Ensemble learning is a machine learning methodology that combines the predictions of multiple models or classifiers to produce a more accurate and robust final output than any single model could achieve alone. In the context of WiFi/CSI-based indoor positioning and human sensing, it matters because it can compensate for the individual weaknesses of heterogeneous models or data sources, improving generalization across varied environments and reducing sensitivity to noise inherent in CSI measurements. Key variants include boosting, bagging, and stacking, as well as fusion-based approaches that aggregate outputs from diverse deep learning architectures such as CNNs, RNNs, and ResNets, which are directly relevant to the multi-model benchmarking frameworks explored in systems like SenseFi and the unified fusion paradigms described in FBIP surveys.
Source Papers
- A Survey on Fusion-Based Indoor Positioning ↗ — A Survey on Fusion-Based Indoor Positioning
- CrossSense: Towards Cross-Site and Large-Scale WiFi Sensing ↗ — CrossSense: Towards Cross-Site and Large-Scale WiFi Sensing
- SenseFi: A library and benchmark on deep-learning-empowered WiFi human sensing ↗ — SenseFi: A library and benchmark on deep-learning-empowered