- Reduced hyperparameter optimization trials
- Lowered max epochs for tuning and final training
- Decreased early stopping patience
- Enabled parallel data loading with num_workers
- Refined hyperparameter search space for models
- Simplified batch size logic for CUDA

- Introduced a new thickness data file `widthsH60_B34.txt` for hysteretic curves.
- Updated the path for thickness data in `hysteretic_curves.py` to include the base and width parameters.
- Modified the loop structure in `hysteretic_curves.py` to ensure thickness data aligns with case folders.
- Enhanced the prediction script `predict_hysteretic_curves.py` with cross-validation strategies and improved training logic.
- Implemented Leave-One-Out and K-Fold cross-validation based on the number of training cases.
- Adjusted model training to handle full training pool without validation and added detailed logging for trials.
- Improved memory management and error handling during training and validation processes.

- Implemented LSTM model with enhanced training features including mixed precision, early stopping, and validation via DataLoader.
- Introduced a new 1D Temporal Convolutional Network (TCN) model for predicting hysteretic curves.
- Added functionality for creating sliding windows from the dataset for both training and testing.
- Integrated scaling for features and targets using StandardScaler.
- Enhanced data handling with explicit cleanup and memory management for GPU.
- Updated main function to include model training and prediction for both LSTM and TCN.
- Saved predictions to CSV files for further analysis.

- Introduced `plot_data_hysteretic_curves.py` for visualizing envelope curves, energy degradation, and stiffness degradation from cycle-level data.
- Implemented `predict_hysteretic_curves.py` to create a sliding window dataset for training an LSTM model to predict hysteretic force-displacement curves.
- Enhanced the manuscript with updated references to force-displacement relationships and clarified the role of LSTM models in the optimization framework.
- Updated manuscript files to reflect changes in the document structure and content.

feat: Generate and store new machine learning and RBF models, cross-validation results, and optimization reports for width optimization, and remove outdated model and report files.