Customized Mid-Air Gestures for Accessibility: A $B Recognizer for Multi-Dimensional Biosignal Gestures
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929499219689472 |
|---|---|
| author | Yamagami, Momona Mitchell, Claire L. Portnova-Fahreeva, Alexandra A. Kong, Junhan Mankoff, Jennifer Wobbrock, Jacob O. |
| author_facet | Yamagami, Momona Mitchell, Claire L. Portnova-Fahreeva, Alexandra A. Kong, Junhan Mankoff, Jennifer Wobbrock, Jacob O. |
| contents | Biosignal interfaces, using sensors in, on, or around the body, promise to enhance wearables interaction and improve device accessibility for people with motor disabilities. However, biosignals are multi-modal, multi-dimensional, and noisy, requiring domain expertise to design input features for gesture classifiers. The \$B-recognizer enables mid-air gesture recognition without needing expertise in biosignals or algorithms. \$B resamples, normalizes, and performs dimensionality reduction to reduce noise and enhance signals relevant to the recognition. We tested \$B on a dataset of 26 participants with and 8 participants without upper-body motor disabilities performing personalized ability-based gestures. For two conditions (user-dependent, gesture articulation variability), \$B outperformed our comparison algorithms (traditional machine learning with expert features and deep learning), with > 95% recognition rate. For the user-independent condition, \$B and deep learning performed comparably for participants with disabilities. Our biosignal dataset is publicly available online. $B highlights the potential and feasibility of accessible biosignal interfaces. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_08402 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Customized Mid-Air Gestures for Accessibility: A $B Recognizer for Multi-Dimensional Biosignal Gestures Yamagami, Momona Mitchell, Claire L. Portnova-Fahreeva, Alexandra A. Kong, Junhan Mankoff, Jennifer Wobbrock, Jacob O. Human-Computer Interaction Biosignal interfaces, using sensors in, on, or around the body, promise to enhance wearables interaction and improve device accessibility for people with motor disabilities. However, biosignals are multi-modal, multi-dimensional, and noisy, requiring domain expertise to design input features for gesture classifiers. The \$B-recognizer enables mid-air gesture recognition without needing expertise in biosignals or algorithms. \$B resamples, normalizes, and performs dimensionality reduction to reduce noise and enhance signals relevant to the recognition. We tested \$B on a dataset of 26 participants with and 8 participants without upper-body motor disabilities performing personalized ability-based gestures. For two conditions (user-dependent, gesture articulation variability), \$B outperformed our comparison algorithms (traditional machine learning with expert features and deep learning), with > 95% recognition rate. For the user-independent condition, \$B and deep learning performed comparably for participants with disabilities. Our biosignal dataset is publicly available online. $B highlights the potential and feasibility of accessible biosignal interfaces. |
| title | Customized Mid-Air Gestures for Accessibility: A $B Recognizer for Multi-Dimensional Biosignal Gestures |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2409.08402 |