In an interdisciplinary effort, a University of Iowa engineering professor and a social work professor are creating software that leverages artificial intelligence to detect violent behavior, aiming to improve intervention strategies .

The technology works like an advanced nanny cam designed to detect physical abuse using artificial intelligence. The device remains dormant until it detects potential abuse, after which it activates to record the incident and sends the footage to the caregiver, who can then choose to forward it to authorities if necessary.

Karim Abdel-Malek, a professor of mechanical engineering at the UI, said the idea for the technology came from his work as director of the UI’s Virtual Soldier Research Program, which develops models predictive tools to analyze body movements and interactions in virtual environments for military applications.

“That led us to the idea that if we could use it for soldiers, why not use it for other things?” » said Abdel Malek.

Abdel-Malek and a team of UI researchers patented the technology in 2020, at which point Abdel-Malek said he wanted to collaborate with an expert in child abuse. He envisions early applications of this technology in settings like day care, child care and elder care, where cases of abuse can often go unnoticed and unreported.

He contacted three UI faculty members in the social work field and said Aislinn Conrad was the first to respond.

“I got a cold call from Karim last September, and he didn’t even tell me what it was about,” Conrad said. “But I just knew, I just had this feeling, it was going to be a big deal.”

Prior to her UI appointment, Conrad worked as a child welfare and foster care reentry investigator. She later earned a Ph.D. and a master’s degree in social work to further specialize in child welfare.

“I decided to dedicate my life as a researcher to the prevention of child abuse because, unfortunately, in society, violence seems to be a very intractable problem,” Conrad said, noting that one in nine children will be victim of abuse or neglect before the age of 17, and that one in nine children will be victims of abuse or neglect. one in three women will be victims of violence during their lifetime.

“And that doesn’t even take into account the elderly, who can experience horrific acts of violence at the hands of caregivers,” Conrad said.

She believes this technology will be a transformative way to overcome the challenge of collecting evidence during retrospective investigations of reported incidents of abuse.

In Iowa, the Department of Health and Human Services evaluated 26,613 reports of child abuse in 2023. Of those, 70% — or more than 18,000 children — resulted in an “unconfirmed” result. “, indicating that there was not enough evidence to support the abuse. allegations.

“It’s a game changer,” Conrad said. “This will significantly change the paradigm of our response to violence. »

Abdel-Malek added that this technology aims to identify abuse before it escalates and causes visible signs.

“The idea here would be before or just before,” Abdel-Malek said. “Then right away you can intervene.”

Conrad emphasized the importance of this technology for child victims of abuse, as they often cannot express their experiences or understand the need to report them.

She added that this would create the opportunity to proactively protect children and correct course with
the attacker.

“Sometimes it’s a lack of emotional regulation. It’s a lack of understanding that the behavior is not acceptable,” Conrad said. “It’s going to change the landscape in many ways for everyone.”

Abdel-Malek said UI students will play an important role in the continued development of this technology.

“We’re going to need actors to replicate different behaviors on mannequins,” Abdel-Malek said, explaining how the AI ​​will be trained.

He emphasized that the technology’s effectiveness depends on collecting data from people of varying heights, weights, hairstyles and clothing, allowing it to accurately recognize a wide range of abusive actions.