Rayeesa Mehmood^*, Sergei Koltcov, Anton Surkov, Vera Ignatenko

CMC-Computers, Materials & Continua, Vol.86, No.3, 2026, DOI:10.32604/cmc.2025.072735 - 12 January 2026

Abstract Activation pruning reduces neural network complexity by eliminating low-importance neuron activations, yet identifying the critical pruning threshold—beyond which accuracy rapidly deteriorates—remains computationally expensive and typically requires exhaustive search. We introduce a thermodynamics-inspired framework that treats activation distributions as energy-filtered physical systems and employs the free energy of activations as a principled evaluation metric. Phase-transition–like phenomena in the free-energy profile—such as extrema, inflection points, and curvature changes—yield reliable estimates of the critical pruning threshold, providing a theoretically grounded means of predicting sharp accuracy degradation. To further enhance efficiency, we propose a renormalized free energy technique that More >

Afnan Alhindi^*, Saad Al-Ahmadi, Mohamed Maher Ben Ismail

CMC-Computers, Materials & Continua, Vol.86, No.3, 2026, DOI:10.32604/cmc.2025.072625 - 12 January 2026

Abstract Split Learning (SL) has been promoted as a promising collaborative machine learning technique designed to address data privacy and resource efficiency. Specifically, neural networks are divided into client and server sub-networks in order to mitigate the exposure of sensitive data and reduce the overhead on client devices, thereby making SL particularly suitable for resource-constrained devices. Although SL prevents the direct transmission of raw data, it does not alleviate entirely the risk of privacy breaches. In fact, the data intermediately transmitted to the server sub-model may include patterns or information that could reveal sensitive data. Moreover,… More >

Xin Ma^1,2, Jin Lei^3,4,*, Chenying Pei⁴, Chunming Wu⁴

CMC-Computers, Materials & Continua, Vol.86, No.2, pp. 1-17, 2026, DOI:10.32604/cmc.2025.069353 - 09 December 2025

Abstract This study proposes a lightweight apple detection method employing cascaded knowledge distillation (KD) to address the critical challenges of excessive parameters and high deployment costs in existing models. We introduce a Lightweight Feature Pyramid Network (LFPN) integrated with Lightweight Downsampling Convolutions (LDConv) to substantially reduce model complexity without compromising accuracy. A Lightweight Multi-channel Attention (LMCA) mechanism is incorporated between the backbone and neck networks to effectively suppress complex background interference in orchard environments. Furthermore, model size is compressed via Group_Slim channel pruning combined with a cascaded distillation strategy. Experimental results demonstrate that the proposed model More >

Yunus Dogan¹, Goksu Tuysuzoglu¹, Elife Ozturk Kiyak², Bita Ghasemkhani³, Kokten Ulas Birant^1,4, Semih Utku¹, Derya Birant^1,*

CMES-Computer Modeling in Engineering & Sciences, Vol.144, No.2, pp. 1677-1715, 2025, DOI:10.32604/cmes.2025.069255 - 31 August 2025

Abstract Accurate traffic flow prediction (TFP) is vital for efficient and sustainable transportation management and the development of intelligent traffic systems. However, missing data in real-world traffic datasets poses a significant challenge to maintaining prediction precision. This study introduces REPTF-TMDI, a novel method that combines a Reduced Error Pruning Tree Forest (REPTree Forest) with a newly proposed Time-based Missing Data Imputation (TMDI) approach. The REPTree Forest, an ensemble learning approach, is tailored for time-related traffic data to enhance predictive accuracy and support the evolution of sustainable urban mobility solutions. Meanwhile, the TMDI approach exploits temporal patterns… More >

Yun Zhang, Zhenhua Yu^*, Xufei Hu, Xuya Cong, Ou Ye

CMC-Computers, Materials & Continua, Vol.84, No.3, pp. 5403-5426, 2025, DOI:10.32604/cmc.2025.067120 - 30 July 2025

Abstract Devices in Industrial Internet of Things are vulnerable to voice adversarial attacks. Studying adversarial speech samples is crucial for enhancing the security of automatic speech recognition systems in Industrial Internet of Things devices. Current black-box attack methods often face challenges such as complex search processes and excessive perturbation generation. To address these issues, this paper proposes a black-box voice adversarial attack method based on enhanced neural predictors. This method searches for minimal perturbations in the perturbation space, employing an optimization process guided by a self-attention neural predictor to identify the optimal perturbation direction. This direction… More >

Xintao Duan^1,2,*, Yinhang Wu¹, Zhao Wang¹, Chuan Qin³

CMC-Computers, Materials & Continua, Vol.84, No.3, pp. 4887-4906, 2025, DOI:10.32604/cmc.2025.064620 - 30 July 2025

Abstract Deep neural network (DNN) models have achieved remarkable performance across diverse tasks, leading to widespread commercial adoption. However, training high-accuracy models demands extensive data, substantial computational resources, and significant time investment, making them valuable assets vulnerable to unauthorized exploitation. To address this issue, this paper proposes an intellectual property (IP) protection framework for DNN models based on feature layer selection and hyper-chaotic mapping. Firstly, a sensitivity-based importance evaluation algorithm is used to identify the key feature layers for encryption, effectively protecting the core components of the model. Next, the L1 regularization criterion is applied to More >

Haiyan Long¹, Chonghao Zhang², Xudong Qiu³, Hai Chen^2,*, Gang Chen^4,*

CMC-Computers, Materials & Continua, Vol.84, No.2, pp. 2975-2988, 2025, DOI:10.32604/cmc.2025.065047 - 03 July 2025

Abstract 3D sparse convolution has emerged as a pivotal technique for efficient voxel-based perception in autonomous systems, enabling selective feature extraction from non-empty voxels while suppressing computational waste. Despite its theoretical efficiency advantages, practical implementations face under-explored limitations: the fixed geometric patterns of conventional sparse convolutional kernels inevitably process non-contributory positions during sliding-window operations, particularly in regions with uneven point cloud density. To address this, we propose Hierarchical Shape Pruning for 3D Sparse Convolution (HSP-S), which dynamically eliminates redundant kernel stripes through layer-adaptive thresholding. Unlike static soft pruning methods, HSP-S maintains trainable sparsity patterns by progressively… More >

Can Hu¹, Shanqing Zhang^2,*, Kewei Tao², Gaoming Yang¹, Li Li²

CMC-Computers, Materials & Continua, Vol.82, No.3, pp. 4913-4930, 2025, DOI:10.32604/cmc.2025.059770 - 06 March 2025

Abstract The surge of large-scale models in recent years has led to breakthroughs in numerous fields, but it has also introduced higher computational costs and more complex network architectures. These increasingly large and intricate networks pose challenges for deployment and execution while also exacerbating the issue of network over-parameterization. To address this issue, various network compression techniques have been developed, such as network pruning. A typical pruning algorithm follows a three-step pipeline involving training, pruning, and retraining. Existing methods often directly set the pruned filters to zero during retraining, significantly reducing the parameter space. However, this… More >

Guoqiong Liao^1,3, Yinxiang Lei^1,2,*, Yufang Xie¹, Neal N. Xiong⁴

CMC-Computers, Materials & Continua, Vol.82, No.2, pp. 3309-3335, 2025, DOI:10.32604/cmc.2024.060077 - 17 February 2025

Abstract As the Internet of Medical Things (IoMT) continues to expand, smart health-monitoring devices generate vast amounts of valuable data while simultaneously raising critical security and privacy challenges. Blockchain technology presents a promising avenue to address these concerns due to its inherent decentralization and security features. However, scalability remains a persistent hurdle, particularly for IoMT applications that involve large-scale networks and resource-constrained devices. This paper introduces a novel lightweight sharding method tailored to the unique demands of IoMT data sharing. Our approach enhances state bootstrapping efficiency and reduces operational overhead by utilizing a dual-chain structure comprising… More >

Jiansheng Peng^1,2,3,4,*, Wei Qian¹, Hongyu Zhang¹

CMC-Computers, Materials & Continua, Vol.82, No.2, pp. 2849-2868, 2025, DOI:10.32604/cmc.2024.058028 - 17 February 2025

Abstract Dynamic visual SLAM (Simultaneous Localization and Mapping) is an important research area, but existing methods struggle to balance real-time performance and accuracy in removing dynamic feature points, especially when semantic information is missing. This paper presents a novel dynamic SLAM system that uses optical flow tracking and epipolar geometry to identify dynamic feature points and applies a regional dynamic probability method to improve removal accuracy. We developed two innovative algorithms for precise pruning of dynamic regions: first, using optical flow and epipolar geometry to identify and prune dynamic areas while preserving static regions on stationary… More >