OBJECTIVE: To compare Cox models, machine learning (ML), and ensemble models combining both approaches, for prediction of stroke risk in a prospective study of Chinese adults. MATERIALS AND METHODS: We evaluated models for stroke risk at varying intervals of follow-up (<9 years, 0-3 years, 3-6 years, 6-9 years) in 503 842 adults without prior history of stroke recruited from 10 areas in China in 2004-2008. Inputs included sociodemographic factors, diet, medical history, physical activity, and physical measurements. We compared discrimination and calibration of Cox regression, logistic regression, support vector machines, random survival forests, gradient boosted trees (GBT), and multilayer perceptrons, benchmarking performance against the 2017 Framingham Stroke Risk Profile. We then developed an ensemble approach to identify individuals at high risk of stroke (>10% predicted 9-yr stroke risk) by selectively applying either a GBT or Cox model based on individual-level characteristics. RESULTS: For 9-yr stroke risk prediction, GBT provided the best discrimination (AUROC: 0.833 in men, 0.836 in women) and calibration, with consistent results in each interval of follow-up. The ensemble approach yielded incrementally higher accuracy (men: 76%, women: 80%), specificity (men: 76%, women: 81%), and positive predictive value (men: 26%, women: 24%) compared to any of the single-model approaches. DISCUSSION AND CONCLUSION: Among several approaches, an ensemble model combining both GBT and Cox models achieved the best performance for identifying individuals at high risk of stroke in a contemporary study of Chinese adults. The results highlight the potential value of expanding the use of ML in clinical practice.

With the advent of the Internet era, the demand for network in various fields is growing, and network applications are increasingly rich, which brings new challenges to network traffic statistics. How to carry out network traffic statistics efficiently and accurately has become the focus of research. Although the current research results are many, they are not very ideal. Based on the era background of big data and machine learning algorithm, this paper uses the ant colony algorithm to solve the typical resource‐constrained project scheduling problem and finds the optimal solution of network traffic resource allocation problem. Firstly, the objective function and mathematical model of the resource‐constrained project scheduling problem are established, and the ant colony algorithm is used for optimization. Then, the project scheduling problem in PSPLIB is introduced, which contains 10 tasks and 1 renewable resource. The mathematical model and ant colony algorithm are used to solve the resource‐constrained project scheduling problem. Finally, the data quantity and frequency of a PCU with a busy hour IP of 112.58.14.66 are analyzed and counted. The experimental results show that the algorithm can get the unique optimal solution after the 94th generation, which shows that the parameters set in the solution method are appropriate and the optimal solution can be obtained. The schedule of each task in the optimal scheduling scheme is very compact and reasonable. The peak time of network traffic is usually between 9 : 00 and 19 : 00‐21 : 00. We can reasonably schedule the network resources according to these time periods. Therefore, the network traffic statistics method based on the solution of resource constrained industrial project group scheduling problem under big data can effectively carry out network traffic statistics and trend analysis.

In many situations, it is desirable to optimize a sequence of decisions by maximizing a primary objective while respecting some constraints with respect to secondary objectives. Such problems can be naturally modeled as constrained partially observable Markov decision processes (CPOMDPs) when the environment is partially observable. In this work, we describe a technique based on approximate linear programming to optimize policies in CPOMDPs. The optimization is performed offline and produces a finite state controller with desirable performance guarantees. The approach outperforms a constrained version of point-based value iteration on a suite of benchmark problems.