RSL system based on transfer learning
A deep-learning powered single-strained electronic skin sensor can capture human motion from a distance. The single strain sensor placed on the wrist decodes complex five-finger motions in real time with a virtual 3D hand that mirrors the original motions.
The deep neural network boosted by rapid situation learning (RSL) ensures stable operation regardless of its position on the surface of the skin.
Conventional approaches require many sensor networks that cover the entire curvilinear surfaces of the target area. Unlike conventional wafer-based fabrication, this laser fabrication provides a new sensing paradigm for motion tracking.
The research team, led by Professor Sungho Jo from the School of Computing, collaborated with Professor Seunghwan Ko from Seoul National University to design this new measuring system that extracts signals corresponding to multiple finger motions by generating cracks in metal nanoparticle films using laser technology. The sensor patch was then attached to a user’s wrist to detect the movement of the fingers.
The concept of this research started from the idea that pinpointing a single area would be more efficient for identifying movements than affixing sensors to every joint and muscle. To make this targeting strategy work, it needs to accurately capture the signals from different areas at the point where they all converge, and then decoupling the information entangled in the converged signals. To maximize users’ usability and mobility, the research team used a single-channeled sensor to generate the signals corresponding to complex hand motions.
The rapid situation learning (RSL) system collects data from arbitrary parts on the wrist and automatically trains the model in a real-time demonstration with a virtual 3D hand that mirrors the original motions. To enhance the sensitivity of the sensor, researchers used laser-induced nanoscale cracking.
This sensory system can track the motion of the entire body with a small sensory network and facilitate the indirect remote measurement of human motions, which is applicable for wearable VR/AR systems.
The research team said they focused on two tasks while developing the sensor. First, they analyzed the sensor signal patterns into a latent space encapsulating temporal sensor behavior and then they mapped the latent vectors to finger motion metric spaces.
Professor Jo said, “Our system is expandable to other body parts. We already confirmed that the sensor is also capable of extracting gait motions from a pelvis. This technology is expected to provide a turning point in health-monitoring, motion tracking, and soft robotics.”
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
- It’s now Hurricane Elsa: South Florida is in forecast track with possible landfall early next weekon July 2, 2021 at 6:17 am
Hurricane Elsa became the season's first hurricane early Friday morning. Most of the state of Florida is in its potential path, according to the National Hurricane Center.
- Endless Stop-Motion Film from Psyop Inspires a New Generation of Track & Field Stars to Keep Runningon July 2, 2021 at 5:16 am
Little Black Book, Film takes place during a hurdling competition at the famed Hayward Stadium with a focus on one ace hurdler as he puts on a gutsy performance while being cheered on ...
- Hurricane Elsa forms, expected to head into Gulf and then hit Florida: See trackon July 2, 2021 at 5:03 am
Hurricane Elsa formed Friday morning in the Atlantic, forecasters said. The storm is expected to head into the Gulf of Mexico and hit Florida as a tropical storm.
- FIRST ALERT: Hurricane Elsa moves into Caribbean, track now includes part of South Carolinaon July 2, 2021 at 1:06 am
Elsa is a category one hurricane and the latest update now includes part of South Carolina in the cone of uncertainty. Elsa continues to move WNW at a fast rate as a category one hurricane this ...
- TROPICAL STORM ELSA: Discussing Forecast Track And Intensity...on July 1, 2021 at 4:33 pm
A rapid west-northwestward motion is likely for the next 48 hours or so as Elsa is steered by the strong subtropical ridge to the north. Tropical storm conditions are expected ...
Go deeper with Google Headlines on:
Go deeper with Bing News on:
Rapid situation learning system
- The exciting future of remote health monitoring depends on learning four lessonson July 2, 2021 at 3:34 am
David Hancock, healthcare executive advisor at InterSystems, identifies four lessons to be learned from remote health monitoring ...
- Brivo's AI-Powered Snapshot Launched to Provide Rapid Insights into Fusion of Access and Video Dataon June 30, 2021 at 6:00 am
Brivo, the global leader in cloud-based access control and smart building technologies, today launched Brivo Snapshot—a high-accuracy video analytics and forensic tool that ...
- E-Learning Services Market to See Massive Growth by 2026 | Aptara, Adobe Systems, Cornerstoneon June 25, 2021 at 12:34 pm
The latest study released on the Global E-Learning Services Market by AMA Research evaluates market size, trend, and forecast to 2026. The E-Learning Services market study covers significant research ...
- Training Software Market is Booming Worldwide | Oracle, EduBrite Systems, Trivantison June 24, 2021 at 1:19 am
Latest released the research study on Global Training Software Market offers a detailed overview of the factors influencing the global business scope Training Software Market research report shows the ...
- Learning from COVID: how to improve future supplies of medical equipment and vaccineson June 23, 2021 at 6:49 am
Supply chains, choke points, and 'just in time' manufacturing – where things went right and wrong during the pandemic.