Pub Date : 2024-09-01DOI: 10.1615/intjmultcompeng.2024052740
Yuezong Yang, Yujie Wang, Zihan LIU
The meso-structure of rock essentially affects its macroscopic mechanical behaviors. Based on the discretized virtual internal bond (DVIB) model, a grain-based DVIB (GB-DVIB) model is developed to investigate the gain-scale micro-cracking process. A meso-structure generation method for granular rock is proposed within the framework of DVIB. By this method, mineral grains, grain-boundaries and voids can be generated conveniently. Based on the relationship between macro and micro-parameters in DVIB, the mechanical parameters of meso-structure obtained by experiments can be employed to calibrate the micro-bond parameters directly. The effect of mechanical parameters of meso-structure, grain size and porosity on the macroscopic mechanical behavior is investigated, which provides a valuable reference for the application of GB-DVIB. The intra-granular and inter-granular cracks both can be reproduced by the method. A three-point bending test and an asymmetric compressive test of granite samples are simulated. The simulated micro-cracking process and macro-failure pattern are consistent with the experimental observation. The GB-DVIB provide a convenient and effective tool for researching the gain-scale micro-cracking process of granular rock.
{"title":"A grain-based discretized virtual internal bond (GB-DVIB) model for modeling micro-cracking of granular rock","authors":"Yuezong Yang, Yujie Wang, Zihan LIU","doi":"10.1615/intjmultcompeng.2024052740","DOIUrl":"https://doi.org/10.1615/intjmultcompeng.2024052740","url":null,"abstract":"The meso-structure of rock essentially affects its macroscopic mechanical behaviors. Based on the discretized virtual internal bond (DVIB) model, a grain-based DVIB (GB-DVIB) model is developed to investigate the gain-scale micro-cracking process. A meso-structure generation method for granular rock is proposed within the framework of DVIB. By this method, mineral grains, grain-boundaries and voids can be generated conveniently. Based on the relationship between macro and micro-parameters in DVIB, the mechanical parameters of meso-structure obtained by experiments can be employed to calibrate the micro-bond parameters directly. The effect of mechanical parameters of meso-structure, grain size and porosity on the macroscopic mechanical behavior is investigated, which provides a valuable reference for the application of GB-DVIB. The intra-granular and inter-granular cracks both can be reproduced by the method. A three-point bending test and an asymmetric compressive test of granite samples are simulated. The simulated micro-cracking process and macro-failure pattern are consistent with the experimental observation. The GB-DVIB provide a convenient and effective tool for researching the gain-scale micro-cracking process of granular rock.","PeriodicalId":50350,"journal":{"name":"International Journal for Multiscale Computational Engineering","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142201526","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-01DOI: 10.1615/intjmultcompeng.2024053300
Juanjuan Li, Shenjie Zhou
In this paper, a smoothed natural neighbour Galerkin method is developed for modeling flexoelectricity in dielectric solids. The domain integrals in the weak form are implemented on the background Delaunay triangle meshes. Each Delaunay triangle is divided into four sub-domains. In each sub-domain, by introducing the gradient smoothing technique, the rotation gradients, and the electric field gradients can be represented as the first-order gradients of the displacement and the electric potential, respectively. Thus, the continuity requirement for the field variables is reduced from C1 to C0, and the integrals within the sub-domains are converted to the line integrals on the boundary. Then, the field variables are approximated via the non-Sibsonian partition of unity scheme, which enables the direct imposition of the essential boundary conditions. The proposed method is validated through examples with analytical solutions. Results show that the numerical solutions agree well with the analytical solutions.
{"title":"A smoothed natural neighbour Galerkin method for flexoelectric solids","authors":"Juanjuan Li, Shenjie Zhou","doi":"10.1615/intjmultcompeng.2024053300","DOIUrl":"https://doi.org/10.1615/intjmultcompeng.2024053300","url":null,"abstract":"In this paper, a smoothed natural neighbour Galerkin method is developed for modeling flexoelectricity in dielectric solids. The domain integrals in the weak form are implemented on the background Delaunay triangle meshes. Each Delaunay triangle is divided into four sub-domains. In each sub-domain, by introducing the gradient smoothing technique, the rotation gradients, and the electric field gradients can be represented as the first-order gradients of the displacement and the electric potential, respectively. Thus, the continuity requirement for the field variables is reduced from C1 to C0, and the integrals within the sub-domains are converted to the line integrals on the boundary. Then, the field variables are approximated via the non-Sibsonian partition of unity scheme, which enables the direct imposition of the essential boundary conditions. The proposed method is validated through examples with analytical solutions. Results show that the numerical solutions agree well with the analytical solutions.","PeriodicalId":50350,"journal":{"name":"International Journal for Multiscale Computational Engineering","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142201527","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-01DOI: 10.1615/intjmultcompeng.2024050495
Goddumarri Vijay Kumar, Mohammed Ismail B, Bhaskara Reddy T, Mansour Tahernezhadi, Mansoor Alam
Prostate cancer is solid organ melanoma which increases mortality amongst humans. Automatic techniques for determining prostate cancer from magnetic resonance images (MRI) are highly recommended. Conventional techniques adapt different steps, which may result in huge computational costs. In order to perform automated prostate cancer classification with MRI, a deep model is developed in this research. Here, the MRI noise is removed using a Non-local Means (NLM) filter. Convolution neural networks (CNN) are also widely used to create segments in order to extract notable features, and they are used in deep recurrent neural networks (Deep RNN) for detecting prostate cancer. To train the classifier, the proposed Bird Squirrel (BS) algorithm is used. By combining the Bird search algorithm (BSA) and Squirrel search algorithm(SSA), the created BS is produced. With a higher accuracy of 0.937, a sensitivity of 0.958, and a specificity of 0.916, the proposed BS-DeepRNN enhanced efficiency.
{"title":"Bird Squirrel Optimization with Deep Recurrent Neural Network forProstate Cancer Detection","authors":"Goddumarri Vijay Kumar, Mohammed Ismail B, Bhaskara Reddy T, Mansour Tahernezhadi, Mansoor Alam","doi":"10.1615/intjmultcompeng.2024050495","DOIUrl":"https://doi.org/10.1615/intjmultcompeng.2024050495","url":null,"abstract":"Prostate cancer is solid organ melanoma which increases mortality amongst humans. Automatic techniques for determining prostate cancer from magnetic resonance images (MRI) are highly recommended. Conventional techniques adapt different steps, which may result in huge computational costs. In order to perform automated prostate cancer classification with MRI, a deep model is developed in this research. Here, the MRI noise is removed using a Non-local Means (NLM) filter. Convolution neural networks (CNN) are also widely used to create segments in order to extract notable features, and they are used in deep recurrent neural networks (Deep RNN) for detecting prostate cancer. To train the classifier, the proposed Bird Squirrel (BS) algorithm is used. By combining the Bird search algorithm (BSA) and Squirrel search algorithm(SSA), the created BS is produced. With a higher accuracy of 0.937, a sensitivity of 0.958, and a specificity of 0.916, the proposed BS-DeepRNN enhanced efficiency.","PeriodicalId":50350,"journal":{"name":"International Journal for Multiscale Computational Engineering","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141754204","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-01DOI: 10.1615/intjmultcompeng.2024052116
Zhengcheng Zhou, Xiaoming Bai, yichao Zhu
This article is aimed to propose a general method in support of efficient and reliable predictions of both the global and local behaviours of spatially-varying multiscale configurations made of materials bearing general nonlinear history-independent stress-strain relationships. The framework is developed based on a complementary approach that integrates asymptotic analysis with machine learning. The use of asymptotic analysis is to identify the homogenised constitutive relationship and the implicit relationships that link the local quantities of interest, say, the site where the maximum Von Mises stress lies, with other onsite mean-field quantities. As for the implementation of the proposed asymptotic formulation, the aforementioned relationships of interest are represented by neural networks using training data generated following a guideline resulting from asymptotic analysis. With the trained neural networks, the desired local behaviours can be quickly accessed at a homogenised level without explicitly resolving the microstructural configurations. The efficiency and accuracy of the proposed scheme are further demonstrated with numerical examples, and it is shown that even for fairly complex multiscale configurations, the predicting error can be maintained at a satisfactory level. Implication from the present study to speed up classical computational homogenisation schemes is also discussed.
本文旨在提出一种通用方法，以支持对空间变化的多尺度构型的全局和局部行为进行高效、可靠的预测，该构型由具有一般非线性历史无关应力应变关系的材料构成。该框架是基于一种将渐近分析与机器学习相结合的互补方法而开发的。使用渐近分析法是为了确定同质化的构成关系，以及将感兴趣的局部量（例如最大 Von Mises 应力所在位置）与其他现场平均场量联系起来的隐含关系。至于建议的渐近公式的实施，上述相关关系由神经网络表示，使用根据渐近分析得出的指导原则生成的训练数据。通过训练有素的神经网络，可以在均质化水平上快速获取所需的局部行为，而无需明确解决微观结构配置问题。通过数值示例进一步证明了所提方案的效率和准确性，并表明即使对于相当复杂的多尺度配置，预测误差也能保持在令人满意的水平。本研究还讨论了加速经典计算均质化方案的意义。
{"title":"Machine-learning-based asymptotic homogenisation and localisation of spatially varying multiscale configurations made of materials with nonlinear stress-strain relationships","authors":"Zhengcheng Zhou, Xiaoming Bai, yichao Zhu","doi":"10.1615/intjmultcompeng.2024052116","DOIUrl":"https://doi.org/10.1615/intjmultcompeng.2024052116","url":null,"abstract":"This article is aimed to propose a general method in support of efficient and reliable predictions of both the global and local behaviours of spatially-varying multiscale configurations made of materials bearing general nonlinear history-independent stress-strain relationships. The framework is developed based on a complementary approach that integrates asymptotic analysis with machine learning. The use of asymptotic analysis is to identify the homogenised constitutive relationship and the implicit relationships that link the local quantities of interest, say, the site where the maximum Von Mises stress lies, with other onsite mean-field quantities. As for the implementation of the proposed asymptotic formulation, the aforementioned relationships of interest are represented by neural networks using training data generated following a guideline resulting from asymptotic analysis. With the trained neural networks, the desired local behaviours can be quickly accessed at a homogenised level without explicitly resolving the microstructural configurations. The efficiency and accuracy of the proposed scheme are further demonstrated with numerical examples, and it is shown that even for fairly complex multiscale configurations, the predicting error can be maintained at a satisfactory level. Implication from the present study to speed up classical computational homogenisation schemes is also discussed.","PeriodicalId":50350,"journal":{"name":"International Journal for Multiscale Computational Engineering","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141061025","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-01DOI: 10.1615/intjmultcompeng.2024052181
GILBERT langat, Beiji Zou, Xiaoyan Kui, Kevin Njagi
A deadly disease that affects people in various countries in the world is Lung Cancer (LC). The rate at which people die due to LC is high because it cannot be detected easily at its initial stage of tumor development. The lives of many people who are affected by LC are assured if it is detected in the initial stage. The diagnosis of LC is possible with conventional Computer-Aided Diagnosis (CAD). The process of diagnosis can be improved by providing the associated evaluation outcomes to the radiologists. Since the results from the process of extraction of features and segmentation of lung nodule are crucial in determining the operation of the traditional CAD system, the results from the CAD system highly depends on these processes. The LC classification from Computed Tomography (CT) images of three dimensions (3D) using a CAD system is the key aspect of this paper. The collection of the 3D-CT images from the standard data source takes place in the first stage. The obtained images are provided as input for the segmentation stage, in which a Multi-scale 3D TransUNet (M-3D-TUNet) is adopted to get the precise segmentation of the LC images. A multi-cascaded model that incorporates Residual Network (ResNet), Visual Geometry Group (VGG)-19, and DenseNet models is utilized to obtain the deep features from the segmented images. The segmented image from the M-3D-TUNet model is given as input to this multi-cascaded network. The features are obtained and fused to form the feature pool. The feature pool features are provided to the Enhanced Long Short Term Memory with Attention Mechanism (ELSTM-AM) for classification of the LC. The ELSTM-AM classifies the images as normal or healthy
{"title":"Multiscale 3D TransUNet-aided Tumor Segmentation and Multi-Cascaded Model for Lung Cancer Diagnosis System from 3D CT Images with Fused Feature Pool Formation","authors":"GILBERT langat, Beiji Zou, Xiaoyan Kui, Kevin Njagi","doi":"10.1615/intjmultcompeng.2024052181","DOIUrl":"https://doi.org/10.1615/intjmultcompeng.2024052181","url":null,"abstract":"A deadly disease that affects people in various countries in the world is Lung Cancer (LC). The rate at which people die due to LC is high because it cannot be detected easily at its initial stage of tumor development. The lives of many people who are affected by LC are assured if it is detected in the initial stage. The diagnosis of LC is possible with conventional Computer-Aided Diagnosis (CAD). The process of diagnosis can be improved by providing the associated evaluation outcomes to the radiologists. Since the results from the process of extraction of features and segmentation of lung nodule are crucial in determining the operation of the traditional CAD system, the results from the CAD system highly depends on these processes. The LC classification from Computed Tomography (CT) images of three dimensions (3D) using a CAD system is the key aspect of this paper. The collection of the 3D-CT images from the standard data source takes place in the first stage. The obtained images are provided as input for the segmentation stage, in which a Multi-scale 3D TransUNet (M-3D-TUNet) is adopted to get the precise segmentation of the LC images. A multi-cascaded model that incorporates Residual Network (ResNet), Visual Geometry Group (VGG)-19, and DenseNet models is utilized to obtain the deep features from the segmented images. The segmented image from the M-3D-TUNet model is given as input to this multi-cascaded network. The features are obtained and fused to form the feature pool. The feature pool features are provided to the Enhanced Long Short Term Memory with Attention Mechanism (ELSTM-AM) for classification of the LC. The ELSTM-AM classifies the images as normal or healthy","PeriodicalId":50350,"journal":{"name":"International Journal for Multiscale Computational Engineering","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140075283","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-01DOI: 10.1615/intjmultcompeng.2024051541
M. Mohana Dhas, N. Suresh Singh
A novel method based on convolutional neural networks (CNNs) to denoise the blood cell images (BCI) is proposed in this paper. CNN is a kind of deep learning technique that specializes in retrieving information from input images instantly and capability to reduce the need for expert knowledge when extracting and selecting features. Hyper parameters like activation functions can have a direct impact on the model's performance in CNN. Hence this paper introduced a novel Improved Rectified Linear Units (I-ReLU)-CNNs approach for denoising the BCI images. In addition, the modified-ReLU and NRMSprop are the two techniques used to fine-tune the MobileNetV3 model. Then this fine-tuned MobileNetV3 model is applied for the feature extraction to remove the unwanted features from the original images. Then the Artificial Hummingbird Algorithm (AHA) based on the Manta Ray Foraging optimization algorithm (MRFOA) is proposed for feature selection. Moreover, this AHA-MRFOA is employed to ensure the development of the overall model classification by choosing only the most essential elements. The proposed model is evaluated based on the blood cell image dataset and achieves 97.86% classification accuracy.
{"title":"Fine-tuning MobileNetV3 with different weight optimization algorithms for classification of denoised blood cell images using convolutional neural network","authors":"M. Mohana Dhas, N. Suresh Singh","doi":"10.1615/intjmultcompeng.2024051541","DOIUrl":"https://doi.org/10.1615/intjmultcompeng.2024051541","url":null,"abstract":"A novel method based on convolutional neural networks (CNNs) to denoise the blood cell images (BCI) is proposed in this paper. CNN is a kind of deep learning technique that specializes in retrieving information from input images instantly and capability to reduce the need for expert knowledge when extracting and selecting features. Hyper parameters like activation functions can have a direct impact on the model's performance in CNN. Hence this paper introduced a novel Improved Rectified Linear Units (I-ReLU)-CNNs approach for denoising the BCI images. In addition, the modified-ReLU and NRMSprop are the two techniques used to fine-tune the MobileNetV3 model. Then this fine-tuned MobileNetV3 model is applied for the feature extraction to remove the unwanted features from the original images. Then the Artificial Hummingbird Algorithm (AHA) based on the Manta Ray Foraging optimization algorithm (MRFOA) is proposed for feature selection. Moreover, this AHA-MRFOA is employed to ensure the development of the overall model classification by choosing only the most essential elements. The proposed model is evaluated based on the blood cell image dataset and achieves 97.86% classification accuracy.","PeriodicalId":50350,"journal":{"name":"International Journal for Multiscale Computational Engineering","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139945415","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The microscopic properties of rocks control the macroscopic mechanical properties and fracture behavior of rocks. Existing studies on the mechanical properties of rocks have focused on treating rock materials as homogeneous or defining material properties based on Weibull random distributions, which are unable to take into account the mineralogical components and porosity characteristics of rocks. In this paper, based on the theory of bonded near-field dynamics (Peridynamics, PD), the Knuth-Durstenfeld shuffling algorithm is introduced to disrupt the mineral distribution and pore parameters, and a near-field dynamics simulation method is proposed to consider the microscopic properties of rocks. The accuracy of the proposed method is verified based on SEM tests, XRD tests and mechanical property tests of sandy mudstone and fine-grained sandstone. Further, computational analyses were carried out for the rock models under different porosities. The results indicate that porosity has a significant impact on the failure mechanism of the model.
{"title":"Peridynamics simulation and influence law analysis considering rock microscopic properties","authors":"Haoran Wang, Chengchao Guo, Wei Sun, Haibo Wang, Xiaodong Yang, Fuming Wang","doi":"10.1615/intjmultcompeng.2024049902","DOIUrl":"https://doi.org/10.1615/intjmultcompeng.2024049902","url":null,"abstract":"The microscopic properties of rocks control the macroscopic mechanical properties and fracture behavior of rocks. Existing studies on the mechanical properties of rocks have focused on treating rock materials as homogeneous or defining material properties based on Weibull random distributions, which are unable to take into account the mineralogical components and porosity characteristics of rocks. In this paper, based on the theory of bonded near-field dynamics (Peridynamics, PD), the Knuth-Durstenfeld shuffling algorithm is introduced to disrupt the mineral distribution and pore parameters, and a near-field dynamics simulation method is proposed to consider the microscopic properties of rocks. The accuracy of the proposed method is verified based on SEM tests, XRD tests and mechanical property tests of sandy mudstone and fine-grained sandstone. Further, computational analyses were carried out for the rock models under different porosities. The results indicate that porosity has a significant impact on the failure mechanism of the model.","PeriodicalId":50350,"journal":{"name":"International Journal for Multiscale Computational Engineering","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139497868","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-01DOI: 10.1615/intjmultcompeng.2023048631
Koochul Ji, Jongmuk Won
Alkali aluminosilicate hydrate (NASH) geopolymer has been utilized as an environmentally friendly binder to replace conventional cement-based binders for ground improvement. Because shear strength is one of the critical mechanical properties in assessing the performance of geopolymer-improved soils, this study investigated the shear strength of silica-NASH geopolymer (S-G-S) composite using molecular dynamic simulation to simulate the shear behavior of geopolymer-improved soils in the molecular scale. The NASH geopolymer was first successfully constructed, which showed comparable modulus of elasticity to the observed experimental results, followed by adding silica layers to develop an S-G-S composite using geometry optimization and isobaric-isothermal ensemble simulation. The obtained interfacial shear strength of the developed S-G-S composite increased as shear velocity increased. In addition, the higher interfacial shear strength of the S-G-S composite than the shear strength of geopolymer-improved soils in literature implies the shear failure of geopolymer-improved soils is unlikely to occur at the soil-geopolymer interface. The framework shown in this study can be used as a reference model to provide molecular-scale insight into the shear behavior of geopolymer-improved soils under the variation of many influencing factors (soil mineralogy, temperature, and alkali activator content).
{"title":"ASSESSING SHEAR STRENGTH OF SILICA-NASH GEOPOLYMER COMPOSITE USING MOLECULAR DYNAMIC SIMULATION","authors":"Koochul Ji, Jongmuk Won","doi":"10.1615/intjmultcompeng.2023048631","DOIUrl":"https://doi.org/10.1615/intjmultcompeng.2023048631","url":null,"abstract":"Alkali aluminosilicate hydrate (NASH) geopolymer has been utilized as an environmentally friendly binder to replace\u0000conventional cement-based binders for ground improvement. Because shear strength is one of the critical mechanical\u0000properties in assessing the performance of geopolymer-improved soils, this study investigated the shear strength of silica-NASH geopolymer (S-G-S) composite using molecular dynamic simulation to simulate the shear behavior of\u0000geopolymer-improved soils in the molecular scale. The NASH geopolymer was first successfully constructed, which\u0000showed comparable modulus of elasticity to the observed experimental results, followed by adding silica layers to\u0000develop an S-G-S composite using geometry optimization and isobaric-isothermal ensemble simulation. The obtained\u0000interfacial shear strength of the developed S-G-S composite increased as shear velocity increased. In addition, the higher interfacial shear strength of the S-G-S composite than the shear strength of geopolymer-improved soils in literature implies the shear failure of geopolymer-improved soils is unlikely to occur at the soil-geopolymer interface. The framework shown in this study can be used as a reference model to provide molecular-scale insight into the shear behavior of geopolymer-improved soils under the variation of many influencing factors (soil mineralogy, temperature, and alkali activator content).","PeriodicalId":50350,"journal":{"name":"International Journal for Multiscale Computational Engineering","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138525402","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-01DOI: 10.1615/intjmultcompeng.2023050387
GILBERT langat, Beiji Zou, Xiaoyan Kui, Kevin Njagi
The segmentation models employing deep learning offer successful outcomes over multiple medical image complex data resources and public data resources important for huge pathologies. During the identification of multiple sclerosis, the observation of entire tumors from the Magnetic Resonance Imaging (MRI) sequence is complex. Furthermore, it is necessary to identify the small tumors from the pictures in the prognosis phase to offer good treatment. The deep learning-assisted identification models solve the issue of the imbalance data and the false positive results are more in the conventional models. Besides, these methodologies offer a good tradeoff between the precision measure and recall measure. Thus, the latest deep learning-assisted MRI image segmentation and categorization model is developed to detect multiple sclerosis at the initial stage. Here, the MRI pictures are initially gathered from traditional online databases. The gathered images are directly given to the image segmentation process, where the Multi-scale Adaptive TransResunet++ (MSAT) is adopted to perform the lesion segmentation appropriately. The attributes present in the MSAT are optimized with the support of the developed Random Opposition of Cicada Swarm Optimization (ROCSO). Then, the segmented pictures are subjected to the categorization process, where the Hybrid and Dilated Convolution-based Adaptive Residual Attention Network (HDCARAN) is utilized to categorize the lesions from the MRI images very effectively to detect the multiple sclerosis of patients. Here, the attributes present within the HDCARAN are tuned via the same ROCSO. The implementation results are analyzed through the previously dev
{"title":"Efficient segmentation model using MRI images and deep learning Techniques for Multiple Sclerosis Classification","authors":"GILBERT langat, Beiji Zou, Xiaoyan Kui, Kevin Njagi","doi":"10.1615/intjmultcompeng.2023050387","DOIUrl":"https://doi.org/10.1615/intjmultcompeng.2023050387","url":null,"abstract":"The segmentation models employing deep learning offer successful outcomes over multiple medical image complex data resources and public data resources important for huge pathologies. During the identification of multiple sclerosis, the observation of entire tumors from the Magnetic Resonance Imaging (MRI) sequence is complex. Furthermore, it is necessary to identify the small tumors from the pictures in the prognosis phase to offer good treatment. The deep learning-assisted identification models solve the issue of the imbalance data and the false positive results are more in the conventional models. Besides, these methodologies offer a good tradeoff between the precision measure and recall measure. Thus, the latest deep learning-assisted MRI image segmentation and categorization model is developed to detect multiple sclerosis at the initial stage. Here, the MRI pictures are initially gathered from traditional online databases. The gathered images are directly given to the image segmentation process, where the Multi-scale Adaptive TransResunet++ (MSAT) is adopted to perform the lesion segmentation appropriately. The attributes present in the MSAT are optimized with the support of the developed Random Opposition of Cicada Swarm Optimization (ROCSO). Then, the segmented pictures are subjected to the categorization process, where the Hybrid and Dilated Convolution-based Adaptive Residual Attention Network (HDCARAN) is utilized to categorize the lesions from the MRI images very effectively to detect the multiple sclerosis of patients. Here, the attributes present within the HDCARAN are tuned via the same ROCSO. The implementation results are analyzed through the previously dev","PeriodicalId":50350,"journal":{"name":"International Journal for Multiscale Computational Engineering","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139497804","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-01DOI: 10.1615/intjmultcompeng.2023050899
Nitesh Kumar Singh, Nishant Kumar Singh
Posterior lumbar interbody fusion is a common technique for decompressing the diseased spinal segment. This study aimed to compare the biomechanical effects of four PLIF scenarios. A finite element model of the L3-L4 segment was used to simulate decompression with different scenarios: S1 (PEEK cage), S2 (PEEK cage with graft), S3 (Titanium cage), and S4 (Titanium cage with graft). Range of motion, stress, and micromotion were measured under various loading conditions. S2 demonstrates sufficient stability, reduced micromotion, and lower stress on the adjacent parts of the lumbar segment, indicating that S2 may be a preferred option for posterior lumbar interbody fusion.
{"title":"A Comparative Biomechanical Analysis of Posterior Lumbar Interbody Fusion Constructs with Four Established Scenarios","authors":"Nitesh Kumar Singh, Nishant Kumar Singh","doi":"10.1615/intjmultcompeng.2023050899","DOIUrl":"https://doi.org/10.1615/intjmultcompeng.2023050899","url":null,"abstract":"Posterior lumbar interbody fusion is a common technique for decompressing the diseased spinal segment. This study aimed to compare the biomechanical effects of four PLIF scenarios. A finite element model of the L3-L4 segment was used to simulate decompression with different scenarios: S1 (PEEK cage), S2 (PEEK cage with graft), S3 (Titanium cage), and S4 (Titanium cage with graft). Range of motion, stress, and micromotion were measured under various loading conditions. S2 demonstrates sufficient stability, reduced micromotion, and lower stress on the adjacent parts of the lumbar segment, indicating that S2 may be a preferred option for posterior lumbar interbody fusion.","PeriodicalId":50350,"journal":{"name":"International Journal for Multiscale Computational Engineering","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139412863","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：