Welcome to the October 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.

Implant Helps Paralyzed Man Use His Arms Again
Silicon Republic
Vish Gain
September 28, 2023

Neurosurgeons at Switzerland's Centre Hospitalier Universitaire Vaudois (University Hospital of Lausanne) used a brain-computer interface coupled with a spinal cord simulator implant to restore upper arm function in a patient paralyzed by a spinal cord injury. The same technology was used earlier this year to help a paralyzed patient stand and walk. Said University Hospital of Lausanne's Jocelyne Bloch, "These devices decode the electrical signals generated by the brain when we think about walking.” Bloch added, “We are now working with the patient to use this cutting-edge innovation to recover movement of his arms, hands and fingers.”

Full Article

AI-Driven Tool Makes It Easy to Personalize 3D-Printable Models
MIT News
Adam Zewe
September 15, 2023

A generative artificial intelligence (AI)-driven tool developed by researchers at the Massachusetts Institute of Technology and Northeastern University allows the addition of custom-design elements to user-generated three-dimensional (3D)-printable models. The Style2Fab tool uses machine learning to profile model topology and monitor the frequency of geometric changes where two planes connect, then partitions models into a specific number of segments. Style2Fab relates those segments to a dataset containing 294 models of 3D objects, with each model's segments annotated as functional or aesthetic; closely matching segments receive functional labels. Users then input natural language prompts describing desired design elements, with a 3D model meeting those criteria composed by an AI system called Text2Mesh.

Full Article

How to Make It Easier for Consumers to Control the Ads They See Online
The Wall Street Journal
Suman Bhattacharyya
September 26, 2023

A study by researchers at the University of Michigan and Carnegie Mellon University found that social media users would accept busier interfaces if they were given more control over the use of their personal data for ads. The study, which focused on Facebook, determined that users typically had to move through three pages and make at least five clicks to locate most privacy-related ad controls. The researchers tested design changes that added two pathways in the desktop version of Facebook via Google Chrome extensions, with one menu allowing direct access to ad settings through the ads themselves and another located at the top of the content feed. During the study, 110 participants were asked to perform three tasks that involved locating the ad settings; more participants were able to complete the tasks when the settings were made more visible.

Full Article

'Garbatrage' Spins E-Waste into Prototyping Gold
Cornell Chronicle
Louis DiPietro
September 14, 2023

Cornell University's Ilan Mandel and Wendy Ju unveiled the "garbatrage" prototyping framework for repurposing electronic waste into useful material. Building on work in human-computer interaction that aims to incorporate sustainability and reuse into the field, the researchers presented hoverboards—hands-free, motorized scooters that enjoyed brief popularity around 2016—as a test case for garbatrage's economic viability. The team sourced wheels and motors from old hoverboards to build what would become a fleet of trash robots in New York City. Mandel and Ju believe now is an opportune time for the practice, given the push for sustainability, and the global supply shortages and international trade issues of the last few years. Said Mandel, "What is often deemed as garbage can be full of value and can be made useful if you are willing to do some bridge work."

Full Article

How FC Copenhagen Uses VR to Boost Players' Brains
Forbes
Steve Price
September 18, 2023

Soccer clubs in Europe are using Norwegian virtual reality (VR) training company Be Your Best's platform to improve players' cognitive functions. Be Your Best's Andreas Olsen said the company's software uses a VR headset to provide "the most realistic VR experience in the VR simulation of a football game as I know it today in the world." Users can practice with artificial intelligence-driven players or watch the finest players in duplications of Champions League and Premier League matches. Be Your Best has partnered with Danish club FC Copenhagen to improve the technology, with the club using the platform to evaluate youth players' scanning, pattern recognition, working memory, and decision-making functions. FC Copenhagen's Sune Smith-Nielsen said this helps the club identify incipient weaknesses that hopefully can be addressed before players enter the Champions League.

Full Article

Glucose Data Reveals Seasonal Patterns in Diabetes Care
Dartmouth College
Harini Barath
September 25, 2023

Researchers at Dartmouth College found diabetics' blood sugar levels tend to be healthier from April through September. The researchers analyzed more than 91,000 days of wearable glucose monitor data from 137 individuals aged two to 76 who mainly had type 1 (juvenile) diabetes. Patients' glucose levels stayed within the healthy range through a larger portion of the day than average during warm months characterized by higher activity levels. The researchers also observed less than average time spent within this range in colder months from October through February, while levels went outside the desired target occurred more frequently during holidays. “There are a lot of questions around how to personalize (diabetes) management,” said Dartmouth’s Temiloluwa Prioleau, "and learning from each individual’s unique data can set the course towards delivering the best possible outcome for them."

Full Article

Japanese City to Use Robots to Tackle Rise in Truancy
The Guardian (U.K.)
Justin McCurry
September 6, 2023

Schools in Kumamoto, Japan, have procured two robots that they hope will address increasing truancy by encouraging absentee children to attend classes remotely, and eventually to return to the classroom. The Mainichi Shimbun newspaper said the microphone-, speaker-, and camera-equipped robots should start appearing in classrooms in November. Remote-learning students will be linked to the tablet-outfitted robots through their laptops so they can "attend" the same lessons as their classmates and participate in discussions, the Mainichi added. A member of Kumamoto's board of education said, "Aside from letting them view the classes, the robots allow students to move freely in the classroom space and communicate with their classmates."

Full Article

CMU Sensor Objectively Measures Scratching Intensity
Carnegie Mellon University School of Computer Science
Byron Spice
September 19, 2023

Carnegie Mellon University researchers have developed a wearable device that aims to help patients with conditions that cause chronic itching by measuring the intensity of their scratching. The ring-like device is worn on a finger and uses an accelerometer in conjunction with a contact microphone to detect high-frequency vibrations associated with scratching by that finger. The researchers also developed a machine learning algorithm that converts scratch intensity measured in milliwatts to a 0-10 scale for use by physicians. University of Pittsburgh School of Medicine's Sonal Choudhary, a dermatologist and study co-author, said the device could help researchers test new drugs to determine whether they reduce itching.

Full Article

Wearable Technology Shows Promise in Early Detection of COVID-19 Among FSU Athletes
Florida State University News
Patty Cox
September 6, 2023

A study of female student-athletes by Florida State University (FSU) researchers found that wearable technology enabled early detection of COVID-19. The study monitored 113 female student-athletes equipped with WHOOP bands for 10 months; 33 of them ultimately tested positive for COVID-19. WHOOP bands measure the wearer's heartbeat, breathing, and sleep using optical sensors; the data is used to determine strain and recovery. The researchers found a WHOOP-wearer's respiratory rate rose three days prior to testing positive for COVID-19. However, changes in resting heart rate and heart rate variability were not observable until one day prior to the positive test, and changes in recovery did not occur until the day of the positive test.

Full Article

How Stressed Are You at Work? Ask Your Mouse
The Wall Street Journal
Suman Bhattacharyya
September 10, 2023

A study of machine learning models by researchers at Switzerland's ETH Zurich found models analyzing keyboard-typing activity and mouse movements to determine users’ stress levels were more accurate than a model based on heart-rate data. In the study of 90 students performing work-related tasks in a simulated office environment, the students were divided into a control group that handled only assigned tasks, a second group that handled questions from managers and assigned tasks, and a third group that performed the same tasks as the other groups but also were interrupted with questions via online chat. The researchers observed that workers who rated themselves as stressed made longer, less-accurate mouse movements and more typing errors, while those reporting lower stress levels made shorter, more direct mouse movements.

Full Article

Robotic Driving Seat Helping to Improve Safety of Automated Vehicles
University College London News (U.K.)
September 7, 2023

Scientists at the U.K.'s University College London (UCL) have created a robotic driving seat that tells drivers in highly automated/self-driving vehicles when they must take the wheel. The researchers developed a driving simulator that records drivers' eye movements and measures brain activity to assess their situational awareness, informing the car whether they can safely take over. The seat can communicate with drivers through touch by pressurizing embedded robotic structures to gently "nudge" them to increase their situational awareness. UCL's Bani Anvari said he hopes "to enable humans to trust and fully exploit the benefits of highly automated and autonomous vehicles in the future" through technology like the robotic seat.

Full Article

Online AI-Based Test for Parkinson's Disease Severity Shows Promising Results
University of Rochester News Center
Luke Auburn
September 6, 2023

An artificial intelligence (AI) tool developed by scientists at the University of Rochester can help remotely evaluate the severity of symptoms experienced by Parkinson's disease patients in minutes. The tool can assess the motor performance of patients when they tap their fingers 10 times before a Webcam. The AI model bases its evaluation on Movement Disorder Society-Unified Parkinson's Disease Rating Scale (UPDRS) guidelines, automatically producing computational metrics like speed, amplitude, frequency, and period for categorizing tremor severity. The researchers had 250 Parkinson's patients perform the finger-tapping task and compared the model's ratings with those of three neurologists and three UPDRS-certified primary care physicians. The neurologists slightly outperformed the model, which outperformed the physicians.

Full Article