Otwarty dostęp

Research on the Utilization Pattern Mining and Impact Mechanism of Open Government Data Based on Deep Learning Algorithms

Ying Zhang

Ying Zhang

School of Public Affairs, Zhejiang UniversityHangzhou, China
Wyszukaj tego autora
Sciendo|Google Scholar
Zhang, Ying
 oraz 
Tianhao He

Tianhao He

Faculty of Industrial Design Engineering, Delft University of Technologythe Netherlands
Wyszukaj tego autora
Sciendo|Google Scholar
He, Tianhao
  
17 mar 2025
Research on the Utilization Pattern Mining and Impact Mechanism of Open Government Data Based on Deep Learning Algorithms's Cover Image
O artykule
Poprzedni artykuł
Następny artykuł
Zacytuj
Pobierz okładkę
Data publikacji: 17 mar 2025
Otrzymano: 04 lis 2024
Przyjęty: 13 lut 2025
DOI: https://doi.org/10.2478/amns-2025-0183
Słowa kluczowe
© 2025 Ying Zhang et al., published by Sciendo
This work is licensed under the Creative Commons Attribution 4.0 International License.

Figure 1.

Open government data ecosystem analysis framework
Open government data ecosystem analysis framework

Figure 2.

Details of the model of the accident risk prediction
Details of the model of the accident risk prediction

Figure 3.

Comparison of experimental results of different models
Comparison of experimental results of different models

Figure 4.

The experimental comparison results of high peak and flat peak(MRE)
The experimental comparison results of high peak and flat peak(MRE)

Figure 5.

The experimental comparison results of weekdays and holidays(MRE)
The experimental comparison results of weekdays and holidays(MRE)

Figure 6.

The experimental comparison results of sunny and rainy(MRE)
The experimental comparison results of sunny and rainy(MRE)

Figure 7.

Open government data utilization model
Open government data utilization model

Figure 8.

Explaining structural models for open government data use
Explaining structural models for open government data use

Consider the experimental results of various factors

Input dimension MAE MSE MRE
SAGCN(F) 0.081 0.041 0.784
SAGCN(F+A) 0.077 0.039 0.776
SAGCN(F+R) 0.078 0.040 0.768
SAGCN(F+V) 0.083 0.038 0.836
SAGCN(F+A+R) 0.075 0.035 0.756
SAGCN(F+A+V) 0.083 0.038 0.836
SAGCN(F+R+V) 0.085 0.044 0.851
SAGCN(F+A+R+V) 0.082 0.042 0.844

Estimate results of the research model

Variable class Variable Regression coefficient Standard deviation Exp(B)
Ability Perceptual behavior control 0.133*** 0.034 0.912
Motive Behavior attitude 0.322** 0.055 0.817
Opportunity Complete facility 0.208*** 0.049 1.172
Data quality 0.156*** 0.124 0.924
Individual characteristics Risk attitude 0.695*** 0.537 0.915
Constants 0.776** 0.489 3.226
Model(Sig.) 0.000 The logarithmic likelihood of the minus double 309.239
Hosmer-Lemeshow 0.531
Język:
Angielski
Częstotliwość wydawania:
1 razy w roku
Dziedziny czasopisma:
Nauki biologiczne, Nauki biologiczne, inne, Matematyka, Matematyka stosowana, Matematyka ogólna, Fizyka, Fizyka, inne
Kanał RSS czasopisma