Device Orientation Independent Human Activity Recognition Model for Patient Monitoring Based on Triaxial Acceleration
Tracking a person’s activities is relevant in a variety of contexts, from health and group-specific assessments, such as elderly care, to fitness tracking and human–computer interaction. In a clinical context, sensor-based activity tracking could help monitor patients’ progress or deterioration duri...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/7/4175 |
| _version_ | 1797608376297848832 |
|---|---|
| author | Sara Caramaschi Gabriele B. Papini Enrico G. Caiani |
| author_facet | Sara Caramaschi Gabriele B. Papini Enrico G. Caiani |
| author_sort | Sara Caramaschi |
| collection | DOAJ |
| description | Tracking a person’s activities is relevant in a variety of contexts, from health and group-specific assessments, such as elderly care, to fitness tracking and human–computer interaction. In a clinical context, sensor-based activity tracking could help monitor patients’ progress or deterioration during their hospitalization time. However, during routine hospital care, devices could face displacements in their position and orientation caused by incorrect device application, patients’ physical peculiarities, or patients’ day-to-day free movement. These aspects can significantly reduce algorithms’ performances. In this work, we investigated how shifts in orientation could impact Human Activity Recognition (HAR) classification. To reach this purpose, we propose an HAR model based on a single three-axis accelerometer that can be located anywhere on the participant’s trunk, capable of recognizing activities from multiple movement patterns, and, thanks to data augmentation, can deal with device displacement. Developed models were trained and validated using acceleration measurements acquired in fifteen participants, and tested on twenty-four participants, of which twenty were from a different study protocol for external validation. The obtained results highlight the impact of changes in device orientation on a HAR algorithm and the potential of simple wearable sensor data augmentation for tackling this challenge. When applying small rotations (<20 degrees), the error of the baseline non-augmented model steeply increased. On the contrary, even when considering rotations ranging from 0 to 180 along the frontal axis, our model reached a f1-score of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.85</mn><mo>±</mo><mn>0.11</mn></mrow></semantics></math></inline-formula> against a baseline model f1-score equal to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.49</mn><mo>±</mo><mn>0.12</mn></mrow></semantics></math></inline-formula>. |
| first_indexed | 2024-03-11T05:42:37Z |
| format | Article |
| id | doaj.art-26507867ed6e42f99f301b49590b816c |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T05:42:37Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-26507867ed6e42f99f301b49590b816c2023-11-17T16:16:35ZengMDPI AGApplied Sciences2076-34172023-03-01137417510.3390/app13074175Device Orientation Independent Human Activity Recognition Model for Patient Monitoring Based on Triaxial AccelerationSara Caramaschi0Gabriele B. Papini1Enrico G. Caiani2Department of Electronics, Information and Bioengineering, Politecnico di Milano, 20133 Milan, ItalyDepartment of Patient Care & Monitoring, Philips Research, 5656 AE Eindhoven, The NetherlandsDepartment of Electronics, Information and Bioengineering, Politecnico di Milano, 20133 Milan, ItalyTracking a person’s activities is relevant in a variety of contexts, from health and group-specific assessments, such as elderly care, to fitness tracking and human–computer interaction. In a clinical context, sensor-based activity tracking could help monitor patients’ progress or deterioration during their hospitalization time. However, during routine hospital care, devices could face displacements in their position and orientation caused by incorrect device application, patients’ physical peculiarities, or patients’ day-to-day free movement. These aspects can significantly reduce algorithms’ performances. In this work, we investigated how shifts in orientation could impact Human Activity Recognition (HAR) classification. To reach this purpose, we propose an HAR model based on a single three-axis accelerometer that can be located anywhere on the participant’s trunk, capable of recognizing activities from multiple movement patterns, and, thanks to data augmentation, can deal with device displacement. Developed models were trained and validated using acceleration measurements acquired in fifteen participants, and tested on twenty-four participants, of which twenty were from a different study protocol for external validation. The obtained results highlight the impact of changes in device orientation on a HAR algorithm and the potential of simple wearable sensor data augmentation for tackling this challenge. When applying small rotations (<20 degrees), the error of the baseline non-augmented model steeply increased. On the contrary, even when considering rotations ranging from 0 to 180 along the frontal axis, our model reached a f1-score of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.85</mn><mo>±</mo><mn>0.11</mn></mrow></semantics></math></inline-formula> against a baseline model f1-score equal to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.49</mn><mo>±</mo><mn>0.12</mn></mrow></semantics></math></inline-formula>.https://www.mdpi.com/2076-3417/13/7/4175device displacementaccelerationwearable devicesdata augmentationpatient monitoringhuman activity recognition |
| spellingShingle | Sara Caramaschi Gabriele B. Papini Enrico G. Caiani Device Orientation Independent Human Activity Recognition Model for Patient Monitoring Based on Triaxial Acceleration Applied Sciences device displacement acceleration wearable devices data augmentation patient monitoring human activity recognition |
| title | Device Orientation Independent Human Activity Recognition Model for Patient Monitoring Based on Triaxial Acceleration |
| title_full | Device Orientation Independent Human Activity Recognition Model for Patient Monitoring Based on Triaxial Acceleration |
| title_fullStr | Device Orientation Independent Human Activity Recognition Model for Patient Monitoring Based on Triaxial Acceleration |
| title_full_unstemmed | Device Orientation Independent Human Activity Recognition Model for Patient Monitoring Based on Triaxial Acceleration |
| title_short | Device Orientation Independent Human Activity Recognition Model for Patient Monitoring Based on Triaxial Acceleration |
| title_sort | device orientation independent human activity recognition model for patient monitoring based on triaxial acceleration |
| topic | device displacement acceleration wearable devices data augmentation patient monitoring human activity recognition |
| url | https://www.mdpi.com/2076-3417/13/7/4175 |
| work_keys_str_mv | AT saracaramaschi deviceorientationindependenthumanactivityrecognitionmodelforpatientmonitoringbasedontriaxialacceleration AT gabrielebpapini deviceorientationindependenthumanactivityrecognitionmodelforpatientmonitoringbasedontriaxialacceleration AT enricogcaiani deviceorientationindependenthumanactivityrecognitionmodelforpatientmonitoringbasedontriaxialacceleration |