Real-time activity and fall detection using transformer-based deep learning models for elderly care applications

This study aims to develop a transformer-based deep learning model for real-time activity recognition and fall detection, addressing the limitations of existing methods in terms of accuracy and real-time applicability.

The proposed system uses sliding window segmentation technique to process wearable sensor data, including accelerometer, gyroscope and orientation signals. The transformer encoder models temporal dependencies through a self-attention mechanism, enabling the extraction of global and local temporal patterns. The performance of the model is evaluated on an updated version of the MobiAct data set, which includes over 14 million sensor records collected from 66 participants and 16 activities, including four types of falls and multiple scenario-based activities of daily living.

The transformer model achieved an accuracy of over 98% and demonstrated excellent precision and recall for difficult fall categories such as forward-lying and sideward-lying. Comparative analysis shows that transformers outperform convolutional neural networks long short-term memory (CNN-LSTM) and temporal convolutional networks in terms of classification metrics, confusion matrix results and training stability.

The results highlight the effectiveness of the transformer model in capturing complex temporal dependencies, addressing key challenges such as misclassification and false positives. Compared with traditional models, its parallel processing capabilities improve real-time deployment efficiency.

This research establishes transformer-based models as powerful solutions for activity recognition and fall detection, providing reliable applications for elderly care and fall prevention. Future work will focus on optimising edge devices and validating on real-world data sets.