Results
- Showing results for:
- Reset all filters
Search results
-
Journal articleGraham N, Junghans C, Downes R, et al., 2020,
SARS-CoV-2 infection, clinical features and outcome of COVID-19 in United Kingdom nursing homes
, Journal of Infection, Vol: 81, Pages: 411-419, ISSN: 0163-4453OBJECTIVES: To understand SARS-Co-V-2 infection and transmission in UK nursing homes in order to develop preventive strategies for protecting the frail elderly residents. METHODS: An outbreak investigation involving 394 residents and 70 staff, was carried out in 4 nursing homes affected by COVID-19 outbreaks in central London. Two point-prevalence surveys were performed one week apart where residents underwent SARS-CoV-2 testing and had relevant symptoms documented. Asymptomatic staff from three of the four homes were also offered SARS-CoV-2 testing. RESULTS: Overall, 26% (95% CI 22 to 31) of residents died over the two-month period. All-cause mortality increased by 203% (95% CI 70 to 336) compared with previous years. Systematic testing identified 40% (95% CI 35 to 46) of residents as positive for SARS-CoV-2, and of these 43% (95% CI 34 to 52) were asymptomatic and 18% (95% CI 11 to 24) had only atypical symptoms; 4% (95% CI -1 to 9) of asymptomatic staff also tested positive. CONCLUSIONS: The SARS-CoV-2 outbreak in four UK nursing homes was associated with very high infection and mortality rates. Many residents developed either atypical or no discernible symptoms. A number of asymptomatic staff members also tested positive, suggesting a role for regular screening of both residents and staff in mitigating future outbreaks.
-
Journal articleLi H, Barnaghi P, Enshaeifar S, et al., 2020,
Continual learning using Bayesian neural networks
, IEEE Transactions on Neural Networks and Learning Systems, Vol: 32, Pages: 4243-4252, ISSN: 2162-2388Continual learning models allow them to learn and adapt to new changes and tasks over time. However, in continual and sequential learning scenarios, in which the models are trained using different data with various distributions, neural networks (NNs) tend to forget the previously learned knowledge. This phenomenon is often referred to as catastrophic forgetting. The catastrophic forgetting is an inevitable problem in continual learning models for dynamic environments. To address this issue, we propose a method, called continual Bayesian learning networks (CBLNs), which enables the networks to allocate additional resources to adapt to new tasks without forgetting the previously learned tasks. Using a Bayesian NN, CBLN maintains a mixture of Gaussian posterior distributions that are associated with different tasks. The proposed method tries to optimize the number of resources that are needed to learn each task and avoids an exponential increase in the number of resources that are involved in learning multiple tasks. The proposed method does not need to access the past training data and can choose suitable weights to classify the data points during the test time automatically based on an uncertainty criterion. We have evaluated the method on the MNIST and UCR time-series data sets. The evaluation results show that the method can address the catastrophic forgetting problem at a promising rate compared to the state-of-the-art models.
-
Journal articleLi R, Song H, Cao J, et al., 2020,
Big data intelligence network
, IEEE Network: the magazine of global information exchange, Vol: 34, Pages: 6-7, ISSN: 0890-8044The thirteen articles in this special section focus on big data analytics for intelligent networking. The Internet of Things (IoT) is likely to have a significant impact on human lives as new services and applications are developed through integration of the physical and digital worlds. IoT is an umbrella term referring to a large number of sensing and actuation devices connected to the Internet. The vast amounts of data will be generated from those devices and form big data to provide smarter living and/or improve production efficiency. The huge amount of data opens new challenges in the era of new data-driven solutions, which also have significant influence on communication networks. Current networks are often designed based on static end-to-end design principles hindering the efficient and intelligent provisioning of big data. This special issue features recent and emerging advances in the areas of big data analytics in networking applications and networking for big data
-
Journal articlePopescu SG, Whittington A, Gunn RN, et al., 2020,
Nonlinear biomarker interactions in conversion from mild cognitive impairment to Alzheimer's disease
, Human Brain Mapping, Vol: 41, Pages: 4406-4418, ISSN: 1065-9471Multiple biomarkers can capture different facets of Alzheimer's disease. However, statistical models of biomarkers to predict outcomes in Alzheimer's rarely model nonlinear interactions between these measures. Here, we used Gaussian Processes to address this, modelling nonlinear interactions to predict progression from mild cognitive impairment (MCI) to Alzheimer's over 3 years, using Alzheimer's Disease Neuroimaging Initiative (ADNI) data. Measures included: demographics, APOE4 genotype, CSF (amyloid‐β42, total tau, phosphorylated tau), [18F]florbetapir, hippocampal volume and brain‐age. We examined: (a) the independent value of each biomarker; and (b) whether modelling nonlinear interactions between biomarkers improved predictions. Each measured added complementary information when predicting conversion to Alzheimer's. A linear model classifying stable from progressive MCI explained over half the variance (R2 = 0.51, p < .001); the strongest independently contributing biomarker was hippocampal volume (R2 = 0.13). When comparing sensitivity of different models to progressive MCI (independent biomarker models, additive models, nonlinear interaction models), we observed a significant improvement (p < .001) for various two‐way interaction models. The best performing model included an interaction between amyloid‐β‐PET and P‐tau, while accounting for hippocampal volume (sensitivity = 0.77, AUC = 0.826). Closely related biomarkers contributed uniquely to predict conversion to Alzheimer's. Nonlinear biomarker interactions were also implicated, and results showed that although for some patients adding additional biomarkers may add little value (i.e., when hippocampal volume is high), for others (i.e., with low hippocampal volume) further invasive and expensive examination may be warranted. Our framework enables visualisation of these interactions, in individual patient biomarker ‘space', providing information for per
-
Conference paperJaneiko V, Rezvani R, Pourshahrokhi N, et al., 2020,
Enabling Context-Aware Search using Extracted Insights from IoT Data Streams
, 4th IEEE Global Internet of Things Summit (GIoTS), Publisher: IEEE
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.
Awards
- Finalist: Best Paper - IEEE Transactions on Mechatronics (awarded June 2021)
- Finalist: IEEE Transactions on Mechatronics; 1 of 5 finalists for Best Paper in Journal
- Winner: UK Institute of Mechanical Engineers (IMECHE) Healthcare Technologies Early Career Award (awarded June 2021): Awarded to Maria Lima (UKDRI CR&T PhD candidate)
- Winner: Sony Start-up Acceleration Program (awarded May 2021): Spinout company Serg Tech awarded (1 of 4 companies in all of Europe) a place in Sony corporation start-up boot camp
- “An Extended Complementary Filter for Full-Body MARG Orientation Estimation” (CR&T authors: S Wilson, R Vaidyanathan)
Established in 2017 by its principal funder the Medical Research Council, in partnership with Alzheimer's Society and Alzheimer’s Research UK, The UK Dementia Research Institute (UK DRI) is the UK’s leading biomedical research institute dedicated to neurodegenerative diseases.
