Welcome to the December 2021 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.

How Smart Homes Alter Human Behavior
IEEE Spectrum
Michelle Hampson
December 1, 2021

Researchers at the Royal Military College of Canada found that smart home systems, while good at predicting human preferences, could alter human behavior. The researchers performed a series of simulations in which a smart home system was tasked with learning a human's room temperature preference while the human engaged in their regular activities. They found both the human and the artificial intelligence system exhibited misaligned behaviors if there was a slight inaccuracy in the system's predictions. Said the college’s Francois Rivest, "This led to more time spent by the individual changing temperature and activities than without the smart home system—the opposite of the smart home objective."

Full Article

Personalized Exosuit for Real-World Walking
Wyss Institute at Harvard
Leah Burrows
November 10, 2021

Harvard University researchers have developed a system that enables robotic exosuits to be calibrated to individuals and quickly adapted for real-world walking. The researchers created personalized activity-specific assistance profiles for users based on ultrasound measurements of their calf muscles during different walking tasks. By measuring the amount of metabolic energy used by the individual walking with and without the exosuit, the researchers determined the exosuit's muscle-based assistance lowered metabolic energy requirements over a range of walking speeds and inclines. Said Harvard's Sangjun Lee, "By measuring the muscle directly, we can work more intuitively with the person using the exosuit. With this approach, the exosuit isn't overpowering the wearer, it's working cooperatively with them."

Full Article

Brands No Longer See Metaverse-Like Worlds as Abstract Gimmicks
The Wall Street Journal
Alexandra Bruell
November 29, 2021

Chipotle Mexican Grill Inc., Verizon, and Vans are among the brands looking to engage customers in the "metaverse," a futuristic Internet where people can have virtual experiences using customized avatars. Although the widespread adoption of the metaverse likely is years away, these efforts—along with Facebook's $10-billion investment in developing a metaverse environment and changing its name to Meta Platforms Inc.—indicate that advertisers increasingly are willing to spend money on new digital platforms. Chipotle, for instance, built a virtual store in Roblox that allowed users to dress their avatars in Halloween costumes and move through a virtual maze to get a code for a free burrito. Said Chipotle's Chris Brandt, "Being at home, using avatars, having the ability to get everything delivered to your home—that changes the way people think about digital. I think the world is more ready for it."

Full Article

Smartwatches Alert Wearers to Bodily Stress, Including COVID-19
Stanford Medicine News Center
Hanae Armitage
November 29, 2021

Scientists at Stanford and Case Western Reserve universities have developed an algorithm that can alert smartwatch wearers to stress, and even COVID-19, before symptoms begin to appear. The researchers used the program to identify when a smartwatch wearer's heart rate was abnormally high. Stanford's Michael Snyder said the algorithm-equipped watch also could detect 80% of confirmed COVID-19 cases before or when participants exhibited symptoms. Snyder said the algorithm allows people to contextualize the smartwatch’s alerts. "The idea is for people to eventually use this information to decide whether they need to get a COVID-19 test or self-isolate," Snyder explained.

Full Article

South Korea to Use VR to Determine if Elderly Can Keep Driving
The Next Web
Ioanna Lykiardopoulou
November 29, 2021

The Korean National Police Agency (KNPA) has launched a three-year research project using virtual reality (VR) technology to determine whether drivers aged 65 and older should receive conditional licenses. KNPA, concerned about the number of auto accidents in which senior drivers are found to be at fault, is pushing for conditional licenses for those 65 and older to be implemented by 2025. Currently, South Korea does not regulate seniors' driver's licenses unless they have dementia.

Full Article

Decentralized AI/Human Artist Botto Makes Its First Million
New Atlas
Loz Blain
November 29, 2021

Botto, an artificial intelligence algorithm that creates artwork, recently earned about $1.3 million in an auction of its first six non-fungible tokens (NFTs). Botto feeds a random string of words and sentences into a Vector Quantized Generative Adversarial Network (VQGAN), which generates images. VQGAN's parameters are adjusted based on feedback from CLIP (Contrastive Language-Image Pre-training) software as to how closely the images represent the initial word string. Botto can create 300 images daily, and 350 are chosen weekly by a "taste model" and voted on by Botto community members; winning pieces are minted as NFTs and auctioned on the SuperRare platform.

Full Article

3D Printing of Blood Plasma May Speed Up Wound Healing
Royal College of Surgeons in Ireland
November 30, 2021

A team led by researchers at the Royal College of Surgeons in Ireland (RCSI) University of Medicine and Health Sciences found that using a three-dimensional (3D) printer to replicate platelet-rich plasma (PRP), and applying it to a wound as an implant, could improve wound healing. The researchers extracted PRP from the blood of a patient with a complex skin wound and used 3D printing to create an implant for tissue repair. The implant spurred the development of new blood vessels and prevented tissue scarring and thickening. RCSI's Fergal O'Brien said, "As well as promising results for skin wound healing, this technology can potentially be used to regenerate different tissues, therefore dramatically influencing the ever-growing regenerative medicine, 3D printing, and personalized medicine markets."

Full Article

The Long Search for a Computer That Speaks Your Mind
Wired
Adam Rogers
November 9, 2021

Researchers at the Netherlands' Maastricht University have developed a brain computer interface (BCI) that can take imagined speech and form an audible signal, essentially speaking what is on a person's mind without them having to say a word. The researchers were able to go from brain data to sound in 30 milliseconds, though the sounds were unintelligible. Maastricht's Christian Herff explained, "We just wanted to show that if you train on audible speech, you can get something on imagined speech as well." One challenge is that BCI-assisted prosthetics require validation and training, but people who cannot speak are unable to provide words in their own voices. Said Herff, "The problem with imagined speech is that we don't have an observable outcome."

Full Article

Giving Robots Social Skills
MIT News
Adam Zewe
November 5, 2021

Massachusetts Institute of Technology researchers have embedded social interactions within a framework for robotics, which could lead to smoother and more beneficial human-robot engagement. The researchers built a simulated environment where robots pursue physical goals and social goals in a two-dimensional grid; social goals involved guessing what another robot is trying to do, then acting based on that guess. The researchers particularized a robot's physical and social goals, and how much it should emphasize one over the other. The robot is rewarded for actions that bring it closer to its goals, based on whether it helps or hinders other robots. Humans watched video clips of the robots interacting, and most of the time the model agreed with what they thought about the social interactions that were occurring in each frame.

Full Article

'Surgery Selfies' Could Spot Infections Early
University of Edinburgh (U.K.)
November 18, 2021

Patient-captured smartphone photos of post-surgical wounds can help identify infections early, according to a study by researchers at the U.K.'s University of Edinburgh. A randomized clinical trial involving 492 emergency abdominal surgery patients had one patient cohort answer questions and take selfies of their wounds at various times after surgery, which clinicians inspected for signs of infection; a second cohort received routine care. The smartphone group was almost four times as likely to have their wound infection diagnosed within a week of surgery, compared to the routine care group. They also had fewer general practitioner visits and a more positive experience accessing post-operative care.

Full Article

Researchers Develop Device to Detect Opioid Overdose, Inject Antidote
GeekWire
Charlotte Schubert
November 22, 2021

A prototype wearable device developed by researchers at the University of Washington (UW) can detect opioid overdoses and inject naloxone to reverse them. The device, worn on the abdomen, uses sensors to identify changes in body movement and respiration. The device features a processor to analyze that data, detect whether the wearer has stopped breathing, and administer the life-saving injection of naloxone. Said UW’s Shyamnath Gollakota of the device, “We are hopeful it can have a tangible impact on a big source of suffering in this country.”

Full Article

Automated Texting System Saved Lives During First COVID Surge
Penn Medicine News
November 15, 2021

An automated text messaging system developed by the University of Pennsylvania's Penn Medicine research center saved two lives weekly during the initial COVID-19 surge. The COVID Watch system monitors outpatients using automated texts and refers those with concerning conditions to healthcare providers. The system uses algorithmically directed text conversations to evaluate patient conditions, sending patients twice-daily routine questions; if responses suggest increasing distress, the system sends follow-up questions for possible elevation to the health team to check in and recommend hospitalization, if warranted. Almost 20,000 patients have enrolled in COVID Watch since its launch, and the researchers said those in the program were 68% less likely to die from COVID-19 than non-enrollees.

Full Article