• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권4호
• /
• pp.1760-1778
• /
• 2018

For image segmentation with intensity inhomogeneity, many region-based level set methods have been proposed. Some of them however can't get the relatively ideal segmentation results under the severe intensity inhomogeneity and weak edges, and without use of the image gradient information. To improve that, we propose a new level set method combined with local direction gradient in this paper. Firstly, based on two assumptions on intensity inhomogeneity to images, the relationships between segmentation objects and image gradients to local minimum and maximum around a pixel are presented, from which a new pixel classification method based on weight of Euclidian distance is introduced. Secondly, to implement the model, variational level set method combined with image spatial neighborhood information is used, which enhances the anti-noise capacity of the proposed gradient information based model. Thirdly, a new diffusion process with an edge indicator function is incorporated into the level set function to classify the pixels in homogeneous regions of the same segmentation object, and also to make the proposed method more insensitive to initial contours and stable numerical implementation. To verify our proposed method, different testing images including synthetic images, magnetic resonance imaging (MRI) and real-world images are introduced. The image segmentation results demonstrate that our method can deal with the relatively severe intensity inhomogeneity and obtain the comparatively ideal segmentation results efficiently.

• Steel and Composite Structures
• /
• 제29권1호
• /
• pp.53-66
• /
• 2018

A high-order nonlocal strain gradient model is developed for wave propagation analysis of porous FG nanoplates resting on a gradient hybrid foundation in thermal environment, for the first time. Material properties are assumed to be temperature-dependent and graded in the nanoplate thickness direction. To consider the thermal effects, uniform, linear, nonlinear, exponential, and sinusoidal temperature distributions are considered for temperature-dependent FG material properties. On the basis of the refined-higher order shear deformation plate theory (R-HSDT) in conjunction with the bi-Helmholtz nonlocal strain gradient theory (B-H NSGT), Hamilton's principle is used to derive the equations of wave motion. Then the dispersion relation between frequency and wave number is solved analytically. The influences of various parameters (such as temperature rise, volume fraction index, porosity volume fraction, lower and higher order nonlocal parameters, material characteristic parameter, foundations components, and wave number) on the wave propagation behaviors of porous FG nanoplates are investigated in detail.

• Advances in nano research
• /
• 제8권4호
• /
• pp.265-276
• /
• 2020

A study that primarily focuses on nonlocal strain gradient plate model for the sole purpose of vibration examination, for graphene sheets under linearly variable in-plane mechanical loads. To study a better or more precise examination on graphene sheets, a new advance model was conducted which carries two scale parameters that happen to be related to the nonlocal as well as the strain gradient influences. Through the usage of two-variable shear deformation plate approach, that does not require the inclusion of shear correction factors, the graphene sheet is designed. Based on Hamilton's principle, fundamental expressions in regard to a nonlocal strain gradient graphene sheet on elastic half-space is originated. A Galerkin's technique is applied to resolve the fundamental expressions for distinct boundary conditions. Influence of distinct factors which can be in-plane loading, length scale parameter, load factor, elastic foundation, boundary conditions, and nonlocal parameter on vibration properties of the graphene sheets then undergo investigation.

• Advances in nano research
• /
• 제9권4호
• /
• pp.221-235
• /
• 2020

The following composition establishes a nonlocal strain gradient plate model that is essentially related to mass sensors laying on Winkler-Pasternak medium for the vibrational analysis from graphene sheets. To achieve a seemingly accurate study of graphene sheets, the posited theorem actually accommodates two parameters of scale in relation to the gradient of the strain as well as non-local results. Model graphene sheets are known to have double variant shear deformation plate theory without factors from shear correction. By using the principle of Hamilton, to acquire the governing equations of a non-local strain gradient graphene layer on an elastic substrate, Galerkin's method is therefore used to explicate the equations that govern various partition conditions. The influence of diverse factors like the magnetic field as well as the elastic foundation on graphene sheet's vibration characteristics, the number of nanoparticles, nonlocal parameter, nanoparticle mass as well as the length scale parameter had been evaluated.

• Steel and Composite Structures
• /
• 제45권3호
• /
• pp.331-348
• /
• 2022

The main goal of this article is to develop the finite element formulation based on the nonlocal strain gradient and the refined higher-order deformation theory employing a new function f(z) to investigate the static bending and free vibration of functionally graded porous (FGP) nanobeams. The proposed model considers the simultaneous effects of two parameters: nonlocal and strain gradient coefficients. The nanobeam is made by FGP material that exists in un-even and logarithmic-uneven distribution. The governing equation of the nanobeam is established based on Hamilton's principle. The authors use a 2-node beam element, each node with 8 degrees of freedom (DOFs) approximated by the C¹ and C² continuous Hermit functions to obtain the elemental stiffness matrix and mass matrix. The accuracy of the proposed model is tested by comparison with the results of reputable published works. From here, the influences of the parameters: nonlocal elasticity, strain gradient, porosity, and boundary conditions are studied.

• Asia pacific journal of information systems
• /
• 제34권2호
• /
• pp.565-584
• /
• 2024

More than 1 million automobile insurance repairs occur per year globally, and the related repair costs add up to astronomical amounts. Insurance companies and repair shops are spending a great deal of money on manpower every year to claim reasonable insurance repair costs. For this reason, promptly predicting insurance claims for vehicles in accidents can help reduce social costs related to auto insurance. Several recent studies have been conducted in auto insurance repair prediction using variables such as photos of vehicle damage. We propose a new model that reflects auto insurance repair characteristics to predict auto insurance repair claims through an association rule method that combines gradient descent and location information. This method searches for the appropriate number of rules by applying the gradient descent method to results generated by association rules and eventually extracting main rules with a distance filter that reflects automobile part location information to find items suitable for insurance repair claims. According to our results, predictive performance could be improved by applying the rule set extracted by the proposed method. Therefore, a model combining the gradient descent method and a location-based association rule method is suitable for predicting auto insurance repair claims.

• Steel and Composite Structures
• /
• 제52권2호
• /
• pp.145-163
• /
• 2024

This paper presents six novel hybrid machine learning (ML) models that combine support vector machines (SVM), Decision Tree (DT), Random Forest (RF), Gradient Boosting (GB), extreme gradient boosting (XGB), and categorical gradient boosting (CGB) with the Harris Hawks Optimization (HHO) algorithm. These models, namely HHO-SVM, HHO-DT, HHO-RF, HHO-GB, HHO-XGB, and HHO-CGB, are designed to predict the ultimate strength of both rectangular and circular reinforced concrete (RC) columns. The prediction models are established using a comprehensive database consisting of 325 experimental data for rectangular columns and 172 experimental data for circular columns. The ML model hyperparameters are optimized through a combination of cross-validation technique and the HHO. The performance of the hybrid ML models is evaluated and compared using various metrics, ultimately identifying the HHO-CGB model as the top-performing model for predicting the ultimate shear strength of both rectangular and circular RC columns. The mean R-value and mean a20-index are relatively high, reaching 0.991 and 0.959, respectively, while the mean absolute error and root mean square error are low (10.302 kN and 27.954 kN, respectively). Another comparison is conducted with four existing formulas to further validate the efficiency of the proposed HHO-CGB model. The Shapely Additive Explanations method is applied to analyze the contribution of each variable to the output within the HHO-CGB model, providing insights into the local and global influence of variables. The analysis reveals that the depth of the column, length of the column, and axial loading exert the most significant influence on the ultimate shear strength of RC columns. A user-friendly graphical interface tool is then developed based on the HHO-CGB to facilitate practical and cost-effective usage.

• 대한기계학회논문집B
• /
• 제22권3호
• /
• pp.280-293
• /
• 1998

Numerical study on turbulent and mean structures of a turbulent boundary layer with longitudinal and spanwise pressure gradient is carried out by using Reynolds-stress-model (RSM). The existence of pressure gradient in a turbulent boundary layer causes the skewing or divergence of rates of strain, which contributes to production of turbulent kinetic energy. Also, this augmentation of production due to extra rates of strain can increase the turbulent mixing and cause the anisotropy of turbulent intensities in the outer layer. This paper uses the Reynolds Stress Model to capture anisotropy of turbulent structures effectively and is devoted to compare the results computed by using RSM and the standard k-.epsilon. model with experimental data. It is concluded that the RSM can produce the more accurate predictions for capturing the anisotropy of turbulent structure than the standard k-.epsilon. model.

• 한국추진공학회지
• /
• 제3권2호
• /
• pp.1-9
• /
• 1999

층류 유동을 기준으로 형성된 압력구배기법의 적용성을 난류유동에 대하여 검증하였다. 압력구배기법은 압력 자체보다는 연속방정식을 이용하여 구한 압력의 구배를 활용하므로서 유동장의 해석에 질량보존의 물리적 법칙을 용이하게 반영할 수 있는 특징이 있다. 압력구배기법은 모든 유동변수를 한 점에 위치시키고 압력구배는 그 사이에 위치시키는 준 엇갈림 좌표계를 기준으로 형성되었다. 이러한 격자계는 프로그램하기가 용이하며 유동의 물리적 특성을 올바로 반영할 수 있는 장점이 있다. 난류유동에 대한 검증은 저 레이놀즈수 $\kappa$-$\varepsilon$ 모델을 이용하여 완전히 발달한 채널유동, 후향계단유동, 원추형 디퓨저유동 등에 대하여 수행하였다. 이러한 해석결과로부터 압력구배기법은 난류유동의 해석에 적용이 가능한 것으로 판단된다. 그러나 압력구배기법은 계산시간이 다소 길게 요구되며 압력구배식의 적정 $\gamma$를 구하는 방법이 용이하지 않아 이에 대한 개선이 요구되고 있다.

• Structural Engineering and Mechanics
• /
• 제64권6권
• /
• pp.683-693
• /
• 2017

According to a generalized nonlocal strain gradient theory (NSGT), dynamic modeling and free vibrational analysis of nanoporous inhomogeneous nanoplates is presented. The present model incorporates two scale coefficients to examine vibration behavior of nanoplates much accurately. Porosity-dependent material properties of the nanoplate are defined via a modified power-law function. The nanoplate is resting on a viscoelastic substrate and is subjected to hygro-thermal environment and in-plane linearly varying mechanical loads. The governing equations and related classical and non-classical boundary conditions are derived based on Hamilton's principle. These equations are solved for hinged nanoplates via Galerkin's method. Obtained results show the importance of hygro-thermal loading, viscoelastic medium, in-plane bending load, gradient index, nonlocal parameter, strain gradient parameter and porosities on vibrational characteristics of size-dependent FG nanoplates.