Ruiqi Pan¹, Wei Xiong², Liang Hao^1,*, Yan Li^1,*

The International Conference on Computational & Experimental Engineering and Sciences, Vol.30, No.2, pp. 1-1, 2024, DOI:10.32604/icces.2024.011651

Abstract As metal additive manufacturing (MAM) becomes more widely used in engineering, an increasing number of novel lattice structures are being developed. However, most recently developed lattice structures do not match the requirement of MAM efficiently. Based on the Design for Additive Manufacturing (DfAM), comparing the mainstream implicit and explicit modelling methods, it is proposed to introduce a Subdivisional (Sub-D) modelling method to model lattice structures with better modelling versatility, 3D printability, and mechanical properties. To this end, a novel negative Poisson's ratio (NPR) structure is developed as an example to demonstrate the efficient and wide… More >

Laviza Falak Naz¹, Rohail Qamar^2,*, Raheela Asif¹, Muhammad Imran², Saad Ahmed³

Intelligent Automation & Soft Computing, Vol.39, No.5, pp. 855-887, 2024, DOI:10.32604/iasc.2024.055074 - 31 October 2024

Abstract Domain shift is when the data used in training does not match the ones it will be applied to later on under similar conditions. Domain shift will reduce accuracy in results. To prevent this, domain adaptation is done, which adapts the pre-trained model to the target domain. In real scenarios, the availability of labels for target data is rare thus resulting in unsupervised domain adaptation. Herein, we propose an innovative approach where source-free domain adaptation models and Generative Adversarial Networks (GANs) are integrated to improve the performance of computer vision or robotic vision-based systems in… More >

Licheng Sun¹, Heping Li^2,3, Liang Wang^1,4,*

CMC-Computers, Materials & Continua, Vol.80, No.3, pp. 4543-4560, 2024, DOI:10.32604/cmc.2024.055115 - 12 September 2024

Abstract It is crucial to ensure workers wear safety helmets when working at a workplace with a high risk of safety accidents, such as construction sites and mine tunnels. Although existing methods can achieve helmet detection in images, their accuracy and speed still need improvements since complex, cluttered, and large-scale scenes of real workplaces cause server occlusion, illumination change, scale variation, and perspective distortion. So, a new safety helmet-wearing detection method based on deep learning is proposed. Firstly, a new multi-scale contextual aggregation module is proposed to aggregate multi-scale feature information globally and highlight the details… More >

Pawat Chunhachatrachai^1,*, Chyi-Yeu Lin^1,2

Intelligent Automation & Soft Computing, Vol.39, No.4, pp. 599-618, 2024, DOI:10.32604/iasc.2024.055385 - 06 September 2024

Abstract Angle detection is a crucial aspect of industrial automation, ensuring precise alignment and orientation of components in manufacturing processes. Despite the widespread application of computer vision in industrial settings, angle detection remains an underexplored domain, with limited integration into production lines. This paper addresses the need for automated angle detection in industrial environments by presenting a methodology that eliminates training time and higher computation cost on Graphics Processing Unit (GPU) from machine learning in computer vision (e.g., Convolutional Neural Networks (CNN)). Our approach leverages advanced image processing techniques and a strategic combination of algorithms, including More >

Prasanalakshmi Balaji^1,*, Omar Alqahtani¹, Sangita Babu², Mousmi Ajay Chaurasia³, Shanmugapriya Prakasam⁴

CMES-Computer Modeling in Engineering & Sciences, Vol.141, No.1, pp. 443-458, 2024, DOI:10.32604/cmes.2024.053158 - 20 August 2024

Abstract Breast cancer is a significant threat to the global population, affecting not only women but also a threat to the entire population. With recent advancements in digital pathology, Eosin and hematoxylin images provide enhanced clarity in examining microscopic features of breast tissues based on their staining properties. Early cancer detection facilitates the quickening of the therapeutic process, thereby increasing survival rates. The analysis made by medical professionals, especially pathologists, is time-consuming and challenging, and there arises a need for automated breast cancer detection systems. The upcoming artificial intelligence platforms, especially deep learning models, play an More >

Zia Ullah^1,2,*, Lin Qi¹, E. J. Solteiro Pires², Arsénio Reis², Ricardo Rodrigues Nunes²

CMC-Computers, Materials & Continua, Vol.80, No.2, pp. 2387-2421, 2024, DOI:10.32604/cmc.2024.047572 - 15 August 2024

Abstract The rapid evolution of wireless communication technologies has underscored the critical role of antennas in ensuring seamless connectivity. Antenna defects, ranging from manufacturing imperfections to environmental wear, pose significant challenges to the reliability and performance of communication systems. This review paper navigates the landscape of antenna defect detection, emphasizing the need for a nuanced understanding of various defect types and the associated challenges in visual detection. This review paper serves as a valuable resource for researchers, engineers, and practitioners engaged in the design and maintenance of communication systems. The insights presented here pave the way… More >

Wanrun Li^1,2,3,*, Wenhai Zhao¹, Tongtong Wang¹, Yongfeng Du^1,2,3

Structural Durability & Health Monitoring, Vol.18, No.5, pp. 553-575, 2024, DOI:10.32604/sdhm.2024.050751 - 19 July 2024

Abstract The accumulation of defects on wind turbine blade surfaces can lead to irreversible damage, impacting the aerodynamic performance of the blades. To address the challenge of detecting and quantifying surface defects on wind turbine blades, a blade surface defect detection and quantification method based on an improved Deeplabv3+ deep learning model is proposed. Firstly, an improved method for wind turbine blade surface defect detection, utilizing Mobilenetv2 as the backbone feature extraction network, is proposed based on an original Deeplabv3+ deep learning model to address the issue of limited robustness. Secondly, through integrating the concept of… More > Graphic Abstract

Chunjuan Bo^1,*, Xin Chen², Junxing Zhang¹

CMC-Computers, Materials & Continua, Vol.80, No.1, pp. 1105-1122, 2024, DOI:10.32604/cmc.2024.052329 - 18 July 2024

Abstract Significant advancements have been witnessed in visual tracking applications leveraging ViT in recent years, mainly due to the formidable modeling capabilities of Vision Transformer (ViT). However, the strong performance of such trackers heavily relies on ViT models pretrained for long periods, limiting more flexible model designs for tracking tasks. To address this issue, we propose an efficient unsupervised ViT pretraining method for the tracking task based on masked autoencoders, called TrackMAE. During pretraining, we employ two shared-parameter ViTs, serving as the appearance encoder and motion encoder, respectively. The appearance encoder encodes randomly masked image data,… More >

Haotang Tan¹, Song Sun^2,*, Tian Cheng³, Xiyuan Shu²

CMC-Computers, Materials & Continua, Vol.80, No.1, pp. 661-678, 2024, DOI:10.32604/cmc.2024.052208 - 18 July 2024

Abstract Cloud detection from satellite and drone imagery is crucial for applications such as weather forecasting and environmental monitoring. Addressing the limitations of conventional convolutional neural networks, we propose an innovative transformer-based method. This method leverages transformers, which are adept at processing data sequences, to enhance cloud detection accuracy. Additionally, we introduce a Cyclic Refinement Architecture that improves the resolution and quality of feature extraction, thereby aiding in the retention of critical details often lost during cloud detection. Our extensive experimental validation shows that our approach significantly outperforms established models, excelling in high-resolution feature extraction and More >

Dinh Phu Cuong Le^1,2, Dong Wang¹, Viet-Tuan Le^3,*

CMC-Computers, Materials & Continua, Vol.80, No.1, pp. 37-60, 2024, DOI:10.32604/cmc.2024.050790 - 18 July 2024

Abstract Transformer models have emerged as dominant networks for various tasks in computer vision compared to Convolutional Neural Networks (CNNs). The transformers demonstrate the ability to model long-range dependencies by utilizing a self-attention mechanism. This study aims to provide a comprehensive survey of recent transformer-based approaches in image and video applications, as well as diffusion models. We begin by discussing existing surveys of vision transformers and comparing them to this work. Then, we review the main components of a vanilla transformer network, including the self-attention mechanism, feed-forward network, position encoding, etc. In the main part of More >