Nahdi Saubari^1,2,*, Kunfeng Wang^1,*, Rachmat Muwardi^3,*, Andri Pranolo⁴

CMC-Computers, Materials & Continua, Vol.87, No.3, 2026, DOI:10.32604/cmc.2026.077087 - 09 April 2026

Abstract This study proposes an Adaptive Pooling method based on an alpha (α) parameter to enhance the effectiveness and stability of convolutional neural networks (CNNs) in image classification tasks. Conventional pooling techniques, such as max pooling and average pooling, often exhibit limited adaptability when applied to datasets with heterogeneous distributions and varying levels of complexity. To address this limitation, the proposed approach introduces an α parameter ranging from 0 to 1 that continuously regulates the contribution of maximum-based and average-based pooling operations in a unified and flexible framework. The proposed method is evaluated using two benchmark… More >

Faten S. Alamri¹, Muhammad Amjad Raza^2,3, Abeer Rashad Mirdad⁴, Adil Ali Saleem², Tanzila Saba^4,*

CMC-Computers, Materials & Continua, Vol.87, No.3, 2026, DOI:10.32604/cmc.2026.077084 - 09 April 2026

Abstract Rapid expansion of Industrial Internet of Things (IIoT) systems has heightened the vulnerability of critical infrastructure to sophisticated malware attacks. Traditional signature-based detection methods are ineffective against evolving threats, and many machine learning models fail to capture temporal behavior, offer interpretability, or operate efficiently in resource-constrained environments. This study proposes HMF-Net, a Hierarchical Multi-Feature Network, for accurate, interpretable, and efficient IIoT malware detection. HMF-Net combines hierarchical VT-Tag embedding (HVTE) to model semantic behavioral information, temporal detection ratio analysis (TDRA) to capture confidence variations for polymorphic malware, and static structural binary features. These features are fused… More >

Dmytro Tymoshchuk^1,*, Oleh Yasniy¹, Iryna Didych², Pavlo Maruschak^3,*, Yuri Lapusta⁴

CMC-Computers, Materials & Continua, Vol.87, No.3, 2026, DOI:10.32604/cmc.2026.077062 - 09 April 2026

Abstract This article presents an approach to predicting the hysteresis behavior of shape memory alloys (SMAs) using a Temporal Convolutional Network (TCN) deep learning model, followed by the interpretation of the results using Explainable Artificial Intelligence (XAI) methods. The experimental dataset was prepared based on cyclic loading tests of nickel-titanium wire at loading frequencies of 0.3, 0.5, 1, 3, and 5 Hz. For training, validation, and testing, 100–250 loading-unloading cycles were used. The input features of the models were stress σ (MPa), cycle number (Cycle parameter), and loading-unloading stage indicator, while the output variable was strain… More >

Ali Hamidoğlu^1,2, Ali Elghirani^3,4, Ömer Melih Gül^5,6,7, Seifedine Kadry^8,*

CMC-Computers, Materials & Continua, Vol.87, No.3, 2026, DOI:10.32604/cmc.2026.077060 - 09 April 2026

Abstract Multi-Robot Task Allocation (MRTA) has proven its importance in the current and near-future era, wherein in every aspect of life, there will be robots to handle tasks effectively and efficiently. While there has been a growing interest in MRTA problems in the robotics industry, the question arises of how to make robots more decentralized and intelligent through rational decision-makers rather than ones that are centralized and filled with black boxes. This survey aims to address that question by examining recent MRTA literature and exploring topics including MRTA taxonomy, centralized and decentralized controls, static and dynamic… More >

Yu Wang^1,2, Yabin Wang¹, Liang Wen¹, Bingyu Li¹, Mengze Qin¹, Fang Li¹, Zhonghua Cheng^1,*

CMC-Computers, Materials & Continua, Vol.87, No.3, 2026, DOI:10.32604/cmc.2026.077026 - 09 April 2026

Abstract Remaining useful life (RUL) prediction for complex equipment is a critical technology for ensuring the safe and reliable operation of industrial systems. However, existing data-driven models commonly suffer from limitations such as weak cross-operational condition generalization, insufficient physical interpretability, and unstable training on non-stationary time-series data. To address these challenges, this paper proposes a temporal degradation prediction model that integrates context adaptation and physics-consistent constraints, named the Context-Adaptive Physics-informed Time-aware meta-Network (CAPTAIN). The model incorporates four core components: a Context-Aware Meta-Learning (CAML) module that enables lightweight parameter adaptation to diverse scenarios; Physics-Informed Neural Network (PINN)… More >

Pratik Goswami^1,#, Hamid Naseem^2,#, Khizar Abbas^3,*, Kwonhue Choi^1,*

CMC-Computers, Materials & Continua, Vol.87, No.3, 2026, DOI:10.32604/cmc.2026.077012 - 09 April 2026

Abstract In a distributed edge computing environment, Internet of Things (IoT) and Vehicular-IoT (V-IoT) devices communicate through Wireless Sensor Networks (WSNs) by collecting and transmitting data from different environments. Although energy efficiency is always a critical challenge in WSN due to limited battery power, along with the demand for fast communication over edge devices in 5G and beyond 5G scenarios. Therefore, to overcome the challenges, an advanced hierarchical agent-based power management scheme is proposed for WSNs that optimizes energy distribution while maintaining reliable communication. The proposed model employs Master Agents (MAs), Coordination Agents (CoAs), and Task More >

Daiki Nobayashi^1,*, Meiya Tanaka², Naoki Tanaka², Riku Nakamura², Kazuya Tsukamoto³, Takeshi Ikenaga¹, Shu Sekigawa⁴, Myung Lee⁵

CMC-Computers, Materials & Continua, Vol.87, No.3, 2026, DOI:10.32604/cmc.2026.077008 - 09 April 2026

Abstract To realize local production and consumption of Spatio-temporal data (STD), it is essential to address two key challenges: (1) maintaining data locality by retaining and distributing STD close to their generation area, and (2) enabling application execution on heterogeneous and resource-constrained devices through a lightweight and portable execution platform. To address these challenges, we developed a Floating Cyber-Physical System (F-CPS) that retains both STD and the functions required to process and use the STD within a specific area. In the F-CPS, the STD Retention System directly distributes STD from the generation location and maintains the… More >

Lan Xiong, Liang Wan^*, Jingxia Ren

CMC-Computers, Materials & Continua, Vol.87, No.3, 2026, DOI:10.32604/cmc.2026.076986 - 09 April 2026

Abstract The semantic complexity of large-scale malicious payloads in modern network traffic severely limits the robustness and generalization of existing Intrusion Detection Systems (IDS). This limitation presents a major challenge to network security. This paper proposes a dual-branch intrusion detection method called CPS-IDS. This method fuses deep semantic features with statistical features. The first branch uses the DeBERTav2 module. It performs deep semantic modeling on the session payload. This branch also incorporates a Time Encoder. The Time Encoder models the temporal behavior of the packet arrival interval time series. A Cross-Attention mechanism achieves the joint modeling… More >

Guanfeng Wang^1,2, Xuliang Yao^1,*, Jingfang Wang¹, Yongxin Sun², Jincheng Geng², Erlou Shi², Zhili Zhou^3,*

CMC-Computers, Materials & Continua, Vol.87, No.3, 2026, DOI:10.32604/cmc.2026.076846 - 09 April 2026

Abstract In a real-world industrial system, it is challenging to reduce interference from operating conditions and extract high-quality feature data. To address these issues, this paper proposes a time-domain feature generation and analysis (FGA) scheme, which designs a grouping-aggregation (GA) scheme and an index decomposition (ID) method to extract and analyze high-quality feature data for industrial systems. The FGA represents a designed GA-based hybrid algorithm collaborative architecture, which overcomes the limitations of single algorithms and enables joint feature extraction from multi-condition, multi-scale industrial data. Simultaneously, FGA incorporates a feedback-driven threshold self-calibration mechanism, integrating LSTM-VAE to dynamically… More >

Yan-Hao Huang^*, Yu-Tse Huang

CMC-Computers, Materials & Continua, Vol.87, No.3, 2026, DOI:10.32604/cmc.2026.076800 - 09 April 2026

Abstract Diabetic Retinopathy (DR) is a common microvascular complication of diabetes that progressively damages the retinal blood vessels and, without timely treatment, can lead to irreversible vision loss. In clinical practice, DR is typically diagnosed by ophthalmologists through visual inspection of fundus images, a process that is time-consuming and prone to inter- and intra-observer variability. Recent advances in artificial intelligence, particularly Convolutional Neural Networks (CNNs) and Transformer-based models, have shown strong potential for automated medical image classification and decision support. In this study, we propose a Position-Wise Attention-Enhanced Vision Transformer (PWAE-ViT), which integrates a positional attention… More >