Soaring cases of coronavirus disease (COVID-19) are pummeling the global health system. Overwhelmed health facilities have endeavored to mitigate the pandemic, but mortality of COVID-19 continues to increase. Here, we present a mortality risk prediction model for COVID-19 (MRPMC) that uses patients’ clinical data on admission to stratify patients by mortality risk, which enables prediction of physiological deterioration and death up to 20 days in advance. This ensemble model is built using four machine learning methods including Logistic Regression, Support Vector Machine, Gradient Boosted Decision Tree, and Neural Network. We validate MRPMC in an internal validation cohort and two external validation cohorts, where it achieves an AUC of 0.9621 (95% CI: 0.9464–0.9778), 0.9760 (0.9613–0.9906), and 0.9246 (0.8763–0.9729), respectively. This model enables expeditious and accurate mortality risk stratification of patients with COVID-19, and potentially facilitates more responsive health systems that are conducive to high risk COVID-19 patients.
In this paper we first exploit cash-tags ("$" followed by stocks' ticker symbols) in Twitter to build a stock network, where nodes are stocks connected by edges when two stocks co-occur frequently in tweets. We then employ a labeled topic model to jointly model both the tweets and the network structure to assign each node and each edge a topic respectively. This Semantic Stock Network (SSN) summarizes discussion topics about stocks and stock relations. We further show that social sentiment about stock (node) topics and stock relationship (edge) topics are predictive of each stock's market. For prediction, we propose to regress the topic-sentiment time-series and the stock's price time series. Experimental results demonstrate that topic sentiments from close neighbors are able to help improve the prediction of a stock markedly.
This paper addresses the problems of observerbased fault reconstruction and fault-tolerant control for TakagiSugeno fuzzy descriptor systems subject to time delays and external disturbances. A novel fuzzy descriptor learning observer is constructed to achieve simultaneous reconstruction of system states and actuator faults. Sufficient conditions for existence of the proposed observer are explicitly provided. Utilizing the reconstructed fault information, a reconfigurable fuzzy faulttolerant controller based on the separation property is designed to compensate for the impact of actuator faults on system performance by stabilizing the closed-loop system. In addition, the design of the fault reconstruction observer and the fault-tolerant controller is formulated in terms of linear matrix inequalities that can be conveniently solved using convex optimization techniques. At last, simulation results on a truck trailer system are presented to verify the effectiveness of the proposed approaches.
Abstract-Online reviews have become an increasingly important resource for decision making and product designing. But reviews systems are often targeted by opinion spamming. Although fake review detection has been studied by researchers for years using supervised learning, ground truth of large scale datasets is still unavailable and most of existing approaches of supervised learning are based on pseudo fake reviews rather than real fake reviews. Working with Dianping 1 , the largest Chinese review hosting site, we present the first reported work on fake review detection in Chinese with filtered reviews from Dianping's fake review detection system. Dianping's algorithm has a very high precision, but the recall is hard to know. This means that all fake reviews detected by the system are almost certainly fake but the remaining reviews (unknown set) may not be all genuine. Since the unknown set may contain many fake reviews, it is more appropriate to treat it as an unlabeled set. This calls for the model of learning from positive and unlabeled examples (PU learning). By leveraging the intricate dependencies among reviews, users and IP addresses, we first propose a collective classification algorithm called Multi-typed Heterogeneous Collective Classification (MHCC) and then extend it to Collective Positive and Unlabeled learning (CPU). Our experiments are conducted on real-life reviews of 500 restaurants in Shanghai, China. Results show that our proposed models can markedly improve the F1 scores of strong baselines in both PU and non-PU learning settings. Since our models only use language independent features, they can be easily generalized to other languages.
In this work, we report a novel antiferroelectric-like performance at high poling fields obtained in poly(ethyl methacrylate) (PEMA) grafted poly(vinylidene fluoride-co-trifluoroethylene) (P(VDF-TrFE)) series copolymers for application as high energy density and low loss capacitor dielectrics films. Compared with the pristine P(VDF-TrFE) random copolymer, an enhanced discharged energy density but a lowered energy loss has been observed as more PEMA is grafted. This novel antiferroelectric-like behavior at high poling field was explained by the crystalline impediment and polarization confinement effect induced by PEMA side chains. The highest discharged energy density of 14 J cm À3 and a low loss of 30% at 550 MV m À1 are achieved in the sample containing 22 wt% PEMA. This finding represents one of the effective routes to design potential dielectric polymer films for high energy storage applications.
Fluoropolymer containing unsaturation, an important intermediate for many reactions such as radical addition and Michael addition reaction, could be either utilized to synthesize fluoropolymer with desired functions or cured for rubber applications, which has rarely been investigated because of the absence of a synthetic strategy. A facile method to synthesize fluoropolymer with tunable unsaturation via controlled dehydrochlorination of commercially available poly(vinylidene fluoride-cochlorotrifluoroethylene) (P(VDF-co-CTFE)) catalyzed by tertiary monoamines under mild conditions has been reported in this work. The resultant copolymers are carefully characterized with nuclear magnetic resonance (NMR), Fourier transform infrared (FTIR), and thermal gravimetric analysis (TGA). It has been shown that the elimination could be well controlled by employing proper solvent, catalyst and reaction conditions. The typical side reactions catalyzed with amines, such as Michael addition reaction and main chain scission during the dehydrofluorination of fluoropolymer, could be avoided in the present reaction system. The kinetics results indicate that the elimination reaction is in a bi-molecular mechanism (E2), which is well recognized in strong base-catalyzed elimination of halogenated hydrocarbon. The concentration, alkalinity and steric bulk of the catalysts, the polarity and capability to absorb HCl acid of solvents, and the reaction time and temperature exhibit dominant influences on the dehydrochlorination of P(VDF-co-CTFE). The fluoropolymer containing unsaturation is readily cured with peroxide, and the crosslinked fluoropolymer exhibits excellent solvent resistance and mechanical properties.
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.