Penn State, Ohio State team up for $1.8M construction worker safety research

To address the high level of injuries in the construction sector, Penn State University (Penn State) and Ohio State University (Ohio State) have been awarded a four-year, $1.8M grant from the National Science Foundation (NSF) to create an artificial intelligence-(AI)-based health monitoring system for construction worker safety. Photo courtesy

To address the high level of injuries in the construction sector, Penn State University (Penn State) and Ohio State University (Ohio State) have been awarded a four-year, $1.8M grant from the National Science Foundation (NSF) to create an artificial intelligence-(AI)-based health monitoring system for construction worker safety.

This system will be designed as a real-time, context-aware, holistic health monitoring tool—aiming to lower the rate of work injuries experienced in the construction industry. In 2020, there were more than 1,000 fatal work injuries reported, and in 2021, there were 169,200 nonfatal work injuries reported.

In an article on Penn State’s website, Houtan Jebelli, an assistant professor at the university, refers to the constrained ability of wearable sensors to combine multiple physiological signals in one place. For instance, headsets can only measure brain activity, and wristbands can only monitor cardiac activity.

“We want to design and fabricate a flexible wireless sensing device that can capture workers’ diverse physiological signals and biological markers to the stressors in the field and can be worn in a way that is non-invasive and non-disruptive to workers,” Jebelli says in a statement. “We also want to develop innovative machine learning algorithms and frameworks to infer meaningful cues from the elicited bodily responses for continuous and real-time assessment of workers’ holistic health conditions. Importantly, we must also maintain workers’ privacy.”

For the technical side, the research team will rely on a digital twin-assisted system, which can run simulations and generate forecasts. The system can maintain employee privacy as it will build digital health maps with information (not traceable to a single employee). Yet, the system will still provide health information, personalized for specific employees. An example is the system’s communication to employees to let them in on the room temperatures, to keep them away from being overheated.

“The goal is to integrate the crowdsensing of workers’ de-identified health measures and digital twin technology to generate a comprehensive health map of the construction workplace, so the safety managers get the aggregated health information of the job site,” says Jebelli. “To ensure workers’ privacy, managers will not be able to identify the specific worker who is exposed to, for example, high physical fatigue; but they could identify the locations at the job site where stress is highest, or where workers are most fatigued, and then better identify the hazards of their job site.”

The AI-based system will offer an added advantage—it will be able to use computationally efficient algorithms, which will enable navigating through the signal noise expected in a fast-paced and active environment such as a construction site, where there can be a lot of triggering activity signals.

image
Bookmark
ClosePlease login

Read the original article here

Responses

Login expired, please login and try again later.