New coronavirus disease (COVID-19) has constituted a global pandemic and has spread to most countries and regions in the world. Through understanding the development trend of confirmed cases in a region, the government can control the pandemic by using the corresponding policies. However, the common traditional mathematical differential equations and population prediction models have limitations for time series population prediction, and even have large estimation errors. To address this issue, we propose an improved method for predicting confirmed cases based on LSTM (Long-Short Term Memory) neural network. This work compares the deviation between the experimental results of the improved LSTM prediction model and the digital prediction models (such as Logistic and Hill equations) with the real data as reference. Furthermore, this work uses the goodness of fitting to evaluate the fitting effect of the improvement. Experiments show that the proposed approach has a smaller prediction deviation and a better fitting effect. Compared with the previous forecasting methods, the contributions of our proposed improvement methods are mainly in the following aspects: 1) we have fully considered the spatiotemporal characteristics of the data, rather than single standardized data. 2) the improved parameter settings and evaluation indicators are more accurate for fitting and forecasting. 3) we consider the impact of the epidemic stage and conduct reasonable data processing for different stage.
Metabolites are important biomarkers in human body fluids, conveying direct information of cellular activities and physical conditions. Metabolite detection has long been a research hotspot in the field of biology and medicine. Surface-enhanced Raman spectroscopy (SERS), based on the molecular “fingerprint” of Raman spectrum and the enormous signal enhancement (down to a single-molecule level) by plasmonic nanomaterials, has proven to be a novel and powerful tool for metabolite detection. SERS provides favorable properties such as ultra-sensitive, label-free, rapid, specific, and non-destructive detection processes. In this review, we summarized the progress in recent 10 years on SERS-based sensing of endogenous metabolites at the cellular level, in tissues, and in biofluids, as well as drug metabolites in biofluids. We made detailed discussions on the challenges and optimization methods of SERS technique in metabolite detection. The combination of SERS with modern biomedical technology were also anticipated.
Improving the performance of clinical departments is not only the significant content of the healthcare system reform in China, but also the essential approach to better satisfying the Chinese growing demand for medical services. Performance management is vital and meaningful to public hospitals in China. Several studies are conducted in hospital internal performance management, but almost none of them consider the effects of informational tools. Therefore, we carried out an empirical study on effects of using performance management information system in Shanghai Ninth People’s Hospital. The main feature of the system is that it provides a real-time query platform for users to analyze and dynamically monitor the key performance indexes, timely detect problems and make adjustments. We collected pivotal medical data on 35 clinical departments of this hospital from January 2013 until December 2014, 1 year before and after applying the performance management information system. Comparative analysis was conducted by statistical methods. The results show that the system is beneficial to improve performance scores of clinical departments and lower the proportion of drug expenses, meanwhile, shorten the average hospitalized days and increase the bed turnover rate. That is to say, with the increasing medical services, the quality and efficiency is greatly improved. In a word, application of the performance management information system has a positive effect on improving performance of clinical departments.
The heavily-threaded data processing demands of streaming multiprocessors (SM) in a GPGPU require a large register file (RF). The fast increasing size of the RF makes the area cost and power consumption unaffordable for traditional SRAM designs in the future technologies. In this paper, we propose to use embedded-DRAM (eDRAM) as an alternative in future GPGPUs. Compared with SRAM, eDRAM provides higher density and lower leakage power. However, the limited data retention time in eDRAM poses new challenges. Periodic refresh operations are needed to maintain data integrity. This is exacerbated with the scaling of eDRAM density, process variations and temperature. Unlike conventional CPUs which make use of multi-ported RF, most of the RFs in modern GPGPU are heavily banked but not multi-ported to reduce the hardware cost. This provides a unique opportunity to hide the refresh overhead. We propose two different eDRAM implementations based on 3T1D and 1T1C memory cells. To mitigate the impact of periodic refresh, we propose two novel refresh solutions using bank bubble and bank walk-through. Plus, for the 1T1C RF, we design an interleaved bank organization together with an intelligent warp scheduling strategy to reduce the impact of the destructive reads. The analysis shows that our schemes present better energy efficiency, scalability and variation tolerance than traditional SRAM-based designsPeer ReviewedPostprint (published version
This study presents a spatial approach for the macrolevel traffic crashes analysis based on point-of-interest (POI) data and other related data from an open source. The spatial autoregression is explored by Moran's I Index with three spatial weight features (i.e., (a) Rook, (b) Queen, and (c) Euclidean distance). The traditional Ordinary Least Square (OLS) model, the Spatial Lag Model (SLM), the Spatial Error Model (SEM), and the Spatial Durbin Model (SDM) were developed to describe the spatial correlations among 2,114 Traffic Analysis Zones (TAZs) of Tianjin, one of the four municipalities in China. Results of the models indicated that the SDM with the Rook spatial weight feature is found to be the optimal spatial model to characterize the relationship of various variables and crashes. The results show that population density, consumption density, intersection density, and road density have significantly positive influence on traffic crashes, whereas company density, hotel density, and residential density have significant but negative effects in the local TAZ. The spillover effects coefficient of population density and road density are positive, indicating that the increase of these variables in the surrounding TAZs will lead to the increase of crashes in the target zone. The impacts of company density and hotel density are just the opposite. In general, the research findings can help transportation planners and managers better understand the general characteristics of traffic crashes and improve the situation of traffic security.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.