Chunhua Wang^1,2, Wenqian Shang^1,2,*, Tong Yi^3,*, Haibin Zhu⁴

CMC-Computers, Materials & Continua, Vol.79, No.2, pp. 1939-1956, 2024, DOI:10.32604/cmc.2024.048135

Abstract The advent of self-attention mechanisms within Transformer models has significantly propelled the advancement of deep learning algorithms, yielding outstanding achievements across diverse domains. Nonetheless, self-attention mechanisms falter when applied to datasets with intricate semantic content and extensive dependency structures. In response, this paper introduces a Diffusion Sampling and Label-Driven Co-attention Neural Network (DSLD), which adopts a diffusion sampling method to capture more comprehensive semantic information of the data. Additionally, the model leverages the joint correlation information of labels and data to introduce the computation of text representation, correcting semantic representation biases in the data, and More >

LING MA^1,#, ZIRUI JIANG^1,#, XIAO HOU¹, YUTING XU¹, ZIYUN CHEN¹, SIYI ZHANG¹, HANXUE LI¹, SHAOJIE MA¹, GENG ZHANG², XIUJUN WANG^1,*, JING JI^1,*

BIOCELL, Vol.48, No.5, pp. 847-860, 2024, DOI:10.32604/biocell.2024.050868

Abstract Background: Regulatory proteins involved in human cellular division and proliferation, cyclin-dependent kinases 4 and 6 (CDK4/6) are overexpressed in numerous cancers, including triple-negative breast cancer (TNBC). TNBC is a common pathological subtype of breast cancer that is prone to recurrence and metastasis, and has a single treatment method. As one of the CDK4/6 inhibitors, abemaciclib can effectively inhibit the growth of breast tumors. In this study, we synthesized LA-D-B1, a derivative of Abemaciclib, and investigated its anti-tumor effects in breast cancer. Methods: Cellular viability was assessed using the 3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide (MTT) assay. Cell cloning and… 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 >

Fatma Nese Efil¹, Sania Qureshi^1,2,3, Nezihal Gokbulut^1,4, Kamyar Hosseini^1,3, Evren Hincal^1,4,*, Amanullah Soomro²

CMES-Computer Modeling in Engineering & Sciences, Vol.140, No.1, pp. 485-512, 2024, DOI:10.32604/cmes.2024.047907

Abstract The global population has been and will continue to be severely impacted by the COVID-19 epidemic. The primary objective of this research is to demonstrate the future impact of COVID-19 on those who suffer from other fatal conditions such as cancer, heart disease, and diabetes. Here, using ordinary differential equations (ODEs), two mathematical models are developed to explain the association between COVID-19 and cancer and between COVID-19 and diabetes and heart disease. After that, we highlight the stability assessments that can be applied to these models. Sensitivity analysis is used to examine how changes in… More >

Zhuoqun Xia¹, Hangyu Hu¹, Wenjing Li^2,3, Qisheng Jiang¹, Lan Pu¹, Yicong Shu¹, Arun Kumar Sangaiah^4,5,*

CMES-Computer Modeling in Engineering & Sciences, Vol.140, No.1, pp. 409-430, 2024, DOI:10.32604/cmes.2024.030052

Abstract Early screening of diabetes retinopathy (DR) plays an important role in preventing irreversible blindness. Existing research has failed to fully explore effective DR lesion information in fundus maps. Besides, traditional attention schemes have not considered the impact of lesion type differences on grading, resulting in unreasonable extraction of important lesion features. Therefore, this paper proposes a DR diagnosis scheme that integrates a multi-level patch attention generator (MPAG) and a lesion localization module (LLM). Firstly, MPAG is used to predict patches of different sizes and generate a weighted attention map based on the prediction score and… More >

Liliane Nga¹, Benoit Ndiwe^1,2, Achille Bernard Biwolé¹, Antonio Pizzi^3,*, Jean Jalin Eyinga Biwole¹, Joseph Zobo Mfomo¹

Journal of Renewable Materials, Vol.12, No.3, pp. 553-568, 2024, DOI:10.32604/jrm.2023.046568

Abstract Extracts of plant origin, particularly tannins, are attracting growing interest for the sustainable development of materials in the industrial sector. The discovery of new tannins is therefore necessary. The aim of this work was to contribute to the understanding of the properties of Paraberlinia bifoliolata tannin by Matrix Assisted Laser Desorption Ionization Time of Flight Mass Spectroscopy MALDI-TOF/MS and Carbon 13 Nuclear Magnetic Resonance (¹³C NMR). The chemical composition of tannin extracted from Paraberlinia bifoliolata bark was determined, as was the mechanical strength of the resin hardened with Acacia nilotica extracts. Yield by successive water extraction was 35%. MALDI-TOF/MS… More >

Yuting Xu^1,*, Deqing Zhang¹, Huaibei Guo², Mengyue Wang¹

Journal on Artificial Intelligence, Vol.6, pp. 53-69, 2024, DOI:10.32604/jai.2024.049083

Abstract In multi-label learning, the label-specific features learning framework can effectively solve the dimensional catastrophe problem brought by high-dimensional data. The classification performance and robustness of the model are effectively improved. Most existing label-specific features learning utilizes the cosine similarity method to measure label correlation. It is well known that the correlation between labels is asymmetric. However, existing label-specific features learning only considers the private features of labels in classification and does not take into account the common features of labels. Based on this, this paper proposes a Causality-driven Common and Label-specific Features Learning, named CCSF More >

Yamixa Delgado^1,*, Caliani Gaytan¹, Naydi Perez², Eric Miranda³, Bryan Colón Morales¹, Mónica Santos¹

Congenital Heart Disease, Vol.19, No.1, pp. 19-31, 2024, DOI:10.32604/chd.2024.046339

Abstract Background: Given the pervasive issues of obesity and diabetes both in Puerto Rico and the broader United States, there is a compelling need to investigate the intricate interplay among body mass index (BMI), pregestational, and gestational maternal diabetes, and their potential impact on the occurrence of congenital heart defects (CHD) during neonatal development. Methods: Using the comprehensive System of Vigilance and Surveillance of Congenital Defects in Puerto Rico, we conducted a focused analysis on neonates diagnosed with CHD between 2016 and 2020. Our assessment encompassed a range of variables, including maternal age, gestational age, BMI,… More >

Anas Bilal¹, Azhar Imran², Talha Imtiaz Baig^3,4, Xiaowen Liu^1,*, Haixia Long¹, Abdulkareem Alzahrani⁵, Muhammad Shafiq⁶

Computer Systems Science and Engineering, Vol.48, No.2, pp. 511-528, 2024, DOI:10.32604/csse.2023.039672

Abstract Artificial Intelligence (AI) is being increasingly used for diagnosing Vision-Threatening Diabetic Retinopathy (VTDR), which is a leading cause of visual impairment and blindness worldwide. However, previous automated VTDR detection methods have mainly relied on manual feature extraction and classification, leading to errors. This paper proposes a novel VTDR detection and classification model that combines different models through majority voting. Our proposed methodology involves preprocessing, data augmentation, feature extraction, and classification stages. We use a hybrid convolutional neural network-singular value decomposition (CNN-SVD) model for feature extraction and selection and an improved SVM-RBF with a Decision Tree More >

Kai Jiang, Bin Cao^*, Jing Fan

CMES-Computer Modeling in Engineering & Sciences, Vol.139, No.3, pp. 2965-2984, 2024, DOI:10.32604/cmes.2023.046348

Abstract Multimodal sentiment analysis utilizes multimodal data such as text, facial expressions and voice to detect people’s attitudes. With the advent of distributed data collection and annotation, we can easily obtain and share such multimodal data. However, due to professional discrepancies among annotators and lax quality control, noisy labels might be introduced. Recent research suggests that deep neural networks (DNNs) will overfit noisy labels, leading to the poor performance of the DNNs. To address this challenging problem, we present a Multimodal Robust Meta Learning framework (MRML) for multimodal sentiment analysis to resist noisy labels and correlate More >