Rongbin Yao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Rongbin Yao has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Changbiao Gu C Gu
School of Information and Communication, Guilin University of Electronic Technology, Guilin, Guangxi, China
1 shared publication Dajian Liu
1 shared publicationHaiying Gao
1 shared publication- Luye Liang
School of Electronic Engineering and Automation, Guilin University of Electronic Technology, Guilin, Guangxi, China
1 shared publication - Qian Chen
School of Architecture and Transportation Engineering, Guilin University of Electronic Technology, Guilin, China
1 shared publication - Shengyuan Zhou S Zhou
School of Information and Communication, Guilin University of Electronic Technology, Guilin, Guangxi, China
1 shared publication
Latest Publications
- Open Access
- 27 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-7
A Landslide Displacement Prediction Method Based on Convolutional Neural Networks_Bidirectional Long Short-Term Memory and Extreme Gradient Boosting
To address the limitations of traditional single deep learning network models in landslide displacement prediction, this paper proposes a combined prediction model based on Convolutional Neural Networks (CNN)_Bidirectional Long Short-Term Memory (BiLSTM)-Extreme Gradient Boosting (XGB). In this paper, the Sparrow Search Algorithm (SSA)- Variational Mode Decomposition (VMD) method is used to decompose the landslide displacement series into periodic, random, and trend components. Appropriate influencing factors are selected as input variables based on Grey Relation Analysis (GRA) Using ensemble learning method, the CNN_BiLSTM-XGB combination model is constructed to predict the periodic and random components. The trend component is fitted by double exponential smoothing method. Finally, the cumulative landslide predicted displacement is obtained by time series theory. The model is evaluated by Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Coefficient of Determination (R2), and is validated by the Baishuihe landslide, the performance is compared with CNN-Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Support Vector Machine (SVM) models. The experimental prediction results demonstrate that the CNN_BiLSTM-XGB combination model has higher prediction accuracy. This paper provides new insights and exploration for landslide displacement prediction.
- 27 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessA Landslide Displacement Prediction Method Based on Convolutional Neural Networks_Bidirectional Long Short-Term Memory and Extreme Gradient Boosting
To address the limitations of traditional single deep learning network models in landslide displacement prediction, this paper proposes a combined prediction model based on Convolutional Neural Networks (CNN)_Bidirectional Long Short-Term Memory (BiLSTM)-Extreme Gradient Boosting (XGB). In this paper, the Sparrow Search Algorithm (SSA)- Variational Mode Decomposition (VMD) method is used to decompose the landslide displacement series into periodic, random, and trend components. Appropriate influencing factors are selected as input variables based on Grey Relation Analysis (GRA) Using ensemble learning method, the CNN_BiLSTM-XGB combination model is constructed to predict the periodic and random components. The trend component is fitted by double exponential smoothing method. Finally, the cumulative landslide predicted displacement is obtained by time series theory. The model is evaluated by Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Coefficient of Determination (R2), and is validated by the Baishuihe landslide, the performance is compared with CNN-Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Support Vector Machine (SVM) models. The experimental prediction results demonstrate that the CNN_BiLSTM-XGB combination model has higher prediction accuracy. This paper provides new insights and exploration for landslide displacement prediction.
- 24 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Plasma Science
- Vol. 52 (5) , 1721-1727
Improvement of the Spatial Resolution Performance of Miniaturized Streak Tube Using Dual-Focusing
In the context of imaging laser radar systems (ILRS), the miniaturized streak tube (MST) serves as a crucial ultrafast diagnostic equipment, enabling the acquisition of high-quality 3-D images. The evaluation of information acquisition largely hinges on the spatial resolution (SR) performance of the MST, making it a significant parameter of interest. To enhance the system’s performance, the imaging system was designed using the dual-electrode electrostatic focusing (DEEF) technique. In this study, the relationship between the focusing electric field and imaging quality was analyzed, while the static and dynamic pattern was constructed by the CST software. To quantify the SR, the Rayleigh criterion (RC) was employed. Furthermore, the feasibility of a larger detection area and higher SR were investigated. The experimental findings revealed that the dual-focusing MST 120-mm-long has better performance, its detection area is $\Phi $ 30 mm, the deflection sensitivity is 15.05 mm/kV, and the static SR is approximately 41.84 lp/mm. Besides, the model of the voltage discrete port and the matching resistance were established, and the dynamic pattern was implemented by introducing the time-varying scanning ramp pulses. Remarkably, when the gradient of the slope pulse was 1.65 kV/ns, the dynamic SR was approximately 23.70 lp/mm, surpassing the performance of single-focusing techniques. The research conclusions not only verify the feasibility of the dual-focusing MST but also provide theoretical support to the design of the MST with high spatial performance. Furthermore, it also provides a reference method for studying the dynamic characteristics of MST by the CST.
- 24 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Plasma Science
- Vol. 52 (5) , 1721-1727
Improvement of the Spatial Resolution Performance of Miniaturized Streak Tube Using Dual-Focusing
In the context of imaging laser radar systems (ILRS), the miniaturized streak tube (MST) serves as a crucial ultrafast diagnostic equipment, enabling the acquisition of high-quality 3-D images. The evaluation of information acquisition largely hinges on the spatial resolution (SR) performance of the MST, making it a significant parameter of interest. To enhance the system’s performance, the imaging system was designed using the dual-electrode electrostatic focusing (DEEF) technique. In this study, the relationship between the focusing electric field and imaging quality was analyzed, while the static and dynamic pattern was constructed by the CST software. To quantify the SR, the Rayleigh criterion (RC) was employed. Furthermore, the feasibility of a larger detection area and higher SR were investigated. The experimental findings revealed that the dual-focusing MST 120-mm-long has better performance, its detection area is $\Phi $ 30 mm, the deflection sensitivity is 15.05 mm/kV, and the static SR is approximately 41.84 lp/mm. Besides, the model of the voltage discrete port and the matching resistance were established, and the dynamic pattern was implemented by introducing the time-varying scanning ramp pulses. Remarkably, when the gradient of the slope pulse was 1.65 kV/ns, the dynamic SR was approximately 23.70 lp/mm, surpassing the performance of single-focusing techniques. The research conclusions not only verify the feasibility of the dual-focusing MST but also provide theoretical support to the design of the MST with high spatial performance. Furthermore, it also provides a reference method for studying the dynamic characteristics of MST by the CST.