XGBoost (Extreme Gradient Boosting) is an ensemble machine learning algorithm that builds a sequence of decision trees in a gradient-boosted framework, where each successive tree corrects the residual errors of the previous ones, producing a highly accurate and computationally efficient predictive model. In WiFi/CSI sensing and related sensing domains, it is valued for its strong performance on structured, tabular feature data — such as statistical features extracted from CSI signals or Bluetooth-based vehicle counts — often outperforming simpler classifiers and regressors without requiring deep learning infrastructure. It is commonly applied in both classification tasks (e.g., occupancy level estimation) and regression tasks (e.g., correcting sensor count biases toward ground truth), and may be used alongside hyperparameter tuning strategies such as cross-validation to optimize tree depth, learning rate, and the number of estimators.
Source Papers
- A Framework to Estimate Classroom Occupancy using WiFi Channel State Information ↗ — A Framework to Estimate Classroom Occupancy using WiFi Chann
- Bluetooth-Based Vehicle Counting: Bridging the Gap to Ground-Truth With Machine Learning ↗ — Bluetooth-Based Vehicle Counting: Bridging the Gap to Ground
- Occupancy Prediction in IoT-Enabled Smart Buildings: Technologies, Methods, and Future Directions ↗ — Occupancy Prediction in IoT-Enabled Smart Buildings: Technol
- Wi-CaL: WiFi Sensing and Machine Learning Based Device-Free Crowd Counting and Localization ↗ — Wi-CaL: WiFi Sensing and Machine Learning Based Device-Free