首页期刊导航|Applied Soft Computing
期刊信息/Journal information
Applied Soft Computing
Elsevier Science, B.V.
Applied Soft Computing

Elsevier Science, B.V.

1568-4946

Applied Soft Computing/Journal Applied Soft ComputingEIISTPSCIAHCI
正式出版
收录年代

    Session-based social and dependency-aware software recommendation

    Yan D.Tang T.Xie W.Zhang Y....
    15页
    查看更多>>摘要：With the increase of complexity of modern software, social collaborative coding and reuse of open source software packages become more and more popular, which thus greatly enhances the development efficiency and software quality. However, the explosive growth of open source software packages exposes developers to the challenge of information overload. While this can be addressed by conventional recommender systems, they usually do not consider particular constraints of social coding such as social influence among developers and dependency relations among software packages. In this paper, we aim to model the dynamic interests of developers with both social influence and dependency constraints, and propose the Session-based Social and Dependency-aware software Recommendation (SSDRec) model. This model integrates recurrent neural network (RNN) and graph attention network (GAT) into a unified framework. An RNN is employed to model the short-term dynamic interests of developers in each session and two GATs are utilized to capture social influence from friends and dependency constraints from dependent software packages, respectively. Extensive experiments are conducted on real-world datasets and the results demonstrate that our model significantly outperforms the competitive baselines.
      原文链接:
    • NSTL
    • Elsevier

    An interval type-2 fuzzy sets based Delphi approach to evaluate site selection indicators of sustainable vehicle shredding facilities

    Deveci M.Simic V.Karagoz S.Antucheviciene J....
    16页
    查看更多>>摘要：This study aims to rank indicators affecting site selection of vehicle shredding facilities using an interval type-2 fuzzy sets based Delphi approach. The introduced methodology consists of four consecutive stages as follows: indicator identification, questionnaire (survey), decision-making analysis, and statistical analysis and indicator classification. In the first stage, the literature searches are performed on vehicle shredding facility location and forty-eight relevant indicators are determined. In the second stage, a questionnaire has been conducted to collect the preferences of relevant international experts from different countries regarding the indicators. Then, the importance of site selection indicators is obtained to define critical, medium, and uncritical indicators. In the last stage, the analysis are carried out to make a distinction between groups of participants who respond similarly and discover viewpoints from the industry and academia. The research findings show that the most important indicator for locating vehicle shredding facilities is a financial benefit. Critical indicators, which should be taken into account when locating vehicle shredding facilities, are acquisition cost, affected population, demand fluctuations, end-of-life vehicle policy, financial benefit, land availability, operational costs, recycling system, resource accessibility, and safety management.
      原文链接:
    • NSTL
    • Elsevier

    A fuzzy mathematical model for tumor growth pattern using generalized Hukuhara derivative and its numerical analysis

    Khaliq R.Iqbal P.Sheergojri A.R.Bhat S.A....
    19页
    查看更多>>摘要：Fuzzy mathematical modeling has been extensively used in recent years as a helpful tool to achieve a stronger and broader understanding of a specific biological topic such as cancer. The Fuzzy mathematical model allows one to analyze the structure both qualitatively and quantitatively using mathematical methods and clarifies a tool for observing the results of different components and making behavioral projection. To reduce the ambiguity of model parameters, a fuzzy environment has been designed to address a more accurate mathematical tumor growth model. The complete pattern of tumor growth mechanism is captured with the fuzzy mathematical model using fuzzy differential equation. The concept of Generalized Hukuhara derivative is used to transform the differential equation into a system of two ordinary differential equations. The numerical simulation has also been given to support the mathematical tumor growth model in a fuzzy environment.
      原文链接:
    • NSTL
    • Elsevier

    Discrete sparrow search algorithm for symmetric traveling salesman problem

    Zhang Z.Han Y.
    18页
    查看更多>>摘要：The traveling salesman problem (TSP) is one of the most intensively studied problems in computational mathematics. This paper proposes a swarm intelligence approach using a discrete sparrow search algorithm (DSSA) with a global perturbation strategy to solve the problem. Firstly, the initial solution in the population is generated by the roulette-wheel selection. Secondly, the order-based decoding method is introduced to complete the update of the sparrow position. Then, the global perturbation mechanism combined with Gaussian mutation and swap operator is adopted to balance exploration and exploitation capability. Finally, the 2-opt local search is integrated to further improve the quality of the solution. Those strategies enhance the solution's quality and accelerate the convergence. Experiments on 34 TSP benchmark datasets are conducted to investigate the performance of the proposed DSSA. And statistical tests are used to verify the significant differences between the proposed DSSA and other state-of-the-art methods. Results show that the proposed method is more competitive and robust in solving the TSP.
      原文链接:
    • NSTL
    • Elsevier

    A triangular hashing learning approach for olfactory EEG signal recognition

    Hou H.-R.Meng Q.-H.Sun B.
    12页
    查看更多>>摘要：Recognition of olfactory-induced electroencephalogram (EEG) signals can provide an effective means for the research on disorder diagnostics and human–machine interaction. A novel triangular hashing (TH) approach is proposed for EEG signal recognition. The TH approach consists of a triangular feature construction and a hash inspired coding idea, which makes effective use of the feature differences between EEG electrodes. Firstly, a triangular feature set with N layers is constructed based on power-spectral density (PSD) features extracted from N electrodes for each frequency band of each olfactory EEG sample. Subsequently, the electrode orders, i.e. the TH codes for each layer of the constructed feature set are obtained by arranging the feature values in ascending order. Finally, the prediction type of the testing sample is determined by finding the most similar TH codes between EEG types and the testing sample. Experimental results reveal that for the recognition of olfactory EEG signals acquired from eleven subjects, the proposed TH recognition approach yields the considerably high accuracy of 93.0%, significantly superior to the other eight traditional methods. Besides, the EEG dataset with 5005 samples used in this study is made public through the website presented in this paper. In this way, the proposed TH method combined with the published EEG dataset may provide new perspectives for further study in olfactory EEG research.
      原文链接:
    • NSTL
    • Elsevier

    Tree trunk texture classification using multi-scale statistical macro binary patterns and CNN

    Boudra S.Behloul A.Yahiaoui I.
    24页
    查看更多>>摘要：Automated plant classification using tree trunk has attracted increasing interest in the computer vision community as a contributed solution for the management of biodiversity. It is based on the description of the texture information of the bark surface. The multi-scale variants of the local binary patterns have achieved prominent performance in bark texture description. However, these approaches encode the scale levels of the macrostructure separately from each other. In this paper, a novel handcrafted texture descriptor termed multi-scale Statistical Macro Binary Patterns (ms-SMBP) is proposed to encode the characterizing macro pattern of different bark species. The proposed approach consists of defining a sampling scheme at high scale levels and summarizing the intensity distribution using statistical measures. The characterizing macro pattern is encoded by an in-depth gradient that describes the relationship between the scale levels and their adaptive statistical prototype. Besides this handcrafted feature descriptor, a learning-based description is performed with the ResNet34 model for bark classification. Extensive and comprehensive experiments on challenging and large-scale bark datasets demonstrate the effectiveness of ms-SMBP to identify bark species and outperforming different multi-scale LBP approaches. The tree trunk classification with ResNet34 shows interesting results on a very large-scale dataset.
      原文链接:
    • NSTL
    • Elsevier

    An automata algorithm for generating trusted graphs in online social networks

    Fatehi N.Shahhoseini H.S.Wei J.Chang C.-T....
    15页
    查看更多>>摘要：Online social networks (OSNs) are becoming a popular tool for people to socialize and keep in touch with their friends. OSNs need trust evaluation models and algorithms to improve users’ quality of service and quality of experience. Graph-based approaches make up a major portion of existing methods, in which the trust value can be calculated through a trusted graph. However, this approach usually lacks the ability to find all trusted paths, and needs to put some restrictions to admit the process of finding trusted paths, causing trusted relations to be unreachable and leading to reduced coverage and accuracy. In this paper, graph-based and artificial intelligence approaches are combined to formulate a hybrid model for improving the coverage and accuracy of OSNs. In this approach, a distributed learning automata, which can be used to find all trusted relations without limitation, is employed instead of well-known graphic-based searching algorithms such as breadth-first search. Simulation results, conducted on real dataset of Epinions.com, illustrate an improvement of accuracy and coverage in comparison with state-of-the-art algorithms. The accuracy of the proposed algorithm is 0.9398, a 6% increase in accuracy over existing comparable algorithms. Furthermore, by the successful removal of imposed restrictions in the existing searching process for finding trusted paths, this algorithm also leads to a 10% improvement in coverage, reaching approximately 95% of all existing trusted paths.
      原文链接:
    • NSTL
    • Elsevier

    CMML: Combined metaheuristic-machine learning for adaptable routing in clustered wireless sensor networks

    Esmaeili H.Bidgoli B.M.Hakami V.
    19页
    查看更多>>摘要：Cluster-based routing is the most common routing approach to achieve energy efficiency in wireless sensor networks. However, optimal determination of cluster heads is NP-hard, which calls for heuristics or metaheuristics for obtaining a near-optimal solution. Although metaheuristics achieve better performance, they suffer from high computational time, and thus, cannot rapidly respond to routing requests. Also, a large majority of the existing routing protocols cannot easily adapt to changing network or application configurations. In this paper, a Combined model based on Metaheuristics and Machine Learning, named CMML, is proposed to support efficient and adaptable routing in clustered wireless sensor networks. In our CMML model, a multi-criteria heuristic clustering algorithm is used for clustering in which a metaheuristic (e.g., genetic algorithm) is utilized for the automatic tuning of the heuristic algorithm for each configuration separately. We repeat this process for several configurations (i.e., for different network sizes, numbers of nodes, aggregation factors, lifetime definitions, etc.). The tuned heuristic algorithm in each configuration is subsequently used for network simulation to obtain the corresponding solution. As a result, a comprehensive dataset for different configurations is derived, which is used to train a machine learning model (e.g., support vector machine). The input feature vector of a sample comprises local features (current state of a node at a round), global features (current state of the network), and application-specific features, while the output is the priority factor of each node to be selected as a cluster head. After training the CMML model, it can be applied as a quickly adaptable clustering protocol. In fact, our motivation is to utilize the generalizability of machine learning to learn the behavioral pattern of the metaheuristic algorithm in finding best routes for previous configurations. Simulation results demonstrate that the CMML model can effectively adapt with different applications, while prolonging the network lifetime based on the application requirements.
      原文链接:
    • NSTL
    • Elsevier

    A biased genetic algorithm hybridized with VNS for the two-dimensional knapsack packing problem with defects

    Luo Q.Rao Y.Guo X.Du B....
    11页
    查看更多>>摘要：This paper addresses a two-dimensional knapsack packing problem which packing a set of rectangles into a rectangular board to maximize the total value of the rectangles packed. The rectangle has finite types while its quantity is unlimited, and the board has unusable defects. A biased genetic algorithm hybridized with variable neighborhood search (VNS) is proposed to solve the problem as genetic algorithm can effectively solve the combinational optimization problem, has good searching performance, and is easy to implement. We adopt the replacing strategy for increasing the diversity of the population and avoiding converging too early. An improved placement procedure in charge of producing the layout is presented and four neighborhood structures are constructed. We conduct lots of numerical experiments using 5414 benchmark instances taken from the literature for evaluating our approach and comparing it to other excellent approaches. The experimental results show that the proposed algorithm gets many new best solutions in these benchmark instances and is very competitive.
      原文链接:
    • NSTL
    • Elsevier

    Multi-objective optimization of hexahedral pyramid crash box using MOEA/D-DAE algorithm

    Wang W.Zhao W.Wang C.Dai S....
    12页
    查看更多>>摘要：Crash box is an important energy-absorbing part of the automobile body, so this paper aims to explore a novel hexahedral pyramid (H-P) crash box with excellent overall performance, which is composed of H-P negative Poisson's ratio (auxetic) inner core structure and outer shell layer. On this basis, a many-objective optimization design for the novel crash box is conducted to enhance its performance by integrating the response surface model (RSM) method and the multi-objective evolutionary algorithm based on decomposition with detecting and escaping strategy (MOEA/D-DAE). The results demonstrate that, compared with the hollow crash box, the hexagonal honeycomb crash box and the re-entrant hexagon crash box, the initial H-P crash box has better energy absorption characteristics and comprehensive crashworthiness. Moreover, the optimized novel H-P crash box with the MOEA/D-DAE can improve its crashworthiness, energy absorption capability and lightweight more effectively, and make the collision process more controllable and stable.
      原文链接:
    • NSTL
    • Elsevier