Haotong Wang^#,*, Liyan Wang^#, Yves Lepage

CMC-Computers, Materials & Continua, Vol.84, No.1, pp. 305-324, 2025, DOI:10.32604/cmc.2025.066351 - 09 June 2025

Abstract Data curation is vital for selecting effective demonstration examples in graph-to-text generation. However, evaluating the quality of Knowledge Graphs (KGs) remains challenging. Prior research exhibits a narrow focus on structural statistics, such as the shortest path length, while the correctness of graphs in representing the associated text is rarely explored. To address this gap, we introduce a dual-perspective evaluation framework for KG-text data, based on the computation of structural adequacy and semantic alignment. From a structural perspective, we propose the Weighted Incremental Edge Method (WIEM) to quantify graph completeness by leveraging agreement between relation models… More >

Yu-Xiang Zhao^*, Yi Lee

CMC-Computers, Materials & Continua, Vol.84, No.1, pp. 791-810, 2025, DOI:10.32604/cmc.2025.065048 - 09 June 2025

Abstract Bird species classification is not only a challenging topic in artificial intelligence but also a domain closely related to environmental protection and ecological research. Additionally, performing edge computing on low-level devices using small neural networks can be an important research direction. In this paper, we use the EfficientNetV2B0 model for bird species classification, applying transfer learning on a dataset of 525 bird species. We also employ the BiRefNet model to remove backgrounds from images in the training set. The generated background-removed images are mixed with the original training set as a form of data augmentation.… More >

Jinhai Wang¹, Junwei Xue¹, Hongyan Zhang², Hui Xiao^3,4, Huiling Wei^3,4, Mingyou Chen^3,4, Jiang Liao², Lufeng Luo^3,4,*

CMC-Computers, Materials & Continua, Vol.84, No.1, pp. 1839-1861, 2025, DOI:10.32604/cmc.2025.064489 - 09 June 2025

Abstract Defect detection based on computer vision is a critical component in ensuring the quality of industrial products. However, existing detection methods encounter several challenges in practical applications, including the scarcity of labeled samples, limited adaptability of pre-trained models, and the data heterogeneity in distributed environments. To address these issues, this research proposes an unsupervised defect detection method, FLAME (Federated Learning with Adaptive Multi-Model Embeddings). The method comprises three stages: (1) Feature learning stage: this work proposes FADE (Feature-Adaptive Domain-Specific Embeddings), a framework employs Gaussian noise injection to simulate defective patterns and implements a feature discriminator… More >

Qiang Guo^1,2,*, Rubo Zhang¹, Bingbing Zhang³

CMC-Computers, Materials & Continua, Vol.84, No.1, pp. 1307-1327, 2025, DOI:10.32604/cmc.2025.063288 - 09 June 2025

Abstract Pedestrian detection has been a hot spot in computer vision over the past decades due to the wide spectrum of promising applications, and the major challenge is false positives that occur during pedestrian detection. The emergence of various Convolutional Neural Network-based detection strategies substantially enhances pedestrian detection accuracy but still does not solve this problem well. This paper deeply analyzes the detection framework of the two-stage CNN detection methods and finds out false positives in detection results are due to its training strategy misclassifying some false proposals, thus weakening the classification capability of the following… More >

Mohammad Tabrez Quasim^1,*, Khair Ul Nisa¹, Mohammad Shahid Husain², Abakar Ibraheem Abdalla Aadam¹, Mohammed Waseequ Sheraz¹, Mohammad Zunnun Khan¹

CMC-Computers, Materials & Continua, Vol.84, No.1, pp. 1169-1187, 2025, DOI:10.32604/cmc.2025.062989 - 09 June 2025

Abstract Smart edge computing (SEC) is a novel paradigm for computing that could transfer cloud-based applications to the edge network, supporting computation-intensive services like face detection and natural language processing. A core feature of mobile edge computing, SEC improves user experience and device performance by offloading local activities to edge processors. In this framework, blockchain technology is utilized to ensure secure and trustworthy communication between edge devices and servers, protecting against potential security threats. Additionally, Deep Learning algorithms are employed to analyze resource availability and optimize computation offloading decisions dynamically. IoT applications that require significant resources… More >

Seo Yeon Moon¹, Byung Hyun Jo¹, Abir El Azzaoui¹, Sushil Kumar Singh², Jong Hyuk Park^1,*

CMC-Computers, Materials & Continua, Vol.84, No.1, pp. 25-55, 2025, DOI:10.32604/cmc.2025.062966 - 09 June 2025

Abstract With the rapid advancement of ICT and IoT technologies, the integration of Edge and Fog Computing has become essential to meet the increasing demands for real-time data processing and network efficiency. However, these technologies face critical security challenges, exacerbated by the emergence of quantum computing, which threatens traditional encryption methods. The rise in cyber-attacks targeting IoT and Edge/Fog networks underscores the need for robust, quantum-resistant security solutions. To address these challenges, researchers are focusing on Quantum Key Distribution and Post-Quantum Cryptography, which utilize quantum-resistant algorithms and the principles of quantum mechanics to ensure data confidentiality More >

Yinuo Chen¹, Xu Wu¹, Jiaxin Fan¹, Guangyu Zhu^2,*

CMC-Computers, Materials & Continua, Vol.84, No.1, pp. 1597-1613, 2025, DOI:10.32604/cmc.2025.062779 - 09 June 2025

Abstract The consultation intention of emergency decision-makers in urban rail transit (URT) is input into the emergency knowledge base in the form of domain questions to obtain emergency decision support services. This approach facilitates the rapid collection of complete knowledge and rules to form effective decisions. However, the current structured degree of the URT emergency knowledge base remains low, and the domain questions lack labeled datasets, resulting in a large deviation between the consultation outcomes and the intended objectives. To address this issue, this paper proposes a question intention recognition model for the URT emergency domain,… More >

Hanan Hardan^1,*, Osama A. Khashan^2,*, Mohammad Alshinwan¹

CMC-Computers, Materials & Continua, Vol.84, No.1, pp. 1681-1710, 2025, DOI:10.32604/cmc.2025.061659 - 09 June 2025

Abstract This study introduces an Edge-Based Data Hiding and Extraction Algorithm (EBDHEA) to address the problem of data embedding in images while preserving robust security and high image quality. The algorithm produces three classes of pixels from the pixels in the cover image: edges found by the Canny edge detection method, pixels arising from the expansion of neighboring edge pixels, and pixels that are neither edges nor components of the neighboring edge pixels. The number of Least Significant Bits (LSBs) that are used to hide data depends on these classifications. Furthermore, the lossless compression method, Huffman… More >

Yuling Luo^1,2, Xiaoguang Lin^1,2, Junxiu Liu^1,2,*, Qiang Fu^1,2, Sheng Qin^1,2, Zhen Min^1,2, Tinghua Hu^1,2

CMC-Computers, Materials & Continua, Vol.83, No.3, pp. 5323-5343, 2025, DOI:10.32604/cmc.2025.063860 - 19 May 2025

Abstract The majors accredited by the Engineering Education Accreditation (EEA) reflect the accreditation agency’s recognition of the school’s engineering programs. Excellent accreditation management holds significant importance for the advancement of engineering education programs. However, the traditional engineering education system framework suffers from the opacity of raw education data and the difficulty for accreditation bodies to forensically examine the self-assessment reports. To solve these issues, an EEA framework based on Hyperledger Fabric blockchain technology is proposed in this work. Firstly, all relevant stakeholders and information interactions occur within the blockchain network, ensuring the authenticity of educational data More >

Zhipeng Qin^1,2,*, Hanbing Yan³, Biyang Zhang², Peng Wang², Yitao Li³

CMC-Computers, Materials & Continua, Vol.83, No.3, pp. 5811-5829, 2025, DOI:10.32604/cmc.2025.063308 - 19 May 2025

Abstract With the widespread adoption of encrypted Domain Name System (DNS) technologies such as DNS over Hyper Text Transfer Protocol Secure (HTTPS), traditional port and protocol-based traffic analysis methods have become ineffective. Although encrypted DNS enhances user privacy protection, it also provides concealed communication channels for malicious software, compelling detection technologies to shift towards statistical feature-based and machine learning approaches. However, these methods still face challenges in real-time performance and privacy protection. This paper proposes a real-time identification technology for encrypted DNS traffic with privacy protection. Firstly, a hierarchical architecture of cloud-edge-end collaboration is designed, incorporating More >