MSGID: 1:317/3 645091e9   
   PID: hpt/lnx 1.9.0-cur 2019-01-08   
   TID: hpt/lnx 1.9.0-cur 2019-01-08   
    A new technique for recording and analyzing surface-acoustic waves can   
   enable nearly any object to act as a touch input device and power privacy-   
   sensitive sensing systems    
      
     Date:   
         May 1, 2023   
     Source:   
         University of Michigan   
     Summary:   
         Couches, tables, sleeves and more can turn into a high-fidelity   
         input device for computers using a new sensing system.   
      
      
         Facebook Twitter Pinterest LinkedIN Email   
      
   ==========================================================================   
   FULL STORY   
   ==========================================================================   
   Couches, tables, sleeves and more can turn into a high-fidelity input   
   device for computers using a new sensing system developed at the   
   University of Michigan.   
      
   The system repurposes technology from new bone-conduction microphones,   
   known as Voice Pickup Units (VPUs), which detect only those acoustic waves   
   that travel along the surface of objects. It works in noisy environments,   
   along odd geometries such as toys and arms, and on soft fabrics such as   
   clothing and furniture.   
      
   Called SAWSense, for the surface acoustic waves it relies on, the system   
   recognizes different inputs, such as taps, scratches and swipes, with 97%   
   accuracy. In one demonstration, the team used a normal table to replace   
   a laptop's trackpad.   
      
   "This technology will enable you to treat, for example, the whole surface   
   of your body like an interactive surface," said Yasha Iravantchi,   
   U-M doctoral candidate in computer science and engineering. "If you   
   put the device on your wrist, you can do gestures on your own skin. We   
   have preliminary findings that demonstrate this is entirely feasible."   
   Taps, swipes and other gestures send acoustic waves along the surfaces of   
   materials. The system then classifies these waves with machine learning   
   to turn all touch into a robust set of inputs. The system was presented   
   last week at the 2023 Conference on Human Factors in Computing Systems,   
   where it received a best paper award.   
      
   As more objects continue to incorporate smart or connected technology,   
   designers are faced with a number of challenges when trying to give   
   them intuitive input mechanisms. This results in a lot of clunky   
   incorporation of input methods such as touch screens, as well as   
   mechanical and capacitive buttons, Iravantchi says. Touch screens   
   may be too costly to enable gesture inputs across large surfaces like   
   counters and refrigerators, while buttons only allow one kind of input   
   at predefined locations.   
      
   Past approaches to overcome these limitations have included the use   
   of microphones and cameras for audio- and gesture-based inputs, but   
   the authors say techniques like these have limited practicality in the   
   real world.   
      
   "When there's a lot of background noise, or something comes between the   
   user and the camera, audio and visual gesture inputs don't work well,"   
   Iravantchi said.   
      
   To overcome these limitations, the sensors powering SAWSense are housed   
   in a hermetically sealed chamber that completely blocks even very loud   
   ambient noise. The only entryway is through a mass-spring system that   
   conducts the surface-acoustic waves inside the housing without ever   
   coming in contact with sounds in the surrounding environment. When   
   combined with the team's signal processing software, which generates   
   features from the data before feeding it into the machine learning model,   
   the system can record and classify the events along an object's surface.   
      
   "There are other ways you could detect vibrations or surface-acoustic   
   waves, like piezo-electric sensors or accelerometers," said Alanson   
   Sample, U- M associate professor of electrical engineering and computer   
   science, "but they can't capture the broad range of frequencies that we   
   need to tell the difference between a swipe and a scratch, for instance."   
   The high fidelity of the VPUs allows SAWSense to identify a wide range   
   of activities on a surface beyond user touch events. For instance,   
   a VPU on a kitchen countertop can detect chopping, stirring, blending   
   or whisking, as well as identifying electronic devices in use such as   
   a blender or microwave.   
      
   "VPUs do a good job of sensing activities and events happening in a well-   
   defined area," Iravantchi said. "This allows the functionality that comes   
   with a smart object without the privacy concerns of a standard microphone   
   that senses the whole room, for example."  When multiple VPUs are used in   
   combination, SAWSense could enable more specific and sensitive inputs,   
   especially those that require a sense of space and distance like the   
   keys on a keyboard or buttons on a remote.   
      
   In addition, the researchers are exploring the use of VPUs for medical   
   sensing, including picking up delicate noises such as the sounds of   
   joints and connective tissues as they move. The high-fidelity audio data   
   VPUs provide could enable real-time analytics about a person's health,   
   Sample says.   
      
   The research is partially funded by Meta Platforms Inc.   
      
   The team has applied for patent protection with the assistance of U- M   
   Innovation Partnerships and is seeking partners to bring the technology   
   to market.   
      
       * RELATED_TOPICS   
             o Matter_&_Energy   
                   # Ultrasound # Technology # Textiles_and_Clothing #   
                   Detectors   
             o Computers_&_Math   
                   # Computer_Science # Computers_and_Internet #   
                   Artificial_Intelligence # Information_Technology   
       * RELATED_TERMS   
             o Speech_recognition o Quantum_computer o Computer_vision o   
             Feedback o Computer_software o Catalytic_converter o Capacitor   
             o Mathematical_model   
      
   ==========================================================================   
   Story Source: Materials provided by University_of_Michigan. Note:   
   Content may be edited for style and length.   
      
      
   ==========================================================================   
   Journal Reference:   
      1. Yasha Iravantchi, Yi Zhao, Kenrick Kin, Alanson P. Sample. SAWSense:   
         Using Surface Acoustic Waves for Surface-bound Event   
         Recognition. 2023 Conference on Human Factors in Computing Systems,   
         2023 DOI: 10.1145/ 3544548.3580991   
   ==========================================================================   
      
   Link to news story:   
   https://www.sciencedaily.com/releases/2023/05/230501164001.htm   
      
   --- up 1 year, 9 weeks, 10 hours, 50 minutes   
    * Origin: -=> Castle Rock BBS <=- Now Husky HPT Powered! (1:317/3)   
   SEEN-BY: 15/0 106/201 114/705 123/120 153/7715 218/700 226/30 227/114   
   SEEN-BY: 229/110 112 113 307 317 400 426 428 470 664 700 292/854 298/25   
   SEEN-BY: 305/3 317/3 320/219 396/45   
   PATH: 317/3 229/426