Automatic Detection of Magnetic Disturbances in Magnetic Inertial Measurement Unit Sensors Based on Recurrent Neural Networks
This paper proposes a new methodology for the automatic detection of magnetic disturbances from magnetic inertial measurement unit (MIMU) sensors based on deep learning. The proposed approach considers magnetometer data as input to a long short-term memory (LSTM) neural network and obtains a labeled...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/24/9683 |
| _version_ | 1827573535533432832 |
|---|---|
| author | Elkyn Alexander Belalcazar-Bolaños Diego Torricelli José L. Pons |
| author_facet | Elkyn Alexander Belalcazar-Bolaños Diego Torricelli José L. Pons |
| author_sort | Elkyn Alexander Belalcazar-Bolaños |
| collection | DOAJ |
| description | This paper proposes a new methodology for the automatic detection of magnetic disturbances from magnetic inertial measurement unit (MIMU) sensors based on deep learning. The proposed approach considers magnetometer data as input to a long short-term memory (LSTM) neural network and obtains a labeled time series output with the posterior probabilities of magnetic disturbance. We trained our algorithm on a data set that reproduces a wide range of magnetic perturbations and MIMU motions in a repeatable and reproducible way. The model was trained and tested using 15 folds, which considered independence in sensor, disturbance direction, and signal type. On average, the network can adequately detect the disturbances in <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>98</mn><mo>%</mo></mrow></semantics></math></inline-formula> of the cases, which represents a significant improvement over current threshold-based detection algorithms. |
| first_indexed | 2024-03-08T20:22:40Z |
| format | Article |
| id | doaj.art-0291203f61b54c7b82bc033c05ffb638 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-08T20:22:40Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-0291203f61b54c7b82bc033c05ffb6382023-12-22T14:40:15ZengMDPI AGSensors1424-82202023-12-012324968310.3390/s23249683Automatic Detection of Magnetic Disturbances in Magnetic Inertial Measurement Unit Sensors Based on Recurrent Neural NetworksElkyn Alexander Belalcazar-Bolaños0Diego Torricelli1José L. Pons2Neural Rehabilitation Group, Cajal Institute, Spanish National Research Council (CSIC), 28002 Madrid, SpainNeural Rehabilitation Group, Cajal Institute, Spanish National Research Council (CSIC), 28002 Madrid, SpainLegs and Walking AbilityLab, Shirley Ryan AbilityLab, Chicago, IL 60611, USAThis paper proposes a new methodology for the automatic detection of magnetic disturbances from magnetic inertial measurement unit (MIMU) sensors based on deep learning. The proposed approach considers magnetometer data as input to a long short-term memory (LSTM) neural network and obtains a labeled time series output with the posterior probabilities of magnetic disturbance. We trained our algorithm on a data set that reproduces a wide range of magnetic perturbations and MIMU motions in a repeatable and reproducible way. The model was trained and tested using 15 folds, which considered independence in sensor, disturbance direction, and signal type. On average, the network can adequately detect the disturbances in <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>98</mn><mo>%</mo></mrow></semantics></math></inline-formula> of the cases, which represents a significant improvement over current threshold-based detection algorithms.https://www.mdpi.com/1424-8220/23/24/9683inertial measurementmagnetic disturbancemagnetometerdeep neural |
| spellingShingle | Elkyn Alexander Belalcazar-Bolaños Diego Torricelli José L. Pons Automatic Detection of Magnetic Disturbances in Magnetic Inertial Measurement Unit Sensors Based on Recurrent Neural Networks Sensors inertial measurement magnetic disturbance magnetometer deep neural |
| title | Automatic Detection of Magnetic Disturbances in Magnetic Inertial Measurement Unit Sensors Based on Recurrent Neural Networks |
| title_full | Automatic Detection of Magnetic Disturbances in Magnetic Inertial Measurement Unit Sensors Based on Recurrent Neural Networks |
| title_fullStr | Automatic Detection of Magnetic Disturbances in Magnetic Inertial Measurement Unit Sensors Based on Recurrent Neural Networks |
| title_full_unstemmed | Automatic Detection of Magnetic Disturbances in Magnetic Inertial Measurement Unit Sensors Based on Recurrent Neural Networks |
| title_short | Automatic Detection of Magnetic Disturbances in Magnetic Inertial Measurement Unit Sensors Based on Recurrent Neural Networks |
| title_sort | automatic detection of magnetic disturbances in magnetic inertial measurement unit sensors based on recurrent neural networks |
| topic | inertial measurement magnetic disturbance magnetometer deep neural |
| url | https://www.mdpi.com/1424-8220/23/24/9683 |
| work_keys_str_mv | AT elkynalexanderbelalcazarbolanos automaticdetectionofmagneticdisturbancesinmagneticinertialmeasurementunitsensorsbasedonrecurrentneuralnetworks AT diegotorricelli automaticdetectionofmagneticdisturbancesinmagneticinertialmeasurementunitsensorsbasedonrecurrentneuralnetworks AT joselpons automaticdetectionofmagneticdisturbancesinmagneticinertialmeasurementunitsensorsbasedonrecurrentneuralnetworks |