Welcome to the December 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.

Parkinson's Patient Walks 6 Kilometers After Spinal Implant
The Guardian (U.K.)
Hannah Devlin
November 6, 2023

A patient with severe mobility issues due to advanced Parkinson’s disease received a spinal implant at Switzerland's Lausanne University Hospital that, he said, allowed him to walk as much as six kilometers (3.7 miles) at a time. Before receiving the implant, he could not walk without falling. The process involved creating a personalized anatomical map of the patient's spinal cord to pinpoint the precise locations the implant would target to activate his leg muscles, and implanting electrodes in those locations. Movement sensors on each leg automatically switch the implant on when the patient begins walking. Lausanne University Hospital's Jocelyne Block said, "It is impressive to see how by electrically stimulating the spinal cord in a targeted manner, in the same way as we have done with paraplegic patients, we can correct walking disorders caused by Parkinson's disease."

Full Article

Wearables Capture Body Sounds to Monitor Health
Northwestern Now
Amanda Morris
November 16, 2023

Northwestern University researchers developed wearable devices that continuously track the different sounds the body makes through its various processes. Each device contains a flash memory drive, battery, electronic components, Bluetooth capabilities, and two microphones, one facing toward the body and another facing outward. By capturing sounds in both directions, an algorithm can differentiate external sounds and internal body sounds. Capturing sounds from variously-placed devices simultaneously and correlating those sounds to body processes, the devices spatially map how air flows into, through, and out of the lungs; how cardiac rhythm changes in resting and active states; and how food, gas, and fluids move through the intestines. In testing on 15 premature babies with respiratory and intestinal motility disorders and 55 adults, including 20 with chronic lung diseases, the devices performed with clinical-grade accuracy and offered new functionalities.

Full Article

Passwords Can Be Stolen in VR from Avatar Hand Motions
New Scientist
Jeremy Hsu
November 14, 2023

Haitao Zheng at the University of Chicago and colleagues demonstrated that someone typing on a physical keyboard while in a virtual reality (VR) room could end up leaking sensitive information, including passwords, to an attacker who uses artificial intelligence (AI) to interpret the avatar’s hand motions. The team demonstrated several keyboard inference attacks, including some that accessed data from the target person’s VR headset that were trained to recognize keystroke motions, identify individual fingertips that are pressing a key, and then predict the keys being typed. The researchers trained AIs in Meta Horizon Workrooms during brief typing sessions. Said Zheng, “You don’t even need to know the person. As long as you can get into the same VR room with them, they’re done."

Full Article

Noise-Cancelling Headphone Technology Lets Wearers Pick the Sounds They Hear
UW News
Stefan Milne
November 9, 2023

Deep-learning algorithms developed by a team led by University of Washington (UW) researchers aim to improve noise-cancelling headphones by allowing users to make real-time adjustments to which sounds filter through them. The "semantic hearing" system allows the user to choose the desired sounds from 20 classes, including sirens, baby cries, speech, vacuum cleaners, and bird chirps, via voice commands or smartphone app. Said UW's Shyam Gollakota, "Understanding what a bird sounds like and extracting it from all other sounds in an environment requires real-time intelligence that today's noise canceling headphones haven't achieved. The challenge is that the sounds headphone wearers hear need to sync with their visual senses.” As a result, sounds are processed on the connected smartphone, rather than cloud servers.

Full Article

Microsoft Offers AI-Powered Customer Service for Blind Users
Bloomberg
Jackie Davalos
November 15, 2023

Microsoft and Be My Eyes, an app for blind and low-vision people, are partnering to make it easier for the visually impaired to access the tech giant’s customer service. Microsoft will integrate Be My AI, which uses OpenAI’s ChatGPT-4 large language model to generate a description of a photo the person has taken, into its Microsoft Disability Answer Desk, allowing users of Microsoft products to resolve hardware issues or navigate such tasks as installing a new version of Windows software without human assistance. Be My Eyes, which tested the tool with Microsoft users earlier this year, found that just 10% of people interacting with the system chose to escalate to a human agent. The company also said inquiries were resolved faster with the Be My AI tool, with users spending four minutes, on average, on a call with the AI, versus 12 minutes with a human.

Full Article

Robotic System Assesses Mobility After Stroke
USC Viterbi School of Engineering
Caitlin Dawson
November 15, 2023

A robotic tool developed by a team of computer science and biokinesiology experts from the University of Southern California could help clinicians accurately track the recovery progress of stroke survivors. Using a robotic arm to track three-dimensional spatial information and machine learning techniques to process the data, the tool generates an “arm nonuse” metric to help clinicians assess a patient’s rehabilitation progress. A socially assistive robot provides instructions and encouragement throughout the process. Said USC's Maja Mataric, "This work brings together quantitative user-performance data collected using a robot arm, while also motivating the user to provide a representative performance thanks."

Full Article

Zoom Fatigue is Real, According to Brain Scans
IEEE Spectrum
Charles Q. Choi
November 21, 2023

A study by Austrian researchers confirms the "Zoom fatigue" phenomenon, finding that videoconferences are more mentally exhausting than face-to-face meetings. The study involved university students who participated in 50-minute lectures that were held both in-person and virtually. Participants' brain and heart activity was measured via electroencephalography and electrocardiography, and they answered questionnaires about fatigue and mood. The study revealed that those taking part in the virtual lectures showed more signs of fatigue, sadness, drowsiness, negative feelings, and less attention and engagement than those who attended in-person, particularly after 50 minutes of videoconferencing. The researchers recommended breaks after 30 minutes of videoconferencing, the use of "speaker view" for more continuous eye contact, and the development of virtual meeting platforms that replicate the nuanced nonverbal cues that occur in face-to-face communication.

Full Article

App Detects Worsening Heart Failure Based on Changes in Patients’ Voices
American Heart Association
November 13, 2023

A smartphone app using artificial intelligence (AI) to detect changes in the voice of a person with heart failure predicted more than 75% of hospitalizations about three weeks before they happened. The app was designed to detect changes in speech measures in patients over time, which could indicate early increases of lung fluid, a sign of progressing heart failure. In a study of 416 adults diagnosed with heart failure, participants recorded five sentences in their native language into the phone app daily. In a training phase of the study, distinct speech measures from 263 participants were used to develop the AI algorithm. The algorithm was then used on the remaining participants to validate the tool’s effectiveness. “Speech analysis is novel technology that may be a useful tool in remote monitoring of heart failure patients, providing early warning of worsening heart failure that frequently results in hospitalization,” said Dr. William T. Abraham of The Ohio State University Wexner Medical Center.

Full Article

Purdue IoT Software Platform Uses Gaming to Motivate Energy-Efficient Behaviors in Residential Communities
Purdue University Research Foundation News
November 29, 2023

Purdue University researchers developed an Internet of Things (IoT) system that incentivizes residential users to engage in energy-efficient behaviors through gaming. The MySmartE system offers smart thermostat functionality similar to a smart tablet with a voice assistant, social games that increase awareness of energy-efficient practices, an algorithm that provides personalized actionable recommendations, and energy conservation behavior scores. The cloud-based software platform, installed on user-interactive smart devices, aims to address the incorrect usage of smart thermostats due to usability issues, which reduce resident motivation. Purdue's Panagiota Karava said, "Engagement is further accelerated by an intuitive user interface for efficient thermostat control and modularized software infrastructure. The infrastructure is scalable and flexible to support multiple deployments across diverse housing stock, population demographics, and energy programs."

Full Article

Ingestible Electronic Device Detects Breathing Depression in Patients
MIT News
Anne Trafton
November 17, 2023

An ingestible capsule developed by researchers at the Massachusetts Institute of Technology (MIT), West Virginia University, and Massachusetts-based Celero Systems could provide a less-intrusive method for diagnosing sleep apnea and other sleep disorders. It also could be used to detect respiratory changes associated with opioid overdoses or conditions like asthma or chronic obstructive pulmonary disease. The multivitamin-sized capsule, which passes through the digestive tract without causing any damage, measures the user's breathing and heart rates via an accelerometer. Two small batteries and a wireless antenna are used to send the data it collects to a laptop or other external device. Said MIT's Giovanni Traverso, "What we were able to show is that using the capsule, we could capture data that matched what the traditional transdermal sensors would capture. We also observed that the capsule could detect apnea, and that was confirmed with standard monitoring systems that are available in the sleep lab."

Full Article

What if Alexa or Siri Sounded More like You?
PennState News
Francisco Tutella
November 21, 2023

A team led by Pennsylvania State University (Penn State) researchers found that matching user profiles and the voice profiles of virtual assistants (VAs) like Siri and Alexa makes the VAs appear more trustworthy to users and, counterintuitively, can even encourage them to resist misinformation. The researchers randomly assigned a VA to 401 participants who self-reported their levels of extroversion. After the voice assistants gave a brief introduction, the participants rated the VAs on their attractiveness and service quality. They were then played audio clips of the VAs responding to questions about the COVID-19 pandemic with misinformation about the virus. "According to our data, when participants were assigned a voice assistant that had a personality similar to their own, they showed this effect of resistance to persuasion,” said Penn State's S. Shyam Sundar. “It suggests that when you hear information from a voice assistant that is similar to yourself, you are likely to process the message more carefully."

Full Article

Digital Camera, Algorithm Detect Facial Palsy
University of South Australia
November 30, 2023

Computer scientists from the Middle Technical University in Iraq and the University of South Australia developed a diagnostic tool that uses artificial intelligence (AI) and a digital camera to detect facial palsy with 98% accuracy. The real-time detection system uses a microcomputer, digital camera, and a deep learning algorithm. Using a dataset of 26,000 images, containing 19,000 normal images and 1,600 images of patients with facial palsy, researchers employed AI techniques to train computer vision systems to recognize the condition. They then captured images of patients with different degrees of facial palsy, and used the tool to detect the condition in real time.

Full Article

System Makes Human-to-Robot Communication More Seamless
News from Brown
November 6, 2023

Brown University researchers developed software based on artificial intelligence-powered large language models that enables navigation robots to understand complex, expansive directions in English without needing thousands of hours of training. The software, Lang2LTL, breaks down instructions and requires only a detailed map of the environment to allow the robot to understand how to move from point A to point B while avoiding a particular area or stopping at another location first. The researchers found Lang2LTL had an accuracy rate of 80% in simulations in 21 cities using OpenStreetMap. It also was tested using a Boston Dynamics Spot robot. Said Brown's Stefanie Tellex, "This has applications for mobile robots moving through our cities, whether a drone, a self-driving car, or a ground vehicle delivering packages. Anytime you need to talk to a robot and tell it to do stuff, you would be able to do that and give it very rich, detailed, precise instructions."

Full Article

Wearable Device to Perform Balance Exercises at Home
Tokyo University of Science (Japan)
November 27, 2023

A wearable balance exercise device (WBED) developed by researchers at Japan's Tokyo University of Science (TUS) aims to train older adults to improve their postures. The portable, lightweight device can improve reactive postural control by generating forces that pull the user sideways in a certain direction. It uses a computer program or smartphone app to regulate the air pressure in two pneumatic artificial muscles that are worn over the shoulder. In tests of healthy adult males who performed the same exercises, either with or without unexpected perturbation via the device, the researchers found those in the WBED group exhibited lower displacement and peak velocity post-exercise.

Full Article