"Emotion Sensors" Evoke Emotional Response

E-mail Barbara Goode

Recent news has reported several developments in sensors that detect and report human emotional responses. The applications are varied and intriguing—and do a good job of evoking emotional response themselves.

Autism Assistance and More
Some "emotion sensor" systems are based on image recognition technology. New Scientist magazine reports that researchers at MIT are developing a system to help people with autism—who tend to find personal interaction challenging—understand when their conversation partner is becoming disinterested. The setup consists of a camera mounted on a pair of glasses linked to a handheld computer whose image recognition software is designed to decode emotions. "Previous research by the team has shown the device could detect if someone was agreeing, disagreeing, concentrating, thinking, unsure or interested from just a few seconds of film," the report says.

Development has a ways to go on many fronts, including accuracy and practical use, but Professor Simon Baron Cohen of the Autism Research Centre in Cambridge says, "It is a very clever application as a prosthetic device." And the applications extend beyond assistance for people with autism. "I would love it if you could have a computer looking at each student in the room to tell me when 20% of them were bored or confused," says Timothy Bickmore of Northeastern University.

Along similar lines, Engadget.com reports that researchers at the University of Illinois have invented "shrug-detecting" software to recognize the subtle movements that indicate confusion or disinterest. "Future iterations of the technology could be used to detect blinking, hand movements, facial expressions, and other mood indicators," the story says.

Another Technology, Another App
Different technologies and applications come into play in a system developed by Delsys Inc. This company uses precision surface electromyography (EMG) equipment and physiological sensors, and in an experiment with Boston Symphony Orchestra performance, the technology provided "a detailed, high-resolution image of muscle activations of a live human performer in the intense process of making music," according to Dr. Teresa M. Nakra of Immersion Music, who coordinated the project.

"The sensors are designed to measure a person's physical performance and response to emotions. They specifically monitor muscle tension, body movements, heart beats, and other physiological evidence of emotion," explains Professor Carlo De Luca, who is the director of the Neuromuscular Research Center at Boston University as well as president and CEO of Delsys. "By conducting this experiment we can use the gathered information to see how the dynamics of the conductor affects the richness and tonality and emotional character of the music. By placing sensors on the audience, it would be possible to also monitor their emotional response."

The Biggest Question
The intriguing application of sensor-and-software systems to read and interpret human emotional response prompts many questions, the largest of which is what to do with the information once it's gathered. Do we have the skill to use the information effectively and humanely? I doubt it, though hopefully these developments will help drive efforts on that front. I do agree with Sara Paddison, author of The Hidden Power of the Heart, who says, "The emotional frontier is truly the next frontier to conquer in human understanding." Perhaps we should start by applying the sensors to ourselves.

In the meantime there will be a high barrier to acceptance, as indicated in the Engadget report. The development is, it says, "another blundering step towards empowering our future robotic overlords with the ability to recognize when we're being insolent."

Suggested Articles

Revenues overall hit $3.82 billion, up 1% from third quarter of 2019, as auto plants reopened and personal electronics revenues grew

MIT Sloan and Boston Consulting Group call for expanding organizational learning to gain better financial rewards of AI deployments

Originally a 1960s memory manufacturer, Intel wants out of NAND following the market decline in 2018