ActSonic: Recognizing Everyday Activities from Inaudible Acoustic Wave Around the Body
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915034900201472 |
|---|---|
| author | Mahmud, Saif Parikh, Vineet Liang, Qikang Li, Ke Zhang, Ruidong Ajit, Ashwin Gunda, Vipin Agarwal, Devansh Guimbretière, François Zhang, Cheng |
| author_facet | Mahmud, Saif Parikh, Vineet Liang, Qikang Li, Ke Zhang, Ruidong Ajit, Ashwin Gunda, Vipin Agarwal, Devansh Guimbretière, François Zhang, Cheng |
| contents | We present ActSonic, an intelligent, low-power active acoustic sensing system integrated into eyeglasses that can recognize 27 different everyday activities (e.g., eating, drinking, toothbrushing) from inaudible acoustic waves around the body. It requires only a pair of miniature speakers and microphones mounted on each hinge of the eyeglasses to emit ultrasonic waves, creating an acoustic aura around the body. The acoustic signals are reflected based on the position and motion of various body parts, captured by the microphones, and analyzed by a customized self-supervised deep learning framework to infer the performed activities on a remote device such as a mobile phone or cloud server. ActSonic was evaluated in user studies with 19 participants across 19 households to track its efficacy in everyday activity recognition. Without requiring any training data from new users (leave-one-participant-out evaluation), ActSonic detected 27 activities, achieving an average F1-score of 86.6% in fully unconstrained scenarios and 93.4% in prompted settings at participants' homes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_13924 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ActSonic: Recognizing Everyday Activities from Inaudible Acoustic Wave Around the Body Mahmud, Saif Parikh, Vineet Liang, Qikang Li, Ke Zhang, Ruidong Ajit, Ashwin Gunda, Vipin Agarwal, Devansh Guimbretière, François Zhang, Cheng Human-Computer Interaction Emerging Technologies We present ActSonic, an intelligent, low-power active acoustic sensing system integrated into eyeglasses that can recognize 27 different everyday activities (e.g., eating, drinking, toothbrushing) from inaudible acoustic waves around the body. It requires only a pair of miniature speakers and microphones mounted on each hinge of the eyeglasses to emit ultrasonic waves, creating an acoustic aura around the body. The acoustic signals are reflected based on the position and motion of various body parts, captured by the microphones, and analyzed by a customized self-supervised deep learning framework to infer the performed activities on a remote device such as a mobile phone or cloud server. ActSonic was evaluated in user studies with 19 participants across 19 households to track its efficacy in everyday activity recognition. Without requiring any training data from new users (leave-one-participant-out evaluation), ActSonic detected 27 activities, achieving an average F1-score of 86.6% in fully unconstrained scenarios and 93.4% in prompted settings at participants' homes. |
| title | ActSonic: Recognizing Everyday Activities from Inaudible Acoustic Wave Around the Body |
| topic | Human-Computer Interaction Emerging Technologies |
| url | https://arxiv.org/abs/2404.13924 |