RESUMEN
The spread of the global COVID-19 epidemic has resulted in significant shifts in electricity consumption compared to regular days. It is unknown if standard single-task, single-indicator load forecasting algorithms can accurately reflect COVID-19 load patterns. Power practitioners urgently want a simple, efficient, and accurate solution for anticipating reliable load. In this paper, we first propose a unique collaborative TCN-LSTM-MTL short-term load forecasting model based on mobility data, temporal convolutional networks, and multi-task learning. The addition of the parameter sharing layers and the structure with residual convolution improves the data input diversity of the forecasting model and enables the model to obtain a wider time series receptive field. Then, to demonstrate the usefulness of the mobility optimized TCN-LSTM-MTL, tests were conducted in three levels and twelve base regions using 19 different benchmark models. It is capable of controlling predicting mistakes to within 1% in the majority of tasks. Finally, to rigorously explain the model, the Shapley additive explanations (SHAP) visual model interpretation technology based on game theory is introduced. It examines the TCN-LSTM-MTL model's internal mechanism at various time periods and establishes the validity of the mobility indicators as well as the asynchronous relationship between indicator significance and real contribution.
RESUMEN
The Collaborative Cohort of Cohorts for COVID-19 Research (C4R) is a national prospective study of adults at risk for coronavirus disease 2019 (COVID-19) comprising 14 established United States (US) prospective cohort studies. For decades, C4R cohorts have collected extensive data on clinical and subclinical diseases and their risk factors, including behavior, cognition, biomarkers, and social determinants of health. C4R will link this pre-COVID phenotyping to information on SARS-CoV-2 infection and acute and post-acute COVID-related illness. C4R is largely population-based, has an age range of 18-108 years, and broadly reflects the racial, ethnic, socioeconomic, and geographic diversity of the US. C4R is ascertaining severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection and COVID-19 illness using standardized questionnaires, ascertainment of COVID-related hospitalizations and deaths, and a SARS-CoV-2 serosurvey via dried blood spots. Master protocols leverage existing robust retention rates for telephone and in-person examinations, and high-quality events surveillance. Extensive pre-pandemic data minimize referral, survival, and recall bias. Data are being harmonized with research-quality phenotyping unmatched by clinical and survey-based studies; these will be pooled and shared widely to expedite collaboration and scientific findings. This unique resource will allow evaluation of risk and resilience factors for COVID-19 severity and outcomes, including post-acute sequelae, and assessment of the social and behavioral impact of the pandemic on long-term trajectories of health and aging.
Asunto(s)
COVID-19RESUMEN
The spread of SARS-CoV-2 virus in the ongoing global pandemics has led to infections of millions of people and losses of many lives. The rapid, accurate and convenient SARS-CoV-2 virus detection is crucial for controlling and stopping the pandemics. Diagnosis of patients in the early stage infection are so far limited to viral nucleic acid or antigen detection in human nasopharyngeal swab or saliva samples. Here we developed a method for rapid and direct optical measurement of SARS-CoV-2 virus particles in one step nearly without any sample preparation using a spike protein specific nanoplasmonic resonance sensor. We demonstrate that we can detect as few as 30 virus particles in one step within 15 minutes and can quantify the virus concentration linearly in the range of 103 vp/ml to 106 vp/ml. Measurements shown on both generic microplate reader and a handheld smartphone connected device suggest that our low-cost and rapid detection method may be adopted quickly under both regular clinical environment and resource-limited settings.