August 25, 2025Scientific ReportsOpen Access

LSTM-based bi-directional urban safety network using a conditional vector of frequency domain decomposition data

View Full Paper

Ask AI

Bookmark

The proposed method improves prediction accuracy of structural responses by utilizing LSTM models with conditional vectors, significantly enhancing safety measures.
Results show RMSE reductions of up to 27.13% compared to baseline models, demonstrating the method's effectiveness in predicting building dynamics under seismic loads.
The approach analyzes both time-domain and frequency-domain data, improving robustness in dynamic structural response predictions during earthquakes.
Implementing this scalable framework could significantly enhance the resilience of urban infrastructures against seismic events, particularly when sensor data is compromised.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

The bi-directional urban safety network enhances prediction accuracy of structural responses during seismic events, suggesting improved resilience in sensor-deficient environments.

Cite This Study

Lee et al. (2025) studied this question.

synapsesocial.com/papers/68af7b187567bf4f94ff2952 https://doi.org/10.1038/s41598-025-16931-4

View Full Paper

Ask AI

Bookmark

Implication

The bi-directional urban safety network enhances prediction accuracy of structural responses during seismic events, suggesting improved resilience in sensor-deficient environments.

LSTM-based bi-directional urban safety network using a conditional vector of frequency domain decomposition data

Key Points

Discussion

Implication

Cite This Study

LSTM-based bi-directional urban safety network using a conditional vector of frequency domain decomposition data

Key Points

Discussion

Implication

Cite This Study

Also Consider

Also Consider