Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 4 de 4
Filter
1.
17th European Conference on Computer Vision, ECCV 2022 ; 13681 LNCS:437-455, 2022.
Article in English | Scopus | ID: covidwho-2148610

ABSTRACT

Federated learning (FL) is a distributed machine learning technique that enables collaborative model training while avoiding explicit data sharing. The inherent privacy-preserving property of FL algorithms makes them especially attractive to the medical field. However, in case of heterogeneous client data distributions, standard FL methods are unstable and require intensive hyperparameter tuning to achieve optimal performance. Conventional hyperparameter optimization algorithms are impractical in real-world FL applications as they involve numerous training trials, which are often not affordable with limited compute budgets. In this work, we propose an efficient reinforcement learning (RL)-based federated hyperparameter optimization algorithm, termed Auto-FedRL, in which an online RL agent can dynamically adjust hyperparameters of each client based on the current training progress. Extensive experiments are conducted to investigate different search strategies and RL agents. The effectiveness of the proposed method is validated on a heterogeneous data split of the CIFAR-10 dataset as well as two real-world medical image segmentation datasets for COVID-19 lesion segmentation in chest CT and pancreas segmentation in abdominal CT. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

2.
Acm Journal of Data and Information Quality ; 14(2):24, 2022.
Article in English | Web of Science | ID: covidwho-1819938

ABSTRACT

Aspect-level sentiment analysis identifies fine-grained emotion for target words. There are three major issues in current models of aspect-level sentiment analysis. First, few models consider the natural language semantic characteristics of the texts. Second, many models consider the location characteristics of the target words, but ignore the relationships among the target words and among the overall sentences. Third, many models lack transparency in data collection, data processing, and results generating in sentiment analysis. In order to resolve these issues, we propose an aspect-level sentiment analysis model that combines a bidirectional Long Short-Term Memory (LSTM) network and a Graph Convolutional Network (GCN) based on Dependency syntax analysis (Bi-LSTM-DGCN). Our model integrates the dependency syntax analysis of the texts, and explicitly considers the natural language semantic characteristics of the texts. It further fuses the target words and overall sentences. Extensive experiments are conducted on four benchmark datasets, i.e., Restaurantl4, Laptop, Restaurantl6, and Twitter. The experimental results demonstrate that our model outperforms other models like Target-Dependent LSTM (TD-LSTM), Attention-based LSTM with Aspect Embedding (ATAE-LSTM), LSTM+SynATT+TarRep and Convolution over a Dependency Tree (CDT). Our model is further applied to aspect-level sentiment analysis on "government" and "lockdown" of 1,658,250 tweets about "#COVID-19" that we collected from March 1, 2020 to July 1, 2020. The experimental results show that Twitter users' positive and negative sentiments fluctuated over time. Through the transparency analysis in data collection, data processing, and results generating, we discuss the reasons for the evolution of users' emotions over time based on the tweets and on our models.

3.
ACM Transactions on Intelligent Systems and Technology ; 12(6), 2021.
Article in English | Scopus | ID: covidwho-1685720

ABSTRACT

Vehicle mobility optimization in urban areas is a long-standing problem in smart city and spatial data analysis. Given the complex urban scenario and unpredictable social events, our work focuses on developing a mobile sequential recommendation system to maximize the profitability of vehicle service providers (e.g., taxi drivers). In particular, we treat the dynamic route optimization problem as a long-term sequential decision-making task. A reinforcement-learning framework is proposed to tackle this problem, by integrating a self-check mechanism and a deep neural network for customer pick-up point monitoring. To account for unexpected situations (e.g., the COVID-19 outbreak), our method is designed to be capable of handling related environment changes with a self-adaptive parameter determination mechanism. Based on the yellow taxi data in New York City and vicinity before and after the COVID-19 outbreak, we have conducted comprehensive experiments to evaluate the effectiveness of our method. The results show consistently excellent performance, from hourly to weekly measures, to support the superiority of our method over the state-of-the-art methods (i.e., with more than 98% improvement in terms of the profitability for taxi drivers). © 2021 Association for Computing Machinery.

4.
BMJ Supportive & Palliative Care ; 12(Suppl 1):A11-A12, 2022.
Article in English | ProQuest Central | ID: covidwho-1673492

ABSTRACT

IntroductionPeople are living longer with terminal illness, increasing the need for good palliative care. Projections indicate rising home deaths;accelerated by the COVID-19 pandemic but dying at home is reliant on informal carers.AimsTo identify the impact of the COVID-19 pandemic on hospice services from the perspectives of staff and bereaved carers, exploring decision-making for place-of-care and informal caring.MethodScoping reviews explored (1) place of end of life care, and (2) informal caring during the pandemic. Online interviews are being conducted with healthcare professionals in England (n=10) and Scotland (n=10) and bereaved carers who experienced Marie Curie services during lockdown in England (n=10) and Scotland (n=15-20). Once completed by January 2022 and thematically analysed key findings will drive a ‘knowledge exchange’ discussion with policy makers in England and Scotland.ResultsThe reviews and preliminary interview findings indicate the pandemic has put greater pressures on those accessing palliative care services. Decisions were influenced by the media;‘fear of contracting’ or ‘spreading the virus’ are evident in preferences for ‘home-based care. Social distancing, wearing of PPE and shielding restricted practical and emotional support that carers feel enable a good home death. The literature suggests that many carers adjusted to the altered methods of social connection and communication, but interview data suggests concerns about wellbeing especially where ‘grief’ was put ‘on hold’, delaying the bereavement process.ConclusionFindings will identify key considerations for policy and practice change around the future of hospice services if the move to community continues and how we develop and deliver hospice community based services to meet need.ImpactThis research will seek to inform Government policy and Marie Curie services to enable evidence based change and inform future research priorities.

SELECTION OF CITATIONS
SEARCH DETAIL