Gang Li^1,#, Ru Wang^1,#, Yang Zhang^2,*, Chuanyun Xu², Xinyu Fan¹, Zheng Zhou¹, Pengfei Lv¹, Zihan Ruan¹

CMC-Computers, Materials & Continua, Vol.85, No.2, pp. 3267-3288, 2025, DOI:10.32604/cmc.2025.067763 - 23 September 2025

Abstract Currently, challenges such as small object size and occlusion lead to a lack of accuracy and robustness in small object detection. Since small objects occupy only a few pixels in an image, the extracted features are limited, and mainstream downsampling convolution operations further exacerbate feature loss. Additionally, due to the occlusion-prone nature of small objects and their higher sensitivity to localization deviations, conventional Intersection over Union (IoU) loss functions struggle to achieve stable convergence. To address these limitations, LR-Net is proposed for small object detection. Specifically, the proposed Lossless Feature Fusion (LFF) method transfers spatial… More >

Divya Arivalagan, Vignesh Ochathevan^*, Rubankumar Dhanasekaran

Congenital Heart Disease, Vol.20, No.4, pp. 477-501, 2025, DOI:10.32604/chd.2025.070372 - 18 September 2025

Abstract Background: The accurate identification of cardiac abnormalities is essential for proper diagnosis and effective treatment of cardiovascular diseases. Method: This work introduces an advanced methodology for detecting cardiac abnormalities and estimating electrocardiographic age (ECG Age) using sophisticated signal processing and deep learning techniques. This study looks at six main heart conditions found in 12-lead electrocardiogram (ECG) data. It addresses important issues like class imbalances, missing lead scenarios, and model generalizations. A modified residual neural network (ResNet) architecture was developed to enhance the detection of cardiac abnormalities. Results: The proposed ResNet demonst rated superior performance when compared with… More > Graphic Abstract

Hao Sun^1,2, Di Cai¹, Dae-Ki Kang^2,*

CMC-Computers, Materials & Continua, Vol.85, No.1, pp. 1675-1692, 2025, DOI:10.32604/cmc.2025.067675 - 29 August 2025

Abstract Accurately identifying crop pests and diseases ensures agricultural productivity and safety. Although current YOLO-based detection models offer real-time capabilities, their conventional convolutional layers involve high computational redundancy and a fixed receptive field, making it challenging to capture local details and global semantics in complex scenarios simultaneously. This leads to significant issues like missed detections of small targets and heightened sensitivity to background interference. To address these challenges, this paper proposes a lightweight adaptive detection network—StarSpark-AdaptiveNet (SSANet), which optimizes features through a dual-module collaborative mechanism. Specifically, the StarNet module utilizes Depthwise separable convolutions (DW-Conv) and dynamic… More >

Miao Li^1,2,*, Xiaojun Li^1,3, Mingyang Zhao^1,2

CMC-Computers, Materials & Continua, Vol.85, No.1, pp. 1917-1936, 2025, DOI:10.32604/cmc.2025.067382 - 29 August 2025

Abstract Aiming at problems such as large errors and low efficiency in manual counting of drill pipes during drilling depth measurement, an intelligent detection and counting method for the small targets at the end of drill pipes based on the improved YOLO11n is proposed. This method realizes the high-precision detection of targets at drill pipe ends in the image by optimizing the target detection model, and combines a post-processing correction mechanism to improve the drill pipe counting accuracy. In order to alleviate the low-precision problem of YOLO11n algorithm for small target recognition in the complex underground… More >

Senchun Miao^1,*, Wenkai Hu¹, Jiangbo Wu¹, Zhengjing Shen¹, Xiaoze Du^1,2,*

FDMP-Fluid Dynamics & Materials Processing, Vol.21, No.7, pp. 1711-1735, 2025, DOI:10.32604/fdmp.2025.062239 - 31 July 2025

Abstract In Brayton cycle energy storage systems powered by supercritical carbon dioxide (sCO₂), compressors are among the most critical components. Understanding their internal flow loss characteristics is, therefore, essential for enhancing the performance of such systems. This study examines the main sCO₂ compressor from Sandia Laboratory, utilizing entropy production theory to elucidate the sources and distribution of energy losses both across the entire machine and within its key flow components. The findings reveal that turbulent viscous dissipation is the predominant contributor to total entropy production. Interestingly, while the relative importance of the entropy produced by various sources More >

Sandra Gajević¹, Slavica Miladinović¹, Jelena Jovanović¹, Onur Güler², Serdar Özkaya², Blaža Stojanović^1,*

CMC-Computers, Materials & Continua, Vol.84, No.3, pp. 4341-4361, 2025, DOI:10.32604/cmc.2025.065645 - 30 July 2025

Abstract This paper presents an investigation of the tribological performance of AA2024–B₄C composites, with a specific focus on the influence of reinforcement and processing parameters. In this study three input parameters were varied: B₄C weight percentage, milling time, and normal load, to evaluate their effects on two output parameters: wear loss and the coefficient of friction. AA2024 alloy was used as the matrix alloy, while B₄C particles were used as reinforcement. Due to the high hardness and wear resistance of B₄C, the optimized composite shows strong potential for use in aerospace structural elements and automotive brake components. The… More >

Adéla Hamplová^*, Tomáš Novák, Miroslav Žáček, Jiří Brožek

CMES-Computer Modeling in Engineering & Sciences, Vol.143, No.3, pp. 3329-3349, 2025, DOI:10.32604/cmes.2025.066025 - 30 June 2025

Abstract This study proposes a new component of the composite loss function minimised during training of the Super-Resolution (SR) algorithms—the normalised structural similarity index loss , which has the potential to improve the natural appearance of reconstructed images. Deep learning-based super-resolution (SR) algorithms reconstruct high-resolution images from low-resolution inputs, offering a practical means to enhance image quality without requiring superior imaging hardware, which is particularly important in medical applications where diagnostic accuracy is critical. Although recent SR methods employing convolutional and generative adversarial networks achieve high pixel fidelity, visual artefacts may persist, making the design of… More >

Yu-Shiuan Tsai^*, Yuk-Hang Sit

CMES-Computer Modeling in Engineering & Sciences, Vol.143, No.3, pp. 3065-3090, 2025, DOI:10.32604/cmes.2025.064783 - 30 June 2025

Abstract To improve small object detection and trajectory estimation from an aerial moving perspective, we propose the Aerial View Attention-PRB (AVA-PRB) model. AVA-PRB integrates two attention mechanisms—Coordinate Attention (CA) and the Convolutional Block Attention Module (CBAM)—to enhance detection accuracy. Additionally, Shape-IoU is employed as the loss function to refine localization precision. Our model further incorporates an adaptive feature fusion mechanism, which optimizes multi-scale object representation, ensuring robust tracking in complex aerial environments. We evaluate the performance of AVA-PRB on two benchmark datasets: Aerial Person Detection and VisDrone2019-Det. The model achieves 60.9% mAP@0.5 on the Aerial Person… More >

Md Tanjil Sarker^1,*, See Wei Jing¹, Gobbi Ramasamy^1,*, Siva Priya Thiagarajah¹, Md. Golam Sadeque²

Energy Engineering, Vol.122, No.7, pp. 2891-2909, 2025, DOI:10.32604/ee.2025.065331 - 27 June 2025

Abstract Industrial processes often involve rotating machinery that generates substantial kinetic energy, much of which remains untapped. Harvesting rotational kinetic energy offers a promising solution to reduce energy waste and improve energy efficiency in industrial applications. This research investigates the potential of electromagnetic induction for harvesting rotational kinetic energy from industrial machinery. A comparative study was conducted between disk and cylinder-shaped rotational bodies to evaluate their energy efficiency under various load conditions. Experimental results demonstrated that the disk body exhibited higher energy efficiency, primarily due to lower mechanical losses compared to the cylinder body. A power… More >

Yuhe Wang^1,2, Haijun Sun³, Yaqiong Hao^2,4, Xiancan Zhu¹, Ju Min^2,*

Phyton-International Journal of Experimental Botany, Vol.94, No.6, pp. 1735-1750, 2025, DOI:10.32604/phyton.2025.063868 - 27 June 2025

Abstract Over the past three decades, the expansion of intensive vegetable farming in southern China has led to excessive nitrogen (N) and phosphorus (P) fertilizer application, causing substantial N and P runoff losses. This study investigated four major vegetable production regions in southern China—the upper reaches of the Yangtze River (U-YR), the middle lower reaches of the Yangtze River (ML-YR), the Southeast Coast (SC), and the Pearl River basin (PR)—analyzing 175 published articles to characterize spatiotemporal patterns of N and P fertilizer applications and associated runoff losses from 1992 to 2021. The result showed that the… More >