Dynamic System Linearization via Deep Relative Displacement Prediction for Robust IMU-WiFi Indoor Trajectory Estimation
| dc.contributor.author | Chapha, Naphat | |
| dc.contributor.author | Ploysuwan, Tuchsanai | |
| dc.date.accessioned | 2026-08-06T10:48:40Z | |
| dc.date.available | 2026-08-06T10:48:40Z | |
| dc.date.issued | 2025-01-01 | |
| dc.description.abstract | Standalone WiFi fingerprinting and Inertial Measurement Unit (IMU) sensors are unreliable for indoor positioning due to signal instability and cumulative drift error, respectively. We present a novel sensor fusion framework that overcomes these challenges by enhancing WiFi fingerprint quality while simplifying the fusion process. Our approach filters and ranks WiFi signals to create a stable input for a Long Short-Term Memory (LSTM), while a Convolutional Neural Network (CNN) is uniquely trained to predict relative displacement from IMU data. This latter step linearizes the system dynamics, enabling the use of a simple Linear Kalman Filter and avoiding the complexity of traditional non-linear filters. Combining these innovations, the integrated framework achieves a mean position error of 4.30 m, a 32.3% improvement over the best standalone model. This work demonstrates that our approach to WiFi selection and system linearization provides a robust and highly accurate solution for real-time indoor positioning. | |
| dc.identifier.citation | 2025 20th International Joint Symposium on Artificial Intelligence and Natural Language Processing Isai Nlp 2025, 2025 | |
| dc.identifier.doi | 10.1109/iSAI-NLP66160.2025.11320549 | |
| dc.identifier.other | 2-s2.0-105032735616 | |
| dc.identifier.uri | https://dspace.kmitl.ac.th/handle/123456789/16304 | |
| dc.source | 2025 20th International Joint Symposium on Artificial Intelligence and Natural Language Processing Isai Nlp 2025 | |
| dc.subject | Deep Learning | |
| dc.subject | Indoor Localization | |
| dc.subject | Inertial Measurement Unit (IMUs) | |
| dc.subject | Kalman Filter | |
| dc.subject | Sensor Fusion | |
| dc.subject | WiFi Fingerprinting | |
| dc.title | Dynamic System Linearization via Deep Relative Displacement Prediction for Robust IMU-WiFi Indoor Trajectory Estimation | |
| dc.type | Conference Paper |