Fig 1.
Structural framework of a timber building illustrating key components influencing seismic performance.
[Timber-Frames: Anatomy and Joinery – Custom Home Building and Remodeling].
Table 1.
Overview of innovative research on seismic behavior of timber buildings.
Table 2.
Analysis of identified research gaps and research contributions.
Fig 2.
The completed flowchart for enhancing seismic performance parameters of timber structures.
Table 3.
Sample data from the timber seismic performance dataset.
Fig 3.
The schematic representation of GB decision tree.
Fig 4.
The general architecture of the RF classifier.
Fig 5.
The optimization process of SCO (a) the exploration phase, where cheetahs search for potential solutions, (b) transition phase moving toward promising regions, (c) the attacking phase with rapid convergence to the best solutions, and (d) depicts the final convergence phase, where the algorithm stabilizes around the optimal result.
Table 4.
Hyperparameter for GBRF and SCO optimization framework.
Table 5.
Experimental setup for GBRF-SCO model implementation.
Table 6.
MLR analysis of seismic parameters.
Fig 6.
Roof displacement variation for timber structural system types.
Fig 7.
Stacked Area Plot of Seismic Parameters.
Fig 8.
Findings of (a) Relationship between building height and roof displacement, (b) Variation of roof displacement with peak ground acceleration, (c) Trend of roof displacement across samples showing overall fluctuations patterns.
Fig 9.
Graphical findings of (a) roof displacement with number of storys for different roof types, and (b) Parallel coordinate analysis of structural features influencing roof displacement across rooftypes.
Fig 10.
Pairwise correlation analysis of key structural and seismic parameters.
Fig 11.
Correlation analysis of seismic and material parameters in timber structures.
Fig 12.
Comparison of roof displacement and inter-story drift in timber structures.
Fig 13.
Confusion matrix representation of roof displacementclassificarion results.
Fig 14.
Performance analysis of GBRF-SCO model across training epochs.
Table 7.
Evaluation of predictive modelling approaches with error metrics.
Table 8.
Comparison of different classification model performances.
Fig 15.
Evaluation of classification model accuracy across multiple performance indicators.
Table 9.
Ablation research results for model performance comparison.