In recent years, USC Viterbi School of Engineering professor Shrikanth S. Narayanan has worked on behavioral informatics, a new field aimed quantifying and interpreting human interaction and communication through the use of engineering and computing innovations.

In an address given in July at the IEEE International Conference on Multimedia and Expo, Narayanan spoke about his work, which includes the observation of children with autism spectrum disorders (ASD).

Narayanan opened his speech with a universally acknowledged understatement – “human behavior is exceedingly complex” – and moved on to note the new opportunities that advanced sensor and computing technology have opened up for a further understanding of that complexity.

Behavior analysis is central to psychology and associated disciplines, but its progress has been slow and sometimes subjective, according to Narayanan, who approaches the subject by “measuring and quantifying human behavior [as] a challenging engineering problem.”

Some work already has been done along those lines, including the monitoring of emotional responses.

Much more is possible, said Narayanan, who described his effort to bring other objective tools to bear in these areas as part of what he called “multimodal behavioral signal processing.”

The goal is to create “technology and algorithms for quantitatively and objectively understanding typical, atypical and distressed human behavior with a specific focus on communicative and social behavior.”

ASD is an area in which Narayanan and his collaborators have worked intensively for several years.

The behavioral manifestations of ASD can vary considerably, making diagnosis particularly challenging. “We are trying to investigate how technology can assist in and enhance this difficult, predominantly observation-based rating task by using engineering techniques and computational tools to analyze each child’s specific communication and social interaction patterns,” he said.

Early results are encouraging, with IT analysis of videotaped interactions yielding promising results.

Interactions among couples also has been studied by researchers. In the 2005 book Blink, Malcolm Gladwell described studies by University of Washington psychologist John Gottman, who found that after observation of a couple’s interaction during one hour, he could predict with 90 percent accuracy whether the individuals would be married 15 years later.

By analyzing recorded interactions, Narayanan and his team, in collaboration with colleagues in psychology, are finding ways to design new engineering techniques to support research and practice in this domain and other realms of mental health.