Home / Advanced Search

  • Title/Keywords

  • Author/Affliations

  • Journal

  • Article Type

  • Start Year

  • End Year

Update SearchingClear
  • Articles
  • Online
Search Results (562)
  • Open Access


    Enhancing Image Description Generation through Deep Reinforcement Learning: Fusing Multiple Visual Features and Reward Mechanisms

    Yan Li, Qiyuan Wang*, Kaidi Jia

    CMC-Computers, Materials & Continua, Vol.78, No.2, pp. 2469-2489, 2024, DOI:10.32604/cmc.2024.047822

    Abstract Image description task is the intersection of computer vision and natural language processing, and it has important prospects, including helping computers understand images and obtaining information for the visually impaired. This study presents an innovative approach employing deep reinforcement learning to enhance the accuracy of natural language descriptions of images. Our method focuses on refining the reward function in deep reinforcement learning, facilitating the generation of precise descriptions by aligning visual and textual features more closely. Our approach comprises three key architectures. Firstly, it utilizes Residual Network 101 (ResNet-101) and Faster Region-based Convolutional Neural Network (Faster R-CNN) to extract average… More >

  • Open Access


    Recommendation Method for Contrastive Enhancement of Neighborhood Information

    Hairong Wang, Beijing Zhou*, Lisi Zhang, He Ma

    CMC-Computers, Materials & Continua, Vol.78, No.1, pp. 453-472, 2024, DOI:10.32604/cmc.2023.046560

    Abstract Knowledge graph can assist in improving recommendation performance and is widely applied in various personalized recommendation domains. However, existing knowledge-aware recommendation methods face challenges such as weak user-item interaction supervisory signals and noise in the knowledge graph. To tackle these issues, this paper proposes a neighbor information contrast-enhanced recommendation method by adding subtle noise to construct contrast views and employing contrastive learning to strengthen supervisory signals and reduce knowledge noise. Specifically, first, this paper adopts heterogeneous propagation and knowledge-aware attention networks to obtain multi-order neighbor embedding of users and items, mining the high-order neighbor information of users and items. Next,… More >

  • Open Access


    A New Encrypted Traffic Identification Model Based on VAE-LSTM-DRN

    Haizhen Wang1,2,*, Jinying Yan1,*, Na Jia1

    CMC-Computers, Materials & Continua, Vol.78, No.1, pp. 569-588, 2024, DOI:10.32604/cmc.2023.046055

    Abstract Encrypted traffic identification pertains to the precise acquisition and categorization of data from traffic datasets containing imbalanced and obscured content. The extraction of encrypted traffic attributes and their subsequent identification presents a formidable challenge. The existing models have predominantly relied on direct extraction of encrypted traffic data from imbalanced datasets, with the dataset’s imbalance significantly affecting the model’s performance. In the present study, a new model, referred to as UD-VLD (Unbalanced Dataset-VAE-LSTM-DRN), was proposed to address above problem. The proposed model is an encrypted traffic identification model for handling unbalanced datasets. The encoder of the variational autoencoder (VAE) is combined… More >

  • Open Access


    ProNet Adaptive Retinal Vessel Segmentation Algorithm Based on Improved UperNet Network

    Sijia Zhu1,*, Pinxiu Wang2, Ke Shen1

    CMC-Computers, Materials & Continua, Vol.78, No.1, pp. 283-302, 2024, DOI:10.32604/cmc.2023.045506

    Abstract This paper proposes a new network structure, namely the ProNet network. Retinal medical image segmentation can help clinical diagnosis of related eye diseases and is essential for subsequent rational treatment. The baseline model of the ProNet network is UperNet (Unified perceptual parsing Network), and the backbone network is ConvNext (Convolutional Network). A network structure based on depth-separable convolution and 1 × 1 convolution is used, which has good performance and robustness. We further optimise ProNet mainly in two aspects. One is data enhancement using increased noise and slight angle rotation, which can significantly increase the diversity of data and help… More >

  • Open Access


    Predicting the International Roughness Index of JPCP and CRCP Rigid Pavement: A Random Forest (RF) Model Hybridized with Modified Beetle Antennae Search (MBAS) for Higher Accuracy

    Zhou Ji1, Mengmeng Zhou2, Qiang Wang2, Jiandong Huang3,*

    CMES-Computer Modeling in Engineering & Sciences, Vol.139, No.2, pp. 1557-1582, 2024, DOI:10.32604/cmes.2023.046025

    Abstract To improve the prediction accuracy of the International Roughness Index (IRI) of Jointed Plain Concrete Pavements (JPCP) and Continuously Reinforced Concrete Pavements (CRCP), a machine learning approach is developed in this study for the modelling, combining an improved Beetle Antennae Search (MBAS) algorithm and Random Forest (RF) model. The 10-fold cross-validation was applied to verify the reliability and accuracy of the model proposed in this study. The importance scores of all input variables on the IRI of JPCP and CRCP were analysed as well. The results by the comparative analysis showed the prediction accuracy of the IRI of the newly… More > Graphic Abstract

    Predicting the International Roughness Index of JPCP and CRCP Rigid Pavement: A Random Forest (RF) Model Hybridized with Modified Beetle Antennae Search (MBAS) for Higher Accuracy

  • Open Access


    An Effective Hybrid Model of ELM and Enhanced GWO for Estimating Compressive Strength of Metakaolin-Contained Cemented Materials

    Abidhan Bardhan1,*, Raushan Kumar Singh2, Mohammed Alatiyyah3, Sulaiman Abdullah Alateyah4,*

    CMES-Computer Modeling in Engineering & Sciences, Vol.139, No.2, pp. 1521-1555, 2024, DOI:10.32604/cmes.2023.044467

    Abstract This research proposes a highly effective soft computing paradigm for estimating the compressive strength (CS) of metakaolin-contained cemented materials. The proposed approach is a combination of an enhanced grey wolf optimizer (EGWO) and an extreme learning machine (ELM). EGWO is an augmented form of the classic grey wolf optimizer (GWO). Compared to standard GWO, EGWO has a better hunting mechanism and produces an optimal performance. The EGWO was used to optimize the ELM structure and a hybrid model, ELM-EGWO, was built. To train and validate the proposed ELM-EGWO model, a sum of 361 experimental results featuring five influencing factors was… More >

  • Open Access


    Tubular Heat Enhancement Using Twisted Tape Inserts with Large Holes

    Ali Jaber Abdulhamed*, Aws Al-Akam, Wisam J. Khudhayer, Ali Sabri Allw

    Energy Engineering, Vol.121, No.2, pp. 273-290, 2024, DOI:10.32604/ee.2023.045583

    Abstract Heat augmentation techniques play a vital role in the heating and cooling processes in industries, including solar collectors and many applications that utilize heat exchangers. Several studies are based on inserting fillers inside the tubes to enhance heat transfer. This investigation considered the effects of twisted tapes with large holes on a tubular heat exchanger’s (HX) heat transmission, pressure drop, and thermal boosting factor. In the experimental section, counter-swirl flow generators used twisted tapes with pairs of 1.0 cm-diameter holes and changes in porosity (Rp) at 1.30% and 2.70%. In the experiments, air was utilized as a working fluid in… More >

  • Open Access


    A Multi-Objective Genetic Algorithm Based Load Balancing Strategy for Health Monitoring Systems in Fog-Cloud

    Hayder Makki Shakir, Jaber Karimpour*, Jafar Razmara

    Computer Systems Science and Engineering, Vol.48, No.1, pp. 35-55, 2024, DOI:10.32604/csse.2023.038545

    Abstract As the volume of data and data-generating equipment in healthcare settings grows, so do issues like latency and inefficient processing inside health monitoring systems. The Internet of Things (IoT) has been used to create a wide variety of health monitoring systems. Most modern health monitoring solutions are based on cloud computing. However, large-scale deployment of latency-sensitive healthcare applications is hampered by the cloud’s design, which introduces significant delays during the processing of vast data volumes. By strategically positioning servers close to end users, fog computing mitigates latency issues and dramatically improves scaling on demand, resource accessibility, and security. In this… More >

  • Open Access


    Damage Identification Algorithm of Composite Structure Based on Displacement Field

    Xiaoyang Shen1, Xiaojing Zhang1,*

    The International Conference on Computational & Experimental Engineering and Sciences, Vol.28, No.1, pp. 1-3, 2023, DOI:10.32604/icces.2023.010519

    Abstract 1 General Introduction
    Reliable structural health monitoring with high detection probability is very important [1]. Therefore, the method of finite element simulation was adopted. Based on the basic equation of material mechanics and stiffness degradation theory, to detect the damage of composite laminates, and further improves the intelligence of the detection process through the method of visual detection neural network.

    2 Theoretical derivation and simulation
    2.1 Equations for buckling
    In the stratified damage area, each layer bears the load independently, and the bearing capacity is determined by the stiffness there: the larger the axial stiffness, the stronger the bearing capacity… More >

  • Open Access


    Experimental Study of the Electrical Resistance of Graphene OxideReinforced Cement-Based Composites with Notch or Rebar

    Yangao Hu1,*

    The International Conference on Computational & Experimental Engineering and Sciences, Vol.27, No.3, pp. 1-1, 2023, DOI:10.32604/icces.2023.09773

    Abstract This paper investigates the effects of graphene oxide (GO), notch depth, rebar, and load on the resistivity of cement paste and mortar. The electrical conductivity of GO/cement composite reaches its maximum value when the GO content is 0.03%, which is approximately 50% higher compared to the composite without GO. The resistivity of GO/cement composite shows significant changes with increasing load from 0 to 40 kN. The gauge factor for compressive loading varies from about 26 to 73 for different GO contents. Moreover, the resistivity variation with the notch depth in GO/cement is found to be much greater than that in… More >

Displaying 1-10 on page 1 of 562. Per Page