Classification of similar electronic components by transfer learning methods DOI
Göksu Taş

Engineering Applications of Artificial Intelligence, Год журнала: 2024, Номер 139, С. 109658 - 109658

Опубликована: Ноя. 12, 2024

Язык: Английский

Object detection of mural images based on improved YOLOv8 DOI
Penglei Wang, Xing Fan, Qimeng Yang

и другие.

Multimedia Systems, Год журнала: 2025, Номер 31(1)

Опубликована: Фев. 1, 2025

Язык: Английский

Процитировано

0

Deep learning ResNet34 model-assisted diagnosis of sickle cell disease via microcolumn isoelectric focusing DOI
Ali Sani, Youli Tian, Shah Saud

и другие.

Analytical Methods, Год журнала: 2024, Номер unknown

Опубликована: Янв. 1, 2024

The study proposes a ResNet34 DL model for automated SCD diagnosis using mIEF Hb S, achieving 90.1% accuracy in classifying variants. model's precision suggests it could reduce costs and the reliance on need expert diagnosis.

Язык: Английский

Процитировано

1

Metal Surface Defect Detection Using Deep Learning Techniques DOI
Abhinav Sinha,

E. Elakiya

Опубликована: Июль 4, 2024

Язык: Английский

Процитировано

0

Documenting customary land boundaries using unmanned aerial vehicle imagery and artificial intelligence DOI Creative Commons
Dianah Rose Abeho, Moreblessings Shoko, Patroba Achola Odera

и другие.

The Photogrammetric Record, Год журнала: 2024, Номер unknown

Опубликована: Ноя. 3, 2024

Abstract The use of computer vision and deep learning in boundary documentation for land registration stems from the ongoing demand appropriate mapping approaches unregistered rights to eradicate global challenge tenure insecurity. Previous research has yielded promising results towards automated extraction photo‐visible cadastral boundaries high‐resolution imagery. Nonetheless, invisible is still a challenge. This study investigates place sensor/s on‐board unmanned aerial vehicles algorithms detecting boundaries. It develops participatory marking procedure using low‐cost markers bring monument previously ill‐defined After that, researchers trained tested accuracy convolutional neural network, namely single shot multi‐box detector (SSD) based on Residual Neural Network (ResNet) Visual Geometry Group (VGG) backbone networks automatically detect vehicle SSD ResNet34 performed best with 0.88 precision, 0.92 recall 0.91 F measure or (F1) score. VGG19‐based precision 0.47, 0.53 F1 score 0.50. horizontal map generated varied 0.089 0.496 m per parcel, standard deviation 0.120 m. Results show that this approach practical rural areas.

Язык: Английский

Процитировано

0

Deep Ensemble Fusion For Enhanced Multi-Label Land Cover Classification DOI
Anup Kumar, Anjana Mishra,

Rakesh Kumar Raman

и другие.

2022 13th International Conference on Computing Communication and Networking Technologies (ICCCNT), Год журнала: 2024, Номер unknown, С. 1 - 5

Опубликована: Июнь 24, 2024

Язык: Английский

Процитировано

0

Classification of similar electronic components by transfer learning methods DOI
Göksu Taş

Engineering Applications of Artificial Intelligence, Год журнала: 2024, Номер 139, С. 109658 - 109658

Опубликована: Ноя. 12, 2024

Язык: Английский

Процитировано

0