-
1321
Architecture of Swin Transformer Block.
Published 2024“…<div><p>Automatic pavement disease detection aims to address the inefficiency in practical detection. …”
-
1322
Disease distribution map of the GZDL-BD.
Published 2024“…<div><p>Automatic pavement disease detection aims to address the inefficiency in practical detection. …”
-
1323
Token merging module.
Published 2024“…<div><p>Automatic pavement disease detection aims to address the inefficiency in practical detection. …”
-
1324
Comparative results of the ablation experiments.
Published 2024“…<div><p>Automatic pavement disease detection aims to address the inefficiency in practical detection. …”
-
1325
-
1326
-
1327
-
1328
-
1329
-
1330
-
1331
-
1332
-
1333
-
1334
Relevant parameters of the benchmark models.
Published 2025“…Engineering verification calculations indicated that the BP neural network model can predict concrete performance under actual working conditions with a small error rate. Compared with traditional models, the neural network model has comprehensive advantages in terms of fitting accuracy, reduced overfitting, and enhanced stability.…”
-
1335
Peak strain and stress values of the specimens.
Published 2025“…Engineering verification calculations indicated that the BP neural network model can predict concrete performance under actual working conditions with a small error rate. Compared with traditional models, the neural network model has comprehensive advantages in terms of fitting accuracy, reduced overfitting, and enhanced stability.…”
-
1336
Aggregate characteristic curves.
Published 2025“…Engineering verification calculations indicated that the BP neural network model can predict concrete performance under actual working conditions with a small error rate. Compared with traditional models, the neural network model has comprehensive advantages in terms of fitting accuracy, reduced overfitting, and enhanced stability.…”
-
1337
Characteristic chart of algorithm efficiency.
Published 2025“…Engineering verification calculations indicated that the BP neural network model can predict concrete performance under actual working conditions with a small error rate. Compared with traditional models, the neural network model has comprehensive advantages in terms of fitting accuracy, reduced overfitting, and enhanced stability.…”
-
1338
Improved BP network algorithm flow.
Published 2025“…Engineering verification calculations indicated that the BP neural network model can predict concrete performance under actual working conditions with a small error rate. Compared with traditional models, the neural network model has comprehensive advantages in terms of fitting accuracy, reduced overfitting, and enhanced stability.…”
-
1339
TDS530 Static strain gauge.
Published 2025“…Engineering verification calculations indicated that the BP neural network model can predict concrete performance under actual working conditions with a small error rate. Compared with traditional models, the neural network model has comprehensive advantages in terms of fitting accuracy, reduced overfitting, and enhanced stability.…”
-
1340
Antibodies used in this study.
Published 2025“…In one case (<i><i>Ncaph2</i></i>), a C-terminal auxin-inducible degron fusion strongly increased protein stability in some tissues but decreased it in others. Destabilisation resulted from tissue-specific ‘leakage’ of the auxin-inducible degron, which depended on TIR1 expression, and occurred selectively in the small intestine where basal concentrations of auxin/ indole-3-acetic acid can reach levels that are sufficient to trigger protein degradation in cultured cells. …”