Archives of Computational Methods in Engineering最新文献

In recent times, there has been an increasing prevalence of surrogate models and metamodeling techniques in approximating the responses of complex systems. These surrogate models have proven to be effective in various engineering and scientific disciplines due to their ability to handle demanding computational requirements. The utilisation of surrogates can significantly reduce the time and resources required for calculations. However, practitioners and researchers in structural engineering face challenges in selecting the appropriate surrogate model due to the multitude of approaches available in surrogate modelling development. Despite the numerous advantages of surrogate models, their application in civil engineering has only been explored in the past few years. Consequently, there is a need for recommendations to guide practitioners in the proper utilisation of surrogate models. Additionally, comprehensive review studies are necessary to examine the current state-of-the-art in this area. Currently, there is a lack of research that investigates the implementation of surrogate models specifically in the context of structural engineering. Therefore, this article aims to address this gap by reviewing notable papers that have employed data-driven surrogate modelling in calculations within the field of structural engineering. To achieve this, a thorough analysis is conducted, encompassing a review of 91 journal articles published from 2003 onwards. The primary purpose of this analysis is to describe the various surrogate models employed, and to highlight the domains in which surrogates have been utilised so far. The study demonstrates that the utilisation of data-driven surrogate models in the field of structural engineering provides significant benefits owing to their flexible computational methods that produce accurate outcomes. However, there exist certain significant research gaps in the existing literature that need to be addressed in future studies.

Artificial intelligence applications to enhance materials science have reduced the efforts and costs of developing new materials. Although it is still a recent research field, some promising results, and techniques have successfully been deployed for intelligent material discovery. This paper presents a systematic literature review considering applications of Artificial Intelligence (AI) approaches within the Materials Science context, presenting the literature and trends on intelligent materials through Artificial Intelligence. For this literature review, 527 articles and reviews were retrieved from Web of Science and Scopus databases from 1995 to 2022. The results showed that the number of AI applications in Materials Science has grown as well as the number of publications citing AI applications. Among the results, the most popular and relevant algorithms used in materials science are identified with a wide diversity of application possibilities with future directions.

Color space plays an important role in various aspects of imaging tasks. However, in deep learning-based computer vision, the RGB color model is predominantly employed. This research analyzes the impact of deep convolutional neural networks on cancer classification across different color spaces. The five most popular deep learning models undergo training and testing in eleven color spaces, revealing that YUV, LAB, and YIQ consistently outperform other color models in most cases. RGB images are frequently converted to alternative color spaces for enhanced representation in specific applications, like object detection and segmentation. This transformation induces alterations in the features of the color image due to variations in pixel intensity information across different color models. In this research, the aforementioned principle is applied to the classification of skin cancer using deep learning networks on images of skin lesions. The results exhibit diverse responses, with some networks achieving higher accuracy in alternative color spaces compared to RGB, while others do not. This study provides insights into the classification performance across RGB, HED, HSV, LAB, RGBCIE, XYZ, YCbCr, YDbDr, YIQ, YPbPr, and YUV color spaces. The research aims to illustrate how deep learning facilitates the analysis of skin cancer images in different color spaces.

Predicting the time rate of consolidation is one of the major aspects of structure design, founded on compressible fine-grained soil. The time to achieve the required advancement of the consolidation process is proportional to the coefficient of consolidation (c_v). In practical applications, the settlement rate is directly related to the excess pore water pressure dissipation rate. A plethora of interpretation methods have been proposed for determining consolidation parameters from laboratory one-dimensional consolidation test in the past decades. This state-of-the-art review presents a comprehensive literature study of available approaches for establishing both coefficient of consolidation and end of primary (EOP) consolidation using compression and pore water pressure laboratory data. The classification of the methods has been made to set in order interpretation approaches for future selection and comparisons. The first part of the paper describes approaches based on graphical curve-fitting. This part includes five approaches: square root of time fitting approach, Semi-logarithmic fitting approach, Differential methods, Hyperbolic approach, and approach based on excess pore water pressure dissipation. In addition, a method comparison study has been performed to evaluate the degree of agreement between selected methods statistically. For this purpose, simple regression and Bland & Altman differences analysis have been used. The second part refers to the computational-based approach, covering a wide range of methods centred on full-matching treated by least-squares, correlational equations linking c_v with index properties and soft computing approaches. A thorough insight into recently published literature on machine learning and physics-informed deep learning incorporated to derive the representative value of c_v has also been compiled.

This article is a state-of-art review on static structural computations for pin-jointed structures, revising the last forty years of scientific research on the subject matter through the introduction of static modal analysis. This novel paradigm is inspired by the so-called singular value decomposition (SVD) of the equilibrium matrix and by dynamic modal analysis. In dynamics, modal analysis requires the solution of an eigenvalue problem, which returns the natural frequencies of the structure and the corresponding mode shapes of vibration, the eigenvectors. The application of the static modal analysis to the four types of linear trusses—determinate or indeterminate from the static and kinematic viewpoints—allows re-interpreting the well-known force method and displacement method of structural analysis. Central to this proposal is the solution of static equilibrium and compatibility equations in a modal space where the relations between the extensional, inextensional, and self-stress modes are unequivocally identified. Their physical interpretation, also at the equilibrium and compatibility levels, is discussed and illustrated by key accompanying examples of structures subjected to external loads. Several original diagrammatic representations of the static modal analysis contribute to the overall understanding and implementation of the mathematical relations. This approach brings out new aspects of the interrelationship between the force and displacement methods, which strengthen their complementarity.

Fuzzy Systems have shown their ability for solving a wide range of problems in different application domains. Genetic Algorithms are applied to provide the learning and adaptation capabilities for designing fuzzy systems, and this composition is called genetic fuzzy systems (GFSs). This paper reviews the field of GFSs consisting of the pioneer articles, the most cited papers, GFS milestones, recent research trends and, future outlooks. Additionally, there is paid attention to a short discussion on some critical considerations of recent developments and suggestions for potential future research directions.

Machine learning (ML) has emerged as a versatile and powerful tool in various fields of medicine, revolutionizing early disease diagnosis, particularly in cases where traditional diagnostic approaches face challenges due to unclear or overlapping symptoms. This survey provides a comprehensive overview of the wide-ranging applications of ML techniques in detecting and diagnosing various diseases at an early stage, highlighting their potential to transform healthcare practices. The survey commences with a comprehensive review of commonly used ML algorithms, emphasizing their relevance and adaptability in medical domains. With a focus on disease diagnosis, we delve into the specific implementation of ML algorithms for early detection in prominent diseases, including cancer, COVID-19, diabetes, kidney diseases, and heart diseases. By analyzing the current state of research and developments, this survey provides valuable insights into how ML algorithms are being employed to enhance disease diagnosis accuracy and efficacy. In the domain of cancer diagnosis, ML techniques have made significant strides in analyzing medical imaging data, genomic profiling, and predictive modeling. These advancements have led to improved cancer detection rates, enabling timely interventions and personalized treatment plans. Additionally, the survey explores the pivotal role of ML in addressing the challenges posed by the COVID-19 pandemic. ML-based automated screening tools have demonstrated efficiency in detecting potential cases, while predictive modeling has been instrumental in estimating disease progression and optimizing resource allocation. Furthermore, ML’s contributions extend to chronic diseases such as diabetes, kidney diseases, and heart diseases, where it has shown promising results in predicting disease progression, enabling early intervention, and enhancing management strategies. In conclusion, this comprehensive survey showcases the transformative potential of ML in early disease diagnosis across various medical conditions. By providing valuable references and insights into future trends, it serves as a guiding resource for researchers and clinicians interested in leveraging ML technologies to improve patient care and make significant advancements in the field of medical diagnostics. With the capacity to decipher complex patterns and facilitate intelligent predictions, ML has emerged as a pivotal ally in the journey towards early disease detection and improved healthcare outcomes.

This review article presents prior studies on controlling shape and stress in flexible structures. The study offers a comprehensive survey of literature concerning the adjustment and regulation of shape, stress, or both in structures and emphasizes such control’s importance. The control of systems is classified into three primary classes: nodal movement control, axial force control, and controlling the two classes concurrently. Each class is thoroughly assessed, showcasing diverse methods anticipated by various scholars. Furthermore, the paper discusses methods to reduce the number of devices (actuators) to adjust and optimize actuators’ placement to achieve optimal structural control, considering the cost implications of numerous actuators. Additionally, various actuators are presented in detail, their advantages and disadvantages are also discussed. Moreover, the applications of the presented techniques are reviewed in detail, the essential recommendations for future work are also suggested.