首页期刊导航|Information Sciences
期刊信息/Journal information
Information Sciences
Elsevier
Information Sciences

Elsevier

0020-0255

Information Sciences/Journal Information SciencesSCIAHCIISTPEI
正式出版
收录年代

    A multi-autoencoder fusion network guided by perceptual distillation

    Liu X.Hirota K.Jia Z.Dai Y....
    20页
    查看更多>>摘要：? 2022In this study, a novel distillation paradigm named perceptual distillation is proposed to guide the training of image fusion networks without ground truths. In the paradigm, the student network which we called main autoencoder takes in source images and produces a fused image, and the teacher network is a well-trained network exploited to compute teacher representations of images. Knowledge in the teacher representations of source images is distilled and transferred to our student main autoencoder with the help of the perceptual saliency scheme. The scheme also derives a pixel level scheme of pixel compensation, which combines with source image to enhance the pixel intensity of the fused image. Moreover, a multi-autoencoder architecture is developed by assembling two auxiliary decoders behind the main autoencoder. The architecture is trained with self-supervision to consolidate fusion training against the limitation of teacher network. Qualitative and quantitative experiments demonstrate that the proposed network achieves the state-of-the-art performance on multi-source image fusion compared with the existing fusion methods.
      原文链接:
    • NSTL
    • Elsevier

    Selection of appropriate bonds between L-fuzzy formal contexts for recommendation tasks

    Kridlo O.AntoniKrajci S.
    17页
    查看更多>>摘要：? 2022 Elsevier Inc.The bond between L-fuzzy formal contexts can be defined as a (Galois) connection between L-fuzzy concept lattices of L-fuzzy formal contexts. The selection of appropriate bond from the set of all bonds between L-fuzzy formal contexts is an important challenge to apply it in recommendation tasks. We propose the general method for the selection of bonds regarding external information given by L-fuzzy relation. The alternative versions of direct products of L-fuzzy formal contexts are formulated and explored since we demonstrate that the extent of direct product is a bond between input L-fuzzy formal contexts. We present examples of the benevolent and rigorous recommendations in several application domains including the real dataset about music genres. Finally, the connections with factorization of L-fuzzy formal contexts and Sugeno integral are thoroughly studied in our paper.
      原文链接:
    • NSTL
    • Elsevier

    Multi-objective workflow scheduling based on genetic algorithm in cloud environment

    Qiu H.Xia X.Xu X.Zhang Y....
    22页
    查看更多>>摘要：? 2022 Elsevier Inc.In recent years, cloud computing plays a crucial role in many real applications. Thus, how to solve workflow scheduling problems, i.e., allocating and scheduling different resources, under the cloud computing environment becomes more important. Although some evolutionary algorithms (EAs) can solve workflow scheduling problems with a small scale, they show some disadvantages on larger scale workflow applications. In this paper, a multi-objective genetic algorithm (MOGA) is applied to optimize workflow scheduling problems. To enhance the search efficiency, this study proposes an initialization scheduling sequence scheme, in which each task's data size is considered when initializing its virtual machine (VM) instance. Relying on the initial scheduling sequence, a proper trade-off between the makespan and the energy consumption, which are two optimization objectives in this study, can be achieved. In the early evolution stage, traditional crossover and mutate operators are performed to keep the population's exploration. On the contrary, the longest common subsequence (LCS) of multiple elite individuals, which can be regarded as a favorable gene block, is saved during the later evolution stage. Based on the LCS, the probability of some favorable gene blocks being destroyed will be reduced when performing the crossover operator and the mutate operator. Hence, the integration of the LCS in GA can satisfy different requirements in different evolution stages, and then to attain a balance between the exploration and the exploitation. Extensive experimental results verify that the proposed GA combined with LCS, named as GALCS in this paper, can find a better Pareto front than the ordinary GA as well as other state-of-the-art algorithms. Furthermore, effectivenesses of the new proposed strategies are also verified by a set of experiments.
      原文链接:
    • NSTL
    • Elsevier

    Sender anonymity: Applying ring signature in gateway-based blockchain for IoT is not enough

    Voundi Koe A.S.Ai S.Huang P.Tang J....
    12页
    查看更多>>摘要：? 2022Over the last decade, there has been extensive research into the security and privacy of blockchain technology, from the use of ring signatures to ring confidential transactions. Although existing cryptographic methods perform well on traditional blockchain architectures, they do not provide complete privacy in a hierarchical blockchain architecture for Internet of Things (IoT) devices. The blockchain technology is centered at the gateway layer in the hierarchical blockchain architecture, which can easily reveal the transaction sender using network traffic information, thereby violating the sender's anonymity. Furthermore, the gateway can perform eclipse attacks against transaction senders on a case-by-case basis. To this end, this paper proposes a novel security and privacy blockchain protocol that is better suited to the hierarchical blockchain architecture and thus more appropriate for the IoT environment. Specifically, it leverages the relationship among IoT devices at the perception layer of the hierarchical blockchain architecture for IoT, and constructs an overlay social IoT network by exploiting devices’ multi-agent capabilities. Furthermore, circuit establishment based on multilayered encryption is applied to conceal the transaction propagation path through the overlay social IoT. Theoretical analysis shows that our novel protocol is flexible, evades a malicious gateway, and is secure under the decisional Diffie-Hellman assumption.
      原文链接:
    • NSTL
    • Elsevier

    A high-order norm-product regularized multiple kernel learning framework for kernel optimization

    Ching W.-K.Qiu Y.Jiang H.Shen D....
    20页
    查看更多>>摘要：? 2022 Elsevier Inc.Kernels offer an effective alternative to implicitly embed the original data into a higher or infinite-dimensional space in support vector machines. Kernel learning, which attempts to determine optimal kernel functions to evaluate relationships between data, has garnered increasing interest. Employing multiple kernels to enhance optimality and generalization is a promising direction. In this study, we focused on the parameter optimization problem of Hadamard kernel functions, which is a newly proposed kernel in machine learning. Motivated by the multiple kernel learning framework in optimizing kernel combinations and the intriguing properties that L4-norm possess, we proposed a high-order L4Lp(p?3) norm-product regularized multiple kernel learning framework to optimize the discrimination performance, where hinge, log, and square loss functions are detailed. We demonstrated that the Hadamard multiple kernel learning can effectively obtain the optimal performance while implicitly avoiding the parameter specification difficulty by optimizing the linear combination of Hadamard kernel functions over different kernel parameters. The effectiveness of the proposed approach was verified through experiments on several benchmark datasets. In addition, the high-order L4Lp(p?3) norm-product regularized multiple kernel learning framework can be used to optimize radial basis function kernels under different kernel parameters.
      原文链接:
    • NSTL
    • Elsevier

    Evolutionary self-organizing fuzzy system using fuzzy-classification-based social learning particle swarm optimization

    Zhao T.Chen C.Cao H.
    20页
    查看更多>>摘要：? 2022 Elsevier Inc.A self-organizing algorithm based on an online cluster and fuzzy sets update algorithm (OCFU) and fuzzy-classification-based social learning particle swarm optimization (FC-SLPSO) is proposed to address the problem of rule initialization and fitness function evaluation. The OCFU algorithm is used to determine the structure of the fuzzy system and build a flexible partition of fuzzy sets in each input variable. The FC-SLPSO algorithm establishes a fuzzy K-Nearest Neighbor (KNN) classifier in each iteration. The fitness evaluation is performed only when the membership degree of the offspring particles belonging to potential particles is greater than that of the parent particles, which effectively reduces the number of fitness function evaluations and accelerates the PSO algorithm. The tracking results of three nonlinear systems show that the tracking accuracy of the proposed method is better. The Pioneer P3DX mobile robot model and simulation environment with a two-dimensional lidar are constructed based on the Coppeliasim robot simulation platform. Using the algorithms proposed in this paper, the tracking task of the pioneer p3dx mobile robot along a wall is achieved. The effectiveness of the proposed algorithm is verified by the cosimulation of Coppeliasim and MATLAB in multiple scenarios.
      原文链接:
    • NSTL
    • Elsevier

    Blind image quality assessment of magnetic resonance images with statistics of local intensity extrema

    Oszust M.Bielecka M.Bielecki A.Stepien I....
    14页
    查看更多>>摘要：? 2022 Elsevier Inc.Magnetic resonance (MR) imaging provides a large amount of data that requires a visual inspection before a diagnosis can be made. Since the exclusion of low-quality image sequences is performed manually and image processing methods are evaluated using techniques developed for natural images, automatic and reliable MR image quality assessment (IQA) approaches are desirable. Therefore, in this work, a new no-reference (NR) MR-IQA technique is proposed. The method uses introduced quality-aware features addressing characteristics of MR images. Specifically, in the method, an MR image is scaled, filtered with two gradient operators, and subjected to identification of the local intensity extrema. Then, the entropy and κ curvature are calculated to characterize extrema sequences and used as perceptual features to train a quality model with the Support Vector Regression (SVR) technique. In this paper, an extensive comparative evaluation of the method against recent NR approaches, including deep learning-based models, is conducted on two representative MR-IQA benchmarks. The results reveal the superiority of the introduced approach over competing methods as it obtained better overall Spearman and Pearson correlation coefficients by 5% and 3%, respectively.
      原文链接:
    • NSTL
    • Elsevier

    Graph correlated attention recurrent neural network for multivariate time series forecasting

    Geng X.He X.Xu L.Yu J....
    17页
    查看更多>>摘要：? 2022Multivariate time series(MTS) forecasting is an urgent problem for numerous valuable applications. At present, attention-based methods can relieve recurrent neural networks’ limitations in MTS forecasting that are hard to focus on key information and capture long-term dependencies, but they fail to learn the time-varying pattern based on the reliable interaction. To reinforce the memory ability of key features across time, we propose a Graph Correlated Attention Recurrent Neural Network(GCAR). GCAR first nests Feature-level attention in the graph attention module to complement external feature representations on the extraction of multi-head temporal correlations. Then Multi-level attention is designed to add target factors’ impact on the selection of external correlation and achieve a fine-grained distinction of external features’ contribution. To better capture different series’ continuous dynamic changes, two parallel LSTMs are respectively applied to learn historical target series and external feature representations’ temporal dependencies. Finally, a fusion gate is employed to balance their information conflicts. The performance of GCAR model is tested on 4 datasets, and results show GCAR model performs the most stable and greatest predictive accuracy as the increasing of predicted horizons compared with state-of-the-art models even if the multivariate time series present strong volatility and randomness.
      原文链接:
    • NSTL
    • Elsevier

    The usefulness of topological indices

    Ma Y.Dehmer M.Kunzi U.-M.Tripathi S....
    9页
    查看更多>>摘要：? 2022A huge number of topological graph measures have been defined and investigated. It turned out that various graph measures failed to solve problems meaningfully in the context of characterizing graphs. Reasons for this range from selecting redundant and unfavorable graph invariants and the fact that many of those measures have been defined in an unreflected manner. In this paper, we extend the debate in the literature to find useful properties of structural graph measures. For this, we investigate the usefulness of topological indices for graphs quantitatively by assigning a feature vector to graph that contains ‘useful’ properties represented by certain measures. We show examples and compare the usefulness by using this apparatus based on distance measures and on a agglomerative clustering task.
      原文链接:
    • NSTL
    • Elsevier

    A labor division artificial bee colony algorithm based on behavioral development

    Wang Y.Jiao J.Liu J.Xiao R....
    21页
    查看更多>>摘要：? 2022 Elsevier Inc.Artificial bee colony (ABC) algorithm mimics the foraging behaviour of bee colonies to solve optimization problems in which different types of bees adopt the same search equation. In this sense, bees that play different roles do not divide their labor. Moreover, the single search equation in ABC is strongly explorative but weakly exploitative, which limits its performance. To overcome that issue, this study proposes an improved algorithm (hereafter BDLDABC) that introduces the labor division of bee colonies based on behavioral development into ABC. In BDLDABC, employed bees, onlooker bees, and scout bees are regarded as three phases of the behavioral development of bees, and the labor division for the search process is obtained by individual specialization and role plasticity. According to individual specialization, three search equations guided by the global best solution, local best solution, and a random solution are designed for the three types of bees. Based on role plasticity, four patterns of behavioral development (i.e., normal development, accelerated development, delayed development, and reversed development) are designed for bees. Following the mechanics of dividing labor, bees adaptively adjust their search equations in response to changes in the search environment. Two groups of widely used benchmark functions (including fifty-two test functions) and the real-world circle packing problem are employed to verify the performance of BDLDABC, and the experimental results show that, in most cases, BDLDABC is superior, or at least comparable, to its competitors (including eight ABC variants, three DE variants, and three PSO variants).
      原文链接:
    • NSTL
    • Elsevier