Jixin Wu^1,2, Mingtao Zhou^2,3, Di Wu^2,3, Wenqi Ren⁴, Jiatian Mei^2,3, Shu Zhang^1,*

CMC-Computers, Materials & Continua, Vol.86, No.3, 2026, DOI:10.32604/cmc.2025.072964 - 12 January 2026

Abstract End-to-end Temporal Action Detection (TAD) has achieved remarkable progress in recent years, driven by innovations in model architectures and the emergence of Video Foundation Models (VFMs). However, existing TAD methods that perform full fine-tuning of pretrained video models often incur substantial computational costs, which become particularly pronounced when processing long video sequences. Moreover, the need for precise temporal boundary annotations makes data labeling extremely expensive. In low-resource settings where annotated samples are scarce, direct fine-tuning tends to cause overfitting. To address these challenges, we introduce Dynamic Low-Rank Adapter (DyLoRA), a lightweight fine-tuning framework tailored specifically… More >

Anis Zarrad¹, Thomas Armstrong², Jaber Jemai^3,*

CMC-Computers, Materials & Continua, Vol.86, No.3, 2026, DOI:10.32604/cmc.2025.072768 - 12 January 2026

Abstract Test case prioritization and ranking play a crucial role in software testing by improving fault detection efficiency and ensuring software reliability. While prioritization selects the most relevant test cases for optimal coverage, ranking further refines their execution order to detect critical faults earlier. This study investigates machine learning techniques to enhance both prioritization and ranking, contributing to more effective and efficient testing processes. We first employ advanced feature engineering alongside ensemble models, including Gradient Boosted, Support Vector Machines, Random Forests, and Naive Bayes classifiers to optimize test case prioritization, achieving an accuracy score of 0.98847… More >

Sophort Siet¹, Sony Peng², Ilkhomjon Sadriddinov³, Kyuwon Park^4,*

CMC-Computers, Materials & Continua, Vol.86, No.3, 2026, DOI:10.32604/cmc.2025.071192 - 12 January 2026

Abstract Recommendation systems have become indispensable for providing tailored suggestions and capturing evolving user preferences based on interaction histories. The collaborative filtering (CF) model, which depends exclusively on user-item interactions, commonly encounters challenges, including the cold-start problem and an inability to effectively capture the sequential and temporal characteristics of user behavior. This paper introduces a personalized recommendation system that combines deep learning techniques with Bayesian Personalized Ranking (BPR) optimization to address these limitations. With the strong support of Long Short-Term Memory (LSTM) networks, we apply it to identify sequential dependencies of user behavior and then incorporate… More >

Emad Sami Jaha^*

CMES-Computer Modeling in Engineering & Sciences, Vol.144, No.3, pp. 3645-3678, 2025, DOI:10.32604/cmes.2025.068681 - 30 September 2025

Abstract The human ear has been substantiated as a viable nonintrusive biometric modality for identification or verification. Among many feasible techniques for ear biometric recognition, convolutional neural network (CNN) models have recently offered high-performance and reliable systems. However, their performance can still be further improved using the capabilities of soft biometrics, a research question yet to be investigated. This research aims to augment the traditional CNN-based ear recognition performance by adding increased discriminatory ear soft biometric traits. It proposes a novel framework of augmented ear identification/verification using a group of discriminative categorical soft biometrics and deriving… More > Graphic Abstract

Hui Lv^1,#, Yuer Yang^2,3,4,#, Yifeng Lin^2,3,*

CMC-Computers, Materials & Continua, Vol.85, No.1, pp. 925-953, 2025, DOI:10.32604/cmc.2025.065709 - 29 August 2025

Abstract It is evident that complex optimization problems are becoming increasingly prominent, metaheuristic algorithms have demonstrated unique advantages in solving high-dimensional, nonlinear problems. However, the traditional Sparrow Search Algorithm (SSA) suffers from limited global search capability, insufficient population diversity, and slow convergence, which often leads to premature stagnation in local optima. Despite the proposal of various enhanced versions, the effective balancing of exploration and exploitation remains an unsolved challenge. To address the previously mentioned problems, this study proposes a multi-strategy collaborative improved SSA, which systematically integrates four complementary strategies: (1) the Northern Goshawk Optimization (NGO) mechanism… More >

Vishwas Deep Joshi¹, Priya Agarwal¹, Lenka Čepová², Huda Alsaud³, Ajay Kumar^4,*, B. Swarna⁵, Ashish Kumar⁶

CMES-Computer Modeling in Engineering & Sciences, Vol.144, No.1, pp. 969-1011, 2025, DOI:10.32604/cmes.2025.063996 - 31 July 2025

Abstract In a world where supply chains are increasingly complex and unpredictable, finding the optimal way to move goods through transshipment networks is more important and challenging than ever. In addition to addressing the complexity of transportation costs and demand, this study presents a novel method that offers flexible routing alternatives to manage these complexities. When real-world variables such as fluctuating costs, variable capacity, and unpredictable demand are considered, traditional transshipment models often prove inadequate. To overcome these challenges, we propose an innovative fully fuzzy-based framework using LR flat fuzzy numbers. This framework allows for more… More >

Hafiz Muhammad Waqas¹, Tahir Mahmood^1,2, Walid Emam³, Ubaid ur Rehman⁴, Dragan Pamucar^5,*

CMC-Computers, Materials & Continua, Vol.84, No.3, pp. 4699-4727, 2025, DOI:10.32604/cmc.2025.065011 - 30 July 2025

Abstract Cyber threat detection is a crucial aspect of contemporary cybersecurity due to the depth and complexity of cyberattacks. It is the identification of malicious activity, unauthorized access, and possible intrusions in networks and systems. Modern detection methods employ artificial intelligence and machine learning to study vast amounts of data, learn patterns, and anticipate potential threats. Real-time monitoring and anomaly detection improve the capacity to react to changing threats more rapidly. Cyber threat detection systems aim to reduce false positives and provide complete coverage against the broadest possible attacks. This research advocates for proactive measures and… More >

Ali Hamid Farea^1,*, Iman Askerzade^1,2, Omar H. Alhazmi³, Savaş Takan⁴

CMC-Computers, Materials & Continua, Vol.84, No.1, pp. 1457-1484, 2025, DOI:10.32604/cmc.2025.064872 - 09 June 2025

Abstract Feature selection (FS) is a pivotal pre-processing step in developing data-driven models, influencing reliability, performance and optimization. Although existing FS techniques can yield high-performance metrics for certain models, they do not invariably guarantee the extraction of the most critical or impactful features. Prior literature underscores the significance of equitable FS practices and has proposed diverse methodologies for the identification of appropriate features. However, the challenge of discerning the most relevant and influential features persists, particularly in the context of the exponential growth and heterogeneity of big data—a challenge that is increasingly salient in modern artificial… More >

Youwei Huang, Han Zhong^*, Cheng Cheng, Yijie Peng

CMC-Computers, Materials & Continua, Vol.84, No.1, pp. 1863-1882, 2025, DOI:10.32604/cmc.2025.064734 - 09 June 2025

Abstract Hateful meme is a multimodal medium that combines images and texts. The potential hate content of hateful memes has caused serious problems for social media security. The current hateful memes classification task faces significant data scarcity challenges, and direct fine-tuning of large-scale pre-trained models often leads to severe overfitting issues. In addition, it is a challenge to understand the underlying relationship between text and images in the hateful memes. To address these issues, we propose a multimodal hateful memes classification model named LABF, which is based on low-rank adapter layers and bidirectional gated feature fusion. More >

Thanh Bui-Minh¹, Nguyen Long Giang¹, Luan Thanh Le^2,*

CMC-Computers, Materials & Continua, Vol.84, No.1, pp. 1203-1226, 2025, DOI:10.32604/cmc.2025.064403 - 09 June 2025

Abstract Image-based similar trademark retrieval is a time-consuming and labor-intensive task in the trademark examination process. This paper aims to support trademark examiners by training Deep Convolutional Neural Network (DCNN) models for effective Trademark Image Retrieval (TIR). To achieve this goal, we first develop a novel labeling method that automatically generates hundreds of thousands of labeled similar and dissimilar trademark image pairs using accompanying data fields such as citation lists, Vienna classification (VC) codes, and trademark ownership information. This approach eliminates the need for manual labeling and provides a large-scale dataset suitable for training deep learning… More >