Periodicals
Accelerated antimicrobial discovery via deep generative models and molecular dynamics simulations
[no abstract]
Architecture & Planning• 2021• Nature Portfolio
Academic Digital Library for institutions, students, and solo learnersOpen-access discovery•Branded reader•Advanced analytics
Discovery
Content search and filters
This is the first search surface for the seven content types. Next we will connect full-text search and metadata-specific filters.
Results 1,892
Periodicals
Flexible Cognitive Strategies during Motor Learning
Visuomotor rotation tasks have proven to be a powerful tool to study adaptation of the motor system. While adaptation in such tasks is seemingly automatic and incremental, participants may gain knowledge of the perturbation and invoke a compensatory strategy. When provided with an explicit strategy to counteract a rotation, participants are initially very accurate, even without on-line feedback. Surprisingly, with further testing, the angle of their reaching movements drifts in the direction of the strategy, producing an increase in endpoint errors. This drift is attributed to the gradual adaptation of an internal model that operates independently from the strategy, even at the cost of task accuracy. Here we identify constraints that influence this process, allowing us to explore models of the interaction between strategic and implicit changes during visuomotor adaptation. When the adaptation phase was extended, participants eventually modified their strategy to offset the rise in endpoint errors. Moreover, when we removed visual markers that provided external landmarks to support a strategy, the degree of drift was sharply attenuated. These effects are accounted for by a setpoint state-space model in which a strategy is flexibly adjusted to offset performance errors arising from the implicit adaptation of an internal model. More generally, these results suggest that strategic processes may operate in many studies of visuomotor adaptation, with participants arriving at a synergy between a strategic plan and the effects of sensorimotor adaptation.
Architecture & Planning• 2011• Public Library of Science
Periodicals
Advanced internet of things for personalised healthcare systems: A survey
[no abstract]
Architecture & Planning• 2017• Elsevier BV
Periodicals
Radiation hydrodynamics with neutrinos
Neutrino transport and neutrino interactions in dense matter play a crucial role in stellar core collapse, supernova explosions and neutron star formation. Here we present a detailed description of a new numerical code for treating the time and energy dependent neutrino transport in hydrodynamical simulations of such events. The code is based on a variable Eddington factor method to deal with the integro-differential character of the Boltzmann equation. The moments of the neutrino distribution function and the energy and lepton number exchange with the stellar medium are determined by iteratively solving the zeroth and first order moment equations in combination with a model Boltzmann equation. The latter is discretized on a grid of tangent rays. The integration of the transport equations and the neutrino source terms is performed in a time-implicit way. In the present version of the program, the transport part is coupled to an explicit hydrodynamics code which follows the evolution of the stellar plasma by a finite-volume method with piecewise parabolic interpolation, using a Riemann solver to calculate the hydrodynamic states. The neutrino source terms are implemented in an operator-split step. Neutrino transport and hydrodynamics can be calculated with different spatial grids and different time steps. The structure of the described code is modular and offers a high degree of flexibility for an application to relativistic and multi-dimensional problems at different levels of refinement and accuracy. We critically evaluate results for a number of test cases, including neutrino transport in rapidly moving stellar media and approximate relativistic core collapse, and suggest a path for generalizing the code to be used in multi-dimensional simulations of convection in neutron stars and supernovae.
Architecture & Planning• 2002• EDP Sciences
Periodicals
The Use of MQTT in M2M and IoT Systems: A Survey
Nowadays billions of smart devices or things are present in Internet of Things (IoT) environments, such as homes, hospitals, factories, and vehicles, all around the world. As a result, the number of interconnected devices is continuously and rapidly growing. These devices communicate with each other and with other services using various communication protocols for the transportation of sensor or event data. These protocols enable applications to collect, store, process, describe, and analyze data to solve a variety of problems. IoT also aims to provide secure, bi-directional communication between interconnected devices, such as sensors, actuators, microcontrollers or smart appliances, and corresponding cloud services. In this paper we analyze the growth of M2M protocol research (MQTT, AMQP, and CoAP) over the past 20 years, and show how the growth in MQTT research stands out from the rest. We also gather relevant application areas of MQTT, as the most widespread M2M/IoT protocol, by performing a detailed literature search in major digital research archives. Our quantitative evaluation presents some of the important MQTT-related studies published in the past five years, which we compare to discuss the main features, advantages, and limitations of the MQTT protocol. We also propose a taxonomy to compare the properties and features of various MQTT implementations, i.e. brokers and libraries currently available in the public domain to help researchers and end-users to efficiently choose a broker or client library based on their requirements. Finally, we discuss the relevant findings of our comparison and highlight open issues that need further research and attention.
Architecture & Planning• 2020• Institute of Electrical and Electronics Engineers
Periodicals
Nature-based solutions for hydro-meteorological risk reduction: a state-of-the-art review of the research area
Abstract. Hydro-meteorological risks due to natural hazards such as severe floods, storm surges, landslides and droughts are causing impacts on different sectors of society. Such risks are expected to become worse given projected changes in climate, degradation of ecosystems, population growth and urbanisation. In this respect, nature-based solutions (NBSs) have emerged as effective means to respond to such challenges. A NBS is a term used for innovative solutions that are based on natural processes and ecosystems to solve different types of societal and environmental challenges. The present paper provides a critical review of the literature concerning NBSs for hydro-meteorological risk reduction and identifies current knowledge gaps and future research prospects. There has been a considerable growth of scientific publications on this topic, with a more significant rise taking place from 2007 onwards. Hence, the review process presented in this paper starts by sourcing 1608 articles from Scopus and 1431 articles from the Web of Science. The full analysis was performed on 146 articles. The analysis confirmed that numerous advancements in the area of NBSs have been achieved to date. These solutions have already proven to be valuable in providing sustainable, cost-effective, multi-purpose and flexible means for hydro-meteorological risk reduction. However, there are still many areas where further research and demonstration are needed in order to promote their upscaling and replication and to make them become mainstream solutions.
Architecture & Planning• 2020• Copernicus Publications
Periodicals
Cancer drug delivery in the nano era: An overview and perspectives
Nanomaterials are increasingly used as drug carriers for cancer therapy. Nanomaterials also appeal to researchers in the areas of cancer diagnosis and biomarker discovery. Several antitumor nanodrugs are currently being tested in preclinical and clinical trials and show promise in therapeutic and other settings. We review the development of nanomaterial drug carriers, including liposomes, polymer nanoparticles, dendritic polymers, and nanomicelles, for the diagnosis and treatment of various cancers. The prospects of nanomaterials as drug carriers for future clinical applications are also discussed.
Architecture & Planning• 2017• Elsevier BV
Periodicals
Characterization of H7N9 influenza A viruses isolated from humans
[no abstract]
Architecture & Planning• 2013• Nature Portfolio
Periodicals
Discovery of Sexual Dimorphisms in Metabolic and Genetic Biomarkers
Metabolomic profiling and the integration of whole-genome genetic association data has proven to be a powerful tool to comprehensively explore gene regulatory networks and to investigate the effects of genetic variation at the molecular level. Serum metabolite concentrations allow a direct readout of biological processes, and association of specific metabolomic signatures with complex diseases such as Alzheimer's disease and cardiovascular and metabolic disorders has been shown. There are well-known correlations between sex and the incidence, prevalence, age of onset, symptoms, and severity of a disease, as well as the reaction to drugs. However, most of the studies published so far did not consider the role of sexual dimorphism and did not analyse their data stratified by gender. This study investigated sex-specific differences of serum metabolite concentrations and their underlying genetic determination. For discovery and replication we used more than 3,300 independent individuals from KORA F3 and F4 with metabolite measurements of 131 metabolites, including amino acids, phosphatidylcholines, sphingomyelins, acylcarnitines, and C6-sugars. A linear regression approach revealed significant concentration differences between males and females for 102 out of 131 metabolites (p-values<3.8×10(-4); Bonferroni-corrected threshold). Sex-specific genome-wide association studies (GWAS) showed genome-wide significant differences in beta-estimates for SNPs in the CPS1 locus (carbamoyl-phosphate synthase 1, significance level: p<3.8×10(-10); Bonferroni-corrected threshold) for glycine. We showed that the metabolite profiles of males and females are significantly different and, furthermore, that specific genetic variants in metabolism-related genes depict sexual dimorphism. Our study provides new important insights into sex-specific differences of cell regulatory processes and underscores that studies should consider sex-specific effects in design and interpretation.
Architecture & Planning• 2011• Public Library of Science
Periodicals
Circular Business Models: Defining a Concept and Framing an Emerging Research Field
To aid companies in transitioning towards a circular economy and adopting strategies such as reuse, repair, and remanufacturing, the concept of circular business models has been developed. Although the concept draws on contributions from various academic disciplines, and despite its increasingly frequent use, few scholars clearly define what a circular business model is. Understanding about what makes a business model circular is diverse, hampering the theoretical development and practical application of circular business models. This study aims to help frame the field of circular business model research, by clarifying the fundamentals of the concept from the perspectives of resource efficiency and business model innovation. Expanding on these findings, a review of how the concept is used in recent academic literature is provided. It shows that a coherent view is lacking on which resource efficiency strategies classify a business model as circular. This study clarifies which resource efficiency strategies can be deemed as relevant key strategies for circular business models, and suggests a new definition of the concept. With the definition grounded in analysis of the fundamentals in terms of resource efficiency and business models, the study contributes to theoretical advancement and effective implementation of circular business models.
Architecture & Planning• 2017• Multidisciplinary Digital Publishing Institute
Periodicals
Psychedelics, Meditation, and Self-Consciousness
In recent years, the scientific study of meditation and psychedelic drugs has seen remarkable developments. The increased focus on meditation in cognitive neuroscience has led to a cross-cultural classification of standard meditation styles validated by functional and structural neuroanatomical data. Meanwhile, the renaissance of psychedelic research has shed light on the neurophysiology of altered states of consciousness induced by classical psychedelics, such as psilocybin and LSD, whose effects are mainly mediated by agonism of serotonin receptors. Few attempts have been made at bridging these two domains of inquiry, despite intriguing evidence of overlap between the phenomenology and neurophysiology of meditation practice and psychedelic states. In particular, many contemplative traditions explicitly aim at dissolving the sense of self by eliciting altered states of consciousness through meditation, while classical psychedelics are known to produce significant disruptions of self-consciousness, a phenomenon known as drug-induced ego dissolution. In this article, we discuss available evidence regarding convergences and differences between phenomenological and neurophysiological data on meditation practice and psychedelic drug-induced states, with a particular emphasis on alterations of self-experience. While both meditation and psychedelics may disrupt self-consciousness and underlying neural processes, we emphasize that neither meditation nor psychedelic states can be conceived as simple, uniform categories. Moreover, we suggest that there are important phenomenological differences even between conscious states described as experiences of self-loss. As a result, we propose that self-consciousness may be best construed as a multidimensional construct, and that "self-loss," far from being an unequivocal phenomenon, can take several forms. Indeed, various aspects of self-consciousness, including narrative aspects linked to autobiographical memory, self-related thoughts and mental time travel, and embodied aspects rooted in multisensory processes, may be differently affected by psychedelics and meditation practices. Finally, we consider long-term outcomes of experiences of self-loss induced by meditation and psychedelics on individual traits and prosocial behavior. We call for caution regarding the problematic conflation of temporary states of self-loss with "selflessness" as a behavioral or social trait, although there is preliminary evidence that correlations between short-term experiences of self-loss and long-term trait alterations may exist.
Architecture & Planning• 2018• Frontiers Media
Periodicals
Biopolymer-Based Sustainable Food Packaging Materials: Challenges, Solutions, and Applications
Biopolymer-based packaging materials have become of greater interest to the world due to their biodegradability, renewability, and biocompatibility. In recent years, numerous biopolymers-such as starch, chitosan, carrageenan, polylactic acid, etc.-have been investigated for their potential application in food packaging. Reinforcement agents such as nanofillers and active agents improve the properties of the biopolymers, making them suitable for active and intelligent packaging. Some of the packaging materials, e.g., cellulose, starch, polylactic acid, and polybutylene adipate terephthalate, are currently used in the packaging industry. The trend of using biopolymers in the packaging industry has increased immensely; therefore, many legislations have been approved by various organizations. This review article describes various challenges and possible solutions associated with food packaging materials. It covers a wide range of biopolymers used in food packaging and the limitations of using them in their pure form. Finally, a SWOT analysis is presented for biopolymers, and the future trends are discussed. Biopolymers are eco-friendly, biodegradable, nontoxic, renewable, and biocompatible alternatives to synthetic packaging materials. Research shows that biopolymer-based packaging materials are of great essence in combined form, and further studies are needed for them to be used as an alternative packaging material.
Architecture & Planning• 2023• Multidisciplinary Digital Publishing Institute
Periodicals
Predicting Alzheimer’s disease progression using multi-modal deep learning approach
Alzheimer's disease (AD) is a progressive neurodegenerative condition marked by a decline in cognitive functions with no validated disease modifying treatment. It is critical for timely treatment to detect AD in its earlier stage before clinical manifestation. Mild cognitive impairment (MCI) is an intermediate stage between cognitively normal older adults and AD. To predict conversion from MCI to probable AD, we applied a deep learning approach, multimodal recurrent neural network. We developed an integrative framework that combines not only cross-sectional neuroimaging biomarkers at baseline but also longitudinal cerebrospinal fluid (CSF) and cognitive performance biomarkers obtained from the Alzheimer's Disease Neuroimaging Initiative cohort (ADNI). The proposed framework integrated longitudinal multi-domain data. Our results showed that 1) our prediction model for MCI conversion to AD yielded up to 75% accuracy (area under the curve (AUC) = 0.83) when using only single modality of data separately; and 2) our prediction model achieved the best performance with 81% accuracy (AUC = 0.86) when incorporating longitudinal multi-domain data. A multi-modal deep learning approach has potential to identify persons at risk of developing AD who might benefit most from a clinical trial or as a stratification approach within clinical trials.
Architecture & Planning• 2019• Nature Portfolio
Periodicals
Developments in International Video Coding Standardization After AVC, With an Overview of Versatile Video Coding (VVC)
In the last 17 years, since the finalization of the first version of the now-dominant H.264/Moving Picture Experts Group-4 (MPEG-4) Advanced Video Coding (AVC) standard in 2003, two major new generations of video coding standards have been developed. These include the standards known as High Efficiency Video Coding (HEVC) and Versatile Video Coding (VVC). HEVC was finalized in 2013, repeating the ten-year cycle time set by its predecessor and providing about 50% bit-rate reduction over AVC. The cycle was shortened by three years for the VVC project, which was finalized in July 2020, yet again achieving about a 50% bit-rate reduction over its predecessor (HEVC). This article summarizes these developments in video coding standardization after AVC. It especially focuses on providing an overview of the first version of VVC, including comparisons against HEVC. Besides further advances in hybrid video compression, as in previous development cycles, the broad versatility of the application domain that is highlighted in the title of VVC is explained. Included in VVC is the support for a wide range of applications beyond the typical standard- and high-definition camera-captured content codings, including features to support computer-generated/screen content, high dynamic range content, multilayer and multiview coding, and support for immersive media such as 360° video.
Architecture & Planning• 2021• Institute of Electrical and Electronics Engineers
Periodicals
K-nearest neighbour technique for the effective prediction of refrigeration parameter compatible for automobile
Manufacturing simulation is an encouraging research area in resent decade. Creation or development of better simulation tool or technique is one of the major intension in manufacturing simulation. In resent research most of the manufacturing processes are simulated successfully. But some processes are not yet simulated effectively, especially automatic air conditioning (AC) system or refrigeration system. The automatic AC system for the passenger vehicle are not yet effectively simulated. Hence in this paper a machine learning technique is adopted for the effective prediction of parameter of automatic AC system. The proposed system uses k-nearest neighbour technique for the prediction of parameter will less error and high accuracy. The proposed system is implemented using MATLAB and its performance is compared with the support vector machine and ANN in terms of mean square error and accuracy. The proposed technique out-performs the conventional technique and suggest that the k-nearest neighbour become the most suitable technique for the modelling and performance analysis of automatic AC system.
Architecture & Planning• 2019• Vinča Institute of Nuclear Sciences
Periodicals
Emerging materials intelligence ecosystems propelled by machine learning
[no abstract]
Architecture & Planning• 2020• Nature Portfolio
Periodicals
Resource Management in Fog/Edge Computing
Contrary to using distant and centralized cloud data center resources, employing decentralized resources at the edge of a network for processing data closer to user devices, such as smartphones and tablets, is an upcoming computing paradigm, referred to as fog/edge computing. Fog/edge resources are typically resource-constrained, heterogeneous, and dynamic compared to the cloud, thereby making resource management an important challenge that needs to be addressed. This article reviews publications as early as 1991, with 85% of the publications between 2013 and 2018, to identify and classify the architectures, infrastructure, and underlying algorithms for managing resources in fog/edge computing.
Architecture & Planning• 2019• Association for Computing Machinery
Periodicals
The HMO Research Network Virtual Data Warehouse: A Public Data Model to Support Collaboration
The HMO Research Network (HMORN) Virtual Data Warehouse (VDW) is a public, non-proprietary, research-focused data model implemented at 17 health care systems across the United States. The HMORN has created a governance structure and specified policies concerning the VDW's content, development, implementation, and quality assurance. Data extracted from the VDW have been used by thousands of studies published in peer-reviewed journal articles. Advances in software supporting care delivery and claims processing and the availability of new data sources have greatly expanded the data available for research, but substantially increased the complexity of data management. The VDW data model incorporates software and data advances to ensure that comprehensive, up-to-date data of known quality are available for research. VDW governance works to accommodate new data and system complexities. This article highlights the HMORN VDW data model, its governance principles, data content, and quality assurance procedures. Our goal is to share the VDW data model and its operations to those wishing to implement a distributed interoperable health care data system.
Architecture & Planning• 2014• Ubiquity Press
Periodicals
Genome Sequence of Babesia bovis and Comparative Analysis of Apicomplexan Hemoprotozoa
Babesia bovis is an apicomplexan tick-transmitted pathogen of cattle imposing a global risk and severe constraints to livestock health and economic development. The complete genome sequence was undertaken to facilitate vaccine antigen discovery, and to allow for comparative analysis with the related apicomplexan hemoprotozoa Theileria parva and Plasmodium falciparum. At 8.2 Mbp, the B. bovis genome is similar in size to that of Theileria spp. Structural features of the B. bovis and T. parva genomes are remarkably similar, and extensive synteny is present despite several chromosomal rearrangements. In contrast, B. bovis and P. falciparum, which have similar clinical and pathological features, have major differences in genome size, chromosome number, and gene complement. Chromosomal synteny with P. falciparum is limited to microregions. The B. bovis genome sequence has allowed wide scale analyses of the polymorphic variant erythrocyte surface antigen protein (ves1 gene) family that, similar to the P. falciparum var genes, is postulated to play a role in cytoadhesion, sequestration, and immune evasion. The approximately 150 ves1 genes are found in clusters that are distributed throughout each chromosome, with an increased concentration adjacent to a physical gap on chromosome 1 that contains multiple ves1-like sequences. ves1 clusters are frequently linked to a novel family of variant genes termed smorfs that may themselves contribute to immune evasion, may play a role in variant erythrocyte surface antigen protein biology, or both. Initial expression analysis of ves1 and smorf genes indicates coincident transcription of multiple variants. B. bovis displays a limited metabolic potential, with numerous missing pathways, including two pathways previously described for the P. falciparum apicoplast. This reduced metabolic potential is reflected in the B. bovis apicoplast, which appears to have fewer nuclear genes targeted to it than other apicoplast containing organisms. Finally, comparative analyses have identified several novel vaccine candidates including a positional homolog of p67 and SPAG-1, Theileria sporozoite antigens targeted for vaccine development. The genome sequence provides a greater understanding of B. bovis metabolism and potential avenues for drug therapies and vaccine development.
Architecture & Planning• 2007• Public Library of Science
Periodicals
Recommendation Systems: Algorithms, Challenges, Metrics, and Business Opportunities
Recommender systems are widely used to provide users with recommendations based on their preferences. With the ever-growing volume of information online, recommender systems have been a useful tool to overcome information overload. The utilization of recommender systems cannot be overstated, given its potential influence to ameliorate many over-choice challenges. There are many types of recommendation systems with different methodologies and concepts. Various applications have adopted recommendation systems, including e-commerce, healthcare, transportation, agriculture, and media. This paper provides the current landscape of recommender systems research and identifies directions in the field in various applications. This article provides an overview of the current state of the art in recommendation systems, their types, challenges, limitations, and business adoptions. To assess the quality of a recommendation system, qualitative evaluation metrics are discussed in the paper.
Architecture & Planning• 2020• Multidisciplinary Digital Publishing Institute
Periodicals
Compositional texture engineering for highly stable wide-bandgap perovskite solar cells
The development of highly stable and efficient wide-bandgap (WBG) perovskite solar cells (PSCs) based on bromine-iodine (Br–I) mixed-halide perovskite (with Br greater than 20%) is critical to create tandem solar cells. However, issues with Br–I phase segregation under solar cell operational conditions (such as light and heat) limit the device voltage and operational stability. This challenge is often exacerbated by the ready defect formation associated with the rapid crystallization of Br-rich perovskite chemistry with antisolvent processes. We combined the rapid Br crystallization with a gentle gas-quench method to prepare highly textured columnar 1.75–electron volt Br–I mixed WBG perovskite films with reduced defect density. With this approach, we obtained 1.75–electron volt WBG PSCs with greater than 20% power conversion efficiency, approximately 1.33-volt open-circuit voltage ( V oc ), and excellent operational stability (less than 5% degradation over 1100 hours of operation under 1.2 sun at 65°C). When further integrated with 1.25–electron volt narrow-bandgap PSC, we obtained a 27.1% efficient, all-perovskite, two-terminal tandem device with a high V oc of 2.2 volts.
Architecture & Planning• 2022• American Association for the Advancement of Science
Periodicals
A Modified YOLOv8 Detection Network for UAV Aerial Image Recognition
UAV multitarget detection plays a pivotal role in civil and military fields. Although deep learning methods provide a more effective solution to this task, changes in target size, shape change, occlusion, and lighting conditions from the perspective of drones still bring great challenges to research in this field. Based on the above problems, this paper proposes an aerial image detection model with excellent performance and strong robustness. First, in view of the common problem that small targets in aerial images are prone to misdetection and missed detection, the idea of Bi-PAN-FPN is introduced to improve the neck part in YOLOv8-s. By fully considering and reusing multiscale features, a more advanced and complete feature fusion process is achieved while maintaining the parameter cost as much as possible. Second, the GhostblockV2 structure is used in the backbone of the benchmark model to replace part of the C2f module, which suppresses information loss during long-distance feature transmission while significantly reducing the number of model parameters; finally, WiseIoU loss is used as bounding box regression loss, combined with a dynamic nonmonotonic focusing mechanism, and the quality of anchor boxes is evaluated by using “outlier” so that the detector takes into account different quality anchor boxes to improve the overall performance of the detection task. The algorithm’s performance is compared and evaluated on the VisDrone2019 dataset, which is widely used worldwide, and a detailed ablation experiment, contrast experiment, interpretability experiment, and self-built dataset experiment are designed to verify the effectiveness and feasibility of the proposed model. The results show that the proposed aerial image detection model has achieved obvious results and advantages in various experiments, which provides a new idea for the deployment of deep learning in the field of UAV multitarget detection.
Architecture & Planning• 2023• Multidisciplinary Digital Publishing Institute
Periodicals
Progress and Challenges in Intelligent Remote Sensing Satellite Systems
Due to advances in remote sensing satellite imaging and image processing technologies and their wide applications, intelligent remote sensing satellites are facing an opportunity for rapid development. The key technologies, standards, and laws of intelligent remote sensing satellites are also experiencing a series of new challenges. Novel concepts and key technologies in the intelligent hyperspectral remote sensing satellite system have been proposed since 2011. The aim of these intelligent remote sensing satellites is to provide real-time, accurate, and personalized remote sensing information services. This article reviews the current developments in new-generation intelligent remote sensing satellite systems, with a focus on intelligent remote sensing satellite platforms, imaging payloads, onboard processing systems, and other key technological chains. The technological breakthroughs and current defects of intelligence-oriented designs are also analyzed. Intelligent remote sensing satellites collect personalized remote sensing data and information, with real-time data features and information interaction between remote sensing satellites or between satellites and the ground. Such developments will expand the use of remote sensing applications beyond government departments and industrial users to a massive number of individual users. However, this extension faces challenges regarding privacy protection, societal values, and laws regarding the sharing and distribution of data and information.
Architecture & Planning• 2022• Institute of Electrical and Electronics Engineers
Periodicals
Physics-Informed Neural Networks for Cardiac Activation Mapping
A critical procedure in diagnosing atrial fibrillation is the creation of electro-anatomic activation maps. Current methods generate these mappings from interpolation using a few sparse data points recorded inside the atria; they neither include prior knowledge of the underlying physics nor uncertainty of these recordings. Here we propose a physics-informed neural network for cardiac activation mapping that accounts for the underlying wave propagation dynamics and we quantify the epistemic uncertainty associated with these predictions. These uncertainty estimates not only allow us to quantify the predictive error of the neural network, but also help to reduce it by judiciously selecting new informative measurement locations via active learning. We illustrate the potential of our approach using a synthetic benchmark problem and a personalized electrophysiology model of the left atrium. We show that our new method outperforms linear interpolation and Gaussian process regression for the benchmark problem and linear interpolation at clinical densities for the left atrium. In both cases, the active learning algorithm achieves lower error levels than random allocation. Our findings open the door towards physics-based electro-anatomic mapping with the ultimate goals to reduce procedural time and improve diagnostic predictability for patients affected by atrial fibrillation. Open source code is available at https://github.com/fsahli/EikonalNet.
Architecture & Planning• 2020• Frontiers Media