Radar-Based Activity Recognition in Strictly Privacy-Sensitive Settings Through Deep Feature Learning
Human activity recognition in privacy-sensitive environments, such as bathrooms, presents significant challenges due to the need for non-invasive and anonymous monitoring. Traditional vision-based methods raise privacy concerns, while wearable sensors require user compliance. This study explores a r...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Biomimetics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-7673/10/4/243 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849712520155103232 |
|---|---|
| author | Giovanni Diraco Gabriele Rescio Alessandro Leone |
| author_facet | Giovanni Diraco Gabriele Rescio Alessandro Leone |
| author_sort | Giovanni Diraco |
| collection | DOAJ |
| description | Human activity recognition in privacy-sensitive environments, such as bathrooms, presents significant challenges due to the need for non-invasive and anonymous monitoring. Traditional vision-based methods raise privacy concerns, while wearable sensors require user compliance. This study explores a radar-based approach for recognizing the activities of daily living in a bathroom setting, utilizing a BGT60TR13C Xensiv 60 GHz radar, manufactured by Infineon Technologies AG (Munich, Germany, EU), to classify human movements without capturing identifiable biometric features. A dataset was collected from seven volunteers performing ten activities which are part of daily living, including activities unique to bathroom environments, such as face washing, teeth brushing, dressing/undressing, and resting on the toilet seat. Deep learning models based on pre-trained feature extractors combined with bidirectional long short-term memory networks were employed for classification. Among the 16 pre-trained networks evaluated, DenseNet201 achieved the highest overall accuracy (97.02%), followed by ResNet50 (94.57%), with the classification accuracy varying by activity. The results highlight the feasibility of Doppler radar-based human activity recognition in privacy-sensitive settings, demonstrating strong recognition performance for most activities while identifying lying down and getting up as more challenging cases due to their motion similarity. The findings suggest that radar-based human activity recognition is a viable alternative to other more invasive monitoring systems (e.g., camera-based), offering an effective, privacy-preserving solution for smart home and healthcare applications. |
| format | Article |
| id | doaj-art-e0c1b7df10e743eea4386c2e5324ca2b |
| institution | DOAJ |
| issn | 2313-7673 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biomimetics |
| spelling | doaj-art-e0c1b7df10e743eea4386c2e5324ca2b2025-08-20T03:14:14ZengMDPI AGBiomimetics2313-76732025-04-0110424310.3390/biomimetics10040243Radar-Based Activity Recognition in Strictly Privacy-Sensitive Settings Through Deep Feature LearningGiovanni Diraco0Gabriele Rescio1Alessandro Leone2National Research Council of Italy, Institute for Microelectronics and Microsystems, 73100 Lecce, ItalyNational Research Council of Italy, Institute for Microelectronics and Microsystems, 73100 Lecce, ItalyNational Research Council of Italy, Institute for Microelectronics and Microsystems, 73100 Lecce, ItalyHuman activity recognition in privacy-sensitive environments, such as bathrooms, presents significant challenges due to the need for non-invasive and anonymous monitoring. Traditional vision-based methods raise privacy concerns, while wearable sensors require user compliance. This study explores a radar-based approach for recognizing the activities of daily living in a bathroom setting, utilizing a BGT60TR13C Xensiv 60 GHz radar, manufactured by Infineon Technologies AG (Munich, Germany, EU), to classify human movements without capturing identifiable biometric features. A dataset was collected from seven volunteers performing ten activities which are part of daily living, including activities unique to bathroom environments, such as face washing, teeth brushing, dressing/undressing, and resting on the toilet seat. Deep learning models based on pre-trained feature extractors combined with bidirectional long short-term memory networks were employed for classification. Among the 16 pre-trained networks evaluated, DenseNet201 achieved the highest overall accuracy (97.02%), followed by ResNet50 (94.57%), with the classification accuracy varying by activity. The results highlight the feasibility of Doppler radar-based human activity recognition in privacy-sensitive settings, demonstrating strong recognition performance for most activities while identifying lying down and getting up as more challenging cases due to their motion similarity. The findings suggest that radar-based human activity recognition is a viable alternative to other more invasive monitoring systems (e.g., camera-based), offering an effective, privacy-preserving solution for smart home and healthcare applications.https://www.mdpi.com/2313-7673/10/4/243human activity recognitionFMCW radardeep feature learningprivacy |
| spellingShingle | Giovanni Diraco Gabriele Rescio Alessandro Leone Radar-Based Activity Recognition in Strictly Privacy-Sensitive Settings Through Deep Feature Learning Biomimetics human activity recognition FMCW radar deep feature learning privacy |
| title | Radar-Based Activity Recognition in Strictly Privacy-Sensitive Settings Through Deep Feature Learning |
| title_full | Radar-Based Activity Recognition in Strictly Privacy-Sensitive Settings Through Deep Feature Learning |
| title_fullStr | Radar-Based Activity Recognition in Strictly Privacy-Sensitive Settings Through Deep Feature Learning |
| title_full_unstemmed | Radar-Based Activity Recognition in Strictly Privacy-Sensitive Settings Through Deep Feature Learning |
| title_short | Radar-Based Activity Recognition in Strictly Privacy-Sensitive Settings Through Deep Feature Learning |
| title_sort | radar based activity recognition in strictly privacy sensitive settings through deep feature learning |
| topic | human activity recognition FMCW radar deep feature learning privacy |
| url | https://www.mdpi.com/2313-7673/10/4/243 |
| work_keys_str_mv | AT giovannidiraco radarbasedactivityrecognitioninstrictlyprivacysensitivesettingsthroughdeepfeaturelearning AT gabrielerescio radarbasedactivityrecognitioninstrictlyprivacysensitivesettingsthroughdeepfeaturelearning AT alessandroleone radarbasedactivityrecognitioninstrictlyprivacysensitivesettingsthroughdeepfeaturelearning |