faculty research

New Technique Shedding Light on Body Language

A joint research team from the University of Cambridge and Dartmouth College has developed a system for using infrared light tags to monitor face-to-face interactions. The technique could lead to a more precise understanding of how individuals interact in social settings and can increase the effectiveness of communications coaching.

The system, named Protractor by the Cambridge-Dartmouth team, uses invisible light to record how people employ body language by measuring body angles and distances between individuals.

Prior studies have revealed that body language can influence many aspects of everyday life including job interviews, doctor-patient conversations and team projects. Each setting includes a specific set of interaction details such as eye contact and hand gestures for which an accurate monitoring of distance and relative orientation is crucial.

Body language is already commonly studied through video sessions, audio recordings and paper questionnaires. Compared to the new, light-based system, these approaches can require invasive cameras, necessitate complex infrastructure support, and impose high burdens on users.

Exploring Applications of Technology in Health and Wellness

Dartmouth News is running an article about George Boateng ’16, Thayer ’17, and how he is using his CS and engineering degrees to make a difference in education and health in the developing world.

From the article:

George Boateng ’16, Thayer ’17, arrived at Dartmouth in 2012 with an agenda. He had come 5,000 miles, seeking ways to make a difference in education and health in the developing world—in his native Ghana, in particular.

At Dartmouth, he gained hands-on experience in computer science and engineering in a place where his work had the potential to produce real-world applications. Boateng proceeded to blaze a trail marked by accolades for his research and recognition for his humanitarian accomplishments. Most recently, he won Dartmouth’s Martin Luther King Jr. Social Justice Award for Emerging Leadershipfor his work as co-founder and president of the nonprofit Nsesa Foundation.

Can Algorithms Accurately Predict Crime?

Julia Dressel ’17 and Professor Hany Farid caution that the computer algorithms may be no more accurate at predicting recidivism than people with no criminal justice experience. “What we’ve shown should give the courts some pause,” Farid tells The Atlantic.

See the Science Advances article and The Atlantic article for more.

Prof. Hany Farid honored as a 2018 Fellow of the IEEE

Hany Farid has just been elected an IEEE Fellow “for seminal contributions to the field of photo-forensics and its application to fighting the exploitation of children around the globe.”

Hany is being recognized for his research in image analysis and digital forensics, a field he pioneered at Dartmouth. Among many other things, Hany has developed mathematical and computational techniques to determine whether images, videos, or audio recordings have been altered. A noteworthy application was Hany's forensic analysis that demonstrated the authenticity of a controversial photograph of Lee Harvey Oswald holding the alleged assassination rifle. Hany also helped develop a system to find and remove online images pertaining to child exploitation, and is developing a system to scrub the internet of extremist-related content.

“Hany’s research is both technically groundbreaking and incredibly impactful,” says Interim Provost David Kotz ’86, the Champion International Professor in the Department of Computer Science. “Congratulations to him. This is a great honor.”

Dartmouth to debut wearables that warn and wow at UIST 2017

A watch that works in multiple dimensions and a smart ring that provides calendar alerts are among the top technology Dartmouth College will bring to the 30th ACM User Interface Software and Technology Symposium (UIST 2017).

Other technology to be introduced by the Dartmouth team includes a thumb-tip recognition technique that optimizes interaction with computer applications.

The research projects, products of Dartmouth's human computer interface lab, have been chosen by UIST 2017 to feature alongside some of the world's most innovative technology.

"Understanding and improving how humans interact with computers are essential parts of technology development," said Xing-Dong Yang, assistant professor of computer science at Dartmouth. "We look forward to UIST as a unique opportunity to share ideas on innovation."

See details in EurekAlert.

Prof. Campbell wins 3 new grants for $13M on mobile sensing

During 2016-2017 Professor Andrew Campbell took leave from Dartmouth and joined Google and Verily (Google's life science startup) as a visiting research scientist working in the Android group in Mountain View on new wearables and at Verily in South San Francisco on mental health sensing. Now back at Dartmouth he is busy working on 3 new awards from NIH and IARPA with students in the DartNet lab.

The new projects include a collaboration between Dartmouth CS and the Tuck business school funded by IARPA to study collaboration in the workplace using mobile phones, wearables and specialized IOT devices. Another project funded by NIH between Dartmouth CS and UW is investigating auditory verbal hallucination using mobile phones. Finally, we are following 100 undergrads across their 4 years at Dartmouth College as part of another NIH funded project with PBS to study the stress and strain of undergraduate students.

Prof. David Kotz and Kobby Essien Win Prestigious SIGMOBILE Test-of-Time Award

David Kotz and Kobby Essien received mobile computing's most prestigious award for their technical paper:  "Analysis of a Campus-wide Wireless Network".

From the SIGMOBILE website:

This paper was the first to systematically demonstrate how to measure and understand a production-scale wireless network, which was previously considered an impenetrable black box. This led to an incredible amount of follow-on work, with the measurement methods and analysis mechanisms proposed in this paper still being used. This paper was also the spark for the creation of the CRAWDAD data repository, which has been of immense value to the wireless research community.

Check out the full story, including information about the other awardees at the SIGMOBILE ToT award website

You can find more information about this research project at Dartmouth's campus-wide wireless network research page.

Prof. Farid discusses online extremism on Science Friday

Listen here.

Back in the early 2000s, the internet had a problem with child pornography. For its part, the United States hadn’t anticipated the explosion of illegal images that had come online in the early days of the internet. Tracking these illegal activities became much more difficult, and removing all trace of the images from the World Wide Web seemed nearly impossible. So government officials turned to Silicon Valley for help.

Jessica Fan '17 wins CRA's Outstanding Undergraduate Researcher Honorable Mention

Congratulations to Jessica Fan '17, who received the Computing Research Association's (CRA) Outstanding Undergraduate Researcher Honorable Mention for PhD-granting institutions. This award program recognizes undergraduate students in North American universities who show outstanding research potential in an area of computing research.

Jessica Fan worked together with Professor Tom Cormen on the research paper:

Cormen, T. H. and Fan J. C., "Dense Gray Codes, or Easy Ways to Generate Cyclic and Non-Cyclic Gray Codes For the First n Whole Numbers," 54th Annual Allerton Conference on Communication, Control, and Computing, October 2016.

Wojciech Jarosz and team render sand, snow and salt

Be it sand, snow or a bowl of spices, rendering massive aggregations of granular materials is a challenge for animators. A new method developed by researchers from Disney Research, ETH Zurich and Dartmouth's very own Prof. Wojciech Jarosz, proposes a method to handle this problem with unprecedented accuracy and computational efficiency. The technique makes it possible to show fine detail - the varying shapes and colors of grains and glints of light - as well as the smoother appearance that characterizes granular materials when seen at a greater distance. Check out the animated results from the research paper:

Pages