Engineering Applications of Artificial Intelligence, Год журнала: 2024, Номер 139, С. 109646 - 109646
Опубликована: Ноя. 19, 2024
Язык: Английский
Engineering Applications of Artificial Intelligence, Год журнала: 2024, Номер 139, С. 109646 - 109646
Опубликована: Ноя. 19, 2024
Язык: Английский
Expert Systems with Applications, Год журнала: 2024, Номер 257, С. 124972 - 124972
Опубликована: Авг. 10, 2024
Язык: Английский
Процитировано
1Structural durability & health monitoring, Год журнала: 2024, Номер 18(6), С. 871 - 889
Опубликована: Янв. 1, 2024
In the bridge technical condition assessment standards, evaluation of conditions primarily relies on defects identified through manual inspections, which are determined using comprehensive hierarchical analysis method.However, relationship between and bridges warrants further exploration.To address this situation, paper proposes a machine learning-based intelligent diagnosis model for highway bridges.Firstly, collect inspection records in certain region China, then standardize severity diverse accordance with relevant specifications.Secondly, order to enhance independence defects, key defect indicators were screened Principal Component Analysis (PCA) combination weights building blocks.Based this, an enhanced Naive Bayesian Classification (NBC) algorithm is established bridges, juxtaposed four other algorithms comparison.Finally, variables that affect changes grades discussed.The results showed level superstructure had highest correlation cracks; PCA-NBC achieved accuracy 93.50% predicted values, was improvement 19.43% over methods.The purpose provide inspectors convenient predictive information-rich method intelligently diagnose based defects.The research can help even non-specialists better understand defects.
Язык: Английский
Процитировано
0Cogent Food & Agriculture, Год журнала: 2024, Номер 10(1)
Опубликована: Сен. 11, 2024
Язык: Английский
Процитировано
0Engineering Applications of Artificial Intelligence, Год журнала: 2024, Номер 138, С. 109466 - 109466
Опубликована: Окт. 18, 2024
Язык: Английский
Процитировано
0Plant Methods, Год журнала: 2024, Номер 20(1)
Опубликована: Ноя. 4, 2024
With the emergence of new generation vision architecture Vmamba and further demand for agricultural yield efficiency, we propose an efficient high-accuracy target detection network automated pear picking tasks based on Vmamba, aiming to address issue low efficiency in current Transformer architectures. The proposed network, named SRSMamba, employs a Reward Punishment Mechanism (RPM) focus important information while minimizing redundancy interference. It utilizes 3D Selective Scan (SS3D) extend scanning dimensions integrates global across channel dimensions, thereby enhancing model's robustness complex environments effectively adapting extraction features orchards farmlands. Additionally, Stacked Feature Pyramid Network (SFPN) is introduced enhance semantic during feature fusion stage, particularly improving capability small targets. Experimental results show that SRSMamba has parameter count 21.1 M, GFLOPs 50.4, mAP 72.0%, mAP50 reaching 94.8%, mAP75 at 68.1%, FPS 26.9. Compared with other state-of-the-art (SOTA) object methods, it achieves good trade-off between model accuracy.
Язык: Английский
Процитировано
0Agronomy, Год журнала: 2024, Номер 14(11), С. 2605 - 2605
Опубликована: Ноя. 4, 2024
Accurate diagnosis of plant diseases is crucial for crop health. This study introduces the EDA–ViT model, a Vision Transformer (ViT)-based approach that integrates adaptive entropy-based data augmentation diagnosing custard apple (Annona squamosa) diseases. Traditional models like convolutional neural network and ViT face challenges with local feature extraction large dataset requirements. overcomes these by using multi-scale weighted aggregation interaction module, enhancing both global extraction. The method refines training process, boosting accuracy robustness. With 8226 images, achieved classification 96.58%, an F1 score 96.10%, Matthews Correlation Coefficient (MCC) 92.24%, outperforming other models. inclusion Deformable Multi-head Self-Attention (DMSA) mechanism further enhanced capture. Ablation studies revealed contributed to 0.56% improvement 0.34% increase in MCC. In summary, presents innovative solution disease diagnosis, potential applications broader agricultural detection, ultimately aiding precision agriculture health management.
Язык: Английский
Процитировано
0AgriEngineering, Год журнала: 2024, Номер 6(4), С. 4203 - 4219
Опубликована: Ноя. 7, 2024
In Japan, the aging and decreasing number of agricultural workers is a significant problem. For wine grape harvesting, especially for large farming areas, there physical strain to farmers. order solve this problem, study focuses on developing an automated harvesting robot grapes. The needs high dust, water, mud resistance because grapevines are grown in hard conditions. Therefore, three-axis linear was developed using rack pinion mechanism study, which can be used outdoor conditions with low cost. Three brushless DC motors were utilized drive robot. controlled control area network (CAN) bus simplify hardware system. accuracy positioning evaluated at condition. experiment results show that approximately 5 mm, 9 mm x-axis (horizontal), y-axis (vertical), z-axis (depth), respectively. improve accuracy, we constructed error model conducted calibration improved around 2 all three axes after calibration. experimental enough
Язык: Английский
Процитировано
0Опубликована: Сен. 27, 2024
Язык: Английский
Процитировано
0Food Engineering Reviews, Год журнала: 2024, Номер unknown
Опубликована: Ноя. 16, 2024
Язык: Английский
Процитировано
0Engineering Applications of Artificial Intelligence, Год журнала: 2024, Номер 139, С. 109646 - 109646
Опубликована: Ноя. 19, 2024
Язык: Английский
Процитировано
0