The outcomes of hypertension refer to the death or serious complications (such as myocardial infarction or stroke) that may occur in patients with hypertension. The outcomes of hypertension are very concerning for patients and doctors, and are ideally avoided. However, there is no satisfactory method for predicting the outcomes of hypertension. Therefore, this paper proposes a prediction method for outcomes based on physical examination indicators of hypertension patients. In this work, we divide the patients’ outcome prediction into two steps. The first step is to extract the key features from the patients’ many physical examination indicators. The second step is to use the key features extracted from the first step to predict the patients’ outcomes. To this end, we propose a model combining recursive feature elimination with a cross-validation method and classification algorithm. In the first step, we use the recursive feature elimination algorithm to rank the importance of all features, and then extract the optimal features subset using cross-validation. In the second step, we use four classification algorithms (support vector machine (SVM), C4.5 decision tree, random forest (RF), and extreme gradient boosting (XGBoost)) to accurately predict patient outcomes by using their optimal features subset. The selected model prediction performance evaluation metrics are accuracy, F1 measure, and area under receiver operating characteristic curve. The 10-fold cross-validation shows that C4.5, RF, and XGBoost can achieve very good prediction results with a small number of features, and the classifier after recursive feature elimination with cross-validation feature selection has better prediction performance. Among the four classifiers, XGBoost has the best prediction performance, and its accuracy, F1, and area under receiver operating characteristic curve (AUC) values are 94.36%, 0.875, and 0.927, respectively, using the optimal features subset. This article’s prediction of hypertension outcomes contributes to the in-depth study of hypertension complications and has strong practical significance.

Low Earth orbit (LEO) satellites play an important role in human space activities, and market demands for commercial uses of LEO satellites have been increasing rapidly in recent years. LEO satellites mainly consist of Earth observation satellites (EOSs), the major commercial applications of which are various sorts of Earth observations, such as map making, crop growth assessment, and disaster surveillance. However, the success rates of observation tasks are influenced considerably by uncertainties in local weather conditions, inadequate sunlight, observation dip angle, and other practical factors. The available time windows (ATWs) suitable for observing given types of targets and for transmitting data back to ground receiver stations are relatively narrow. In order to utilize limited satellite resources efficiently and maximize their commercial benefits, it is necessary to evaluate the overall effectiveness of satellites and planned tasks considering various factors. In this paper, we propose a method for determining the ATWs considering the influence of sunlight angle, elevation angle, and the type of sensor equipped on the satellite. After that, we develop a satellite effectiveness evaluation (SEE) model for satellite observation and data-downlink scheduling (SODS) based on the Availability–Capacity–Profitability (ACP) framework, which is designed to evaluate the overall performance of satellites from the perspective of time resource utilization, the success rate of tasks, and profit return. The effects of weather uncertainties on the tasks’ success are considered in the SEE model, and the model can be applied to support the decision-makers on optimizing and improving task arrangements for EOSs. Finally, a case study is presented to demonstrate the effectiveness of the proposed method and verify the ACP-based SEE model. The obtained ATWs by the proposed method are compared with those by the Systems Tool Kit (STK), and the correctness of the method is thus validated.

In this study, we investigated the time-varying capacitated lot-sizing problem under a fast-changing production environment, where production factors such as the setup costs, inventory-holding costs, production capacities, or even material prices may be subject to continuous changes during the entire planning horizon. Traditional lot-sizing theorems and algorithms, which often assume a constant production environment, are no longer fit for this situation. We analyzed the time-varying environment of today’s agile enterprises and modeled the time-varying setup costs and the time-varying production capacities. Based on these, we presented two mixed-integer linear programming models for the time-varying capacitated single-level lot-sizing problem and the time-varying capacitated multi-level lot-sizing problem, respectively, with considerations on the impact of time-varying environments and dynamic capacity constraints. New properties of these models were analyzed on the solution’s feasibility and optimality. The solution quality was evaluated in terms of the entropy which indicated that the optimized production system had a lower value than that of the unoptimized one. A number of computational experiments were conducted on well-known benchmark problem instances using the AMPL/CPLEX to verify the proposed models and to test the computational effectiveness and efficiency, which showed that the new models are applicable to the time-varying environment. Two of the benchmark problems were updated with new best-known solutions in the experiments.