Welcome to the February 2023 SIGCHI edition of ACM TechNews.


ACM TechNews - SIGCHI Edition is a sponsored special edition of the ACM TechNews news-briefing service focused on issues in Human Computer Interaction (HCI). This service serves as a resource for ACM-SIGCHI Members to keep abreast of the latest news in areas related to HCI and is distributed to all ACM SIGCHI members the first Tuesday of every month.

ACM TechNews is a benefit of ACM membership and is distributed three times per week on Mondays, Wednesday, and Fridays to over 100,000 ACM members from over 100 countries around the world. ACM TechNews provides timely coverage of established and emerging areas of computer science, the latest trends in information technology, and related science, society, and technology news. For more information on ACM TechNews and joining the ACM, please click.

The Interactions mobile app is available for free on iOS, Android, and Kindle platforms. Download it today and flip through the full-color magazine pages on your tablet or view it in a simplified low-bandwidth text mode on your phone. And be sure to check out the Interactions website, where you can access current and past articles and read the latest entries in our ever-expanding collection of blogs.

Esterwood said researchers must develop more effective repair strategies to help robots better repair trust after these mistakes. Robot: I'm Sorry. Human: I Don't Care Anymore!
University of Michigan News
February 2, 2023


University of Michigan (U-M) researchers looked at ways to restore a human's trust in robots following multiple mistakes. The study involved 240 participants who collaborated with a robot co-worker on a certain task to test whether apologies, denials, explanations, or promises of trustworthiness could overcome trust violations when the robot made mistakes. The researchers found trustworthiness was never repaired fully after the robot made three mistakes. They suggested more effective trust repair strategies are necessary, adding that a robot must master the tasks on which they made mistakes before trying to repair that trust. U-M's Robert Lionel said, "Our study's results indicate that after three violations and repairs, trust cannot be fully restored, thus supporting the adage 'three strikes and you're out.' In doing so, it presents a possible limit that may exist regarding when trust can be fully restored."

Full Article
Paralyzed Patients Effectively Control Computer in Historic Trial
Interesting Engineering
Loukia Papadopoulos
January 15, 2023


Researchers in Australia found that four patients with severe paralysis were able to control a computer using Synchron's Stentrode implantable brain-computer interface, a neuroprosthesis device that transmits neural signals from inside a blood vessel in the brain. The researchers determined the device can be used without serious side effects over a long-term period. During the 12-month study, all of the participants were able to use the device to text, send and receive emails, handle their personal finances, shop online, and communicate care tasks using a personal computing device. Peter Mitchell of Australia's Royal Melbourne Hospital said, "The wide-spread availability of the angiography suite for this procedure could promote a rapid translation of brain-computer interface for people with paralysis."

Full Article

A ShotSpotter Dispatch program in operation within the Fusion Watch department at Las Vegas Metropolitan Police headquarters. Confidential Document Reveals Key Human Role in Gunshot Tech
Associated Press
Garance Burke; Michael Tarm
January 20, 2023


A confidential document from system software company ShotSpotter indicates human employees can override gunfire identification calls by its artificial intelligence (AI) algorithm at their discretion. More than 140 U.S. cities use the algorithm and microphone networks to extrapolate gunfire from hundreds of thousands of recordings a year. The document outlines how reviewers should listen to recordings and evaluate the algorithm's finding of likely gunfire according to factors that may require opinions. A 2021 account estimated reversals occur 10% of the time, which experts say could embed subjectivity within increasingly consequential decisions and undermine AI's deployment by law enforcement to minimize human fallibility.

Full Article
Bot Gives Nonnative Speakers the Floor in Videoconferencing
Cornell Chronicle
Patricia Waldron
January 31, 2023


Researchers at Cornell University and Japan's Nippon Telegraph and Telephone Corporation (NTT) tested a conversational agent to help nonnative speakers express themselves in multilingual exchanges. The agent was programmed to intervene to help nonnative speakers break into dialogues after native speakers took six consecutive turns. Cornell's Xiaoyan Li enlisted and divided 48 volunteers into groups of two native English speakers and a native Japanese speaker in videoconference; the groups engaged in three exercises to discuss imaginary disaster scenarios and to rank salvage items useful for survival. The agent boosted participation from nonnative speakers by 40%, although native speakers considered its interventions distracting and unnecessary.

Full Article

OneButtonPIN addresses security issues by using haptic vibrations imperceptible to outsiders. OneButtonPIN Increases Security for Blind, Low-Vision Users
University of Waterloo (Canada)
January 18, 2023


An authentication method developed by researchers at Canada's University of Waterloo and the Rochester Institute of Technology increases the security of mobile devices for blind and low-vision (BLV) users by allowing them to use one large button and a series of haptic vibrations to input PIN codes. With OneButtonPIN, users press and hold a large button on the smartphone screen to activate a series of haptic vibrations imperceptible to outsiders. The user releases the button after the number of vibrations corresponding to the number they want to enter, then repeats the process until the PIN code is entered completely. The researchers found OneButtonPIN more secure than traditional authentication methods for BLV users due to their use of screen reader technology.

Full Article

Researchers have suggested monitoring audio clips on sites like YouTube could be a quick, inexpensive way of tracking coronavirus cases in the community. AI Detects if YouTubers are Infected with Omicron Variant
New Scientist
Soumya Sagar
January 19, 2023


Artificial intelligence (AI) developed by the U.S. National Institutes of Health's Bradford Wood and colleagues can detect whether YouTubers have caught the omicron coronavirus variant by identifying the presence of "omicron-specific laryngitis." The researchers analyzed 93 hours of YouTube audio samples, processed them to omit silences and noises other than the speaker talking, then split them into 2.5-second segments. They trained the AI on random samples before testing it on unused samples, differentiating omicron audio samples from speakers with no known respiratory infection with 80% sensitivity and 85% specificity. The AI also differentiated omicron-infected speakers from those with non-coronavirus respiratory infections with 70% sensitivity and 76% specificity, and distinguished non-omicron coronavirus infections from those with no respiratory infection with 58% sensitivity and 80% specificity.

Full Article
Autonomous Steering System Keeps Human Drivers Engaged
EPFL (Switzerland)
January 31, 2023


An automated driving system developed by researchers at Switzerland's École polytechnique fédérale de Lausanne and JTEKT Corp., a Japanese steering system supplier, requires active interaction between self-driving vehicles and human drivers. The haptics-based system integrates information from a car's steering column and encourages "collaborative steering." The system distinguishes between four types of human-robot interaction—coordination, coactivity, collaboration, and competition—and shifts between these modes based on what's happening on the road. When the driver intervenes, the system will recompute the vehicle's trajectory instead of turning off as though it's being overridden. In simulations and field tests, researchers saw collaborative steering improve comfort and reduce effort for drivers.

Full Article

eSight Go, worn by Cosmo Moore, has a neck battery pack for added comfort, and OLED screens for improved clarity. Stair-Climbing Wheelchairs, Closed-Caption Glasses: Assistive Tech Gains at CES in Las Vegas
The Wall Street Journal
Dalvin Brown
January 6, 2023


Many of the technologies displayed at CES in Las Vegas last month focused on accessibility. One such product, the eSight Go vision-assistance headset, uses a camera to capture images users cannot see, then projects them onto monitors located closer to users’ eyes. Another, glasses from Boston startup Xander, assist people with hearing loss by generating closed captions in real time for conversations picked up by its built-in microphone. Swiss startup Scewo showcased Scewo Bro, an adjustable-height, two-wheeled wheelchair featuring tank-like treads to navigate rocky terrain and stairs. Among other announcements of upcoming accessible technologies was L’Oréal’s plan to release a computerized makeup device with motion controls, to help people with limited arm mobility apply lipstick.

Full Article

A study participant tests the 'smart' walking stick. 'Smart' Walking Stick Could Help Visually Impaired with Groceries, Finding a Seat
University of Colorado Boulder
Daniel Strain
January 19, 2023


University of Colorado Boulder (CU Boulder) researchers have developed a smart walking stick that uses artificial intelligence (AI) to help people who are blind or visually impaired handle tasks ranging from grocery shopping to finding a seat. The walking stick can map and catalog the user's surroundings using a camera and computer vision technology, and uses handle vibrations and spoken directions to guide users to their desired location. CU Boulder's Shivendra Agrawal said, "AI and computer vision are improving, and people are using them to build self-driving cars and similar inventions. But these technologies also have the potential to improve quality of life for many people."

Full Article
Apps Want to Be Your New Doctor's Office. Is That a Good Idea?
The Washington Post
Hannah Norman
January 15, 2023


Smartphones increasingly are being leveraged by tech companies to produce patient monitoring tools. Camera lenses, microphones, and sensors in these devices can be used to collect data, which will be analyzed by software and transmitted to healthcare providers. These tools include the Google Fit app, which can check a user's heart rate when their fingertip is placed on the rear-facing camera lens. Additionally, Binah.ai checks vital signs using smartphone cameras, Canary Speech uses the microphone to screen for mental health conditions, ResApp's SleepCheckRx screens for sleep apnea by listening to the user's breathing and snoring, and Brightlamp's Reflex app uses the camera to measure how the user's pupils react to changes in light. University of Washington's Eugene Yang noted it is difficult to ensure accuracy and clinical validation when such tools rely on algorithms, rather than hospital-based tools, to collect data.

Full Article
Wearable, Trackable Tech Makes Driving Safer for Teens with ADHD
UNC Research
Carleigh Gabryel
January 12, 2023


Technology developed by University of North Carolina at Chapel Hill (UNC) researchers can reduce traffic crashes by tracking teenage drivers with attention-deficit/hyperactivity disorder (ADHD) in real time. UNC's Adam Kiefer said he and colleagues at Cincinnati Children's Hospital "were able to modify an eye-tracking device to create a behavioral feedback system that would alert the drivers in this training when they were looking away from their target for longer than two seconds." Two groups of teen drivers with ADHD used the Focused Concentration and Attention Learning software platform as a driving simulator while wearing the eye-tracking technology. One group heard an alarm when their gaze diverged from the road for two or more seconds. After a month of training, this group had fewer long glances, near-collisions, and crashes than the control group.

Full Article

The system’s nanowire network senses tiny changes to electrical resistance as the skin underneath stretches. Spray-on Smart Skin Reads Typing, Hand Gestures
IEEE Spectrum
Prachi Patel
January 10, 2023


Spray-on smart skin technology developed by researchers at South Korea's Seoul National University and Stanford University uses artificial intelligence to decode hand gestures and recognize typing, sign language, and the configuration of objects. The system includes a silver nanowire mesh coated with gold and embedded within a polyurethane plastic film printed onto the user's hand. The nanomesh detects fluctuating electrical resistance as the skin stretches, and wirelessly transmits signals to a computer through a Bluetooth unit. Machine learning software then correlates the patterns to physical tasks and gestures. The developers said the system quickly identifies and interprets hand movements with limited data and minimal training and should be universally applicable.

Full Article

The Paro therapeutic robots. Researchers Test Effects of Baby Seal Robots on Potential Mars Dwellers
Interesting Engineering
Loukia Papadopoulos
January 15, 2023


Japan's Paro tested its robotic seals during a two-week simulation of a Mars mission at the Mars Desert Research Station in Utah. The Paro robots could provide companionship to astronauts on Mars and help them manage stress and isolation. Paros have been used as a therapeutic tool in care facilities, where they were found to calm patients with dementia. The robotic seal features dual 32-bit processors, three microphones, 12 tactile sensors, touch-sensitive whiskers, and a network of motors and actuators that allow for graceful and realistic movements. It mimics the sounds of a baby seal and can respond to touch, remember faces, and learn and repeat actions that generate positive reactions from users.

Full Article

The researchers claim the AI Aquarium is 98% accurate at identifying fish species. Eye-Tracking Aquarium Tells Users About the Fish They're Watching
New Atlas
Ben Coxworth
January 11, 2023


The AI Aquarium engineered by Taiwan's Industrial Technology Research Institute and installed in Taiwan's National Museum of Marine Science and Technology can overlay information that lines up with specific fish spectators are following. A depth-sensing three-dimensional camera over the tank tracks viewers' eyes to determine the focus of their gaze. Another camera tracks the fish's positions, producing real-time video analyzed by an object recognition algorithm to visually match each fish to photos of known species in a database. The AI Aquarium compares the viewer's line of sight to the positions of the fish to ascertain which individual fish is being stared and what is its species. The system displays this information on a transparent screen overlying the front glass of the tank, while hand gestures can prompt the display for more information.

Full Article
Calendar of Events

TEI ’23: 17th International Conference on Tangible, Embedded, and Embodied Interaction
Feb. 26 – Mar. 1
Warsaw, Poland

HRI ’23: ACM/IEEE International Conference on Human-Robot Interaction
Mar. 13 - 16
Stockholm, Sweden

IUI ’23: 28th International Conference on Intelligent User Interfaces
Mar. 27 – 31
Syndey, Australia

CHI ’23: ACM CHI Conference on Human Factors in Computing Systems
Hamburg, Germany
Apr. 23 - 28

IMX ’23: ACM International Conference on Interactive Media Experiences
Nantes, France
Jun. 13 – 15

C&C ’23: Creativity and Cognition
Jun. 19 - 21
Online

IDC ’23: Interaction Design and Children
Jun. 19 – 22
Evanston, IL

UMAP ’23: 31st ACM Conference on User Modeling, Adaptation and Personalization
Jun. 26 – 29
Limassol, Cyprus

EICS ’23: ACM SIGCHI Symposium on Engineering Interactive Computing Systems
Jun. 27 - 30
Swansea, UK

COMPASS ’23: ACM SIGCAS/SIGCHI Conference on Computing and Sustainable Societies
Aug. 16 - 19
Cape Town, South Africa

AutomotiveUI ’23: 15th International Conference on Automotive User Interfaces and Interactive Vehicular Applications
Sep. 18 - 21
Ingolstadt, Germany

RecSys ’23: 17th ACM Conference on Recommender Systems
Sep. 18 - 22
Singapore

MobileHCI ’23: 25th International Conference on Mobile Human-Computer Interaction
Sep. 26 - 29
Athens, Greece

UbiComp ’23: Ubiquitous Computing
Oct. 7 – 11
Melbourne, Australia

CSCW ’23: The 26th ACM Conference on Computer-Supported Cooperative Work and Social Computing
Oct. 13 - 18
Minneapolis, MN

UIST ’23: The 35th Annual ACM Symposium on User Interface Software and Technology
Oct. 29 – Nov. 1
San Francisco, CA

ISS ’23: Interactive Surfaces and Spaces
Nov. 5 – 8
Pittsburgh, PA


About SIGCHI

SIGCHI is the premier international society for professionals, academics and students who are interested in human-technology and human-computer interaction (HCI). We provide a forum for the discussion of all aspects of HCI through our conferences, publications, web sites, email discussion groups, and other services. We advance education in HCI through tutorials, workshops and outreach, and we promote informal access to a wide range of individuals and organizations involved in HCI. Members can be involved in HCI-related activities with others in their region through Local SIGCHI chapters. SIGCHI is also involved in public policy.



ACM Media Sales

If you are interested in advertising in ACM TechNews or other ACM publications, please contact ACM Media Sales or (212) 626-0686, or visit ACM Media for more information.

Association for Computing Machinery
1601 Broadway, 10th Floor
New York, NY 10019-7434
Phone: 1-800-342-6626
(U.S./Canada)

To submit feedback about ACM TechNews, contact: [email protected]

Unsubscribe

About ACM | Contact us | Boards & Committees | Press Room | Membership | Privacy Policy | Code of Ethics | System Availability | Copyright © 2024, ACM, Inc.