Asghari, MohsenSierra-Sosa, DanielElmaghraby, Adel S.
17页
查看更多>>摘要：A primary focus of the healthcare industry is to improve patient experience and quality of service. Practitioners and health workers are generating large volumes of text that are captured in Electronic Medical Records, clinical reports, and publications. Additionally, patients post millions of comments on social media related to healthcare, on diverse topics such as hospital services, disease symptoms, and drugs effects. Unifying various data sources can guide physicians and healthcare workers to avoid unnecessary, irrelevant information and expedite access to helpful information. The main challenge to creating Biomedical Natural Language Understanding is the lack of standard datasets and the extensive computational resources needed to develop different models. This paper proposes a model trained on low-tier GPU computers, producing comparable results to larger models like BioBERT. We propose BINER, a Biomedical Named Entity Recognition architecture using limited data and computational resources. (c) 2022 The Authors. Published by Elsevier Inc.
查看更多>>摘要：Hyperspectral image classification (HSIC) is essential in remote sensing image analysis. Applying a graph neural network (GNN) to hyperspectral image (HSI) classification has attracted increasing attention. However, the available GNNs for HSIC only adopt a kind of graph filter and an aggregator, which cannot well deal with the problems of land cover discrimination, noise impaction, and spatial feature learning. To overcome these problems, a graph convolution with adaptive filters and aggregator fusion (AF2GNN) is developed for HSIC. To reduce the number of graph nodes, a superpixel segment algorithm is employed to refine the local spatial features of the HSI. A two-layer 1D CNN is proposed to transform the spectral features of superpixels. In addition, a linear function is designed to combine the different graph filters, with which the graph filter can be adaptively determined by training different weight matrices. Moreover, degree-scalers are defined to combine the multiple filters and present the graph structure. Finally, the AF2GNN is proposed to realize the adaptive filters and aggregator fusion mechanism within a single network. In the proposed network, a softMax function is utilized for graph feature interpretation and pixel-label prediction. Compared with state-of-the-art methods, the proposed method achieves superior experimental results. (c) 2022 Elsevier Inc. All rights reserved.
查看更多>>摘要：In recent years, attributed networks are increasingly available for us. How to leverage attri-bute information to gain a better performance of community detection has attracted grow-ing attention. Most established approaches focus on exploiting attribute information based on the observed homophily assumption that nodes with similar attributes are more likely to be connected. Since not all attributes are truly relevant for the formation of communi-ties, such an assumption may not hold in real-world attributed networks. In many cases, only a subset of attributes are the key factors to make nodes connected to form communi-ties and they may differ largely for different communities. In this paper, we propose a new community detection approach in attributed networks, called SOA, by examining the Subspaces Of Attributes. The basic idea is to regard the community detection as an opti-mization problem, which aims at learning a new similarity matrix to maximize the homo-phily. By employing an efficient optimization strategy, the high-quality communities as well as their corresponding relevant attributes (i.e., attribute subspaces) are automatically identified. Extensive experimental results on both synthetic and real-world networks have demonstrated the effectiveness of SOA, and shown its superiority over state-of-the-art approaches.(c) 2022 Published by Elsevier Inc.
查看更多>>摘要：A structural hole spanner in a social network is a user who bridges multiple communities, and he can benefit from acting the bridging role, such as arbitrating information across different communities or getting earlier access to valuable and diverse information. Existing studies of finding hole spanners either identified redundant hole spanners (i.e., communities bridged by different hole spanners are redundant) or found nonredundant hole spanners only by network structure. Unlike the existing studies, we not only study a problem of finding top -k hole spanners that connect nonredundant communities in the social network, but also consider the tie strengths between different pairs of users and the different information sharing rates of different users, so that after removing the found users, the number of blocked information diffusion is maximized. In addition, we devise a novel 1 -1 ( )- e approximation algorithm for the problem, where e is the base of the natural logarithm. We further propose a fast randomized algorithm with a smaller time complexity. Our experiment results demonstrate that, after removing the nodes found by the proposed two algorithms, the numbers of blocked information diffusion can be up to 80% larger than those by existing algorithms.@2022 Elsevier Inc. All rights reserved.
查看更多>>摘要：Difficult and expensive financing has always been a problem for domestic and foreign enterprises, and how to effectively improve financing efficiency and improve the financing environment is a key issue to be studied. LightGBM is an advanced machine learning algo-rithm, which uses histogram algorithm and Leaf-wise strategy with depth limitation to improve the accuracy of the model. However, there are almost no cases of applying this method to corporate financing risk prediction. Therefore, the paper establishes the LightGBM model to predict the financing risk profile of 186 enterprises. In order to com-pare the prediction performance of LightGBM for enterprise financing risk, the paper con-ducted comparison experiments using k-nearest-neighbors algorithm, decision tree algorithm, and random forest algorithm on the same data set. The experiments show that LightGBM has better prediction results than the other three algorithms for several metrics in corporate financing risk prediction. Therefore, we believe that the LightGBM algorithm can be used as an effective tool to predict the financing risk of enterprises.(c) 2022 Published by Elsevier Inc.
查看更多>>摘要：Nowadays, with the increasing complexity of decision-making environment, more and more large-scale group decision making (LGDM) problems are faced. Due to the existence of social network relationships among experts, social network analysis (SNA) is proved to be an effective analysis method for LGDM problems. Meanwhile, it is crucial for LGDM issues to determine the weights of decision groups and to lessen the large-scale DMs' dimension, which will affect the result of decision making directly. This study proposes a clustering- and maximum consensus-based resolution framework with linguistic distribution (LD) for social network large-scale group decision making (SNLGDM) problems. In the consensus framework, independent sub-groups can be obtained by the division of largescale DMs according to trust relationship using the proposed SNA-based trust network clustering model, and the LD assessments are used to represent the preference relation of sub-groups. Following this, by considering three dependable sources: consistency, similarity, and in-centrality degree, this paper devises a maximum consensus-based method, which can generate the sub-groups' comprehensive weight by maximizing the level of consensus between sub-groups and the collective matrix. Meanwhile, the final ranking of alternatives can be obtained based on collective preference relation. Conclusively, the availability and advantage of this research are verified through numerical example, coefficient analysis and comparative analysis.
查看更多>>摘要：Large-scale optimization problems (LSOPs) have drawn researchers' increasing attention since their resemblance to real-world problems. However, due to the complex search space and massive local optima, it is challenging to simultaneously guarantee the diversity and convergence of the algorithms. As a widely used evolutionary algorithm with fast convergence, particle swarm optimization (PSO) shows competitive performances on some LSOPs. Nevertheless, it can easily get trapped into local optima. Overcoming the complexity of LSOPs and improving search efficiency have become vital issues. The reinforcement learning method has proven to be an effective technique in self-adaptive adjustment, which can help search for better results in large-scale solution space more effectively. In this paper, we propose a large-scale optimization algorithm called reinforcement learning level based particle swarm optimization algorithm (RLLPSO). In RLLPSO, a level-based population structure is constructed to improve population diversity. A reinforcement learning strategy for level number control is employed to help improve the search efficiency of RLLPSO. To further enhance the convergence ability of RLLPSO, a level competition mechanism is introduced. The experimental results from two large-scale benchmark test suites demonstrate that, compared with five state-of-the-art large-scale optimization algorithms, RLLPSO shows superiority in most cases. (c) 2022 Elsevier Inc. All rights reserved.
Flor-Sanchez, Carlos O.Resendiz-Flores, Edgar O.Altamirano-Guerrero, Gerardo
15页
查看更多>>摘要：A new hybrid metaheuristic method is proposed which is inspired from the recently proposed gradient-evolution method. This study introduces for the first time the concept of reproducing kernel in order to correctly estimate the numerical gradient which is used as an updating rule. This proposed method is called Kernel-based Gradient Evolution (GE) which inherits good exploration and exploitation abilities as well as non localization through several operators taken from the original gradient-evolution algorithm. In the proposed KGE algorithm the gradient vector is computed using a kernel reproducing function. Thus the local gradient estimation is numerically computed considering a local Taylor series expansion. The IEEE CEC 2019 test suite is considered in order to evaluate the numerical performance of the proposed KGE algorithm. A numerical comparison between some competitive methods and the one proposed in this work is reported. The obtained numerical results suggested that in terms of convergence, KGE algorithm performs in most cases significantly better than the original GE algorithm and gets respectable results against other considered methods.(c) 2022 Elsevier Inc. All rights reserved.
查看更多>>摘要：Studying the representational capacity of neural networks to learn nonlinear rewards is necessary in a complex and nonlinear environment. Over recent years, the maximum entropy deep inverse reinforcement learning algorithm (ME-DIRL) has been increasingly applied to the learning of nonlinear rewards. However, under cases of limited and imbalanced expert demonstration data, complex calculations, or overfitting, the learning nonlinear rewards remains a challenging problem. A novel ME-DIRL with AdaBoost algorithm (AME-DIRL) is our proposed solution. The focus of AME-DIRL is to utilize the AdaBoost algorithm. This combines multiple ME-DIRL processes to form a strong learner and thus overcome the imbalance of the data set. Furthermore, to deal with the complex calculations in AME-DIRL, a truncated gradient (TG) method is applied for getting the sparse rewards obtained by the strong learner, thus reducing the model complexity. To prevent overfitting, a correction factor is then added to the linear combination of weak learners. AME-DIRL models the relationship between input features and output rewards. Rewards are approximated by means of a convolutional neural network (CNN) with scaled exponential linear units (SELUs). Numerical results indicate that our proposed AME-DIRL shows higher accuracy in learning rewards when compared with several classical inverse reinforcement learning (IRL) algorithms. (c) 2022 Elsevier Inc. All rights reserved.
查看更多>>摘要：In partial label learning (PLL), each instance is associated with a candidate label set, and only one label is ground-truth. PLL aims to identify the ground-truth label out of these candidate labels. Most of the existing PLL approaches focus on single-task PLL, and ignore the auxiliary information of the related tasks. This paper puts forward a novel multi-task manifold learning method for partial label learning (MT-PLL), which learns multiple PLL tasks jointly, and incorporates the auxiliary information of the related tasks to improve the performance of PLL classifiers. MT-PLL assumes that the graph manifold structure guides the generation of labeling confidence for instances in each task. In addition, the information of related tasks can be used to boost the performance of the overall classification model. Then, a heuristic framework is used to optimize the objective function. Numerical experiments have demonstrated that MT-PLL can deliver better performance than state-of-the-art single-task PLL methods. (c) 2022 Published by Elsevier Inc.
NSTL
Elsevier