Showing papers in "Information Sciences in 2022"

TL;DR: Wang et al. as discussed by the authors proposed an enhanced fast NSGA-II based on a special congestion strategy and adaptive crossover strategy, which can improve PS distribution and convergence and maintain PF precision.

TL;DR: In this article , a new reinforcement learning (RL)-based control approach that uses the Policy Iteration (PI) and a metaheuristic Grey Wolf Optimizer (GWO) algorithm to train the Neural Networks (NNs) is presented.

TL;DR: In this article , a reinforcement learning (RL)-based control approach that uses a combination of a deep Q-learning (DQL) algorithm and a metaheuristic Gravitational search algorithm (GSA) is presented.

TL;DR: In this paper, a novel reinforcement learning (RL)-based control approach that uses a combination of a deep Q-learning (DQL) algorithm and a metaheuristic Gravitational Search Algorithm (GSA) is employed to initialize the weights and the biases of the Neural Network (NN) involved in DQL in order to avoid the instability.

TL;DR: Wang et al. as mentioned in this paper proposed an incremental learning mechanism based on progressive fuzzy three-way concept for object classification in dynamic environment, which can directly process the continuous data through contrasting the numerical data into the membership degree of object to attribute.

TL;DR: Wang et al. as discussed by the authors proposed an incremental learning mechanism based on progressive fuzzy three-way concept for object classification in dynamic environment, which can directly process the continuous data through contrasting the numerical data into the membership degree of object to attribute.

TL;DR: In this article , a modified CSO by introducing three-phase co-evolutionary strategy (TPCSO) is developed, where the population is divided into two sub-populations and the losers in each subpopulation are coevolved.

TL;DR: Zhang et al. as discussed by the authors proposed RL level-based particle swarm optimization algorithm (RLLPSO) to improve the search efficiency of large-scale optimization problems, where a RL strategy for level number control is employed to improve search efficiency and a level competition mechanism is introduced to optimize the convergence performance.

TL;DR: In this paper , a graph convolution with adaptive filters and aggregator fusion (AF2GNN) is developed for hyperspectral image classification, which can deal with the problems of land cover discrimination, noise impaction, and spatial feature learning.

TL;DR: Wang et al. as discussed by the authors proposed a Bayesian optimization-based dynamic ensemble (BODE) that overcomes the single model-based methods limitation and provides a dynamic ensemble forecast combination for TS with time-varying underlying patterns.

TL;DR: EDEAdam as discussed by the authors is an ensemble of differential evolution and Adam, which integrates a modern version of the differential evolution algorithm with Adam, using two different sub-algorithms to evolve two sub-populations in parallel and thereby achieving good results in both global and local search.

TL;DR: In this paper, a systematic literature review of the state-of-the-art on emotion expression recognition from facial images is presented, where the most commonly used strategies employed to interpret and recognize facial emotion expressions, published over the past few years.

TL;DR: In this article , a method for screening spatial time-delayed traffic series based on the maximal information coefficient is proposed, from which traffic flow is predicted by adopting the combination of support vector regression method and k-nearest neighbors method.

TL;DR: In this paper , a lightweight deep neural network (DNN) with a reduced number of epochs and parameters was proposed for non-healthy versus healthy CXR screening using three different datasets: Covid-19, Pneumonia and Tuberculosis (TB).

TL;DR: A systematic literature review of the state-of-the-art on emotion expression recognition from facial images is presented in this article , where the most commonly used strategies employed to interpret and recognize facial emotion expressions, published over the past few years.

TL;DR: In this article , an adaptive finite-time tracking control for under-actuated nonlinear systems with unknown backlash-like hysteresis and arbitrary switchings is investigated. But the authors do not consider the effect of external disturbances on the system.

TL;DR: Wang et al. as discussed by the authors proposed a machine learning and genetic-algorithm-based hybrid method named MGH to obtain a prediction model that can make a good trade-off between two industry-required criteria, i.e., prediction accuracy and interpretability.

TL;DR: In this article , a new multi-objective scheduling model for extinguishing the fire of forests considering rescue priority with the limited rescue resources is proposed. But the main challenges to make these decisions are to consider the severity of each fire point with regards to the limited resources of vehicles.

TL;DR: In this paper , the convergence rate of the convergent Newton method and gradient steepest descent for the neural networks adaptation was investigated in the electric energy usage data prediction, where the second-order partial derivatives were incorporated inside of the time-varying adaptation rates.

TL;DR: In this article , the current status of studies on green shop scheduling problems in the context of Industry 4.0 is presented, and further research directions for GSSPs in the future are suggested.

TL;DR: In this paper , a probabilistic dominance relation with intuitionistic fuzzy sets is proposed for multi-attribute decision-making, and the conditional probability of the set is derived to evaluate the part supplier selection.

TL;DR: In this paper, a probabilistic dominance relation with intuitionistic fuzzy sets is proposed for multi-attribute decision-making, and the conditional probability of the set is derived to evaluate the part supplier selection.

TL;DR: In this article, the convergence rate of the convergent Newton method and gradient steepest descent for the neural networks adaptation was investigated. But the convergence of the convergence was not shown for electric energy usage data prediction.

TL;DR: Experimental results indicate that the proposed feature selection algorithm for label distribution learning was more effective than five state-of-art feature selection algorithms on twelve datasets, with respect to six representative evaluation measures.

TL;DR: Zhang et al. as discussed by the authors proposed a new social recommendation system called SocialLGN, where the representation of each user and item is propagated in the user-item interaction graph with light graph convolutional layers; in the meantime, the user's representation is updated in the social graph.

TL;DR: Wang et al. as mentioned in this paper proposed a clustering-and maximum consensus-based resolution framework with linguistic distribution for social network large-scale group decision making (SNLGDM) problems.

TL;DR: Wang et al. as mentioned in this paper developed an integrated design alternative assessment model integrating Z-cloud rough numbers (ZCRNs), best-worst method (BWM), and multi-attributive border approximation area comparison (MABAC).

TL;DR: Zhang et al. as discussed by the authors defined a new divergence measurement to quantify the differences between BPAs; they named this new metric the belief Rényi divergence, which takes the number of possible hypotheses into consideration, which makes it a more rational and effective difference measurement in the realm of evidence theory.

TL;DR: In this article , a 2D chaotic map based on Euler and Pi numbers, called eπ-map, is presented, which exploits infinity diversity attribute of these numbers and a diffusion operation referred to as bit reversion is proposed for manipulating the pixel value.