Shuai Li¹, Xiaodong Zhao^1,2,*, Jinghu Zhou¹, Xiyue Wang¹

CMES-Computer Modeling in Engineering & Sciences, Vol.140, No.3, pp. 2587-2611, 2024, DOI:10.32604/cmes.2024.052203

Abstract Accurate quantification of the uncertainty in the mechanical characteristics of dielectric solids is crucial for advancing their application in high-precision technological domains, necessitating the development of robust computational methods. This paper introduces a Conditional Generation Adversarial Network Isogeometric Analysis (CGAN-IGA) to assess the uncertainty of dielectric solids’ mechanical characteristics. IGA is utilized for the precise computation of electric potentials in dielectric, piezoelectric, and flexoelectric materials, leveraging its advantage of integrating seamlessly with Computer-Aided Design (CAD) models to maintain exact geometrical fidelity. The CGAN method is highly efficient in generating models for piezoelectric and flexoelectric materials, More >

Cheng Yang^1,2, Miaojia Lou^2,*, Xiaoyu Chen^1,2, Zixuan Ren¹

CMC-Computers, Materials & Continua, Vol.79, No.3, pp. 4107-4126, 2024, DOI:10.32604/cmc.2024.049183

Abstract Chinese shadow puppetry has been recognized as a world intangible cultural heritage. However, it faces substantial challenges in its preservation and advancement due to the intricate and labor-intensive nature of crafting shadow puppets. To ensure the inheritance and development of this cultural heritage, it is imperative to enable traditional art to flourish in the digital era. This paper presents an Interactive Collaborative Creation System for shadow puppets, designed to facilitate the creation of high-quality shadow puppet images with greater ease. The system comprises four key functions: Image contour extraction, intelligent reference recommendation, generation network, and… More >

Mahatir Ahmed Tusher¹, Saket Choudary Kongara¹, Sagar Dhanraj Pande², SeongKi Kim^3,*, Salil Bharany^4,*

CMC-Computers, Materials & Continua, Vol.79, No.3, pp. 4063-4080, 2024, DOI:10.32604/cmc.2024.049007

Abstract The challenging task of handwriting style synthesis requires capturing the individuality and diversity of human handwriting. The majority of currently available methods use either a generative adversarial network (GAN) or a recurrent neural network (RNN) to generate new handwriting styles. This is why these techniques frequently fall short of producing diverse and realistic text pictures, particularly for terms that are not commonly used. To resolve that, this research proposes a novel deep learning model that consists of a style encoder and a text generator to synthesize different handwriting styles. This network excels in generating conditional… More >

Xueya Wang¹, Yiming Zhang^2,3,*, Qi Liu⁴, Huanran Wang¹

CMC-Computers, Materials & Continua, Vol.79, No.2, pp. 2907-2922, 2024, DOI:10.32604/cmc.2024.050736

Abstract Concrete subjected to fire loads is susceptible to explosive spalling, which can lead to the exposure of reinforcing steel bars to the fire, substantially jeopardizing the structural safety and stability. The spalling of fire-loaded concrete is closely related to the evolution of pore pressure and temperature. Conventional analytical methods involve the resolution of complex, strongly coupled multifield equations, necessitating significant computational efforts. To rapidly and accurately obtain the distributions of pore-pressure and temperature, the Pix2Pix model is adopted in this work, which is celebrated for its capabilities in image generation. The open-source dataset used herein… More >

Di Wang, Yuefei Zhu, Jinlong Fei^*, Maohua Guo

CMC-Computers, Materials & Continua, Vol.79, No.2, pp. 2253-2276, 2024, DOI:10.32604/cmc.2024.049504

Abstract Website fingerprinting, also known as WF, is a traffic analysis attack that enables local eavesdroppers to infer a user’s browsing destination, even when using the Tor anonymity network. While advanced attacks based on deep neural network (DNN) can perform feature engineering and attain accuracy rates of over 98%, research has demonstrated that DNN is vulnerable to adversarial samples. As a result, many researchers have explored using adversarial samples as a defense mechanism against DNN-based WF attacks and have achieved considerable success. However, these methods suffer from high bandwidth overhead or require access to the target… More >

Shuyi Li, Hongchao Hu^*, Xiaohan Yang, Guozhen Cheng, Wenyan Liu, Wei Guo

CMC-Computers, Materials & Continua, Vol.79, No.2, pp. 2331-2359, 2024, DOI:10.32604/cmc.2024.047275

Abstract Adversarial distillation (AD) has emerged as a potential solution to tackle the challenging optimization problem of loss with hard labels in adversarial training. However, fixed sample-agnostic and student-egocentric attack strategies are unsuitable for distillation. Additionally, the reliability of guidance from static teachers diminishes as target models become more robust. This paper proposes an AD method called Learnable Distillation Attack Strategies and Evolvable Teachers Adversarial Distillation (LDAS&ET-AD). Firstly, a learnable distillation attack strategies generating mechanism is developed to automatically generate sample-dependent attack strategies tailored for distillation. A strategy model is introduced to produce attack strategies that… More >

Siyuan Liu^1,*, Jinying Huang², Jiancheng Ma¹, Licheng Jing², Yuxuan Wang²

CMC-Computers, Materials & Continua, Vol.79, No.1, pp. 761-777, 2024, DOI:10.32604/cmc.2024.049484

Abstract Recent research in cross-domain intelligence fault diagnosis of machinery still has some problems, such as relatively ideal speed conditions and sample conditions. In engineering practice, the rotational speed of the machine is often transient and time-varying, which makes the sample annotation increasingly expensive. Meanwhile, the number of samples collected from different health states is often unbalanced. To deal with the above challenges, a complementary-label (CL) adversarial domain adaptation fault diagnosis network (CLADAN) is proposed under time-varying rotational speed and weakly-supervised conditions. In the weakly supervised learning condition, machine prior information is used for sample annotation More >

Jingyi Mao, Yuchen Zhou, Yifan Wang, Junyu Li, Ziqing Liu, Fanliang Bu^*

CMC-Computers, Materials & Continua, Vol.79, No.1, pp. 837-855, 2024, DOI:10.32604/cmc.2024.048703

Abstract Voice portrait technology has explored and established the relationship between speakers’ voices and their facial features, aiming to generate corresponding facial characteristics by providing the voice of an unknown speaker. Due to its powerful advantages in image generation, Generative Adversarial Networks (GANs) have now been widely applied across various fields. The existing Voice2Face methods for voice portraits are primarily based on GANs trained on voice-face paired datasets. However, voice portrait models solely constructed on GANs face limitations in image generation quality and struggle to maintain facial similarity. Additionally, the training process is relatively unstable, thereby… More >

Fangfang Shan^1,2,*, Huifang Sun^1,2, Mengyi Wang^1,2

CMC-Computers, Materials & Continua, Vol.79, No.1, pp. 581-605, 2024, DOI:10.32604/cmc.2024.046202

Abstract As social networks become increasingly complex, contemporary fake news often includes textual descriptions of events accompanied by corresponding images or videos. Fake news in multiple modalities is more likely to create a misleading perception among users. While early research primarily focused on text-based features for fake news detection mechanisms, there has been relatively limited exploration of learning shared representations in multimodal (text and visual) contexts. To address these limitations, this paper introduces a multimodal model for detecting fake news, which relies on similarity reasoning and adversarial networks. The model employs Bidirectional Encoder Representation from Transformers… More >

Chengkan Xu^1,2,4, Xiaofei Wang³, Yixuan Li², Guannan Wang^2,*, He Zhang^2,4,*

CMES-Computer Modeling in Engineering & Sciences, Vol.140, No.1, pp. 957-974, 2024, DOI:10.32604/cmes.2024.047327

Abstract Structural damage in heterogeneous materials typically originates from microstructures where stress concentration occurs. Therefore, evaluating the magnitude and location of localized stress distributions within microstructures under external loading is crucial. Repeating unit cells (RUCs) are commonly used to represent microstructural details and homogenize the effective response of composites. This work develops a machine learning-based micromechanics tool to accurately predict the stress distributions of extracted RUCs. The locally exact homogenization theory efficiently generates the microstructural stresses of RUCs with a wide range of parameters, including volume fraction, fiber/matrix property ratio, fiber shapes, and loading direction. Subsequently, More > Graphic Abstract