Welcome to the May 2019 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.

The ACM Special Interest Group on Computer Human Interaction (SIGCHI) is in the midst of its annual flagship conference, the ACM Conference on Human Factors in Computing Systems (CHI 2019), in Glasgow, U.K. The conference, which began on Saturday, May 4, runs through Thursday, May 9. "CHI offers a unique look into the inspiring visions of future technologies," said Stephen Brewster, CHI 2019 Co-chair. "This year, we are proud to host the conference in the U.K. for the first time ever. We are also excited to continue the commitment to make CHI, and CHI content, more widely accessible, including livestreaming most paper sessions. As the premier international conference celebrating HCI innovation and exploring its tremendous potential, CHI 2019 promises to reflect the myriad ways these technologies are changing the ways in which we live and work."

Data Privacy Research Front and Center at Human Computer Interaction Event
University of Michigan
Laurel Thomas
April 30, 2019

Researchers at the University of Michigan are presenting several projects at the ongoing ACM CHI Conference on Human Factors in Computing Systems in Glasgow, Scotland. The studies being presented include examinations of the shortcomings of security breach notifications, best practices for phishing warnings, and lessons learned from the use of analytics to improve student performance. In one study, researchers found that 97% of 161 sampled security breach notifications were difficult or fairly difficult to read based on readability metrics, and that the language used in them may have contributed to confusion about whether a recipient of the communication was at risk and should take action. In a separate study, researchers found that when compared with banner warnings, link-focused phishing warnings reduced the chance of participants clicking through to a phishing link; forced attention warnings were the most effective. A third study showed that students want more input into how their data is processed and used with learning analytics; students also want a say in what happens to their data.

Full Article

Better Email Automation
MIT News
Rachel Gordon
April 29, 2019

Researchers at the Massachusetts Institute of Technology's Computer Science and Artificial Intelligence Laboratory (CSAIL) have developed a tool that lets users write more specific filter rules for incoming emails. The YouPS tool allows users to craft fine-grained email filter rules by adding multiple editor tabs related to an independent email mode. Users also can write distinct rules for each mode, to ensure their inbox follows different behavioral patterns based on the current mode. Said CSAIL’s Soya Park, “Managing our inboxes in a such fine-grained manner with something like YouPS could eventually help give non-programmers the tools to manage their emails, and help save time for more intensive tasks or work.”

Full Article

Assistive Robot Learns to Feed
National Institute of Biomedical Imaging and Bioengineering
Thomas M. Johnson
April 10, 2019

Researchers at the University of Washington (UW) have developed a robot that can autonomously pick up food with a fork and gently deliver it to a person's mouth. The researchers used data on the different strategies people use to eat different foods to program the Assistive Dexterous Arm (ADA) robot to identify each item on a plate accurately, and then perform the optimal movements that result in successfully skewering each item and delivering it to a person's mouth. Said UW researcher Siddhartha Srinivasa, "We see ADA as a win-win for caregivers and their clients that will ultimately improve the experience for everyone involved—especially as the country's population ages and the need to optimize strategies for their care increases." A study detailing the development of ADA received the Best Tech Paper Award at the joint ACM/IEEE International Conference on Human Robot Interaction in March.

Full Article

Microsoft Equips Veterans in Rehab with Accessible Xbox Controllers
GeekWire
James Thorne
April 30, 2019

Microsoft has provided patients at 22 Veterans Affairs (VA) rehabilitation centers with Xbox Adaptive Controllers for players with disabilities, to provide them a social outlet that is also therapeutic and can help with rehabilitation. The controllers are equipped with two large programmable buttons, allowing gamers to build their own custom setups and add devices like buttons and joysticks to fit their needs. The controller works with Xbox One and Windows 10 PC games. Microsoft is using its partnership with the VA to gather data and improve the device going forward. Said Dr. Leif Nelson, director of national veterans sports programs and special events for the VA, "Gaming is now everywhere in the world, and while people tend to think of it as isolating, we're finding that it actually has the opposite effect and can increase interactions with other veterans and folks who are non-veterans."

Full Article

Scientists Have Found a Way to Translate Thoughts Into Computer-Generated Speech
CNBC
Chloe Taylor
April 25, 2019

Researchers from the University of California, San Francisco have designed a computer simulation that turns brain signals into a virtual voice. According to a study published in Nature, the device uses a brain-computer interface (BCI) that determines a person's speech intentions by matching brain signals to physical movements that are typically activated in a person's vocal tract; the data is then translated by a computer into spoken words. Previous BCI systems for speech facilitation have focused on typing, generally allowing people to type a maximum of 10 words per minute; the average speaking speed is around 150 words per minute. As many as 69% of the words generated by the new model were accurately identified by people asked to transcribe the computer's voice. Researchers believe the system could eventually reproduce the "musicality" of the human voice that conveys a speaker's emotions and personality.

Full Article

New Research Uses Search Data to Understand Public Health Needs
Forbes
Jessica Baron
April 24, 2019

Researchers from Cornell University, the State University of New York at Stony Brook, Microsoft Research, and the Rockefeller Foundation Fellowship have used search data to better understand public health needs. The researchers explored public health on the African continent using online searches, investigating whether such data can be used to understand what citizens want to know about diseases, but are afraid to ask health professionals directly. The team collected common search themes and topics from Bing search data, then cataloged how people searched for data on disease symptoms, drugs, and breastfeeding issues, as well as information that might have been difficult to gather from surveys. The team employed a statistical model that derived sets of semantically related words from online searches, and from this identified common topics. The researchers said the search engine data supplies insight into "people's real-time activities, experiences, concerns, and misconceptions relatively cheaply," especially in "data-sparse regions."

Full Article

Deep Learning-Powered Tool Creates Better Personalized Workout Recommendations From Fitness Tracking Data
Jacobs School of Engineering (UCSD)
Ioana Patringenaru
April 22, 2019

University of California, San Diego researchers have developed a recommendation tool that can better estimate runners' heart rates during a workout, and predict and recommend routes. The researchers trained the FitRec tool on a dataset of more than 250,000 records for more than 1,000 runners, and built a model that analyzed past performance to predict speed and heart rate, given future workout times and routes. FitRec also can identify important features that affect workout performance, like whether a route has hills and the user's level of fitness. The system can suggest alternate routes for runners who want to achieve a specific target heart rate, and make short-term predictions, like telling runners when to slow down to avoid exceeding their desired maximum heart rate. The researchers used a deep learning architecture called long short-term memory networks, which were adapted to capture the individual dynamic behaviors of each user in the dataset.

Full Article

The First Commercial Product Made Using Generative Design
Fast Company
Katharine Schwab
April 16, 2019

Furniture company Kartell this summer will begin retailing chairs co-designed by French designer Philippe Starck and a computer algorithm from the software company Autodesk. Starck worked with Autodesk's experimental generative design software platform to create a chair using a minimum of material, by incorporating his creative vision and the technical constraints of the injection molding process to the software. The software organically formulated hundreds of unique chair designs, from which Starck chose. The algorithm operates within mostly technical constraints, but the addition of aesthetic precepts to its repertoire could expand Autodesk's commercial potential. The company is developing an experimental algorithm that can emulate a particular firm's industrial design ethos, hoping to enable aesthetically pleasing computer-generated designs.

Full Article

Off-the-Shelf Smart Fabric Aids Athletes, Physical Therapy Patients
R&D Magazine
April 10, 2019

Researchers at Dartmouth College have developed a smart fabric that can help athletes and physical therapy patients correct arm angles to optimize their performance. The fabric-sensing system is a flexible, motion-capture textile that monitors joint rotation. The researchers focused on increasing the sensing capability and reliability of existing sensors, using low-cost, off-the-shelf fabrics without extra electrical components. The team used fabric made with nylon, elastic fiber, and yarns plated with a thin silver layer for conductivity. The system uses the stretchable fabrics to sense skin deformation and pressure fabrics to sense the pressure during joint motion. The system uses this information to determine the joint rotational angle through changes in resistance. Said Dartmouth’s Xia Zhou, "This study demonstrates the high level of performance and precision that can be acquired through basic, off-the-shelf fabrics."

Full Article

Movie Theaters Turn to 4D Technology, Haptic Vests to Draw New Audiences
Fox News
Benjamin Brown
April 4, 2019

Cinemas are investing in new technology to augment the film-going experience and attract new audiences with sensory enhancement. MediaMation's MX4D technology, for example, features full-motion cinema chairs that can blow wind and spray water in spectators' faces, paired with sensor-equipped haptic vests worn by audience members. Such innovations are seen by theater owners as essential to reversing shrinkage in attendance, which is being driven by increasingly sophisticated home entertainment alternatives. Hollywood Esports CEO Robert Laity is equipping Los Angeles' TCL Chinese Theater with 4D, hoping to exploit the burgeoning electronic-sports industry. Laity said, "Our theaters convert between movie mode showing motion special effects movies, IMAX 4D movies, over to e-sports mode in about an hour."

Full Article

Want to Check Out Frieze? All You Need Is an App and a Headset
The New York Times
Sophie Haigney
May 1, 2019

For the first time, Frieze New York—an eight-year-old art fair—will include a virtual reality (VR) component. This year, fairgoers will be able to go into a booth, put on a high-tech headset, and view works of art in VR. The system will also be available to viewers around the world via the free-to-download Acute Art app, which only requires a basic VR headset. The VR section of Frieze New York is called Electric and is curated by Daniel Birnbaum, a leader in the field of artistic production using VR. Birnbaum selected seven works—six in VR and one in augmented reality (AR)—for Frieze's inaugural exhibit in the medium. The AR work is an exploration of physical drawing. Two VR works are historically focused pieces done in collaboration with contemporary artists.

Full Article

Does Your Smartphone Know If You're Depressed?
The Wall Street Journal
Sumathi Reddy
April 2, 2019

Columbia University and University of Pittsburgh scientists are conducting a clinical trial in which they are monitoring adolescents at risk of suicide. Participants' smartphones will be tapped for content like selfies and voice recordings, words used on social media sites and in texts or emails, and information tracking their location. This data will be used to analyze facial features and tone, pitch, and cadence of speech using pre-established behavioral biomarkers. Researchers then hope to apply artificial intelligence to this data to determine suicide risk. In a separate study, researchers at the University of Pittsburgh are recording therapy sessions between depressed patients and therapists using high-resolution cameras and microphones. Data from the sessions, such as how often patients smile or mirror body language of the therapist, will be captured to generate an algorithm on patient-therapist interactions. Researchers will use the algorithm to compare different types of therapy and predict their effectiveness. Such technologies have great potential in mental healthcare, where evaluations are subjective and often based on patients' reports about themselves, but questions about privacy, cost, and implementation arise when the technologies move from the lab to the marketplace.

Full Article

Chernobyl Comes Back to Life in Ukrainian Computer Game
Reuters
Margaryta Chornokondratenko
April 29, 2019

A Ukrainian computer game in which participants explore the abandoned town of Prypyat near the site of the Chernobyl nuclear plant disaster 33 years ago has attracted 62,615 players since its October debut. Novices assume at first that they are in a virtual environment, when they actually are controlling a camera- and computer-equipped robot tank that navigates a model of Prypyat, which reproduces the smallest details of the original town, gleaned from Google maps and hundreds of images from the Chernobyl area. The tank camera transmits high-quality video signals in real time, so far-flung players experience the game without any time delay. The creators next want to devise a game featuring the colonization of Mars, in which players will be able to simultaneously control robots on different missions involved in an operation.

Full Article