Reducing the Impact of Sensor Orientation Variability in Human Activity Recognition Using a Consistent Reference System
Sensor- orientation is a critical aspect in a Human Activity Recognition (HAR) system based on tri-axial signals (such as accelerations); different sensors orientations introduce important errors in the activity recognition process. This paper proposes a new preprocessing module to reduce the negati...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/13/5845 |
| _version_ | 1797590870575284224 |
|---|---|
| author | Manuel Gil-Martín Javier López-Iniesta Fernando Fernández-Martínez Rubén San-Segundo |
| author_facet | Manuel Gil-Martín Javier López-Iniesta Fernando Fernández-Martínez Rubén San-Segundo |
| author_sort | Manuel Gil-Martín |
| collection | DOAJ |
| description | Sensor- orientation is a critical aspect in a Human Activity Recognition (HAR) system based on tri-axial signals (such as accelerations); different sensors orientations introduce important errors in the activity recognition process. This paper proposes a new preprocessing module to reduce the negative impact of sensor-orientation variability in HAR. Firstly, this module estimates a consistent reference system; then, the tri-axial signals recorded from sensors with different orientations are transformed into this consistent reference system. This new preprocessing has been evaluated to mitigate the effect of different sensor orientations on the classification accuracy in several state-of-the-art HAR systems. The experiments were carried out using a subject-wise cross-validation methodology over six different datasets, including movements and postures. This new preprocessing module provided robust HAR performance even when sudden sensor orientation changes were included during data collection in the six different datasets. As an example, for the WISDM dataset, sensors with different orientations provoked a significant reduction in the classification accuracy of the state-of-the-art system (from 91.57 ± 0.23% to 89.19 ± 0.26%). This important reduction was recovered with the proposed algorithm, increasing the accuracy to 91.46 ± 0.30%, i.e., the same result obtained when all sensors had the same orientation. |
| first_indexed | 2024-03-11T01:29:36Z |
| format | Article |
| id | doaj.art-ac54ed24ea9d427fa1b431716672efee |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T01:29:36Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-ac54ed24ea9d427fa1b431716672efee2023-11-18T17:27:37ZengMDPI AGSensors1424-82202023-06-012313584510.3390/s23135845Reducing the Impact of Sensor Orientation Variability in Human Activity Recognition Using a Consistent Reference SystemManuel Gil-Martín0Javier López-Iniesta1Fernando Fernández-Martínez2Rubén San-Segundo3Speech Technology and Machine Learning, Information Processing and Telecommunications Center, E.T.S.I. de Telecomunicación, Universidad Politécnica de Madrid, 28040 Madrid, SpainSpeech Technology and Machine Learning, Information Processing and Telecommunications Center, E.T.S.I. de Telecomunicación, Universidad Politécnica de Madrid, 28040 Madrid, SpainSpeech Technology and Machine Learning, Information Processing and Telecommunications Center, E.T.S.I. de Telecomunicación, Universidad Politécnica de Madrid, 28040 Madrid, SpainSpeech Technology and Machine Learning, Information Processing and Telecommunications Center, E.T.S.I. de Telecomunicación, Universidad Politécnica de Madrid, 28040 Madrid, SpainSensor- orientation is a critical aspect in a Human Activity Recognition (HAR) system based on tri-axial signals (such as accelerations); different sensors orientations introduce important errors in the activity recognition process. This paper proposes a new preprocessing module to reduce the negative impact of sensor-orientation variability in HAR. Firstly, this module estimates a consistent reference system; then, the tri-axial signals recorded from sensors with different orientations are transformed into this consistent reference system. This new preprocessing has been evaluated to mitigate the effect of different sensor orientations on the classification accuracy in several state-of-the-art HAR systems. The experiments were carried out using a subject-wise cross-validation methodology over six different datasets, including movements and postures. This new preprocessing module provided robust HAR performance even when sudden sensor orientation changes were included during data collection in the six different datasets. As an example, for the WISDM dataset, sensors with different orientations provoked a significant reduction in the classification accuracy of the state-of-the-art system (from 91.57 ± 0.23% to 89.19 ± 0.26%). This important reduction was recovered with the proposed algorithm, increasing the accuracy to 91.46 ± 0.30%, i.e., the same result obtained when all sensors had the same orientation.https://www.mdpi.com/1424-8220/23/13/5845human activity recognitiongravity estimationsensor-orientation-independentforward movement directionwearable sensorsacceleration signals |
| spellingShingle | Manuel Gil-Martín Javier López-Iniesta Fernando Fernández-Martínez Rubén San-Segundo Reducing the Impact of Sensor Orientation Variability in Human Activity Recognition Using a Consistent Reference System Sensors human activity recognition gravity estimation sensor-orientation-independent forward movement direction wearable sensors acceleration signals |
| title | Reducing the Impact of Sensor Orientation Variability in Human Activity Recognition Using a Consistent Reference System |
| title_full | Reducing the Impact of Sensor Orientation Variability in Human Activity Recognition Using a Consistent Reference System |
| title_fullStr | Reducing the Impact of Sensor Orientation Variability in Human Activity Recognition Using a Consistent Reference System |
| title_full_unstemmed | Reducing the Impact of Sensor Orientation Variability in Human Activity Recognition Using a Consistent Reference System |
| title_short | Reducing the Impact of Sensor Orientation Variability in Human Activity Recognition Using a Consistent Reference System |
| title_sort | reducing the impact of sensor orientation variability in human activity recognition using a consistent reference system |
| topic | human activity recognition gravity estimation sensor-orientation-independent forward movement direction wearable sensors acceleration signals |
| url | https://www.mdpi.com/1424-8220/23/13/5845 |
| work_keys_str_mv | AT manuelgilmartin reducingtheimpactofsensororientationvariabilityinhumanactivityrecognitionusingaconsistentreferencesystem AT javierlopeziniesta reducingtheimpactofsensororientationvariabilityinhumanactivityrecognitionusingaconsistentreferencesystem AT fernandofernandezmartinez reducingtheimpactofsensororientationvariabilityinhumanactivityrecognitionusingaconsistentreferencesystem AT rubensansegundo reducingtheimpactofsensororientationvariabilityinhumanactivityrecognitionusingaconsistentreferencesystem |