GIS partial discharge diagnosis method under sample imbalance conditions by Tianyu Hu, Hongzhong Ma, Dawei Duan, Yuan Dong

“…The experimental results demonstrate that the LeViT-FECA-LCF model achieves a recognition accuracy of 99.5%, showing improvements of 1.0%, 1.5%, 1.5%, and 2.5% over EfficientNet-B0, MobileNetV3, ShuffleNetV2, and LeViT, respectively. …”
Get full text

Research on the Real-Time Scoring of Chest Ring Target Based on Transfer Learning and Improved Lightweight Neural Network by Minghui Meng, Chuande Zhou

“…To achieve real-time scoring of chest ring targets during outdoor shooting training while addressing the issues of limited memory and low performance in portable devices, this paper proposes a real-time scoring method for chest ring targets based on an improved lightweight neural network architecture. To enable efficient and high-precision real-time bullet hole detection, the paper lightweight processes the YOLOv10n end-to-end regression framework. …”
Get full text

AI based diagnostics product design for osteosarcoma cells microscopy imaging of bone cancer patients using CA-MobileNet V3 by Qian Liu, Xing She, Qian Xia

“…Compared with models such as ShuffleNet V2, EfficientNet V2, Mobilenet V3 (without transfer learning), TL-MobileNet V3 (with transfer learning), etc., the model size is only 5.33 MB, is a lightweight model, and the accuracy of the improved model reached 98.69 %. …”
Get full text

YOLO-GCOF: A Lightweight Low-Altitude Drone Detection Model by Wanjun Yu, Kongxin Mo

“…To address this issue, we propose a lightweight model named YOLO-GCOF, leveraging an optimized version of the YOLOv8 architecture to enhance accuracy and enable efficient deployment on embedded devices. YOLO-GCOF incorporates the GSConv-Integrated Dynamic Group Convolution Shuffle Transformer (GI-DGCST) module as the feature extraction module, which captures fine-grained details and improves the detection of small-scale features. …”
Get full text

TCSRNet: a lightweight tobacco leaf curing stage recognition network model by Panzhen Zhao, Panzhen Zhao, Songfeng Wang, Shijiang Duan, Aihua Wang, Lingfeng Meng, Yichong Hu

“…Compared to models such as ResNet34, GhostNet, ShuffleNetV2×1.5, EfficientNet-b0, MobileViT-xs, MobileNetV2, MobileNetV3-large, and MobileNetV3-small, TCSRNet demonstrates superior performance in terms of accuracy, FLOPs, and parameter count. …”
Get full text

Petrographic image classification of complex carbonate rocks from the Brazilian pre-salt using convolutional neural networks by Mateus Basso, João Paulo da Ponte Souza, Guilherme Furlan Chinelatto, Luis Augusto Antoniossi Mansini, Alexandre Campane Vidal

“…We evaluated five computational models: EfficientNet, MobileNet v3, RegNet, ResNet, and ShuffleNet v2. …”
Get full text

Cimiciato defect detection in hazelnuts: CNN models applied on X-ray images by Andrea Vitale, Matteo Giaccone, Antonio Gaetano Napolitano, Flavia de Benedetta, Laura Gargiulo, Giacomo Mele

“…Lightweight models such as SqueezeNet and ShuffleNet provided fast and resource-efficient training, though with moderate trade-offs in classification accuracy. …”
Get full text

YOLO-SRMX: A Lightweight Model for Real-Time Object Detection on Unmanned Aerial Vehicles by Shimin Weng, Han Wang, Jiashu Wang, Changming Xu, Ende Zhang

“…Firstly, the model utilizes ShuffleNetV2 as an efficient lightweight backbone and integrates the novel Multi-Scale Dilated Attention (MSDA) module. …”
Get full text

Research on High-Accuracy, Lightweight, Superfast Model for Nitrogen Diagnosis and Plant Growth in Lettuce (<i>Lactuca sativa</i> L.) by Xuyang Li, Iftikhar Hussain Shah, Xiaohao Gong, Muhammad Azam, Wu Jinhui, Pengli Li, Yidong Zhang, Qingliang Niu, Liying Chang

“…Applying the transfer learning technique in RGB images exhibited EfficientNet-v2-s, the best model for precise determination of nitrogen diagnostics, with R² of 0.9859, MSE of 24.0755, and MAE of 2.3433. …”
Get full text

Fast and Accurate Identification of Kiwifruit Diseases Using a Lightweight Convolutional Neural Network Architecture by Kangchen Liu, Li Li, Xiujun Zhang

“…These findings underscore the utility of ShuffleNet_V2_x0_5 in supporting scalable and efficient disease management within precision kiwifruit agriculture. …”
Get full text

Deep Learning–Based Enhanced Optimization for Automated Rice Plant Disease Detection and Classification by P. Preethi, R. Swathika, S. Kaliraj, R. Premkumar, J. Yogapriya

“…To enhance the optimization process, an innovative variant of the Shuffled Shepherd Optimization (SSO) algorithm, known as Enhanced Artificial Shuffled Shepherd Optimization (EASSO), is introduced. …”
Get full text

Directed evolution of nucleotide-based libraries using lambda exonuclease by Bee Nar Lim, Yee Siew Choong, Asma Ismail, Jörn Glökler, Zoltán Konthur, Theam Soon Lim

“…We conclude that our method is an efficient and convenient approach to generate diversity in nucleic acid based libraries, especially recombinant antibody libraries.…”
Get full text

An innovative rheometric tool to study chemorheology by Altobelli Annarita, Pasquino Rossana, Grizzuti Nino

“…The new tool, adaptable to all conventional rheometers equipped with a disposable shuffle, incorporates a custom spiral channel geometry that allows immediate and efficient merging of two-component systems directly within the measurement system. …”
Get full text

BiSeNeXt: a yam leaf and disease segmentation method based on an improved BiSeNetV2 in complex scenes by Bibo Lu, Yanjun Lu, Di Liang, Jie Yang

“…Firstly, dynamic feature extraction block (DFEB) enhances the precision of leaf and disease edge pixels and reduces lesion omission through dynamic receptive-field convolution (DRFConv) and pixel shuffle (PixelShuffle) downsampling. Secondly, efficient asymmetric multi-scale attention (EAMA) effectively alleviates the problem of lesion adhesion by combining asymmetric convolution with a multi-scale parallel structure. …”
Get full text

Improved RT-DETR for Infrared Ship Detection Based on Multi-Attention and Feature Fusion by Chun Liu, Yuanliang Zhang, Jingfu Shen, Feiyue Liu

“…Additionally, a channel attention module is employed during feature selection, leveraging high-level features to filter low-level information and enabling efficient multi-level fusion. The model’s target detection performance on resource-constrained devices is further enhanced by incorporating advanced techniques such as group convolution and ShuffleNetV2. …”
Get full text

Uncertainty monitoring in Eurasian jays (Garrulus glandarius) by M. Loconsole, A. K. Schnell, E. Garcia-Pelegrin, N. S. Clayton

“…Metacognition abilities encompass enhanced decision-making in uncertain situations, more efficient resource management, error detection and correction, and improved problem-solving skills. …”
Get full text

Potato late blight leaf detection in complex environments by Jingtao Li, Jiawei Wu, Rui Liu, Guofeng Shu, Xia Liu, Kun Zhu, Changyi Wang, Tong Zhu

“…These reductions make the model lighter and more efficient. The detection speed increased by 16 %, enabling faster detection of potato late blight leaves. …”
Get full text

A Deep Learning-Driven CAD for Breast Cancer Detection via Thermograms: A Compact Multi-Architecture Feature Strategy by Omneya Attallah

“…Features are primarily obtained from various layers of MobileNet, EfficientNetB0, and ShuffleNet architectures to assess the impact of individual layers on classification performance. …”
Get full text

Continual learning with hebbian plasticity in sparse and predictive coding networks: a survey and perspective by Ali Safa

“…Recently, the use of bio-inspired learning techniques such as Hebbian learning and its closely-related spike-timing-dependent plasticity (STDP) variant have drawn significant attention for the design of compute-efficient AI systems that can continuously learn on-line at the edge. …”
Get full text

MSKFaceNet: A Lightweight Face Recognition Neural Network for Low-Power Devices by Peng Zhang, Qinghua Ma, Yi Li, Min Cui

“…MSKFNet adopts a bottleneck design and introduces variable kernel convolutions from VarKNet, combined with channel shuffle and structural re-parameterization techniques, establishing an efficient CNN module for embedded systems. …”
Get full text