Yuting Xu^1,*, Deqing Zhang¹, Huaibei Guo², Mengyue Wang¹

Journal on Artificial Intelligence, Vol.6, pp. 53-69, 2024, DOI:10.32604/jai.2024.049083

Abstract In multi-label learning, the label-specific features learning framework can effectively solve the dimensional catastrophe problem brought by high-dimensional data. The classification performance and robustness of the model are effectively improved. Most existing label-specific features learning utilizes the cosine similarity method to measure label correlation. It is well known that the correlation between labels is asymmetric. However, existing label-specific features learning only considers the private features of labels in classification and does not take into account the common features of labels. Based on this, this paper proposes a Causality-driven Common and Label-specific Features Learning, named CCSF algorithm. Firstly, the causal learning… More >

Pranab Kumar Mondal^*, Sanchayan Mukherjee

Frontiers in Heat and Mass Transfer, Vol.3, No.3, pp. 1-6, 2012, DOI:10.5098/hmt.v3.3.3004

Abstract The present paper deals with the analytical investigation for the limiting value of Nusselt number, including the effect of viscous dissipation on heat transfer for a laminar shear driven flow between two infinite parallel plates, where the bottom plate is fixed and the top plate is moving in an axial direction at a constant speed. The study concentrates on hydro-dynamically fully developed flow of a Newtonian fluid of constant properties without considering the axial conduction in the fluid. To investigate the effect of viscous dissipation on heat transfer by defining the limiting Nusselt number, plates are kept at constant equal… More >

Linlin Zhu, Yu Han, Xiaoqi Xi, Zhicun Zhang, Mengnan Liu, Lei Li, Siyu Tan, Bin Yan^*

CMC-Computers, Materials & Continua, Vol.77, No.3, pp. 3367-3386, 2023, DOI:10.32604/cmc.2023.045878

Abstract Deep learning techniques have significantly improved image restoration tasks in recent years. As a crucial component of deep learning, the loss function plays a key role in network optimization and performance enhancement. However, the currently prevalent loss functions assign equal weight to each pixel point during loss calculation, which hampers the ability to reflect the roles of different pixel points and fails to exploit the image’s characteristics fully. To address this issue, this study proposes an asymmetric loss function based on the image and data characteristics of the image recovery task. This novel loss function can adjust the weight of… More >

Swetha Lanka¹, Venkata Subrahmanyam Sajja^1,*, Dhaneshwar Prasad²

Frontiers in Heat and Mass Transfer, Vol.21, pp. 385-405, 2023, DOI:10.32604/fhmt.2023.042544

Abstract An attempt is made to analyse some lubrication characteristics of rigid cylindrical asymmetric rollers under adiabatic and isothermal boundaries with rolling and sliding motion lubricated by a non-Newtonian incompressible Bingham plastic fluid under the behaviour of line contact. Here the lower surface is considered to move quicker than that of the upper surface; and the Roelands viscosity model is considered and assumed to depend upon the fluid pressure and the mean film temperature. The governing equations for fluid flow such as equations of motion with continuity and the momentum energy equation are solved using Runge-Kutta forth order and MATLAB is… More >

A. Vijayalakshmi, S. Srinivas^*

Frontiers in Heat and Mass Transfer, Vol.7, pp. 1-11, 2016, DOI:10.5098/hmt.7.10

Abstract In the present study, the flow and heat transfer characteristics of a nanofluid in an expanding or contracting porous channel with different permeabilities in presence of thermal radiation are investigated. Analytical solutions for the flow variables are obtained by employing homotopy analysis method (HAM). Maxwell-Garnetts and Brinkman models are considered to calculate the thermal conductivity and the viscosity of nanofluid. In this investigation, we considered water and ethylene glycol as base fluids and silver ( Ag ), copper ( Cu ), titanium dioxide ( TiO₂ ) and alumina ( Al₂O₃ ) as nanoparticles. The effects of various emerging parameters on… More >

Yasir Khan¹, Safia Akram^2,*, Maria Athar³, Khalid Saeed⁴, Alia Razia², A. Alameer¹

CMES-Computer Modeling in Engineering & Sciences, Vol.138, No.2, pp. 1501-1520, 2024, DOI:10.32604/cmes.2023.029878

Abstract The application of mathematical modeling to biological fluids is of utmost importance, as it has diverse applications in medicine. The peristaltic mechanism plays a crucial role in understanding numerous biological flows. In this paper, we present a theoretical investigation of the double diffusion convection in the peristaltic transport of a Prandtl nanofluid through an asymmetric tapered channel under the combined action of thermal radiation and an induced magnetic field. The equations for the current flow scenario are developed, incorporating relevant assumptions, and considering the effect of viscous dissipation. The impact of thermal radiation and double diffusion on public health is… More >

Lu Wei, Zhong Ma^*, Chaojie Yang

CMES-Computer Modeling in Engineering & Sciences, Vol.138, No.1, pp. 981-1000, 2024, DOI:10.32604/cmes.2023.027085

Abstract The demand for adopting neural networks in resource-constrained embedded devices is continuously increasing. Quantization is one of the most promising solutions to reduce computational cost and memory storage on embedded devices. In order to reduce the complexity and overhead of deploying neural networks on Integer-only hardware, most current quantization methods use a symmetric quantization mapping strategy to quantize a floating-point neural network into an integer network. However, although symmetric quantization has the advantage of easier implementation, it is sub-optimal for cases where the range could be skewed and not symmetric. This often comes at the cost of lower accuracy. This… More > Graphic Abstract

Mohammad Mazyad Hazzazi¹, Hafeez Ur Rehman^2,*, Tariq Shah², Hajra Younas²

CMC-Computers, Materials & Continua, Vol.76, No.2, pp. 2033-2060, 2023, DOI:10.32604/cmc.2023.040629

Abstract Protecting the integrity and secrecy of digital data transmitted through the internet is a growing problem. In this paper, we introduce an asymmetric key algorithm for specifically processing images with larger bit values. To overcome the separate flaws of elliptic curve cryptography (ECC) and the Hill cipher (HC), we present an approach to picture encryption by combining these two encryption approaches. In addition, to strengthen our scheme, the group laws are defined over the rational points of a given elliptic curve (EC) over a Galois field (GF). The exclusive-or (XOR) function is used instead of matrix multiplication to encrypt and… More >

Lu He^1,*, Yuhang Zhou¹, Guoqing Zhu¹

The International Conference on Computational & Experimental Engineering and Sciences, Vol.26, No.2, pp. 1-1, 2023, DOI:10.32604/icces.2023.08939

Abstract The longitudinal position of the fire source is one of the key parameters affecting the flow field characteristics in a long-distance tunnel. In this paper, a series of numerical simulations were carried out to analyze the influence of the longitudinal position and the heat release rate (HRR) on the induced airflow on both sides of the fire source and the smoke movement behaviors characteristics in the long-distance tunnel. It is found that under the induction of thermal pressure, an asymmetric induced air flow is formed near the fire source, resulting in asymmetric dynamic parameters of ceiling jet. The wind speed… More >

Huanan Yu¹, Gang Han^1,*, Hansong Luo², He Wang¹

Energy Engineering, Vol.120, No.9, pp. 2029-2057, 2023, DOI:10.32604/ee.2023.028365

Abstract Aiming at the problem that most of the cables in the power collection system of offshore wind farms are buried deep in the seabed, which makes it difficult to detect faults, this paper proposes a two-step fault location method based on compressed sensing and ranging equation. The first step is to determine the fault zone through compressed sensing, and improve the data measurement, dictionary design and algorithm reconstruction: Firstly, the phase-locked loop trigonometric function method is used to suppress the spike phenomenon when extracting the fault voltage, so that the extracted voltage value will not have a large error due… More >