Zobrazeno 1 - 10
of 84
pro vyhledávání: '"cross-entropy loss function"'
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-20 (2024)
Abstract Pavement cracks affect the structural stability and safety of roads, making accurate identification of crack for assessing the extent of damage and evaluating road health. However, traditional convolutional neural networks often struggle wit
Externí odkaz:
https://doaj.org/article/e85e674ba1af41ce8a53371c242ae9c3
Autor:
Li, Diyou a, Zhang, Lijuan a, ⁎, Zhou, Juncheng a, Huang, Jie a, Xiong, Neal b, Zhang, Lei a, Wan, Jian a
Publikováno v:
In Expert Systems With Applications 15 March 2025 265
Publikováno v:
Entropy, Vol 26, Iss 8, p 628 (2024)
Support vector data description (SVDD) is widely regarded as an effective technique for addressing anomaly detection problems. However, its performance can significantly deteriorate when the training data are affected by outliers or mislabeled observ
Externí odkaz:
https://doaj.org/article/a5724fafae2a460dabebf0c43e075fcb
Publikováno v:
Applied Mathematics and Nonlinear Sciences, Vol 9, Iss 1 (2024)
To predict the workability of community nursing staff and provide corresponding training strategies based on the results. In this study, a nursing staff workability prediction model based on R-GCN-GRU was constructed. In the process of community nurs
Externí odkaz:
https://doaj.org/article/149f22e7b578435c8285758ee7aa1f37
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Xiao-bin Xu, Ming-hui Zhao, Jian Yang, Yi-yang Xiong, Feng-lin Pang, Zhi-ying Tan, Min-zhou Luo
Publikováno v:
Defence Technology, Vol 18, Iss 9, Pp 1727-1739 (2022)
A 3D laser scanning strategy based on cascaded deep neural network is proposed for the scanning system converted from 2D Lidar with a pitching motion device. The strategy is aimed at moving target detection and monitoring. Combining the device charac
Externí odkaz:
https://doaj.org/article/4594b8c653c14691ab07348d937592bf
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
George Tzougas, Konstantin Kutzkov
Publikováno v:
Algorithms, Vol 16, Iss 2, p 99 (2023)
We developed a methodology for the neural network boosting of logistic regression aimed at learning an additional model structure from the data. In particular, we constructed two classes of neural network-based models: shallow–dense neural networks
Externí odkaz:
https://doaj.org/article/71c8bd1930db49d4a1aec23533ccfa15
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
IEEE Access, Vol 8, Pp 54564-54573 (2020)
Concrete pavement defects are an important indicator reflecting the safety status of pavement. However, it is difficult to accurately detect the concrete pavement cracks due to the complex concrete pavement environment, such as uneven illumination, d
Externí odkaz:
https://doaj.org/article/1832a2d3808747b4b959879d95a78728