Deep Attention-based Sequential Ensemble Learning for BLE-Based Indoor Localization in Care Facilities
It addresses indoor localization for care facilities to optimize staff allocation and care delivery, representing a domain-specific incremental improvement.
This paper tackled the problem of indoor localization in care facilities by introducing Deep Attention-based Sequential Ensemble Learning (DASEL), which achieved a macro F1 score of 0.4438, a 53.1% improvement over the best traditional baseline.
Indoor localization systems in care facilities enable optimization of staff allocation, workload management, and quality of care delivery. Traditional machine learning approaches to Bluetooth Low Energy (BLE)-based localization treat each temporal measurement as an independent observation, fundamentally limiting their performance. To address this limitation, this paper introduces Deep Attention-based Sequential Ensemble Learning (DASEL), a novel framework that reconceptualizes indoor localization as a sequential learning problem. The framework integrates frequency-based feature engineering, bidirectional GRU networks with attention mechanisms, multi-directional sliding windows, and confidence-weighted temporal smoothing to capture human movement trajectories. Evaluated on real-world data from a care facility using 4-fold temporal cross-validation, DASEL achieves a macro F1 score of 0.4438, representing a 53.1% improvement over the best traditional baseline (0.2898).