查看更多>>摘要：The influence maximization problem is aimed at determining influential nodes as seeds to reach the maximal influential range. Considering the wide application in marketing and social dynamics, increasing attention has been paid to modeling the information diffusion process and efficient seed selection algorithms on both single-layer and multi-layer networks. Interestingly, some recent studies indicate that the robustness of seeds in the diffusion process against potential disturbances like structural failures is significant in applications. But the current study only considers scenarios on single-layer networks. Meanwhile, multi-layer networks have shown non-negligible values in theoretical analyses and practical applications; the study on the robust influence maximization on such networks is urgent but remains to be an open question. Therefore, this paper gives the design of a performance measure to evaluate the influence ability of seeds on multi-layer networks under structural destructions. And a rational configuration of the included changeable parameter is determined based on qualitative analyses. Further, a Memetic algorithm, termed MA-RIMMulti, has been devised with several problem-orientated operators to find influential and robust seeds. This algorithm successfully solves the robust influence maximization problem on multi-layer networks, and shows competitive performance over existing optimization methods on several synthetic and real-world networks. Additionally, the effect of structural changes on the performance of seeds is also studied, and the topological rewiring technique is validated to be effective to improve the influence range of seeds. From the perspective of the influence maximization problem and its robustness, the underlying information behind multi-layer networks has been excavated. Meanwhile, key nodes in such networks can be found via the proposed approach to facilitate possible tasks in social propagation and information diffusion.
查看更多>>摘要：Surgical cases assignment problem (SCAP) is among the most investigated parts in healthcare scheduling and assignment problems, in which a set of surgical cases are assigned to operating rooms within a specified planning horizon. Several methods have been developed to provide approximate solutions for SCAP. Nevertheless, existing methods underperform at the large-scale instances. In this paper, a discrete squirrel search algorithm (DSSA) is proposed for SCAP with the objective of minimizing total operating cost. First, four heuristics are presented to improve quality and diversity of initial population. Second, a surgical case sequence vector is employed to encode individuals, and a corresponding decoding scheme is designed to construct feasible schedules. Third, several efficient heuristics are embedded into DSSA to enhance the search capacity. Moreover, the Taguchi method of design-of-experiment (DOE) is adopted to explore the influence of parameter settings. To the best of our knowledge, it is the first application of the squirrel search algorithm for SCAP. The effectiveness of DSSA is conducted on a typical benchmark dataset. Computational results and comparisons demonstrate the superiority of the proposed scheme over the existing methods in solution accuracy and consuming time for solving SCAP.
查看更多>>摘要：As is known, the financial market prediction and high investing value is receiving more increasing attentions nowadays. But affected by many complex factors, it is difficult to perform the financial market forecast accurately. Among the solving methods, the time-series prediction has caused the focus for its great predictive effect in many fields. However, most of the existing works focus on single-time-series analysis and cannot obtain good learning results because it trains tasks independently and ignores the cross-correlation among multiple time series. Motivated by the multitask learning, a novel online multitask learning based on the least squares support vector regression (OMTL-LS-SVR) algorithm is proposed for multi-step-ahead financial time-series prediction. OMTL-LS-SVR regards multiple related time series as different learning tasks, which are trained in parallel to obtain the prediction model and shorten the training time. Under this scheme, the knowledge from one certain task can benefit others, allowing it to exploit the relatedness among multiple subtasks. The OMTL-LS-SVR is applied to perform the time-series tendency prediction in four branches of China's financial market, and the experimental results demonstrate the effectiveness of the proposed multitask learning algorithm.
查看更多>>摘要：The COVID-19 pandemic has significantly affected the supply chains (SCs) of many industries, including the oil and gas (O&G) industry. This study aims to identify and analyze the drivers that affect the resilience level of the O&G SC under the COVID-19 pandemic. The analysis helps to understand the driving intensity of one driver over those of others as well as drivers with the highest driving power to achieve resilience. Through an extensive literature review and an overview of experts’ opinions, the study identified fourteen supply chain resilience (SCR) drivers of the O&G industry. These drivers were analyzed using the integrated fuzzy interpretive structural modeling (ISM) and decision-making trial and evaluation laboratory (DEMATEL) approaches. The analysis shows that the major drivers of SCR are government support and security. These two drivers help to achieve other drivers of SCR, such as collaboration and information sharing, which, in turn, influence innovation, trust, and visibility among SC partners. Two more drivers, robustness and agility, are also essential drivers of SCR. However, rather than influencing other drivers for their achievement, robustness and agility are influenced by others. The results show that collaboration has the highest overall driving intensity and agility has the highest intensity of being influenced by other drivers.
查看更多>>摘要：In a fuzzy multicriteria decision-making (MCDM) problem, a decision maker may have differing viewpoints on the relative priorities of criteria. However, traditional methods merge these viewpoints into a single one, which leads to an unrepresentative decision-making result. Several recent methods identify the multiple viewpoints of a decision maker by decomposing the decision maker's fuzzy judgment matrix into several symmetric fuzzy subjudgment matrices, which is an inflexible strategy. To enhance flexibility, this study proposed a fuzzy geometric mean (FGM) decomposition-based fuzzy MCDM method in which FGM is applied to decompose a fuzzy judgment matrix into several fuzzy subjudgment matrices that can be asymmetric. These fuzzy subjudgment matrices are diverse and more consistent than the original fuzzy judgment matrix. The proposed methodology was applied to select the best choice from a group of smart technology applications for supporting mobile health care during and after the COVID-19 pandemic. According to the experimental results, the proposed methodology provided a novel approach to decomposing fuzzy judgment matrices and produced more diverse fuzzy subjudgment matrices.
查看更多>>摘要：This paper presents a new fitness evaluation approach based on aggregated pairwise comparisons (APC), i.e., a multiplicative maximin fitness ranking indicator with norm-p (M2F-p), for solving multi/many-objective problems. The M2F-p uses an adjustable aggregation of pairwise comparisons induced by p to alleviate the incomparability of solutions in terms of Pareto dominance when the number of objectives increases. We analyze the search ability of M2F-p under different p values. It is shown that the p values can control the shape of contour lines (i.e., a set of equal M2F-p values), which can affect the convergence and uniformity of solutions. Then, we illustrate that the M2F-p offers a set of promising properties that can enhance the discriminability of solutions. Further, we develop an efficient algorithm based on M2F-p by using an adaptive p-selection strategy and a diversity-maintenance mechanism. We conduct experiments on a suit of test problems with up to 10 objectives. The experimental results validate the effectiveness of the proposed algorithm on both multi-objective problems and many-objective problems.
查看更多>>摘要：Across the globe, solar photovoltaic (PV) sources are treated as the most favorable renewable sources which can fulfill a larger percentage of the total electricity demand with its clean form of energy. But due to its intermittent characteristics, the PV injects lots of uncertainty into the power system. Because of variation in input solar intensity due to climatic conditions, it will impact on the power quality (PQ) issues in power industries. Therefore, in this proposal, a solar PV integrated with shunt hybrid active filter (SHAF) is taken to fulfill the objective of (a) reducing the current harmonics and (b) supplying the active power generated from the PV system. The challenging task in the proposal is to control the PV variables and current control in voltage source inverter (VSI) of the SHAF. Therefore, three-key contributions are made as follows: (a) a control strategy designed which is based on adaptive notch filters (ANF) for reducing the harmonics by generating accurate reference currents; (b) a hysteresis controller is implemented for gating signal pulses; and (c) for maximum power tracking, a fuzzy based maximum power point tracking (MPPT) is developed for the solar tracker. We showed embedded applications of a SHAF for regulating the grid interfaced PV system. Besides a SHAF operated with the ANF and based on the direct current control (DCC) method is used for computing the compensated current. A comparative analysis has been done between ANF (least mean square (LMS) and recursive least square (RLS) method) and the existing non-adaptive notch filters (NNF). Rigorous computer simulations are performed to determine the effectiveness of the proposed system. The real-time digital simulator using OP 5142 designed with low cost and advanced monitoring capability is employed for validating results.
查看更多>>摘要：Evaluating patient criticality is the foremost step in administering appropriate COVID-19 treatment protocols. Learning an Artificial Intelligence (AI) model from clinical data for automatic risk-stratification enables accelerated response to patients displaying critical indicators. Chest CT manifestations including ground-glass opacities and consolidations are a reliable indicator for prognostic studies and show variability with patient condition. To this end, we propose a novel attention framework to estimate COVID-19 severity as a regression score from a weakly annotated CT scan dataset. It takes a non-locality approach that correlates features across different parts and spatial scales of the 3D scan. An explicit guidance mechanism from limited infection labeling drives attention refinement and feature modulation. The resulting encoded representation is further enriched through cross-channel attention. The attention model also infuses global contextual awareness into the deep voxel features by querying the base CT scan to mine relevant features. Consequently, it learns to effectively localize its focus region and chisel out the infection precisely. Experimental validation on the MosMed dataset shows that the proposed architecture has significant potential in augmenting existing methods as it achieved a 0.84 R-squared score and 0.133 mean absolute difference.
查看更多>>摘要：In the field of medical informatics, the accuracy of medical data classification plays a vital role. Multi-layer Perceptron (MLP), as one of the most widely used neural networks, has been widely used in the medical fields. In recent years, the Biogeography-based Optimization (BBO) algorithm has been proposed to train MLP, but the original algorithm often encounters local minimums, slow convergence, and sensitivity to initialized values during the optimization process. To this end, this paper adopted the different probability distributions to improve the BBO (PD-BBO) algorithm to train MLP so as to improve medical data classification accuracy. These distributions include Gamma distribution, Beta distribution, Gaussian distribution, Exponential distribution, Poisson distribution, Geometric distribution, Rayleigh distribution and Weber distribution Then these different probability distributions were embed into the migration process of the BBO algorithm to replace the random distribution and the migration probability was defined. Finally, simulation experiments were carried out, and the benchmark function was used to prove the effectiveness of the proposed algorithms. And then it was used to train a multi-layer perceptron, and five medical data sets were selected for classification. After that, the performance of the standard BBO algorithm and five typical meta-heuristic algorithms were compared. The results showed that the PD-BBO algorithms to train MLP was better than the BBO algorithm and the selected meta-heuristic algorithms, and the classification accuracy has been improved to a certain extent.
查看更多>>摘要：‘Curse of dimensionality’ and the trade-off between low false alarm rate and high detection rate are the major concerns while designing an efficient intrusion detection system. In this study, we propose a hybrid framework comprising deep auto-encoder (AE) with the long short term memory (LSTM) and the bidirectional long short term memory (Bi-LSTM) for intrusion detection system by obtaining optimal features using AE and then LSTMs for classification into normal and anomaly samples. The performance of the proposed models is evaluated on the well-known dataset NSL-KDD in terms of error indices including precision, recall, F-score, accuracy, detection rate (DR), and false alarm rate (FAR). Experimental results indicate that the proposed AE-LSTM performance is significantly better with less prediction error as compared to other deep and shallow machine learning techniques including other recently reported methods. On the NSL-KDD dataset, AE-LSTM shows classification accuracy of 89% with DR of 89.84% and FAR of 11% which demonstrates the enhanced performance of the proposed model over recent state-of-the-art techniques.
NSTL
Elsevier