Home / Advanced Search

  • Title/Keywords

  • Author/Affliations

  • Journal

  • Article Type

  • Start Year

  • End Year

Update SearchingClear
  • Articles
  • Online
Search Results (77)
  • Open Access

    ARTICLE

    An Attention-Based CNN Framework for Alzheimer’s Disease Staging with Multi-Technique XAI Visualization

    Mustafa Lateef Fadhil Jumaili1,2, Emrullah Sonuç1,*

    CMC-Computers, Materials & Continua, Vol.83, No.2, pp. 2947-2969, 2025, DOI:10.32604/cmc.2025.062719 - 16 April 2025

    Abstract Alzheimer’s disease (AD) is a significant challenge in modern healthcare, with early detection and accurate staging remaining critical priorities for effective intervention. While Deep Learning (DL) approaches have shown promise in AD diagnosis, existing methods often struggle with the issues of precision, interpretability, and class imbalance. This study presents a novel framework that integrates DL with several eXplainable Artificial Intelligence (XAI) techniques, in particular attention mechanisms, Gradient-Weighted Class Activation Mapping (Grad-CAM), and Local Interpretable Model-Agnostic Explanations (LIME), to improve both model interpretability and feature selection. The study evaluates four different DL architectures (ResMLP, VGG16, Xception, More >

  • Open Access

    ARTICLE

    Enhanced Boiling Heat Transfer in Water Pools with Perforated Copper Beads and Sodium Dodecyl Sulfate Surfactant

    Pengcheng Cai1,2, Teng Li3, Jianxin Xu1,2,*, Xiaobo Li3, Zhiqiang Li1,2, Zhiwen Xu3, Hua Wang1,2

    FDMP-Fluid Dynamics & Materials Processing, Vol.21, No.2, pp. 325-349, 2025, DOI:10.32604/fdmp.2024.057496 - 06 March 2025

    Abstract In modern engineering, enhancing boiling heat transfer efficiency is crucial for optimizing energy use and several industrial processes involving different types of materials. This study explores the enhancement of pool boiling heat transfer potentially induced by combining perforated copper particles on a heated surface with a sodium dodecyl sulfate (SDS) surfactant in saturated deionized water. Experiments were conducted at standard atmospheric pressure, with heat flux ranging from 20 to 100 kW/m2. The heating surface, positioned below the layer of freely moving copper beads, allowed the particle layer to shift due to liquid convection and steam More > Graphic Abstract

    Enhanced Boiling Heat Transfer in Water Pools with Perforated Copper Beads and Sodium Dodecyl Sulfate Surfactant

  • Open Access

    ARTICLE

    Steel Surface Defect Detection Using Learnable Memory Vision Transformer

    Syed Tasnimul Karim Ayon1,#, Farhan Md. Siraj1,#, Jia Uddin2,*

    CMC-Computers, Materials & Continua, Vol.82, No.1, pp. 499-520, 2025, DOI:10.32604/cmc.2025.058361 - 03 January 2025

    Abstract This study investigates the application of Learnable Memory Vision Transformers (LMViT) for detecting metal surface flaws, comparing their performance with traditional CNNs, specifically ResNet18 and ResNet50, as well as other transformer-based models including Token to Token ViT, ViT without memory, and Parallel ViT. Leveraging a widely-used steel surface defect dataset, the research applies data augmentation and t-distributed stochastic neighbor embedding (t-SNE) to enhance feature extraction and understanding. These techniques mitigated overfitting, stabilized training, and improved generalization capabilities. The LMViT model achieved a test accuracy of 97.22%, significantly outperforming ResNet18 (88.89%) and ResNet50 (88.90%), as well… More >

  • Open Access

    ARTICLE

    Malicious Document Detection Based on GGE Visualization

    Youhe Wang, Yi Sun*, Yujie Li, Chuanqi Zhou

    CMC-Computers, Materials & Continua, Vol.82, No.1, pp. 1233-1254, 2025, DOI:10.32604/cmc.2024.057710 - 03 January 2025

    Abstract With the development of anti-virus technology, malicious documents have gradually become the main pathway of Advanced Persistent Threat (APT) attacks, therefore, the development of effective malicious document classifiers has become particularly urgent. Currently, detection methods based on document structure and behavioral features encounter challenges in feature engineering, these methods not only have limited accuracy, but also consume large resources, and usually can only detect documents in specific formats, which lacks versatility and adaptability. To address such problems, this paper proposes a novel malicious document detection method-visualizing documents as GGE images (Grayscale, Grayscale matrix, Entropy). The… More >

  • Open Access

    ARTICLE

    Security Strategy of Digital Medical Contents Based on Blockchain in Generative AI Model

    Hoon Ko1, Marek R. Ogiela2,*

    CMC-Computers, Materials & Continua, Vol.82, No.1, pp. 259-278, 2025, DOI:10.32604/cmc.2024.057257 - 03 January 2025

    Abstract This study presents an innovative approach to enhancing the security of visual medical data in the generative AI environment through the integration of blockchain technology. By combining the strengths of blockchain and generative AI, the research team aimed to address the timely challenge of safeguarding visual medical content. The participating researchers conducted a comprehensive analysis, examining the vulnerabilities of medical AI services, personal information protection issues, and overall security weaknesses. This multifaceted exploration led to an in-depth evaluation of the model’s performance and security. Notably, the correlation between accuracy, detection rate, and error rate was… More >

  • Open Access

    TECHNICAL REPORT

    User Instructions for the Dynamic Database of Solid-State Electrolyte 2.0 (DDSE 2.0)

    Fangling Yang, Qian Wang, Eric Jianfeng Cheng, Di Zhang, Hao Li*

    CMC-Computers, Materials & Continua, Vol.81, No.3, pp. 3413-3419, 2024, DOI:10.32604/cmc.2024.060288 - 19 December 2024

    Abstract The Dynamic Database of Solid-State Electrolyte (DDSE) is an advanced online platform offering a comprehensive suite of tools for solid-state battery research and development. Its key features include statistical analysis of both experimental and computational solid-state electrolyte (SSE) data, interactive visualization through dynamic charts, user data assessment, and literature analysis powered by a large language model. By facilitating the design and optimization of novel SSEs, DDSE serves as a critical resource for advancing solid-state battery technology. This Technical Report provides detailed tutorials and practical examples to guide users in effectively utilizing the platform. More >

  • Open Access

    ARTICLE

    Data-Efficient Image Transformers for Robust Malware Family Classification

    Boadu Nkrumah1,*, Michal Asante1, Gaddafi Adbdul-Salam1, Wofa K. Adu-Gyamfi2

    Journal of Cyber Security, Vol.6, pp. 131-153, 2024, DOI:10.32604/jcs.2024.053954 - 17 December 2024

    Abstract The changing nature of malware poses a cybersecurity threat, resulting in significant financial losses each year. However, traditional antivirus tools for detecting malware based on signatures are ineffective against disguised variations as they have low levels of accuracy. This study introduces Data Efficient Image Transformer-Malware Classifier (DeiT-MC), a system for classifying malware that utilizes Data-Efficient Image Transformers. DeiT-MC treats malware samples as visual data and integrates a newly developed Hybrid GridBay Optimizer (HGBO) for hyperparameter optimization and better model performance under varying malware scenarios. With HGBO, DeiT-MC outperforms the state-of-the-art techniques with a strong accuracy More >

  • Open Access

    ARTICLE

    Experimental Analyses of Flow Pattern and Heat Transfer in a Horizontally Oriented Polymer Pulsating Heat Pipe with Merged Liquid Slugs

    Zhengyuan Pei1, Yasushi Koito2,*

    Frontiers in Heat and Mass Transfer, Vol.22, No.5, pp. 1381-1397, 2024, DOI:10.32604/fhmt.2024.056624 - 30 October 2024

    Abstract Extended experiments were conducted on the oscillation characteristics of merged liquid slugs in a horizontally oriented polymer pulsating heat pipe (PHP). The PHP’s serpentine channel comprised 14 parallel channels with a width of 1.3 and a height of 1.1 . The evaporator and condenser sections were 25 and 50 long, respectively, and the adiabatic section in between was 75 mm long. Using a plastic 3D printer and semi-transparent filament made from acrylonitrile butadiene styrene, the serpentine channel was printed directly onto a thin polycarbonate sheet to form the PHP. The PHP was charged with hydrofluoroether-7100.… More >

  • Open Access

    ARTICLE

    Data-Driven Decision-Making for Bank Target Marketing Using Supervised Learning Classifiers on Imbalanced Big Data

    Fahim Nasir1, Abdulghani Ali Ahmed1,*, Mehmet Sabir Kiraz1, Iryna Yevseyeva1, Mubarak Saif2

    CMC-Computers, Materials & Continua, Vol.81, No.1, pp. 1703-1728, 2024, DOI:10.32604/cmc.2024.055192 - 15 October 2024

    Abstract Integrating machine learning and data mining is crucial for processing big data and extracting valuable insights to enhance decision-making. However, imbalanced target variables within big data present technical challenges that hinder the performance of supervised learning classifiers on key evaluation metrics, limiting their overall effectiveness. This study presents a comprehensive review of both common and recently developed Supervised Learning Classifiers (SLCs) and evaluates their performance in data-driven decision-making. The evaluation uses various metrics, with a particular focus on the Harmonic Mean Score (F-1 score) on an imbalanced real-world bank target marketing dataset. The findings indicate… More >

  • Open Access

    ARTICLE

    A GAN-EfficientNet-Based Traceability Method for Malicious Code Variant Families

    Li Li*, Qing Zhang, Youran Kong

    CMC-Computers, Materials & Continua, Vol.80, No.1, pp. 801-818, 2024, DOI:10.32604/cmc.2024.051916 - 18 July 2024

    Abstract Due to the diversity and unpredictability of changes in malicious code, studying the traceability of variant families remains challenging. In this paper, we propose a GAN-EfficientNetV2-based method for tracing families of malicious code variants. This method leverages the similarity in layouts and textures between images of malicious code variants from the same source and their original family of malicious code images. The method includes a lightweight classifier and a simulator. The classifier utilizes the enhanced EfficientNetV2 to categorize malicious code images and can be easily deployed on mobile, embedded, and other devices. The simulator utilizes… More >

Displaying 1-10 on page 1 of 77. Per Page