Research on ensemble learning algorithm for fall detection

This research aims to address the issue of fall detection in the elderly using a wearable device-based fall detection system. Data is collected through acceleration sensors and barometric pressure sensors. After applying certain algorithms to the dataset, it was found that a single machine learning algorithm had poor generalization ability for fall detection. To improve classification accuracy, attempts were made to use ensemble learning algorithms for training and validation of the fall detection dataset. By employing Bagging and GBDT ensemble learning algorithms, the generalization ability of the model was successfully enhanced. On the validation set after 0.2 cross-validation, our model achieved an average accuracy of 99.28%, significantly improving the model's high performance and strong generalization ability.