Showing papers in "Information Sciences in 2020"

TL;DR: A novel metaheuristic optimization algorithm, gradient-based optimizer (GBO) is proposed, which yielded very promising results due to its enhanced capabilities of exploration, exploitation, convergence, and effective avoidance of local optima.

TL;DR: YAKE!, a light-weight unsupervised automatic keyword extraction method which rests on statistical text features extracted from single documents to select the most relevant keywords of a text, is described.

TL;DR: A Boolean network encryption algorithm for a synchronous update process is proposed, and a matrix semi-tensor product technique to generate an encrypted image in a second round of diffusion shows good security characteristics.

TL;DR: The goal of this paper is to demonstrate the effects of class imbalance on classification models and determine that the relationship between the class imbalance ratio and the accuracy is convex.

TL;DR: Experimental results on a series of public datasets show that the effective combination of the binary mutation and OPS makes the MOFS-BDE achieve a trade-off between local exploitation and global exploration.

TL;DR: Compared with other encryption algorithms, the algorithm proposed in this paper is more secure and effective, and it is also suitable for color image encryption.

TL;DR: A hybrid deep learning model to efficiently detect network intrusions based on a convolutional neural network (CNN) and a weight-dropped, long short-term memory (WDLSTM) network is proposed, which uses the deep CNN to extract meaningful features from IDS big data and W DLSTM to retain long-term dependencies among extracted features to prevent overfitting on recurrent connections.

TL;DR: The proposed RB divergence is the first such measure to consider the correlations between both belief functions and subsets of the sets of belief functions, thus allowing it to provide a more convincing and effective solution for measuring the discrepancy between BBAs in D–S evidence theory.

TL;DR: The results show that the proposed Dynamic-GRCNN effectively captures comprehensive spatial-temporal correlations significantly and outperforms both traditional and deep learning based urban traffic passenger flows prediction methods.

TL;DR: Zhang et al. as mentioned in this paper proposed a dense connection and spatial pyramid pooling (SPP) based YOLO (DC-SPP-YOLO) method for ameliorating the object detection accuracy.

TL;DR: Qualitative and quantitative experimental results on publicly available datasets demonstrate that the proposed target-enhanced multiscale transform (MST) decomposition model for infrared and visible image fusion can generate fused images with clearly highlighted targets and abundant details.

TL;DR: In this article, the authors proposed an innovative MAGDM (multiattribute group decision making) process based on weighted averaging neutral aggregation operators (AOs) to aggregate the q-ROF erudition.

TL;DR: Since the network is characterised by smooth fourth-order exponential nonlinearity, a distinctive approach is employed to assess its different properties: the circuit stability near fixed points is examined and dynamic complexity is evaluated using the Lyaponov spectrum analysis, bifurcation analysis and phase space trajectories.

TL;DR: Enhanced versions of the NSGA-III algorithm are proposed through introducing the concept of Stud and designing several improved crossover operators of SBX, UC, and SI, and experimental results indicate that the NS GA-III methods with UC and UC-Stud (UCS) outperform the other developed variants.

TL;DR: Four methods based on neighbourhood searching with different criteria to identify potential overlapped instances are proposed in this paper and show comparable performance with state-of-the-art methods across different common metrics with exceptional and statistically significant improvements in sensitivity.

TL;DR: Evaluation of the proposed one-dimensional sine powered chaotic system indicates the existence of chaotic behavior with high sensitivity and randomness, and a new image encryption scheme using 1DSP (1DSP-IE), which uses the 1D SP for sequence addition to improve its security.

TL;DR: This work proposes BotMark, an automated model that detects botnets with hybrid analysis of flow-based and graph-based network traffic behaviors with superior detection accuracy, and collects a very large size of network traffic by simulating 5 newly propagated botnets in a real computing environment.

TL;DR: An active three-way clustering method via low-rank matrices that can improve clustering accuracy as clustering proceeds for the multi-view data of high dimensionality and suggests an active learning strategy to learn important informative pairwise constraints after measuring the uncertainty of an object based on the entropy concept.

TL;DR: A novel artificial intelligence algorithm, called deep Q-learning task scheduling (DQTS), that combines the advantages of the Q- learning algorithm and a deep neural network is proposed, aimed at solving the problem of handling directed acyclic graph tasks in a cloud computing environment.

TL;DR: A hybrid many-objective particle swarm optimization (HMaPSO) algorithm is designed to solve the established model of green coal production and can provide promising choices for decision makers in regional planning.

TL;DR: The proposed framework, with support vector machines, resulted in mean accuracies of 97% and 93% for binary classification of human breast cancer and CMT respectively, which validates the efficacy of the proposed system.

TL;DR: An improved Pawlak conflict analysis model is presented by using the principle of three-way decision based on probabilistic rough set over two universes that provides a new perspective and methodology to handle the conflict analysis problems and overcomes the limitations of the original model.

TL;DR: A learning-based algorithm is proposed, aimed to enhance the generalization ability, on the basis of a decomposition-based many-objective optimization framework, and a learning automaton (LA) is included in the algorithm.

TL;DR: An end-to-end method that uses bidirectional tree-structured long short-term memory (LSTM) to extract structural features based on the dependency tree of a sentence to enhance the performance of the relation extraction.

TL;DR: In this paper, confusion matrix is endowed with semantics of three-way decisions, and a collection of measures are deduced and summarized into seven measure modes, which can deduce more satisfying three- way regions.

TL;DR: This study develops the notion of multigranulation decision-theoretic rough sets (MG-DTRSs) into the HFL background within the two-universe framework and proposes a hybrid model named adjustable HFL MG-D TRSs over two universes by introducing an adjustable parameter for the expected risk appetite of experts.

TL;DR: A fast probabilistic cryptosystem to secure medical keyframes that are extracted from wireless capsule endoscopy procedure using a prioritization method and exhibits randomness behavior, which guarantee computational efficiency as well as a highest level of security for the keyframes against various attacks.

TL;DR: This paper discusses the applications on evolutionary computations for different types of ARM approaches including numerical rules, fuzzy rules, high-utility itemsets, class association rules, and rare association rules and discusses the remaining challenges of evolutionary ARM.

TL;DR: This paper proposes six variants of MOEA/D, and these algorithms can be divided into two categories according to the way of selecting individuals whether it is random or fixed, and a new selection strategy has been introduced to further improve the performance of MOE/D-IFM.

TL;DR: To reduce the number of interactions in the execution of contract, the notion of non-interactive public provable data possession is presented and a blockchain-based smart contract for public cloud storage auditing based on this primitive is designed.