Home / Advanced Search

  • Title/Keywords

  • Author/Affliations

  • Journal

  • Article Type

  • Start Year

  • End Year

Update SearchingClear
  • Articles
  • Online
Search Results (174)
  • Open Access

    ARTICLE

    DT-Net: Joint Dual-Input Transformer and CNN for Retinal Vessel Segmentation

    Wenran Jia1, Simin Ma1, Peng Geng1, Yan Sun2,*

    CMC-Computers, Materials & Continua, Vol.76, No.3, pp. 3393-3411, 2023, DOI:10.32604/cmc.2023.040091

    Abstract Retinal vessel segmentation in fundus images plays an essential role in the screening, diagnosis, and treatment of many diseases. The acquired fundus images generally have the following problems: uneven illumination, high noise, and complex structure. It makes vessel segmentation very challenging. Previous methods of retinal vascular segmentation mainly use convolutional neural networks on U Network (U-Net) models, and they have many limitations and shortcomings, such as the loss of microvascular details at the end of the vessels. We address the limitations of convolution by introducing the transformer into retinal vessel segmentation. Therefore, we propose a… More >

  • Open Access

    ARTICLE

    FedTC: A Personalized Federated Learning Method with Two Classifiers

    Yang Liu1,3, Jiabo Wang1,2,*, Qinbo Liu1, Mehdi Gheisari1, Wanyin Xu1, Zoe L. Jiang1, Jiajia Zhang1,*

    CMC-Computers, Materials & Continua, Vol.76, No.3, pp. 3013-3027, 2023, DOI:10.32604/cmc.2023.039452

    Abstract Centralized training of deep learning models poses privacy risks that hinder their deployment. Federated learning (FL) has emerged as a solution to address these risks, allowing multiple clients to train deep learning models collaboratively without sharing raw data. However, FL is vulnerable to the impact of heterogeneous distributed data, which weakens convergence stability and suboptimal performance of the trained model on local data. This is due to the discarding of the old local model at each round of training, which results in the loss of personalized information in the model critical for maintaining model accuracy… More >

  • Open Access

    ARTICLE

    State Accurate Representation and Performance Prediction Algorithm Optimization for Industrial Equipment Based on Digital Twin

    Ying Bai1,*, Xiaoti Ren2, Hong Li1

    Intelligent Automation & Soft Computing, Vol.37, No.3, pp. 2999-3018, 2023, DOI:10.32604/iasc.2023.040124

    Abstract The combination of the Industrial Internet of Things (IIoT) and digital twin (DT) technology makes it possible for the DT model to realize the dynamic perception of equipment status and performance. However, conventional digital modeling is weak in the fusion and adjustment ability between virtual and real information. The performance prediction based on experience greatly reduces the inclusiveness and accuracy of the model. In this paper, a DT-IIoT optimization model is proposed to improve the real-time representation and prediction ability of the key equipment state. Firstly, a global real-time feedback and the dynamic adjustment mechanism… More >

  • Open Access

    ARTICLE

    DOUBLE-DIFFUSIVE NATURAL CONVECTION OF LOW PRANDTL NUMBER LIQUIDS WITH SORET AND DUFOUR EFFECTS

    Gang Qiua , Mo Yanga,*, Jin Wangb , Yuwen Zhangc

    Frontiers in Heat and Mass Transfer, Vol.10, pp. 1-8, 2018, DOI:10.5098/hmt.10.24

    Abstract An unsteady numerical model for double-diffusive natural convection of low Prandtl number liquids with Soret and Dufour effects inside the horizontal cavity is developed. The thermosolutal model is solved numerically using the SIMPLE algorithm with QUICK scheme. The flow field, temperature and concentration distributions for different buoyancy ratios, Rayleigh numbers and aspect ratios under different Prandtl numbers are studied systematically. The results reveal that the flow structure develops from conduction-dominated to convection as buoyancy ratio increases under different Prandtl numbers. Heat transfer intensity keeps constant and mass transfer intensity grows slowly before a critical point More >

  • Open Access

    ARTICLE

    SORET AND RADIATION EFFECTS ON AN UNSTEADY FLOW OF A CASSON FLUID THROUGH POROUS VERTICAL CHANNEL WITH EXPANSION AND CONTRACTION

    N. Vijayaa,*, Y. Hari Krishnaa , K. Kalyanib, G.V.R. Reddya

    Frontiers in Heat and Mass Transfer, Vol.11, pp. 1-11, 2018, DOI:10.5098/hmt.11.19

    Abstract The present paper deals with the thermo physical properties of a Casson fluid through an oscillating vertical wall embedded through porous medium under the influence transverse magnetic field, radiation, constant heat source and first order chemical reaction. The radiative heat loss is modelled by using Rosseland approximation. Similarity variables were used to convert the partial differential equations into ordinary differential equation. The transformed ordinary differential equations are solved numerically using Runge - Kutta -Fehlberg method with shooting technique. In order to get perfect perception of the flow pattern we obtain the graphs of axial velocity, More >

  • Open Access

    ARTICLE

    STUDY ON WAX DEPOSITION RATE OPTIMIZATION ALGORITHM BASED ON LEVENBERG-MARQUARDT ALGORITHM AND GLOBAL OPTIMIZATION

    Rongge Xiaoa , Yue Zhub,*, Wenbo Jina , Zheng Daia , Shifang Lia , Fan Zhangc

    Frontiers in Heat and Mass Transfer, Vol.12, pp. 1-6, 2019, DOI:10.5098/hmt.12.28

    Abstract In order to accurately obtain the wax deposition rate model, according to the kinetic principle of wax deposition, several factors affecting the wax deposition rate were selected, and by a optimization software of First Optimization(1stOpt), The parameters of two typical wax deposition rate models are solved respectively based on optimization algorithm combined by Levenberg-Marquardt (L-M) algorithm and global optimization and the calculated data were compared. The results show that: compared with the model parameters obtained by least squares method, the model parameters obtained by this optimization algorithm can describe the variation of wax deposition rate… More >

  • Open Access

    ARTICLE

    THERMAL ANALYSIS OF NATURAL CONVECTION AND RADIATION HEAT TRANSFER IN MOVING POROUS FINS

    Partner L. Ndlovua,b,∗, Raseelo J. Moitshekia,†

    Frontiers in Heat and Mass Transfer, Vol.12, pp. 1-8, 2019, DOI:10.5098/hmt.12.7

    Abstract In this article, the Differential Transform Method (DTM) is used to perform thermal analysis of natural convective and radiative heat transfer in moving porous fins of rectangular and exponential profiles. This study is performed using Darcy’s model to formulate the governing heat transfer equations. The effects of porosity parameter, irregular profile and other thermo-physical parameters, such as Peclet number and the radiation parameter are also analyzed. The results show that the fin rapidly dissipates heat to the surrounding temperature with an increase in the values of the porosity parameter and the dimensionless time parameter. The More >

  • Open Access

    ARTICLE

    FLUID FLOW AND HEAT TRANSFER OVER A STRETCHING SHEET WITH TEMPERATURE DEPENDENT PRANDTL NUMBER AND VISCOSITY

    N. Govindaraj, A. K. Singh, Pankaj Shukla

    Frontiers in Heat and Mass Transfer, Vol.15, pp. 1-8, 2020, DOI:10.5098/hmt.15.20

    Abstract A numerical study of fluid flow over stretching sheet with temperature dependent properties has been performed induced by mixed convection. The significant variation of the Prandtl number and viscosity in the temperature is observed [see table 1]. Viscosity and Prandtl number are vary in inverse of the linear function. The physical problem modeled in the mathematical equations in dimension form, which is converted to the non-dimensional equations by applying similarity transformations and suitable boundary conditions. The mathematical modelling problem is transformed PDE’s are numerically solved using Quasilinearization technique and FDM. The current numerical data has… More >

  • Open Access

    ARTICLE

    THE SIMULTANEOUS EFFECT OF ECKERT NUMBER AND MAGNETIC PRANDTL NUMBER ON CASSON FLUID FLOW

    Silpisikha Goswamia,b, Dipak Sarmab

    Frontiers in Heat and Mass Transfer, Vol.16, 2021, DOI:10.5098/hmt.16.12

    Abstract This study includes the observation of electrically conducting non-Newtonian fluid flow through a vertical porous plate considering the effect of the induced magnetic field. Our approach is numerical to investigate how the variation of magnetic Prandtl number and Eckert number effect the flow profiles. Influence of Casson parameter and Hartmann number in the profiles is also observed and depicted in graphs. The rate of heat transfer, the rate of mass transfer and the skin friction are calculated and presented in tables. A significant effect of magnetic Prandtl number and Eckert number is observed. We compared More >

  • Open Access

    ARTICLE

    INDUCED MAGNETIC FIELD AND RADIATION ABSORPTION EFFECTS ON MHD FREE CONVECTIVE CHEMICALLY REACTING FLUID FLOW

    K.S. Balamurugana,*, S. Sreelathab

    Frontiers in Heat and Mass Transfer, Vol.18, pp. 1-8, 2022, DOI:10.5098/hmt.18.21

    Abstract This study is focused on the investigation of magneto hydrodynamic mixed convection radiative heat and mass transfer flow of a steady, viscous, incompressible electrically conducting Newtonian fluid which is an optically thin gray gas over a permeable vertical infinite plate in the presence of first order chemical reaction, temperature gradient heat source, induced magnetic field and magnetic Prandtl number. The governing equations for this flow model are formulated and solved using perturbation technique. The velocity, temperature, concentration and induced magnetic field are studied through graphs, and the skin friction coefficient, Nusselt number and Sherwood number More >

Displaying 21-30 on page 3 of 174. Per Page