A three-dimensional morpho-volumetric similarity study of Down syndrome keratopathy vs. keratoconus by Ibrahim Toprak, Francisco Cavas, José S. Velázquez, Jorge L. Alio del Barrio, Jorge L. Alio

Get full text

Machine learning-based approach for bandwidth and frequency prediction of circular SIW antenna by Md Mahabub Alam, Nurhafizah Abu Talip Yusof, Ahmad Afif Mohd Faudzi, Md Raihanul Islam Tomal, Md Ershadul Haque, Md. Suaibur Rahman

“…Abstract Machine Learning (ML) has significantly transformed antenna design by enabling efficient optimization of geometrical parameters, modeling complex electromagnetic behavior, and accelerating performance prediction with reduced computational cost. …”
Get full text

IVP-YOLOv5: an intelligent vehicle-pedestrian detection method based on YOLOv5s by Yang Sun, Jiankun Song, Yong Li, Yi Li, Song Li, Zehao Duan

“…Computer vision is now vital in intelligent vehicle environment perception systems. …”
Get full text

Machine learning and complex network analysis of drug effects on neuronal microelectrode biosensor data by Manuel Ciba, Marc Petzold, Caroline L. Alves, Francisco A. Rodrigues, Yasuhiko Jimbo, Christiane Thielemann

Get full text

NeuroTutor: Neural Decoding of Student Engagement During Virtual and Robotic Tutoring by Shahd Elgammal, Shaymaa Alsereidi, Mahra Almansoori, Shamma Alblooshi, Abdelhadi Hireche, Abdelkader Nasreddine Belkacem

Get full text

Fast Quality Detection of <i>Astragalus</i> Slices Using FA-SD-YOLO by Fan Zhao, Jiawei Zhang, Qiang Liu, Chen Liang, Song Zhang, Mingbao Li

“…This model introduces several novel modifications to enhance feature extraction and fusion while reducing computational complexity. …”
Get full text

MRFP-Mamba: Multi-Receptive Field Parallel Mamba for Hyperspectral Image Classification by Xiaofei Yang, Lin Li, Suihua Xue, Sihuan Li, Wanjun Yang, Haojin Tang, Xiaohui Huang

“…Deep learning has achieved remarkable success in hyperspectral image (HSI) classification, attributed to its powerful feature extraction capabilities. However, existing methods face several challenges: Convolutional Neural Networks (CNNs) are limited in modeling long-range spectral dependencies because of their limited receptive fields; Transformers are constrained by their quadratic computational complexity; and Mamba-based methods fail to fully exploit spatial–spectral interactions when handling high-dimensional HSI data. …”
Get full text

In-silico platform for the multifunctional design of 3D printed conductive components by Javier Crespo-Miguel, Sergio Lucarini, Sara Garzon-Hernandez, Angel Arias, Emilio Martínez-Pañeda, Daniel Garcia-Gonzalez

“…A full-field homogenisation model first provides the influence of material and mesostructural features (i.e., filament orientations, voids and adhesion between filaments). …”
Get full text

A Defect Detection Algorithm for Optoelectronic Detectors Utilizing GLV-YOLO by Xinfang Zhao, Qinghua Lyu, Hui Zeng, Zhuoyi Ling, Zhongsheng Zhai, Hui Lyu, Saffa Riffat, Benyuan Chen, Wanting Wang

“…The experimental results showed that the proposed algorithm achieved 98.9% accuracy, with 2.1 million parameters and a computational cost of 7.0 GFLOPs. Compared to other methods, our approach outperforms them in both performance and efficiency, fulfilling the real-time and precise defect detection needs of photodetectors.…”
Get full text

Classification of shale gas “sweet spot” based on Random Forest machine learning by NIE Yunli, GAO Guozhong

“…Firstly, data from ten wells in Changning area are selected and eleven features are selected for “sweet spot” classification by the Kendall correlation. …”
Get full text

Ground Fissure Identification in Mining Areas from UAV Images Based on DN-CAMSCBNet by Haibin Hu, Xinhui Guo, Jie Xiao

“…These are used to enhance its ability to capture complex image features, expand the receptive field of the original model, reduce the number of parameters, and reduce computational complexity. …”
Get full text

Optimized Deep Neural Network for High-Precision Psoriasis Classification from Dermoscopic Images by Charu Bolia, Sunil Joshi

“…This compact design with low trainable parameters reduces the computational time and memory makes the model well-suited for deployment for portable devices and enabling real-time mobile-based dermatological assessments. …”
Get full text

OW-YOLO: An Improved YOLOv8s Lightweight Detection Method for Obstructed Walnuts by Haoyu Wang, Lijun Yun, Chenggui Yang, Mingjie Wu, Yansong Wang, Zaiqing Chen

“…Additionally, the model’s parameter count decreased by 49.2%, weight file size was reduced by 48.1%, and computational load dropped by 37.3%, effectively mitigating the impact of obstruction on detection accuracy. …”
Get full text

Steel Surface Defect Detection Technology Based on YOLOv8-MGVS by Kai Zeng, Zibo Xia, Junlei Qian, Xueqiang Du, Pengcheng Xiao, Liguang Zhu

“…Compared with YOLOv8n from experimental results, the average accuracy, recall rate, and frames per second of the improved model were improved by 5.2%, 10.5%, and 6.4%, respectively, while the number of parameters and computational costs were reduced by 5.8% and 14.8%, respectively. …”
Get full text

A Lightweight Network for Water Body Segmentation in Agricultural Remote Sensing Using Learnable Kalman Filters and Attention Mechanisms by Dingyi Liao, Jun Sun, Zhiyong Deng, Yudong Zhao, Jiani Zhang, Dinghua Ou

“…The encoder is built using a shallow Channel Attention-Enhanced Deformable Convolution module (CADCN), while the decoder combines a Convolutional Additive Token Mixer (CATM) and a learnable Kalman filter (LKF) to achieve adaptive noise suppression and enhance global context modeling. Additionally, a feature-based knowledge distillation strategy is employed to further improve the representational capacity of the lightweight model. …”
Get full text

Underground personnel detection and tracking using improved YOLOv7 and DeepSORT by Weiqiang FAN, Xuejin WANG, Yinghui ZHANG, Xiaoyu LI

“…After that, in order to be able to further improve the tracking accuracy of personnel targets while reducing the number of model parameters and network complexity, the ShuffleNetV2 lightweight module is introduced into the feature extraction network of DeepSORT, and the improved DeepSORT model is used to encode and track downhole personnel targets. …”
Get full text

Improved YOLOv10 for Visually Impaired: Balancing Model Accuracy and Efficiency in the Case of Public Transportation by Rio Arifando, Shinji Eto, Tibyani Tibyani, Chikamune Wada

“…The model also exhibits reduced computational complexity and storage requirements, highlighting its efficiency. …”
Get full text

Real-Time Lightweight Morphological Detection for Chinese Mitten Crab Origin Tracing by Xiaofei Ma, Nannan Shen, Yanhui He, Zhuo Fang, Hongyan Zhang, Yun Wang, Jinrong Duan

“…In the first stage, an improved YOLOv10n-based model is designed by incorporating omni-dimensional dynamic convolution, a SlimNeck structure, and a Lightweight Shared Convolutional Detection head, which effectively enhances the detection accuracy of crab targets under complex multi-scale environments while reducing computational cost. In the second stage, an Improved GoogleNet’s Inception Net for Crab is developed based on the Inception module, with further integration of Asymmetric Convolution Blocks and Squeeze and Excitation modules to improve the feature extraction and classification ability for regional origin. …”
Get full text

Benchmarking Hook and Bait Urdu news dataset for domain-agnostic and multilingual fake news detection using large language models by Sheetal Harris, Jinshuo Liu, Hassan Jalil Hadi, Naveed Ahmad, Mohammed Ali Alshara

“…The lightweight LoRA fine-tuning method, with  0.032% trainable parameters, ensured robust data handling, computational efficiency while leveraging early stopping and optimized hyperparameters for reliable and high-performing monolingual and multilingual FND. …”
Get full text

Adapting SAM2 Model from Natural Images for Tooth Segmentation in Dental Panoramic X-Ray Images by Zifeng Li, Wenzhong Tang, Shijun Gao, Yanyang Wang, Shuai Wang

“…We employ adapter modules to fine-tune the SAM2 model and introduce ScConv modules and gated attention mechanisms to enhance the model’s semantic understanding and multi-scale feature extraction capabilities for medical images. …”
Get full text