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]

• This paper proposed a comprehensive framework for parametric semi-automatic BIM and bridge member segmentation. • The parametric algorithm accounted for diverse types of bridge members and produced BIM bridge models using shape information automatically extracted per parameter. • The parametrically generated bridge BIM model was converted into PCD, serving as deep learning train data for automatic segmentation of bridge members. • The trained deep learning model showed high accuracy for segmenting superstructures, indicating promise for automated segmentation of bridge members. • The segmentation accuracy increased when accounting for the point density of members corresponding to the different sizes of bridge members. This paper proposes a comprehensive framework for parametric semi-automatic BIM and bridge member segmentation. For this, a parametric algorithm was developed to accommodate diverse superstructures, piers, abutments, and bearings. Each structural member in a bridge was classified to designate its shape information as parameters. The range of each parameter was defined to account for various dimensions of the shape of the bridge member. Therefore, libraries for each member were established to produce BIM bridge models using shape information automatically extracted per parameter. Then, the framework includes an algorithm that is developed to convert bridge BIM models generated by the parametric algorithm into PCD data. The virtually generated PCD is used as deep learning train data for automatic member segmentation based on the Point-Net algorithm. The trained algorithm using the virtual PCD was applied to a real bridge PCD. The segmentation of the bridge members showed high accuracy for the superstructure but low accuracy for the bearing. The segmentation accuracy of the algorithm including the bearing member could increase by modifying the density of PCD to account for the different sizes of bridge members. Furthermore, the proposed framework was applied to a UK bridge PCD and showed its applicability for use in bridges in different countries. [ABSTRACT FROM AUTHOR]

Breast cancer claims 11,400 lives on average every year in the UK, making it one of the deadliest diseases. Mammography is the gold standard for detecting early signs of breast cancer, which can help cure the disease during its early stages. However, incorrect mammography diagnoses are common and may harm patients through unnecessary treatments and operations (or a lack of treatment). Therefore, systems that can learn to detect breast cancer on their own could help reduce the number of incorrect interpretations and missed cases. Various deep learning techniques, which can be used to implement a system that learns how to detect instances of breast cancer in mammograms, are explored throughout this paper. Convolution Neural Networks (CNNs) are used as part of a pipeline based on deep learning techniques. A divide and conquer approach is followed to analyse the effects on performance and efficiency when utilising diverse deep learning techniques such as varying network architectures (VGG19, ResNet50, InceptionV3, DenseNet121, MobileNetV2), class weights, input sizes, image ratios, pre-processing techniques, transfer learning, dropout rates, and types of mammogram projections. This approach serves as a starting point for model development of mammography classification tasks. Practitioners can benefit from this work by using the divide and conquer results to select the most suitable deep learning techniques for their case out-of-the-box, thus reducing the need for extensive exploratory experimentation. Multiple techniques are found to provide accuracy gains relative to a general baseline (VGG19 model using uncropped 512 × 512 pixels input images with a dropout rate of 0.2 and a learning rate of 1 × 10−3) on the Curated Breast Imaging Subset of DDSM (CBIS-DDSM) dataset. These techniques involve transfer learning pre-trained ImagetNet weights to a MobileNetV2 architecture, with pre-trained weights from a binarised version of the mini Mammography Image Analysis Society (mini-MIAS) dataset applied to the fully connected layers of the model, coupled with using weights to alleviate class imbalance, and splitting CBIS-DDSM samples between images of masses and calcifications. Using these techniques, a 5.6% gain in accuracy over the baseline model was accomplished. Other deep learning techniques from the divide and conquer approach, such as larger image sizes, do not yield increased accuracies without the use of image pre-processing techniques such as Gaussian filtering, histogram equalisation and input cropping. [ABSTRACT FROM AUTHOR]

Large epidemiological studies such as the UK Biobank (UKBB) or German National Cohort (NAKO) provide unprecedented health-related data of the general population aiming to better understand determinants of health and disease. As part of these studies, Magnetic Resonance Imaging (MRI) is performed in a subset of participants allowing for phenotypical and functional characterization of different organ systems. Due to the large amount of imaging data, automated image analysis is required, which can be performed using deep learning methods, e. g. for automated organ segmentation. In this paper we describe a computational pipeline for automated segmentation of abdominal organs on MRI data from 20,000 participants of UKBB and NAKO and provide results of the quality control process. We found that approx. 90% of data sets showed no relevant segmentation errors while relevant errors occurred in a varying proportion of data sets depending on the organ of interest. Image-derived features based on automated organ segmentations showed relevant deviations of varying degree in the presence of segmentation errors. These results show that large-scale, deep learning-based abdominal organ segmentation on MRI data is feasible with overall high accuracy, but visual quality control remains an important step ensuring the validity of down-stream analyses in large epidemiological imaging studies. [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]

Segmenting anatomical structures in medical images has been successfully addressed with deep learning methods for a range of applications. However, this success is heavily dependent on the quality of the image that is being segmented. A commonly neglected point in the medical image analysis community is the vast amount of clinical images that have severe image artefacts due to organ motion, movement of the patient and/or image acquisition related issues. In this paper, we discuss the implications of image motion artefacts on cardiac MR segmentation and compare a variety of approaches for jointly correcting for artefacts and segmenting the cardiac cavity. The method is based on our recently developed joint artefact detection and reconstruction method, which reconstructs high quality MR images from k-space using a joint loss function and essentially converts the artefact correction task to an under-sampled image reconstruction task by enforcing a data consistency term. In this paper, we propose to use a segmentation network coupled with this in an end-to-end framework. Our training optimises three different tasks: 1) image artefact detection, 2) artefact correction and 3) image segmentation. We train the reconstruction network to automatically correct for motion-related artefacts using synthetically corrupted cardiac MR k-space data and uncorrected reconstructed images. Using a test set of 500 2D+time cine MR acquisitions from the UK Biobank data set, we achieve demonstrably good image quality and high segmentation accuracy in the presence of synthetic motion artefacts. We showcase better performance compared to various image correction architectures. [ABSTRACT FROM AUTHOR]

High-frequency financial data is more difficult to predict than low-frequency data because it possesses nonlinearity, nonstationarity, higher volatility, and long memory and is frequently accompanied by the jump phenomena. In this paper, the nonparametric regression (NR) model based on kernel function is used to fit the nonlinear relationship between the nonstationary series Y t and its lagging series to model the trend of high frequency financial time series. Furthermore, the deep learning LSTM (long short-term memory) model is applied to capture the high volatility and frequent jumps of high frequency financial data and to improve the forecasting accuracy of the residual series. The results demonstrate that the hybrid NR and LSTM model has greatly improved the forecasting accuracy in several evaluation criteria. In comparison to NR, support vector machine (SVM), LSTM, ARIMA and NR-SVM models, the mean absolute error (MAE) of NR-LSTM has reduced by 89.78%, 97.85%, 86.48%, 32.47% and 89%, respectively. In addition, we have constructed the trading strategy for the Shanghai-Shenzhen 300 index by using the NR-LSTM model. The NR-LSTM model can continue to provide good returns even during a bear market, which can serve as a guide for investors. Furthermore, the NR-LSTM model also exhibits the best forecasting effect when we model the high-frequency data of Ping An bank in China, the FTSE 100 index in the UK, and the S&P 500 index in the US. [ABSTRACT FROM AUTHOR]

[Display omitted] The environment where we live and recreate can have a significant effect on our well-being. More beautiful landscapes have considerable benefits to both health and quality of life. When we chose where to live or our next holiday destination, we do so according to some perception of the environment around us. In a way, we value nature and assign an ecosystem service to it. Landscape aesthetics, or scenicness, is one such service, which we consider in this paper as a collective perceived quality. We present a deep learning model called ScenicNet for the large-scale inventorisation of landscape scenicness from satellite imagery. We model scenicness with an interpretable deep learning model and learn a landscape beauty estimator based on crowdsourced scores derived from more than two hundred thousand landscape images in the United Kingdom. Our ScenicNet model learns the relationship between land cover types and scenicness by using land cover prediction as an interpretable intermediate task to scenicness regression. It predicts landscape scenicness and land cover from the Corine Land Cover product concurrently, without compromising the accuracy of either task. In addition, our proposed model is interpretable in the sense that it learns to express preferences for certain types of land covers in a manner that is easily understandable by an end-user. Our semantic bottleneck also allows us to further our understanding of crowd preferences for landscape aesthetics. [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]

This paper reviews some of the challenges posed by the huge growth of experimental data generated by the new generation of large-scale experiments at UK national facilities at the Rutherford Appleton Laboratory (RAL) site at Harwell near Oxford. Such 'Big Scientific Data' comes from the Diamond Light Source and Electron Microscopy Facilities, the ISIS Neutron and Muon Facility and the UK's Central Laser Facility. Increasingly, scientists are now required to use advanced machine learning and other AI technologies both to automate parts of the data pipeline and to help find new scientific discoveries in the analysis of their data. For commercially important applications, such as object recognition, natural language processing and automatic translation, deep learning has made dramatic breakthroughs. Google's DeepMind has now used the deep learning technology to develop their AlphaFold tool to make predictions for protein folding. Remarkably, it has been able to achieve some spectacular results for this specific scientific problem. Can deep learning be similarly transformative for other scientific problems? After a brief review of some initial applications of machine learning at the RAL, we focus on challenges and opportunities for AI in advancing materials science. Finally, we discuss the importance of developing some realistic machine learning benchmarks using Big Scientific Data coming from several different scientific domains. We conclude with some initial examples of our 'scientific machine learning' benchmark suite and of the research challenges these benchmarks will enable. [ABSTRACT FROM AUTHOR]

Currently available risk prediction methods are limited in their ability to deal with complex, heterogeneous, and longitudinal data such as that available in primary care records, or in their ability to deal with multiple competing risks. This paper develops a novel deep learning approach that is able to successfully address current limitations of standard statistical approaches such as landmarking and joint modeling. Our approach, which we call Dynamic-DeepHit, flexibly incorporates the available longitudinal data comprising various repeated measurements (rather than only the last available measurements) in order to issue dynamically updated survival predictions for one or multiple competing risk(s). Dynamic-DeepHit learns the time-to-event distributions without the need to make any assumptions about the underlying stochastic models for the longitudinal and the time-to-event processes. Thus, unlike existing works in statistics, our method is able to learn data-driven associations between the longitudinal data and the various associated risks without underlying model specifications. We demonstrate the power of our approach by applying it to a real-world longitudinal dataset from the U.K. Cystic Fibrosis Registry, which includes a heterogeneous cohort of 5883 adult patients with annual follow-ups between 2009 to 2015. The results show that Dynamic-DeepHit provides a drastic improvement in discriminating individual risks of different forms of failures due to cystic fibrosis. Furthermore, our analysis utilizes post-processing statistics that provide clinical insight by measuring the influence of each covariate on risk predictions and the temporal importance of longitudinal measurements, thereby enabling us to identify covariates that are influential for different competing risks. [ABSTRACT FROM AUTHOR]

• A framework for LRV detection, segmentation in large CMR studies. • Automatic initialization of bi-ventricles for the first time frame without any user intervention. • Automatic End-diastole and End-systole phase assessments. • Supervised deep neural network employed to train and segment the heart. • 3D-ASM image search procedure improved by combining image intensity models with derived distance maps for LV and RV edge localization. The sheer volume of data generated by population imaging studies is unparalleled by current capabilities to extract objective and quantitative cardiac phenotypes; subjective and time-consuming manual image analysis remains the gold standard. Automated image analytics to compute quantitative imaging biomarkers of cardiac function are desperately needed. Data volumes and their variability pose a challenge to most state-of-the-art methods for endo- and epicardial contours, which lack robustness when applied to very large datasets. Our aim is to develop an analysis pipeline for the automatic quantification of cardiac function from cine magnetic resonance imaging data. This work adopt 4,638 cardiac MRI cases coming from UK Biobank with ground truth available for left and RV contours. A hybrid and robust algorithm is proposed to improve the accuracy of automatic left and right ventricle segmentation by harnessing the localization accuracy of deep learning and the morphological accuracy of 3D-ASM (three-dimensional active shape models). The contributions of this paper are three-fold. First, a fully automatic method is proposed for left and right ventricle initialization and cardiac MRI segmentation by taking full advantage of spatiotemporal constraint. Second, a deeply supervised network is introduced to train and segment the heart. Third, the 3D-ASM image search procedure is improved by combining image intensity models with convolutional neural network (CNN) derived distance maps improving endo- and epicardial edge localization. The proposed architecture outperformed the state of the art for cardiac MRI segmentation from UK Biobank. The statistics of RV landmarks detection errors for Triscuspid valve and RV apex are 4.17 mm and 5.58 mm separately. The overlap metric, mean contour distance, Hausdorff distance and cardiac functional parameters are calculated for the LV (Left Ventricle) and RV (Right Ventricle) contour segmentation. Bland–Altman analysis for clinical parameters shows that the results from our automated image analysis pipelines are in good agreement with results from expert manual analysis. Our hybrid scheme combines deep learning and statistical shape modeling for automatic segmentation of the LV/RV from cardiac MRI datasets is effective and robust and can compute cardiac functional indexes from population imaging. [ABSTRACT FROM AUTHOR]

Population imaging studies generate data for developing and implementing personalised health strategies to prevent, or more effectively treat disease. Large prospective epidemiological studies acquire imaging for pre-symptomatic populations. These studies enable the early discovery of alterations due to impending disease, and enable early identification of individuals at risk. Such studies pose new challenges requiring automatic image analysis. To date, few large-scale population-level cardiac imaging studies have been conducted. One such study stands out for its sheer size, careful implementation, and availability of top quality expert annotation; the UK Biobank (UKB). The resulting massive imaging datasets (targeting ca. 100,000 subjects) has put published approaches for cardiac image quantification to the test. In this paper, we present and evaluate a cardiac magnetic resonance (CMR) image analysis pipeline that properly scales up and can provide a fully automatic analysis of the UKB CMR study. Without manual user interactions, our pipeline performs end-to-end image analytics from multi-view cine CMR images all the way to anatomical and functional bi-ventricular quantification. All this, while maintaining relevant quality controls of the CMR input images, and resulting image segmentations. To the best of our knowledge, this is the first published attempt to fully automate the extraction of global and regional reference ranges of all key functional cardiovascular indexes, from both left and right cardiac ventricles, for a population of 20,000 subjects imaged at 50 time frames per subject, for a total of one million CMR volumes. In addition, our pipeline provides 3D anatomical bi-ventricular models of the heart. These models enable the extraction of detailed information of the morphodynamics of the two ventricles for subsequent association to genetic, omics, lifestyle habits, exposure information, and other information provided in population imaging studies. We validated our proposed CMR analytics pipeline against manual expert readings on a reference cohort of 4620 subjects with contour delineations and corresponding clinical indexes. Our results show broad significant agreement between the manually obtained reference indexes, and those automatically computed via our framework. 80.67% of subjects were processed with mean contour distance of less than 1 pixel, and 17.50% with mean contour distance between 1 and 2 pixels. Finally, we compare our pipeline with a recently published approach reporting on UKB data, and based on deep learning. Our comparison shows similar performance in terms of segmentation accuracy with respect to human experts. [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]

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]

Most existing deep learning based methods for vessel segmentation neglect two important aspects of retinal vessels: The orientation information of vessels and the contextual information of the whole fundus region. In this paper, we propose a robust orientation and context entangled network (OCE-Net), which can extract complex orientation and context information from blood vessels. To achieve complex orientation-aware convolution, we propose a dynamic complex orientation-aware convolution (DCOA Conv) to extract complex vessels with multiple orientations for improving vessel continuity. To simultaneously capture the global context information and emphasize the important local information, we propose a global and local fusion module (GLFM) to simultaneously model the long-range dependency of vessels and give sufficient attention to local thin vessels. A novel orientation and context entangled nonlocal (OCE-NL) module is also proposed to entangle the orientation and context information together. In addition, an unbalanced attention refining module (UARM) is proposed to deal with the unbalanced pixel numbers of the background and thick and thin vessels. Extensive experiments were performed on several commonly used datasets (DRIVE, STARE, and CHASEDB1) and some more challenging datasets (AV-WIDE, UoA-DR, RFMiD, and UK Biobank). The ablation study results show the proposed method's good performance in maintaining the continuity of thin vessels, and the comparative experimental results show OCE-Net's good performance in retinal vessel segmentation. Thus, the proposed framework can effectively carry out retinal vessel segmentation. • An Orientation and Context Entangled Network is proposed for vessel segmentation. • A DCOA convolution is proposed to capture the orientation of vessels. • A Global and Local Fusion Module is proposed to modeling the global dependencies. • An OCE-DNL is proposed to entangle the orientation and context. • An Unbalanced Attention Refine Module is designed to refine the output features. [ABSTRACT FROM AUTHOR]

Deformable image registration (DIR) can be used to track cardiac motion. Conventional DIR algorithms aim to establish a dense and non-linear correspondence between independent pairs of images. They are, nevertheless, computationally intensive and do not consider temporal dependencies to regulate the estimated motion in a cardiac cycle. In this paper, leveraging deep learning methods, we formulate a novel hierarchical probabilistic model, termed DragNet, for fast and reliable spatio-temporal registration in cine cardiac magnetic resonance (CMR) images and for generating synthetic heart motion sequences. DragNet is a variational inference framework, which takes an image from the sequence in combination with the hidden states of a recurrent neural network (RNN) as inputs to an inference network per time step. As part of this framework, we condition the prior probability of the latent variables on the hidden states of the RNN utilised to capture temporal dependencies. We further condition the posterior of the motion field on a latent variable from hierarchy and features from the moving image. Subsequently, the RNN updates the hidden state variables based on the feature maps of the fixed image and the latent variables. Different from traditional methods, DragNet performs registration on unseen sequences in a forward pass, which significantly expedites the registration process. Besides, DragNet enables generating a large number of realistic synthetic image sequences given only one frame, where the corresponding deformations are also retrieved. The probabilistic framework allows for computing spatio-temporal uncertainties in the estimated motion fields. Our results show that DragNet performance is comparable with state-of-the-art methods in terms of registration accuracy, with the advantage of offering analytical pixel-wise motion uncertainty estimation across a cardiac cycle and being a motion generator. We will make our code publicly available. [Display omitted] • We propose an unsupervised probabilistic motion generative model (DragNet). • We infer probabilistic displacement fields in their original high dimensional spaces. • Generating high temporal resolution image sequences given only one reference frame. • Explicit modelling spatio-temporal uncertainties at the pixel level for motion fields. [ABSTRACT FROM AUTHOR]

This paper explores disciplinary patterns of assessment and feedback, using data from the Transforming the Experience of Students through Assessment project. Its central research question concerns the effect of disciplinary assessment patterns on student learning. Audit data from 18 degree programmes at 8 UK universities showed variations in assessment patterns across three disciplinary fields: Humanities, Professional and Science courses. There were variations in assessment demands; in the quantity of feedback and in the proportion of examinations. Statistical analysis of Assessment Experience Questionnaire data (n = 762) explored whether these differences influenced students' perceptions of learning across the disciplines. Findings showed that there were no significant differences in students' perceptions of learning from examinations. Humanities students evaluated the appropriateness of their assessment lower than other discipline groups; professional students were less clear about goals and standards. The researchers propose explanations for these findings and suggest avenues for further research. [ABSTRACT FROM PUBLISHER]

• A transfer learning architecture is proposed to improve the transferability of traffic prediction models. • A novel insight is provided to deal with data insufficient problems in traffic prediction. • The data selection criteria during model transfer are tested and discussed. Short-term traffic flow forecasting is a key element in Intelligent Transport Systems (ITS) to provide proactive traffic state information to road network operators. A variety of methods to predict traffic variables in the short-term can be found in the literature, ranging from time-series algorithms, machine learning tools and deep learning methods to a selective hybrid of these approaches. Despite the advances in prediction techniques, a challenging problem that affects the application of such methods in the real world is the prevalence of insufficient data across an entire network. It is rare that extensive historical training data required for model training are available for all the links in a city. In order to address this data insufficiency problem, this paper applies transfer learning techniques to machine learning methods in short-term traffic prediction. All the traffic data used in this paper were collected from Highways England road networks in the UK. The results show that through improving the transferability of machine learning-based models, the computational burden due to the model training process can be significantly reduced and the prediction accuracy under data deficient scenarios can be improved for one-step ahead prediction. However, the prediction accuracy gradually decreases in multi-step ahead prediction. It is also found that the accuracy of the proposed hybrid method is highly dependent upon consistency between datasets but less dependent on geographical attributes of links. [ABSTRACT FROM AUTHOR]

By constructing digital twins (DT) of an integrated energy system (IES), one can benefit from DT's predictive capabilities to improve coordinations among various energy converters, hence enhancing energy efficiency, cost savings and carbon emission reduction. This paper is motivated by the fact that practical IESs suffer from multiple uncertainty sources, and complicated surrounding environment. To address this problem, a novel DT-based day-ahead scheduling method is proposed. The physical IES is modelled as a multi-vector energy system in its virtual space that interacts with the physical IES to manipulate its operations. A deep neural network is trained to make statistical cost-saving scheduling by learning from both historical forecasting errors and day-ahead forecasts. Case studies of IESs show that the proposed DT-based method is able to reduce the operating cost of IES by 63.5%, comparing to the existing forecast-based scheduling methods. It is also found that both electric vehicles and thermal energy storages play proactive roles in the proposed method, highlighting their importance in future energy system integration and decarbonisation. • A deep learning and digital twins (DT) based scheduling method is proposed. • Physical IES performance is addressed by its virtual replica's predictive capability. • A machine learning method is proposed to address multiple uncertainty challenges. • Historical U.K. datasets are used for performance evaluations. • Results demonstrate the Digital Twin model reduces the extra operating cost by 63.5%. [ABSTRACT FROM AUTHOR]

Traffic cameras are a widely available source of open data that offer tremendous value to public authorities by providing real-time statistics to understand and monitor the activity levels of local populations and their responses to policy interventions such as those seen during the COrona VIrus Disease 2019 (COVID-19) pandemic. This paper presents an end-to-end solution based on the Google Cloud Platform with scalable processing capability to deal with large volumes of traffic camera data across the UK in a cost-efficient manner. It describes a deep learning pipeline to detect pedestrians and vehicles and to generate mobility statistics from these. It includes novel methods for data cleaning and post-processing using a Structure SImilarity Measure (SSIM)-based static mask that improves reliability and accuracy in classifying people and vehicles from traffic camera images. The solution resulted in statistics describing trends in the 'busyness' of various towns and cities in the UK. We validated time series against Automatic Number Plate Recognition (ANPR) cameras across North East England, showing a close correlation between our statistical output and the ANPR source. Trends were also favorably compared against traffic flow statistics from the UK's Department of Transport. The results of this work have been adopted as an experimental faster indicator of the impact of COVID-19 on the UK economy and society by the Office for National Statistics (ONS). [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]

• A novel method for investment builds from classic statistics and deep-learning. • Portfolio formation by mean-variance and deep learning for predictive finance. • Emphasis on preselection of high quality assets. • Considering long-term dependences in time-series fluctuation. • The results outperform other strategies with respect to potential returns and risks. Portfolio theory is an important foundation for portfolio management which is a well-studied subject yet not fully conquered territory. This paper proposes a mixed method consisting of long short-term memory networks and mean-variance model for optimal portfolio formation in conjunction with the asset preselection, in which long-term dependences of financial time-series data can be captured. The experiment uses a large volume of sample data from the UK Stock Exchange 100 Index between March 1994 and March 2019. In the first stage, long short-term memory networks are used to forecast the return of assets and select assets with higher potential returns. After comparing the outcomes of the long short-term memory networks against support vector machine, random forest, deep neural networks, and autoregressive integrated moving average model, we discover that long short-term memory networks are appropriate for financial time-series forecasting, to beat the other benchmark models by a very clear margin. In the second stage, based on selected assets with higher returns, the mean-variance model is applied for portfolio optimisation. The validation of this methodology is carried out by comparing the proposed model with the other five baseline strategies, to which the proposed model clearly outperforms others in terms of the cumulative return per year, Sharpe ratio per triennium as well as average return to the risk per month of each triennium. i.e. potential returns and risks. [ABSTRACT FROM AUTHOR]

• A centralised digital architecture is developed to handle large imbalanced data. • A Regional–Convolution Neural Network (R-CNN) model is used to generate conflict data. • A Deep Neural Network (DNN) model is employed to predict real-time traffic conflicts. • Traffic variables and Safety Surrogate Measures (SSM) are used as inputs to DNN model. • This traffic conflict detection technique is suitable for ADAS, CVs and AVs. Recently, technologies for predicting traffic conflicts in real-time have been gaining momentum due to their proactive nature of application and the growing implementation of ADAS technology in intelligent vehicles. In ADAS, machine learning classifiers are utilised to predict potential traffic conflicts by analysing data from in-vehicle sensors. In most cases, a condition is classified as a traffic conflict when a safety surrogate (e.g. time-to-collision, TTC) crosses a pre-defined threshold. This approach, however, largely ignores other factors that influence traffic conflicts such as speed variance, traffic density, speed and weather conditions. Considering all these factors in detecting traffic conflicts is rather complex as it requires an integration and mining of heterodox data, the unavailability of traffic conflicts and conflict prediction models capable of extracting meaningful and accurate information in a timely manner. In addition, the model has to effectively handle large imbalanced data. To overcome these limitations, this paper presents a centralised digital architecture and employs a Deep Learning methodology to predict traffic conflicts. Highly disaggregated traffic data and in-vehicle sensors data from an instrumented vehicle are collected from a section of the UK M1 motorway to build the model. Traffic conflicts are identified by a Regional–Convolution Neural Network (R-CNN) model which detects lane markings and tracks vehicles from images captured by a single front-facing camera. This data is then integrated with traffic variables and calculated safety surrogate measures (SSMs) via a centralised digital architecture to develop a series of Deep Neural Network (DNN) models to predict these traffic conflicts. The results indicate that TTC, as expected, varies by speed, weather and traffic density and the best DNN model provides an accuracy of 94% making it reliable to employ in ADAS technology as proactive safety management strategies. Furthermore, by exchanging this traffic conflict awareness data, connected vehicles (CVs) can mitigate the risk of traffic collisions. [ABSTRACT FROM AUTHOR]

• Proposed an intelligent diagnosis framework for skin lesion classification. • Designed a multi-class multi-level algorithm to enhance the accuracy. • Proposed improved techniques for noise removal from the images. • Deep learning and other machine learning approaches developed and compared. • So far, the best multi-class result (∼96.5% accuracy) achieved using deep learning. Skin diseases remain a major cause of disability worldwide and contribute approximately 1.79% of the global burden of disease measured in disability-adjusted life years. In the United Kingdom alone, 60% of the population suffer from skin diseases during their lifetime. In this paper, we propose an intelligent digital diagnosis scheme to improve the classification accuracy of multiple diseases. A Multi-Class Multi-Level (MCML) classification algorithm inspired by the "divide and conquer" rule is explored to address the research challenges. The MCML classification algorithm is implemented using traditional machine learning and advanced deep learning approaches. Improved techniques are proposed for noise removal in the traditional machine learning approach. The proposed algorithm is evaluated on 3672 classified images, collected from different sources and the diagnostic accuracy of 96.47% is achieved. To verify the performance of the proposed algorithm, its metrics are compared with the Multi-Class Single-Level classification algorithm which is the main algorithm used in most of the existing literature. The results also indicate that the MCML classification algorithm is capable of enhancing the classification performance of multiple skin lesions. [ABSTRACT FROM AUTHOR]

Objective: Atrial fibrillation (AF) is the most common cardiac arrhythmia, with an estimated prevalence of around 1.6% in the adult population. The analysis of the electrocardiogram (ECG) data acquired in the UK Biobank represents an opportunity to screen for AF in a large sub-population in the UK. The main objective of this paper is to assess ten machine-learning methods for automated detection of subjects with AF in the UK Biobank dataset. Approach: Six classical machine-learning methods based on support vector machines are proposed and compared with state-of-the-art techniques (including a deep-learning algorithm), and finally a combination of a classical machine-learning and deep learning approaches. Evaluation is carried out on a subset of the UK Biobank dataset, manually annotated by human experts. Main results: The combined classical machine-learning and deep learning method achieved an F1 score of 84.8% on the test subset, and a Cohen’s kappa coefficient of 0.83, which is similar to the inter-observer agreement of two human experts. Significance: The level of performance indicates that the automated detection of AF in patients whose data have been stored in a large database, such as the UK Biobank, is possible. Such automated identification of AF patients would enable further investigations aimed at identifying the different phenotypes associated with AF. [ABSTRACT FROM AUTHOR]