formal open and informal open spaces where shallow trees are abundant, in high density residential areas with backyard trees, and along street networks with high density of high trees. The proposed approach is scalable and automatable. It can be applied to cities across the world and provides robust estimates of urban trees to advance our understanding of the link between mental health, well-being, green space and air pollution. [ABSTRACT FROM AUTHOR]