Orientation-Independent Human Activity Recognition Using Complementary Radio Frequency Sensing
RF sensing offers an unobtrusive, user-friendly, and privacy-preserving method for detecting accidental falls and recognizing human activities. Contemporary RF-based HAR systems generally employ a single monostatic radar to recognize human activities. However, a single monostatic radar cannot detect...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-06-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/23/13/5810 |
_version_ | 1797590839250124800 |
---|---|
author | Muhammad Muaaz Sahil Waqar Matthias Pätzold |
author_facet | Muhammad Muaaz Sahil Waqar Matthias Pätzold |
author_sort | Muhammad Muaaz |
collection | DOAJ |
description | RF sensing offers an unobtrusive, user-friendly, and privacy-preserving method for detecting accidental falls and recognizing human activities. Contemporary RF-based HAR systems generally employ a single monostatic radar to recognize human activities. However, a single monostatic radar cannot detect the motion of a target, e.g., a moving person, orthogonal to the boresight axis of the radar. Owing to this inherent physical limitation, a single monostatic radar fails to efficiently recognize orientation-independent human activities. In this work, we present a complementary RF sensing approach that overcomes the limitation of existing single monostatic radar-based HAR systems to robustly recognize orientation-independent human activities and falls. Our approach used a distributed mmWave MIMO radar system that was set up as two separate monostatic radars placed orthogonal to each other in an indoor environment. These two radars illuminated the moving person from two different aspect angles and consequently produced two time-variant micro-Doppler signatures. We first computed the mean Doppler shifts (MDSs) from the micro-Doppler signatures and then extracted statistical and time- and frequency-domain features. We adopted feature-level fusion techniques to fuse the extracted features and a support vector machine to classify orientation-independent human activities. To evaluate our approach, we used an orientation-independent human activity dataset, which was collected from six volunteers. The dataset consisted of more than 1350 activity trials of five different activities that were performed in different orientations. The proposed complementary RF sensing approach achieved an overall classification accuracy ranging from 98.31 to 98.54%. It overcame the inherent limitations of a conventional single monostatic radar-based HAR and outperformed it by 6%. |
first_indexed | 2024-03-11T01:29:10Z |
format | Article |
id | doaj.art-305d1922fab44df8890e498bab43b8b0 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-11T01:29:10Z |
publishDate | 2023-06-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-305d1922fab44df8890e498bab43b8b02023-11-18T17:27:06ZengMDPI AGSensors1424-82202023-06-012313581010.3390/s23135810Orientation-Independent Human Activity Recognition Using Complementary Radio Frequency SensingMuhammad Muaaz0Sahil Waqar1Matthias Pätzold2Faculty of Engineering and Science, University of Agder, 4898 Grimstad, NorwayFaculty of Engineering and Science, University of Agder, 4898 Grimstad, NorwayFaculty of Engineering and Science, University of Agder, 4898 Grimstad, NorwayRF sensing offers an unobtrusive, user-friendly, and privacy-preserving method for detecting accidental falls and recognizing human activities. Contemporary RF-based HAR systems generally employ a single monostatic radar to recognize human activities. However, a single monostatic radar cannot detect the motion of a target, e.g., a moving person, orthogonal to the boresight axis of the radar. Owing to this inherent physical limitation, a single monostatic radar fails to efficiently recognize orientation-independent human activities. In this work, we present a complementary RF sensing approach that overcomes the limitation of existing single monostatic radar-based HAR systems to robustly recognize orientation-independent human activities and falls. Our approach used a distributed mmWave MIMO radar system that was set up as two separate monostatic radars placed orthogonal to each other in an indoor environment. These two radars illuminated the moving person from two different aspect angles and consequently produced two time-variant micro-Doppler signatures. We first computed the mean Doppler shifts (MDSs) from the micro-Doppler signatures and then extracted statistical and time- and frequency-domain features. We adopted feature-level fusion techniques to fuse the extracted features and a support vector machine to classify orientation-independent human activities. To evaluate our approach, we used an orientation-independent human activity dataset, which was collected from six volunteers. The dataset consisted of more than 1350 activity trials of five different activities that were performed in different orientations. The proposed complementary RF sensing approach achieved an overall classification accuracy ranging from 98.31 to 98.54%. It overcame the inherent limitations of a conventional single monostatic radar-based HAR and outperformed it by 6%.https://www.mdpi.com/1424-8220/23/13/5810activity recognitiondata fusiondistributed mmWave MIMO radarfall detectionfeature extractionmicro-Doppler signature |
spellingShingle | Muhammad Muaaz Sahil Waqar Matthias Pätzold Orientation-Independent Human Activity Recognition Using Complementary Radio Frequency Sensing Sensors activity recognition data fusion distributed mmWave MIMO radar fall detection feature extraction micro-Doppler signature |
title | Orientation-Independent Human Activity Recognition Using Complementary Radio Frequency Sensing |
title_full | Orientation-Independent Human Activity Recognition Using Complementary Radio Frequency Sensing |
title_fullStr | Orientation-Independent Human Activity Recognition Using Complementary Radio Frequency Sensing |
title_full_unstemmed | Orientation-Independent Human Activity Recognition Using Complementary Radio Frequency Sensing |
title_short | Orientation-Independent Human Activity Recognition Using Complementary Radio Frequency Sensing |
title_sort | orientation independent human activity recognition using complementary radio frequency sensing |
topic | activity recognition data fusion distributed mmWave MIMO radar fall detection feature extraction micro-Doppler signature |
url | https://www.mdpi.com/1424-8220/23/13/5810 |
work_keys_str_mv | AT muhammadmuaaz orientationindependenthumanactivityrecognitionusingcomplementaryradiofrequencysensing AT sahilwaqar orientationindependenthumanactivityrecognitionusingcomplementaryradiofrequencysensing AT matthiaspatzold orientationindependenthumanactivityrecognitionusingcomplementaryradiofrequencysensing |