Attention-Based Lightweight YOLOv8 Underwater Target Recognition Algorithm by Shun Cheng, Zhiqian Wang, Shaojin Liu, Yan Han, Pengtao Sun, Jianrong Li

“…Firstly, the SPDConv module is utilized in the backbone network to replace the standard convolutional module for feature extraction. This enhances computational efficiency and reduces redundant computations. …”
Get full text

WTSM-SiameseNet: A Wood-Texture-Similarity-Matching Method Based on Siamese Networks by Yizhuo Zhang, Guanlei Wu, Shen Shi, Huiling Yu

Get full text

Dual branch attention network for image super-resolution by Yiwei Hu, Yisu Ge, Mingming Qi, Shuhua Xu

“…Recently, the Transformer architecture has shown significant potential in image super-resolution due to its ability to perceive global features. Yet, the quadratic computational complexity of self-attention mechanisms in these Transformer-based methods leads to substantial computational and parameter overhead, limiting their practical application. …”
Get full text

LMSOE-Net: lightweight multi-scale small object enhancement network for UAV aerial images by Zhixing Ma, Peidong Luo, Xiaole Shen

“…This upgrade strengthens the network’s ability to capture fine details and complex patterns, improving multi-scale feature extraction without a significant increase in parameters. …”
Get full text

YOLO-DLHS-P: A Lightweight Behavior Recognition Algorithm for Captive Pigs by Changhua Zhong, Hao Wu, Junzhuo Jiang, Chaowen Zheng, Hong Song

“…Firstly, the C2f-DRB structure is introduced at the Backbone position, and the sizeable convolutional kernel is used to extend the receptive field to enhance the spatial perception ability of the model, and to enhance the network’s ability to capture spatial information while maintaining the number of learnable parameters and computational efficiency; The LSKA attention mechanism is then introduced to be integrated into the SPPF module to construct the SPPF-LSKA structure, which significantly improves the ability of the SPPF module to aggregate features at multiple scales; Then, the downsampling at the Neck position is optimised to the HWD algorithm, which reduces the spatial resolution of the feature map while retaining more useful information and reduces the uncertainty of the information compared with the downsampling method of the baseline model; finally, the Shape-IoU is used to replace the original CIoU, which significantly improves the detection efficiency and accuracy of the model without increasing the extra computational burden. …”
Get full text

FQDNet: A Fusion-Enhanced Quad-Head Network for RGB-Infrared Object Detection by Fangzhou Meng, Aoping Hong, Hongying Tang, Guanjun Tong

“…FQDNet was evaluated on three public RGB-IR datasets—M3FD, VEDAI, and LLVIP—achieving mAP@[0.5:0.95] gains of 4.4%, 3.5%, and 3.1% over the baseline, with only a 0.4 M increase in parameters and 5.5 GFLOPs overhead. Compared to state-of-the-art RGB-IR object detection algorithms, our method strikes a better balance between detection accuracy and computational efficiency while exhibiting strong robustness across diverse detection scenarios.…”
Get full text

Unlocking the potential of secure communications: A comprehensive systematic review of the network design model for topology control and routing synergy in wireless sensor networks... by Taher Alzahrani, Saima Rashid

“…Dynamics are implemented for researching the behavior of network topologies in delayed parameters. The center manifold theorem applies to figure out the features of expanding recurring fluctuations. …”
Get full text

Full spectrum of novelties in time-dependent urn models by Alessandro Bellina, Giordano De Marzo, Vittorio Loreto

“…We highlight how the TUMT features a “critical” region where both Heaps' and Zipf's laws coexist, for which we compute the exponents.…”
Get full text

Single-Pixel Imaging Reconstruction Network with Hybrid Attention and Enhanced U-Net by Bingrui Xiao, Huibin Wang, Yang Bu

“…This method takes the Generative Adversarial Network (GAN) as the basic architecture, combines the dense residual structure and the deep separable attention mechanism, and reduces the parameters while ensuring the diversity of feature extraction. …”
Get full text

A Lightweight Network with Domain Adaptation for Motor Imagery Recognition by Xinmin Ding, Zenghui Zhang, Kun Wang, Xiaolin Xiao, Minpeng Xu

“…This paper proposes an innovative method that combines a lightweight convolutional neural network (CNN) with domain adaptation. A lightweight feature extraction module is designed to extract key features from both the source and target domains, effectively reducing the model’s parameters and improving the real-time performance and computational efficiency. …”
Get full text

GES-YOLO: A Light-Weight and Efficient Method for Conveyor Belt Deviation Detection in Mining Environments by Hongwei Wang, Ziming Kou, Yandong Wang

“…To address issues such as the high computational complexity, large number of parameters, long inference time, and difficulty in feature extraction of existing conveyor belt deviation detection models, we propose a GES-YOLO algorithm for detecting deviation in mining belt conveyors, based on an improved YOLOv8s model. …”
Get full text

Lightweight Dual-Backbone Detection Transformer for Infrared Insulator Detection by Boyang Zhang, Yanpeng Zhang, Liming Sun

“…To extract target features from complex infrared backgrounds more accurately while reducing computational cost, we propose a multi-scale attention network (MSANet) as the adaptive backbone, which employs a multi-branch parallel structure and dynamically adjusts feature weights through a multi-scale gated attention mechanism. …”
Get full text

Enhanced Digital Acoustic Perception in Hearing Aid Device Using Reconfigurable Filter Bank Structure: A Systematic Review with Recommendation by Rekha Karuppaiah, Umadevi Seerengasamy, Nagajayanthi Boobalakrishnan

“…This proposed architecture features reconfigurable sub-band frequencies tailored to the user’s specific hearing loss, utilizing a Coefficient Scanning Mechanism (CSM) and Floating Point-Computation Sharing High-speed Mechanism (FP-CSHM). …”
Get full text

Meta-Learning-Based Lightweight Method for Food Calorie Estimation by Jinlin Ma, Yuetong Wan, Ziping Ma

“…Then, to achieve efficient calorie estimation with lower computational complexity, the calorie estimation module employs query-based inference to achieve optimal feature expression. …”
Get full text

A 3D lightweight network with Roberts edge enhancement model (LR-Net) for brain tumor segmentation by Qingxu Meng, Weijiang Wang, Hang Qi, Hua Dang, Minli Jia, Xiaohua Wang

“…Although the combination of CNNs and Transformers balances the ability to capture local detailed features and global context information, it inevitably increases the model’s parameters and computational cost, which restricts its equal deployment in real medical scenarios. …”
Get full text

FDCN-C: A deep learning model based on frequency enhancement, deformable convolution network, and crop module for electroencephalography motor imagery classification. by Hong-Jie Liang, Ling-Long Li, Guang-Zhong Cao

“…Secondly, for temporal feature extraction, a deformable convolution network is employed to enhance feature extraction capabilities, utilizing offset parameters to modulate the convolution kernel size. …”
Get full text

A Lightweight Model for Shine Muscat Grape Detection in Complex Environments Based on the YOLOv8 Architecture by Changlei Tian, Zhanchong Liu, Haosen Chen, Fanglong Dong, Xiaoxiang Liu, Cong Lin

“…Automated harvesting of “Sunshine Rose” grapes requires accurate detection and classification of grape clusters under challenging orchard conditions, such as occlusion and variable lighting, while ensuring that the model can be deployed on resource- and computation-constrained edge devices. This study addresses these challenges by proposing a lightweight YOLOv8-based model, incorporating DualConv and the novel C2f-GND module to enhance feature extraction and reduce computational complexity. …”
Get full text

Research on Vehicle Target Detection Method Based on Improved YOLOv8 by Mengchen Zhang, Zhenyou Zhang

“…By designing a shared convolution layer through group normalization, the detection head of the original model was improved, which can reduce redundant calculations and parameters and enhance the ability of global information fusion between feature maps, thereby achieving the purpose of improving computational efficiency. …”
Get full text

Enhancing Real-Time Road Object Detection: The RD-YOLO Algorithm With Higher Precision and Efficiency by Weijian Wang, Wei Yu

“…This integration improves the model’s feature extraction capabilities while reducing the number of parameters. …”
Get full text

Towards Precise Papaya Ripeness Assessment: A Deep Learning Framework with Dynamic Detection Heads by Haohai You, Jing Fan, Dongyan Huang, Weilong Yan, Xiting Zhang, Zhenke Sun, Hongtao Liu, Jun Yuan

“…First, the width factor of YOLOv8n is adjusted to construct a lightweight backbone network, YOLO-Ting. Second, a low-computation ADown module is introduced to replace the standard downsampling structure, aiming to enhance feature extraction efficiency. …”
Get full text