Low-light image enhancement method for underground mines based on an improved Zero-DCE model by WANG Yiwei, LI Xiaoyu, WENG Zhi, BAI Fengshan

“…A Cascaded Convolution Kernel (CCK) was employed in the deep network to reduce the number of model parameters and computational cost, thereby shortening the training time. …”
Get full text

Lightweight detection and segmentation of crayfish parts using an improved YOLOv11n segmentation model by Wei Shi, Jun Zhang, YunFan Fu, DanWei Chen, JianPing Zhu, ChunFeng Lv

“…First, the proposed D-HGNetV2 backbone integrates DynamicConv modules into the HGNetV2 architecture, reducing parameters by 31% (from 2.9 M to 2.0 M) and computational cost by 9.8% (10.2 GFLOPs to 9.2 GFLOPs) through input-dependent kernel aggregation, which enhances multiscale feature extraction for occluded or overlapping parts. …”
Get full text

Toward an Efficient and Robust Process–Structure Prediction Framework for Filigree L-PBF 316L Stainless Steel Structures by Yu Qiao, Marius Grad, Aida Nonn

Get full text

Ghost Module-Enhanced MTCNN: A Lightweight Cascade Framework for High-Accuracy Face Detection in Edge-Deployable Scenarios by Chen Wang, Fen Liu

“…Face detection in complex environments remains challenging due to trade-offs between accuracy and computational efficiency, particularly for edge devices with limited resources. …”
Get full text

A Modified MobileNetv3 Coupled With Inverted Residual and Channel Attention Mechanisms for Detection of Tomato Leaf Diseases by Rubina Rashid, Waqar Aslam, Romana Aziz, Ghadah Aldehim

“…Additionally, inverted residual connections are incorporated to expand the model’s receptive field. To maximize feature utilization, cross-layer connections are introduced between the two parallel streams, integrating the Efficient Channel Attention (ECA) module to reduce the number of parameters. …”
Get full text

Red Raspberry Maturity Detection Based on Multi-Module Optimized YOLOv11n and Its Application in Field and Greenhouse Environments by Rongxiang Luo, Xue Ding, Jinliang Wang

“…Secondly, dilation-wise residual (DWR) is fused with the C3k2 module of the network and applied to the entire network structure to enhance feature extraction, multi-scale perception, and computational efficiency in red raspberry detection. …”
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

Analysis of COVID-19 Disease Model: Backward Bifurcation and Impact of Pharmaceutical and Nonpharmaceutical Interventions by Ibad Ullah, Nigar Ali, Ihtisham Ul Haq, Imtiaz Ahmad, Mohammed Daher Albalwi, Md. Haider Ali Biswas

“…An analysis of the model’s qualitative features was conducted, encompassing the computation of the fundamental reproduction number, R0. …”
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

“…First, ShuffleNetV2 is used as the backbone network to reduce the number of parameters and computational load, making the model more lightweight. …”
Get full text

Depression Analysis and Detection Using Machine Learning: Incorporating Gender Differences in a Comparative Study by Marina Galanina, Anna Rekiel, Anna BaCzyk, Bozena Kostek

“…The research examines four datasets, namely DAIC-WOZ, EATD Corpus, D-Vlog, and EMU, which vary in terms of linguistic background (English and Chinese), depression classification scales, and gender representation proportions. Feature extraction employs parameters such as formant-related, MFCCs (Mel Frequency Cepstral Coefficients), and jitter parameters. …”
Get full text

YOLO-SAATD: An efficient SAR airport and aircraft target detector by Daobin Ma, Zhanhong Lu, Zixuan Dai, Yangyue Wei, Li Yang, Haimiao Hu, Wenqiao Zhang, Dongping Zhang

“…Efficiency: A lightweight hierarchical multi-scale backbone reduces parameters and enhances detection speed. 2. Fine granularity: A ”ScaleNimble Neck” integrates feature reshaping and scale-aware aggregation to enhance detail detection and feature capture in multi-scale SAR images. 3. …”
Get full text

Cotton Weed-YOLO: A Lightweight and Highly Accurate Cotton Weed Identification Model for Precision Agriculture by Jinghuan Hu, He Gong, Shijun Li, Ye Mu, Ying Guo, Yu Sun, Tianli Hu, Yu Bao

“…CW-YOLO is based on YOLOv8 and introduces a dual-branch structure combining a Vision Transformer and a Convolutional Neural Network to address the problems of the small receptive field of the CNN and the high computational complexity of the transformer. The Receptive Field Enhancement (RFE) module is proposed to enable the feature pyramid network to adapt to the feature information of different receptive fields. …”
Get full text

A Lightweight Neural Network for Cell Segmentation Based on Attention Enhancement by Shuang Xia, Qian Sun, Yiheng Zhou, Zhaoyuxuan Wang, Chaoxing You, Kainan Ma, Ming Liu

“…Deep neural networks have made significant strides in medical image segmentation tasks, but their large-scale parameters and high computational complexity limit their applicability on resource-constrained edge devices. …”
Get full text

Optimized YOLOv8 framework for intelligent rockfall detection on mountain roads by Peng Peng, Langchao Gao, Jiachun Li, Hongzhen Zhang

“…The algorithm enhances detection performance through the following optimizations: (1) integrating a lightweight DeepLabv3+ road segmentation module at the input stage to generate mask images, which effectively exclude non-road regions from interference; (2) replacing Conv convolution units in the backbone network with Ghost convolution units, significantly reducing model parameters and computational cost while improving inference speed; (3) introducing the CPCA (Channel Priori Convolution Attention) mechanism to strengthen the feature extraction capability for targets with diverse shapes; and (4) incorporating skip connections and weighted fusion in the Neck feature extraction network to enhance multi-scale object detection. …”
Get full text

Introducing µGUIDE for quantitative imaging via generalized uncertainty-driven inference using deep learning by Maëliss Jallais, Marco Palombo

“…Harnessing a new deep learning architecture for automatic signal feature selection combined with simulation-based inference and efficient sampling of the posterior distributions, µGUIDE bypasses the high computational and time cost of conventional Bayesian approaches and does not rely on acquisition constraints to define model-specific summary statistics. …”
Get full text

OR-FCOS: an enhanced fully convolutional one-stage approach for growth stage identification of Oudemansiella raphanipes by Runze Fang, Huamao Huang, Nuoyan Guo, Haichuan Wei, Shiyi Wang, Haiying Hu, Ming Liu

“…Channel pruning further reduces the decoder’s parameters, decreasing model size and computational requirements while maintaining precision. …”
Get full text

Optimizing Gammatone Cepstral Coefficients for Gear Fault Detection by Zrar Kh Abdul, Abdulbasit K. Al-Talabani, Wisam Hazim Gwad, Entisar Alkayal, Halgurd S. Maghdid, Safar Maghdid Asaad

Get full text

An enhanced moth flame optimization extreme learning machines hybrid model for predicting CO2 emissions by Ahmed Ramdan Almaqtouf Algwil, Wagdi M. S. Khalifa

“…Feature importance analysis highlighted economic growth, foreign direct investment, and renewable energy as key predictors. …”
Get full text

A Lightweight Direction-Aware Network for Vehicle Detection by Luxia Yang, Yilin Hou, Hongrui Zhang, Chuanghui Zhang

“…Moreover, to further reduce model parameters and computational requirements, a lightweight shared convolutional detection head (SCL-Head) is devised using a parameter-sharing mechanism. …”
Get full text

Adaptive Aberration Correction for Laser Processes Improvement by Carmelo Corsaro, Priscilla Pelleriti, Vincenza Crupi, Daniele Cosio, Fortunato Neri, Enza Fazio

Get full text