Prediction of visibility in the Arctic based on dynamic Bayesian network analysis

Zhao, Shuang; Shan, Yulong; Gültepe, Ismail

doi:10.1007/s13131-021-1826-z

Cited by 3 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhao et al Used a dynamic Bayesian network to predict visibility in the Arctic based on the physical basic statistical model. Experiments have proved that using a dynamic Bayesian network to predict visibility is adequate for predicting climate change in the Arctic [10]. Zhou et al Extended Bayesian network feature Finder (Banff), which provides a graphical description package of posterior reasoning, model comparison, and model fitting for understanding biological mechanisms and disease pathology [11].…”

Section: Journals Reviewedmentioning

confidence: 99%

“…After introducing the learning behavior parameters and forgetting behavior parameters of students, the prediction accuracy of the Bayesian knowledge tracking model can be improved in theory. For the evaluation of the prediction effect of the model, the root means square error (RMSE) is used to express the numerical dispersion of the model, and its calculation formula is shown in equation (10).…”

Section: P K P K P F P K P T P Fmentioning

confidence: 99%

“…In equation (10), R represents the root mean square error of the model, i represents the prediction times, n represents the maximum number of prediction samples, P i represents the model prediction value, p i represents the actual probability value, and P i -p i represents the deviation between the model prediction probability and the actual probability value [23]. In the Bayesian knowledge tracking model, the root means square error value represents the ratio of the square of the error between the prediction result of the model and the students' learning and mastering situation to the prediction times [24].…”

Section: P K P K P F P K P T P Fmentioning

confidence: 99%

See 2 more Smart Citations

A MOOC-Based Hybrid Teaching Model of College English

Feng

Abualigah²

2023

Int. J. Emerg. Technol. Learn.

View full text Add to dashboard Cite

In the era of intelligence, Internet + technology is widely used in various fields, and English Teaching in the education industry of colleges and universities gradually tends to be an online and offline mixed teaching mode. However, under the MOOC model, the feedback of College Students’ English learning and the recognition of their knowledge level has become new difficulties. Aiming at the feedback of students’ learning situation under the mixed mode of College English teaching, this paper uses the optimized Bayesian knowledge tracking model (BKTM) to predict students’ English learning situation and introduces students’ learning behavior and forgetting behavior to optimize parameters. Finally, a performance verification experiment is carried out by analyzing the students’ answer performance in College English mixed teaching. The results show that the prediction errors of the four knowledge points of 60 students in the two classes are all about 7%, and the maximum error is 11%. Experiments show that the model has high accuracy and stable performance in predicting the probability of mastering knowledge points.

show abstract

Section: Journals Reviewedmentioning

confidence: 99%

Section: P K P K P F P K P T P Fmentioning

confidence: 99%

Section: P K P K P F P K P T P Fmentioning

confidence: 99%

See 1 more Smart Citation

A MOOC-Based Hybrid Teaching Model of College English

Feng

Abualigah²

2023

Int. J. Emerg. Technol. Learn.

View full text Add to dashboard Cite

show abstract

Research on the Design of Recommendation System for Learning Methods Based on Bayesian Networks

Feng

2023

2023 7th Asian Conference on Artificial Intelligence Technology (ACAIT)

View full text Add to dashboard Cite

A Modified RNN-Based Deep Learning Method for Prediction of Atmospheric Visibility

Zang

Bao

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Accurate atmospheric visibility prediction is of great significance to public transport safety. However, since it is affected by multiple factors, there still remains difficulties in predicting its heterogenous spatial distribution and rapid temporal variation. In this paper, a recursive neural network (RNN) prediction model modified with the frame-hopping transmission gate (FHTG), feature fusion module (FFM) and reverse scheduled sampling (RSS), named SwiftRNN, is developed. The new FHTG is used to accelerate training, the FFM is used for extraction and fusion of global and local features, and the RSS is employed to learn spatial details and improve prediction accuracy. Based on the ground-based monitoring data of atmospheric visibility from the China Meteorological Information Center during 1st January 2018 to 31st December 2020, the SwiftRNN model and two traditional ConvLSTM and PredRNN models are performed to predict hourly atmospheric visibility in central and eastern China at a lead of 12 h. The results show that the SwiftRNN model has better performance in the skill scores of visibility prediction than those of the ConvLSTM and PredRNN model. The averaged structural similarity (SSIM) of predictions at a lead up to 12 h is 0.444, 0.425 and 0.399 for the SwiftRNN, PredRNN and ConvLSTM model, respectively, and the averaged image perception similarity (LPIPS) is 0.289, 0.315 and 0.328, respectively. The averaged critical success index (CSI) of predictions over 1000 m fog area is 0.221, 0.205 and 0.194, respectively. Moreover, the training speed of the SwiftRNN model is 14.3% faster than the PredRNN model. It is also found that the prediction effect of the SwiftRNN model over 1000 m medium grade fog area is significantly improved along with lead times compared with the ConvLSTM and PredRNN model. All above results demonstrate the SwiftRNN model is a powerful tool in predicting atmospheric visibility.

show abstract

Prediction of visibility in the Arctic based on dynamic Bayesian network analysis

Cited by 3 publications

References 25 publications

A MOOC-Based Hybrid Teaching Model of College English

A MOOC-Based Hybrid Teaching Model of College English

Research on the Design of Recommendation System for Learning Methods Based on Bayesian Networks

A Modified RNN-Based Deep Learning Method for Prediction of Atmospheric Visibility

Contact Info

Product

Resources

About