Archives of Computational Methods in Engineering最新文献

Medical image registration seeks to find an optimal spatial transformation that best aligns the underlying anatomical structures. These problems usually require the optimization of a similarity metric. Swarm Intelligence techniques are very effective and efficient optimization methods. This systematic review focuses on 3D medical image registration using Particle Swarm Optimization.

The Differential Evolution (DE) algorithm is one of the most popular and studied approaches in Evolutionary Computation (EC). Its simple but efficient design, such as its competitive performance for many real-world optimization problems, has positioned it as the standard comparison scheme for any proposal in the field. Precisely, its simplicity has allowed the publication of a great number of variants and improvements since its inception in 1997. Moreover, several DE variants are recognized as well-founded and highly competitive algorithms in the literature. In addition, the multiple DE applications and their proposed modifications in the state-of-the-art have propitiated the drafting of many review and survey works. However, none of the DE compilation work has studied the different variants of DE operators exclusively, which would benefit future DE enhancements and other topics. Therefore, in this work, a survey analysis of the variants of DE operators is presented. This study focuses on the proposed DE operators and their impact on the EC literature over the years. The analysis allows understanding of each year’s trends, the improvements that marked a milestone in the DE research, and the feasible future directions of the algorithm. Finally, the results show a downward trend for mutation or crossover variants while readers are increasingly interested in initialization and selection enhancements.

Breast Cancer Disease is identified as one of the prime causes of death in women around the globe standing next to lung cancer. Breast cancer represents the development of malignant neoplasm from the breast cells. This breast cancer can be treated when it is identified at an early stage. Several researchers have contributed different machine learning approaches for maximizing the accuracy during the process of predicting breast cancer. Optimization of selected features is another important step essential for attaining maximized accuracy during the process of detection during the use of Artificial Neural Network. The utilization of optimization algorithm also helps in fine-tuning the hyperparameters of ANN such that the process of classification can be achieved with better precision and less computational time. In this paper, a Review on Swarm Intelligent metaheuristic optimization algorithms-based Artificial Neural Network-based Breast Cancer Diagnosis Schemes is presented for comparing different approaches depending on their efficacy in achieving the classification process. It presents the potentiality of wrapper and filter methods generally used for classifying cancer cells from normal cells. This review specifically concentrates on highlighting the significance of the swarm intelligent algorithms-based optimized ANN models which are contributed with its limitations. This review also demonstrates the future scope of research which could be concentrated from the identified extract of the literature. This review also highlighted the different kinds of evaluation metrics considered for assessing the potentiality of the existing ANN-based Breast Cancer Diagnosis Schemes with its need in utilization during evaluation.

Currently, the engineering problems encountered in digital transformation of the construction industry are very complicated and need to be solved by integrating multiple technologies. Consequently, the concept of digital twin (DT) was introduced and quickly applied throughout the building lifecycle. Despite this, many practitioners lack understanding of DT in the construction industry (DT-CI) and its implementation. To overcome this issue, this paper presents a comprehensive and detailed review of DT-CI through a systematic literature review (SLR) that incorporates both quantitative and qualitative analysis. In this study, 222 DT-CI studies were selected from a pool of 2619 publications across multiple databases, and 43 related researches were supplemented by the backward snowballing method based on co-citation analysis to generate the final bibliographic database. This paper quantitatively analyzes the current state, hotspots, and development trends of DT-CI research through a bibliometric review, and systematically clarifies the concept, creation, services, and future directions of DT-CI through a framework-based review. Finally, based on the SLR outcomes, this paper offers recommendations for future work and DT-CI implementation. Contrary to other reviews within this field, this paper adheres to a rigorous SLR protocol to ensure the reproducibility of review results. Moreover, by comparing construction and non-construction DT concepts, we highlight the unique characteristics of DT-CI, namely its association with building information modeling (BIM) and emphasis on geometric reconstruction of building entities.

Lung cancer represents a significant global health challenge, transcending demographic boundaries of age, gender, and ethnicity. Timely detection stands as a pivotal factor for enhancing both survival rates and post-diagnosis quality of life. Artificial intelligence (AI) emerges as a transformative force with the potential to substantially enhance the accuracy and efficiency of Computer-Aided Diagnosis (CAD) systems for lung cancer. Despite the burgeoning interest, a notable gap persists in the literature concerning comprehensive reviews that delve into the intricate design and architectural facets of these systems. While existing reviews furnish valuable insights into result summaries and model attributes, a glaring absence prevails in offering a reliable roadmap to guide researchers towards optimal research directions. Addressing this gap in automated lung cancer detection within medical imaging, this survey adopts a focused approach, specifically targeting innovative models tailored solely for medical image analysis. The survey endeavors to meticulously scrutinize and merge knowledge pertaining to both the architectural components and intended functionalities of these models. In adherence to PRISMA guidelines, this survey systematically incorporates and analyzes 119 original articles spanning the years 2019–2023 sourced from Scopus and WoS-indexed repositories. The survey is underpinned by three primary areas of inquiry: the application of AI within CAD systems, the intricacies of model architectural designs, and comparative analyses of the latest advancements in lung cancer detection systems. To ensure coherence and depth in analysis, the surveyed methodologies are categorically classified into seven distinct groups based on their foundational models. Furthermore, the survey conducts a rigorous review of references and discerns trend observations concerning model designs and associated tasks. Beyond synthesizing existing knowledge, this survey serves as a guide that highlights potential avenues for further research within this critical domain. By providing comprehensive insights and facilitating informed decision-making, this survey aims to contribute to the body of knowledge in the study of automated lung cancer detection and propel advancements in the field.

Brain tumor segmentation has been a challenging and popular research problem in the area of medical imaging and computer-aided diagnosis. In the last few years, especially since 2017, researchers have significantly contributed for solving and enhancing the performance of brain tumor abnormality detection and tumor segmentation from magnetic resonance (MR) images. This paper presents a detailed and intensive review of automated brain disease diagnosis and tumor segmentation methods obtained by investigating numerous recent articles. In the first phase, an extensive literature search is conducted with more than 600 articles from medical image analysis, brain disease diagnosis, and tumor segmentation. Around 50% of articles are removed after initial scanning based on certain criteria, i.e., publication year, number of citations, and bibliographic indexing. A total of 161 relevant articles are finally selected in the second phase based on their performance and novelty of the proposed methods. Furthermore, the selected articles are investigated from the perspectives of methodology and performance. Overall methods exploited for brain disease detection and tumor segmentation are categorised into three broad classes, i.e., conventional methods, machine learning-based methods, and deep learning-based methods. As deep learning-based methods are state-of-the-art for computer-aided diagnosis (CAD) nowadays, we investigated several deep learning models, such as the convolutional neural network (CNN), the generative adversarial network (GAN), the U-Net, etc., along with residual block and attention gate, with respect to their learning mechanisms and hyper-parameter tuning. Methods from each class are rigorously reviewed and summarised by identifying their advantages, disadvantages, dataset, MR modality used, and type of images (2D/3D) processed. The methods are also analysed and compared based on their performance in various measures such as dice similarity coefficient (DSC), sensitivity, positive predictive value (PPV), Specificity, Jaccard Index (JI), Accuracy, Hausdorff distance, and computation time. In this review, the high heterogeneity of articles based on different methodologies is considered in light of the recent progress and development of brain tumor detection and segmentation. During analysis, it has been observed that deep learning-based methods, especially various variants of the U-Net model, outperform other approaches for brain tumor segmentation.

This scoping review assesses the current use of simulation-based design optimization (SBDO) in marine engineering, focusing on identifying research trends, methodologies, and application areas. Analyzing 277 studies from Scopus and Web of Science, the review finds that SBDO is predominantly applied to optimizing marine vessel hulls, including both surface and underwater types, and extends to key components like bows, sterns, propellers, and fins. It also covers marine structures and renewable energy systems. A notable trend is the preference for deterministic single-objective optimization methods, indicating potential growth areas in multi-objective and stochastic approaches. The review points out the necessity of integrating more comprehensive multidisciplinary optimization methods to address the complex challenges in marine environments. Despite the extensive application of SBDO in marine engineering, there remains a need for enhancing the methodologies’ efficiency and robustness. This review offers a critical overview of SBDO’s role in marine engineering and highlights opportunities for future research to advance the field.

Generative adversarial network, in short GAN, is a new convolution neural network (CNN) based framework with the great potential to determine high dimensional data from its feedback. It is a generative model built using two CNN blocks named generator and discriminator. GAN is a recent and trending innovation in CNN with evident progress in applications like computer vision, cyber security, medical and many more. This paper presents a complete overview of GAN with its structure, variants, application and current existing work. Our primary focus is to review the growth of GAN in the computer vision domain, specifically on image enhancement techniques. In this paper, the review is carried out in a funnel approach, starting with a broad view of GAN in all domains and then narrowing down to GAN in computer vision and, finally, GAN in image enhancement. Since GAN has cleverly acquired its position in various disciplines, we are showing a comparative analysis of GAN v/s ML v/s MATLAB computer vision methods concerning image enhancement techniques in existing work. The primary objective of the paper is to showcase the systematic literature survey and execute a comparative analysis of GAN with various existing research works in different domains and understand how GAN is a better approach compared to existing models using PRISMA guidelines. In this paper, we have also studied the current GAN model for image enhancement techniques and compared it with other methods concerning PSNR and SSIM.

Intelligent reflecting surfaces (IRS) recently gained prominence due to their ability to adapt and tweak their configuration in real-time to create an intelligent wireless environment. Hence, it can elevate wireless connectivity, signal strength, data rate, coverage, and mitigate signal blockage or interference in future wireless networks. A comprehensive review of IRSs has been conveyed in this paper, emphasizing beamforming optimization strategies in the realm of energy harvesting with IRS assistance. The discussion encompasses an overview of IRS hardware design, practical IRS prototypes for hardware design, a summary of related works, and an equivalent RLC circuit model. Additionally, an extensive comparative analysis of IRS architecture, shape, size, advantages, drawbacks, and applications is presented, considering existing research. Further, the paper examines the most pivotal cost and economic aspects of IRS to optimize energy harvesting and coverage enhancement. The paper explores beamforming techniques and examines various optimization methods aimed at maximizing the potential of IRS for energy harvesting. Furthermore, the paper delves into the wide range of potential applications that IRS-assisted wireless communication networks can offer. Despite the significant promises of IRS technology, it faces substantial research challenges in optimization. This paper addresses and highlights these challenges and limitations associated with the IRS, paving the way for future research directions.

Kidney disease affects millions worldwide which emphasizes the need for early detection. Recent advancements in deep learning have transformed medical diagnostics and provide promising solutions to detect various kidney diseases. This paper aims to develop a reliable AI based learning system for effective prediction and classification of kidney diseases. The research involves a dataset of 12,446 kidney images which include cysts, tumor, stones, and healthy samples. The data undergoes thorough preprocessing to eliminate noise and enhance the quality of image. Segmentation techniques like Otsu’s binarization, Distance transform, and watershed transformation are applied to accurately delineate and identify distinct regions of interest followed by contour feature extraction which includes parameters like area, intensity, width, height, etc. Subsequently, different deep learning models such as DenseNet201, EfficientNetB0, InceptionResNetV2, MobileNetv2, ResNet50V2, and Xception are trained on incorporating with three optimizers—RMSprop, SGD, as well as Adam and are examined for the metrics such as accuracy, loss, precision, recall, RMSE, and F1 score. Notably, the Xception model outperformed others by achieving an accuracy of 99.89% with RMSprop. Similarly, ResNet50V2 and DenseNet201 demonstrated impressive accuracy of 99.68% with SGD and Adam optimizers respectively. These findings highlight the effectiveness of AI and deep transfer learning in accurate and effective kidney disease detection as well as classification.