Disaster medical rescue in China mainly adopts the “on‐site rescue” model. Whether the location of emergency temporary blood supply sites is reasonable or not directly affects the rescue efficiency. The paper studies the robust location‐allocation for emergency temporary blood supply after disaster. First, the factors of several candidate sites were quantified by the entropy‐based TOPSIS method, and 12 candidate blood supply sites with higher priority were selected according to the evaluation indicators. At the same time, the uncertainty of blood demand at each disaster site increased the difficulty of decision‐making, and then, a robust location model (MIRP) was constructed with minimum cost with time window constraints. It is also constrained by the uncertain demand for blood in three scenarios. Second, the survival probability function was introduced, and the time window limit was given at the minimum cost to maximize the survival probability of the suffered people. Finally, the numerical example experiments demonstrate that the increase in demand uncertainty and survival probability cause the MIRP model to generate more costs. Compared with the three MIRP models, the MIRP‐ellipsoid set model gained better robustness. Also, given the necessary restrictions on the time window, the cost can be reduced by about 13% with the highest survival probability. Decision‐makers can select different combinations of uncertainty levels and demand disturbance ratios and necessary time constraints to obtain the optimal location‐allocation solution according to risk preference and actual conditions.
18 April 2022 in Physica A: Statistical Mechanics and its Applications
Variable selection plays an important role in various fields, such as process modeling and process monitoring. It generally involves a large number of predictor variables, usually with the number of predictor variables $d$ much larger than the sample size $n$ . Therefore, how to filter useful variables and extract useful information in high-dimensional setup is a critical issue in the era of big data. This paper proposes an improved Forward Regression algorithm for variable selection under the high-dimensional setup. The proposed improved Forward Regression method demonstrates good performance in relevant-variable selection by introducing a predefined stopping rule. The stopping rule links the residual sum of squares to the noise ratio so that the relevant predictors can be distinguished from the random noises. Throughout theoretical analysis and simulations, it is confirmed that the improved Forward Regression algorithm can identify relevant predictors to ensure selection consistency in variable selection. Compared with the traditional Forward Regression method, the proposed Forward Regression algorithm can improve prediction accuracy and reduce computational cost by selecting only the relevant variables.
Social media has become an essential channel for the public to create and obtain information during emergencies. As the theme of public concern for emergencies changes over time, there is a lack of research on its dynamic evolution from its latent stage. This paper selects the Henan rainstorm event as a case study and extracts the theme characteristics by combining the life cycle theory and Latent Dirichlet Allocation (LDA) model. It integrates the Term Frequency–Inverse Document Frequency (TF-IDF) and Pointwise Mutual Information (PMI) algorithms as the theme-coding data source to build a dynamic theme propagation model for emergencies. Our research results showed that the theme coding effectively verified the assumption of latent development trends. The dynamic theme model could reveal the theme characteristics of different time series stages of emergencies, analyze the law of the theme evolution of the network’s public opinion, and provide practical and theoretical insights for the emergency management of urban cities.
The product online review text contains a large number of opinions and emotions. In order to identify the public’s emotional and tendentious information, we present reinforcement learning models in which sentiment classification algorithms of product online review corpus are discussed in this paper. In order to explore the classification effect of different sentiment classification algorithms, we conducted a research on Naive Bayesian algorithm, support vector machine algorithm, and neural network algorithm and carried out some comparison using a concrete example. The evaluation indexes and the three algorithms are compared in different lengths of sentence and word vector dimensions. The results present that neural network algorithm is effective in the sentiment classification of product online review corpus.
Efficient resource configuration is critical to providing sustainable aged care services. Empirical studies are conducted with a two-stage data-driven method of DEA-Tobit. First, the BCC model of data envelopment analysis is employed, to determine whether the values obtained from the three efficiency aspects (namely technical, pure technical, and scale) are situated in the frontiers of production, whether DEA is effective, and whether the problems of uneconomical scale or low technical level are available. Next, the causes of these problems are analyzed. Then, the regression analysis is performed using Tobit with the influencing factors including GDP, the number of institutions engaged in elderly care, the number of day service centers in the communities, the number of medical service institutions for the elderly, and the density of the elderly population. Known as a city with a severely aging population, Shanghai will be selected for a case study to propose countermeasures from the three dimensions of the elderly group, the elderly care industry, and the market environment.