Publications
Results
- Showing results for:
- Reset all filters
Search results
-
Conference paperAfzali J, Casas CQ, Arcucci R, 2021,
Latent GAN: Using a Latent Space-Based GAN for Rapid Forecasting of CFD Models
, Pages: 360-372, ISSN: 0302-9743The focus of this study is to simulate realistic fluid flow, through Machine Learning techniques that could be utilised in real-time forecasting of urban air pollution. We propose a novel Latent GAN architecture which looks at combining an AutoEncoder with a Generative Adversarial Network to predict fluid flow at the proceeding timestep of a given input, whilst keeping computational costs low. This architecture is applied to tracer flows and velocity fields around an urban city. We present a pair of AutoEncoders capable of dimensionality reduction of 3 orders of magnitude. Further, we present a pair of Generator models capable of performing real-time forecasting of tracer flows and velocity fields. We demonstrate that the models, as well as the latent spaces generated, learn and retain meaningful physical features of the domain. Despite the domain of this project being that of computational fluid dynamics, the Latent GAN architecture is designed to be generalisable such that it can be applied to other dynamical systems.
-
Journal articleNurek M, Rayner C, Freyer A, et al., 2021,
Recommendations for the Recognition, Diagnosis, and Management of Patients with Post COVID-19 Condition ('Long COVID'): A Delphi Study
, SSRN Electronic Journal -
Journal articleLertvittayakumjorn P, Toni F, 2021,
Explanation-based human debugging of nlp models: a survey
, Transactions of the Association for Computational Linguistics, Vol: 9, Pages: 1508-1528, ISSN: 2307-387XDebugging a machine learning model is hard since the bug usually involves the training data and the learning process. This becomes even harder for an opaque deep learning model if we have no clue about how the model actually works. In this survey, we review papers that exploit explanations to enable humans to give feedback and debug NLP models. We call this problem explanation-based human debugging (EBHD). In particular, we categorize and discuss existing work along three dimensions of EBHD (the bug context, the workflow, and the experimental setting), compile findings on how EBHD components affect the feedback providers, and highlight open problems that could be future research directions.
-
Conference paperAmendola M, Arcucci R, Mottet L, et al., 2021,
Data Assimilation in the Latent Space of a Convolutional Autoencoder
, Pages: 373-386, ISSN: 0302-9743Data Assimilation (DA) is a Bayesian inference that combines the state of a dynamical system with real data collected by instruments at a given time. The goal of DA is to improve the accuracy of the dynamic system making its result as real as possible. One of the most popular technique for DA is the Kalman Filter (KF). When the dynamic system refers to a real world application, the representation of the state of a physical system usually leads to a big data problem. For these problems, KF results computationally too expensive and mandates to use of reduced order modeling techniques. In this paper we proposed a new methodology we called Latent Assimilation (LA). It consists in performing the KF in the latent space obtained by an Autoencoder with non-linear encoder functions and non-linear decoder functions. In the latent space, the dynamic system is represented by a surrogate model built by a Recurrent Neural Network. In particular, an Long Short Term Memory (LSTM) network is used to train a function which emulates the dynamic system in the latent space. The data from the dynamic model and the real data coming from the instruments are both processed through the Autoencoder. We apply the methodology to a real test case and we show that the LA has a good performance both in accuracy and in efficiency.
-
Journal articleArcucci R, Zhu J, Hu S, et al., 2021,
Deep Data Assimilation: Integrating Deep Learning with Data Assimilation
, APPLIED SCIENCES-BASEL, Vol: 11- Author Web Link
- Cite
- Citations: 34
-
Conference paperPaulino-Passos G, Toni F, 2021,
Monotonicity and Noise-Tolerance in Case-Based Reasoning with Abstract Argumentation
, Pages: 508-518 -
Journal articleChapman M, Dominguez J, Fairweather E, et al., 2021,
Using Computable Phenotypes in Point-of-Care Clinical Trial Recruitment
, PUBLIC HEALTH AND INFORMATICS, PROCEEDINGS OF MIE 2021, Vol: 281, Pages: 560-564, ISSN: 0926-9630 -
Conference paperLauren S, Belardinelli F, Toni F, 2021,
Aggregating Bipolar Opinions
, 20th International Conference on Autonomous Agents and Multiagent Systems -
Conference paperRakicevic N, Cully A, Kormushev P, 2020,
Policy manifold search for improving diversity-based neuroevolution
, Publisher: arXivDiversity-based approaches have recently gained popularity as an alternativeparadigm to performance-based policy search. A popular approach from thisfamily, Quality-Diversity (QD), maintains a collection of high-performingpolicies separated in the diversity-metric space, defined based on policies'rollout behaviours. When policies are parameterised as neural networks, i.e.Neuroevolution, QD tends to not scale well with parameter space dimensionality.Our hypothesis is that there exists a low-dimensional manifold embedded in thepolicy parameter space, containing a high density of diverse and feasiblepolicies. We propose a novel approach to diversity-based policy search viaNeuroevolution, that leverages learned latent representations of the policyparameters which capture the local structure of the data. Our approachiteratively collects policies according to the QD framework, in order to (i)build a collection of diverse policies, (ii) use it to learn a latentrepresentation of the policy parameters, (iii) perform policy search in thelearned latent space. We use the Jacobian of the inverse transformation(i.e.reconstruction function) to guide the search in the latent space. Thisensures that the generated samples remain in the high-density regions of theoriginal space, after reconstruction. We evaluate our contributions on threecontinuous control tasks in simulated environments, and compare todiversity-based baselines. The findings suggest that our approach yields a moreefficient and robust policy search process.
-
Journal articleRuiz LGB, Pegalajar MC, Arcucci R, et al., 2020,
A time-series clustering methodology for knowledge extraction in energy consumption data
, Expert Systems with Applications, Vol: 160, ISSN: 0957-4174In the Energy Efficiency field, the incorporation of intelligent systems in cities and buildings is motivated by the energy savings and pollution reduction that can be attained. To achieve this goal, energy modelling and a better understanding of how energy is consumed are fundamental factors. As a result, this study proposes a methodology for knowledge acquisition in energy-related data through Time-Series Clustering (TSC) techniques. In our experimentation, we utilize data from the buildings at the University of Granada (Spain) and compare several clustering methods to get the optimum model, in particular, we tested k-Means, k-Medoids, Hierarchical clustering and Gaussian Mixtures; as well as several algorithms to obtain the best grouping, such as PAM, CLARA, and two variants of Lloyd’s method, Small and Large. Thus, our methodology can provide non-trivial knowledge from raw energy data. In contrast to previous studies in this field, not only do we propose a clustering methodology to group time series straightforwardly, but we also present an automatic strategy to search and analyse energy periodicity in these series recursively so that we can deepen granularity and extract information at different levels of detail. The results show that k-Medoids with PAM is the best approach in virtually all cases, and the Squared Euclidean distance outperforms the rest of the metrics.
-
Conference paperKotonya N, Toni F, 2020,
Explainable Automated Fact-Checking: A Survey
, Barcelona. Spain, 28th International Conference on Computational Linguistics (COLING 2020), Publisher: International Committee on Computational Linguistics, Pages: 5430-5443A number of exciting advances have been made in automated fact-checkingthanks to increasingly larger datasets and more powerful systems, leading toimprovements in the complexity of claims which can be accurately fact-checked.However, despite these advances, there are still desirable functionalitiesmissing from the fact-checking pipeline. In this survey, we focus on theexplanation functionality -- that is fact-checking systems providing reasonsfor their predictions. We summarize existing methods for explaining thepredictions of fact-checking systems and we explore trends in this topic.Further, we consider what makes for good explanations in this specific domainthrough a comparative analysis of existing fact-checking explanations againstsome desirable properties. Finally, we propose further research directions forgenerating fact-checking explanations, and describe how these may lead toimprovements in the research area.v
-
Journal articleMack J, Arcucci R, Molina-Solana M, et al., 2020,
Attention-based Convolutional Autoencoders for 3D-Variational Data Assimilation
, COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, Vol: 372, ISSN: 0045-7825 -
Journal articleGreenhalgh T, Thompson P, Weiringa S, et al., 2020,
What items should be included in an early warning score for remote assessment of suspected COVID-19? qualitative and Delphi study
, BMJ Open, Vol: 10, Pages: 1-26, ISSN: 2044-6055Background To develop items for an early warning score (RECAP: REmote COVID-19 Assessment in Primary Care) for patients with suspected COVID-19 who need escalation to next level of care.Methods The study was based in UK primary healthcare. The mixed-methods design included rapid review, Delphi panel, interviews, focus groups and software development. Participants were 112 primary care clinicians and 50 patients recovered from COVID-19, recruited through social media, patient groups and snowballing. Using rapid literature review, we identified signs and symptoms which are commoner in severe COVID-19. Building a preliminary set of items from these, we ran four rounds of an online Delphi panel with 72 clinicians, the last incorporating fictional vignettes, collating data on R software. We refined the items iteratively in response to quantitative and qualitative feedback. Items in the penultimate round were checked against narrative interviews with 50 COVID-19 patients. We required, for each item, at least 80% clinician agreement on relevance, wording and cut-off values, and that the item addressed issues and concerns raised by patients. In focus groups, 40 clinicians suggested further refinements and discussed workability of the instrument in relation to local resources and care pathways. This informed design of an electronic template for primary care systems.Results The prevalidation RECAP-V0 comprises a red flag alert box and 10 assessment items: pulse, shortness of breath or respiratory rate, trajectory of breathlessness, pulse oximeter reading (with brief exercise test if appropriate) or symptoms suggestive of hypoxia, temperature or fever symptoms, duration of symptoms, muscle aches, new confusion, shielded list and known risk factors for poor outcome. It is not yet known how sensitive or specific it is.Conclusions Items on RECAP-V0 align strongly with published evidence, clinical judgement and patient experience. The validation phase of this study is ongoing.Tria
-
Conference paperKotonya N, Toni F, 2020,
Explainable Automated Fact-Checking for Public Health Claims
, 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP(1) 2020), Publisher: ACL, Pages: 7740-7754Fact-checking is the task of verifying the veracity of claims by assessing their assertions against credible evidence. The vast major-ity of fact-checking studies focus exclusively on political claims. Very little research explores fact-checking for other topics, specifically subject matters for which expertise is required. We present the first study of explainable fact-checking for claims which require specific expertise. For our case study we choose the setting of public health. To support this case study we construct a new datasetPUBHEALTHof 11.8K claims accompanied by journalist crafted, gold standard explanations(i.e., judgments) to support the fact-check la-bels for claims1. We explore two tasks: veracity prediction and explanation generation. We also define and evaluate, with humans and computationally, three coherence properties of explanation quality. Our results indicate that,by training on in-domain data, gains can be made in explainable, automated fact-checking for claims which require specific expertise.
-
Journal articleWang S, Nadler P, Arcucci R, et al., 2020,
A Bayesian Updating Scheme for Pandemics: Estimating the Infection Dynamics of COVID-19
, IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE, Vol: 15, Pages: 23-33, ISSN: 1556-603X- Author Web Link
- Cite
- Citations: 8
-
Journal articleCasas CQ, Arcucci R, Wu P, et al., 2020,
A Reduced Order Deep Data Assimilation model
, PHYSICA D-NONLINEAR PHENOMENA, Vol: 412, ISSN: 0167-2789- Author Web Link
- Cite
- Citations: 25
-
Conference paperLiu S, Lin Z, Wang Y, et al., 2020,
Shape adaptor: a learnable resizing module
, European Conference on Computer Vision 2020, Publisher: Springer Verlag, Pages: 661-677, ISSN: 0302-9743We present a novel resizing module for neural networks: shape adaptor, a drop-in enhancement built on top of traditional resizing layers, such as pooling, bilinear sampling, and strided convolution. Whilst traditional resizing layers have fixed and deterministic reshaping factors, our module allows for a learnable reshaping factor. Our implementation enables shape adaptors to be trained end-to-end without any additional supervision, through which network architectures can be optimised for each individual task, in a fully automated way. We performed experiments across seven image classification datasets, and results show that by simply using a set of our shape adaptors instead of the original resizing layers, performance increases consistently over human-designed networks, across all datasets. Additionally, we show the effectiveness of shape adaptors on two other applications: network compression and transfer learning.
-
Journal articleRussell F, Kormushev P, Vaidyanathan R, et al., 2020,
The impact of ACL laxity on a bicondylar robotic knee and implications in human joint biomechanics
, IEEE Transactions on Biomedical Engineering, Vol: 67, Pages: 2817-2827, ISSN: 0018-9294Objective: Elucidating the role of structural mechanisms in the knee can improve joint surgeries, rehabilitation, and understanding of biped locomotion. Identification of key features, however, is challenging due to limitations in simulation and in-vivo studies. In particular the coupling of the patello-femoral and tibio-femoral joints with ligaments and its impact on joint mechanics and movement is not understood. We investigate this coupling experimentally through the design and testing of a robotic sagittal plane model. Methods: We constructed a sagittal plane robot comprised of: 1) elastic links representing cruciate ligaments; 2) a bi-condylar joint; 3) a patella; and 4) actuator hamstrings and quadriceps. Stiffness and geometry were derived from anthropometric data. 10° - 110° squatting tests were executed at speeds of 0.1 - 0.25Hz over a range of anterior cruciate ligament (ACL) slack lengths. Results: Increasing ACL length compromised joint stability, yet did not impact quadriceps mechanical advantage and force required for squat. The trend was consistent through varying condyle contact point and ligament force changes. Conclusion: The geometry of the condyles allows the ratio of quadriceps to patella tendon force to compensate for contact point changes imparted by the removal of the ACL. Thus the system maintains a constant mechanical advantage. Significance: The investigation uncovers critical features of human knee biomechanics. Findings contribute to understanding of knee ligament damage, inform procedures for knee surgery and orthopaedic implant design, and support design of trans-femoral prosthetics and walking robots. Results further demonstrate the utility of robotics as a powerful means of studying human joint biomechanics.
-
Journal articleBai W, Suzuki H, Huang J, et al., 2020,
A population-based phenome-wide association study of cardiac and aortic structure and function
, Nature Medicine, Vol: 26, Pages: 1654-1662, ISSN: 1078-8956Differences in cardiac and aortic structure and function are associated with cardiovascular diseases and a wide range of other types of disease. Here we analyzed cardiovascular magnetic resonance images from a population-based study, the UK Biobank, using an automated machine-learning-based analysis pipeline. We report a comprehensive range of structural and functional phenotypes for the heart and aorta across 26,893 participants, and explore how these phenotypes vary according to sex, age and major cardiovascular risk factors. We extended this analysis with a phenome-wide association study, in which we tested for correlations of a wide range of non-imaging phenotypes of the participants with imaging phenotypes. We further explored the associations of imaging phenotypes with early-life factors, mental health and cognitive function using both observational analysis and Mendelian randomization. Our study illustrates how population-based cardiac and aortic imaging phenotypes can be used to better define cardiovascular disease risks as well as heart–brain health interactions, highlighting new opportunities for studying disease mechanisms and developing image-based biomarkers.
-
Conference paperWang K, Marsh DM, Saputra RP, et al., 2020,
Design and control of SLIDER: an ultra-lightweight, knee-less, low-cost bipedal walking robot
, Las Vegas, USA, International Conference on Intelligence Robots and Systems (IROS), Publisher: IEEE, Pages: 3488-3495Most state-of-the-art bipedal robots are designedto be highly anthropomorphic and therefore possess legs withknees. Whilst this facilitates more human-like locomotion, thereare implementation issues that make walking with straight ornear-straight legs difficult. Most bipedal robots have to movewith a constant bend in the legs to avoid singularities at theknee joints, and to keep the centre of mass at a constant heightfor control purposes. Furthermore, having a knee on the legincreases the design complexity as well as the weight of the leg,hindering the robot’s performance in agile behaviours such asrunning and jumping.We present SLIDER, an ultra-lightweight, low-cost bipedalwalking robot with a novel knee-less leg design. This nonanthropomorphic straight-legged design reduces the weight ofthe legs significantly whilst keeping the same functionality asanthropomorphic legs. Simulation results show that SLIDER’slow-inertia legs contribute to less vertical motion in the centerof mass (CoM) than anthropomorphic robots during walking,indicating that SLIDER’s model is closer to the widely usedInverted Pendulum (IP) model. Finally, stable walking onflat terrain is demonstrated both in simulation and in thephysical world, and feedback control is implemented to addresschallenges with the physical robot.
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.