Think back on the last two weeks: try to remember how you spent your time at home. How many hours did you watch television? How many times did you open the refrigerator, and what exactly did you eat? How much water did you use? And did you remember to take your vitamins? Out of context, these questions may seem trivial. But together, they create a comprehensive portrait of everyday activity. And that could lead to better indoor air quality and energy management, technologies that simplify–rather than complicate–everyday tasks, and advances in personalized home health care.
The only problem is that gathering this kind of mundane data is often difficult and tedious. But MIT’s PlaceLab aims to get around that problem by inviting volunteer test subjects to live in a sensor-rich apartment where researchers can monitor everything from how long they leave a window open to exactly what time they wake up. This information will make it easier for researchers not only to study everyday human behavior but also to develop better tools with which to do so.
The lab is a joint project between the MIT House_n Research Group in the department of architecture and Tiax, a product development and research firm in Cambridge. “Too often you have the idea in the academic realm or the small company, and you’ve got a customer-facing organization, and the research that makes it credible to go from here to there is often what’s missing,” says Roger Edwards, director of the biosystems group at Tiax. The PlaceLab research, funded by government grants as well as corporate sponsors, will help bridge that divide.
The PlaceLab is, by all outward appearances, a typical one-bedroom, Ikea-clad Cambridge apartment near Central Square. Volunteers spend 10 to 14 days living there as they would in their own homes. But behind the sleek cabinetry and wall panels are more than 350 sensors and dozens of cameras and microphones that can record every movement and activity of the apartment’s inhabitants. “It turns out that not much is known about continuous living habits of people,” says Kenan Sahin ‘63, PhD ‘69, CEO and founder of Tiax, who along with Kent Larson, MIT’s director of research in the PlaceLab, conceived of the idea nearly three years ago.
The Human Factor
One PlaceLab project is to develop an accurate but nonintrusive means of monitoring food intake–a tool that would be useful for health studies involving obesity or diet-related diseases. The traditional method of obtaining that information is through self-reporting surveys, which are notoriously inaccurate: it’s difficult for people to remember exactly what they ate and when, so they sometimes unintentionally misrepresent themselves. “There are also some things that are difficult to remember, and it’s much easier for technology to record,” says Tyson Lawrence ‘01, SM ‘03, Tiax’s PlaceLab manager.
As it turns out, monitoring what people eat in their homes is harder than anybody imagined. “We eat in so many circumstances,” says Edwards, and not always at the kitchen table. Currently, PlaceLab researchers monitor their subjects’ food consumption with cameras. But even a subject who does sit down to eat at the table will sometimes face away from the nearest camera. The researchers are now experimenting with different camera arrangements, and with ways to mount cameras directly on the subjects themselves.
But the purpose of the lab is not just to gather troves of information on people’s daily habits. Rather, it’s a way to examine how people interact with their home environments and to test new technologies in a real-life setting, outside the confines of a traditional lab. Another PlaceLab project is to develop a device that would help people adhere to complex medication schedules by giving them subtle but highly customized reminders throughout the day–such as flashing a light on the refrigerator when it’s time to take a certain medication with food. “People who have very few medications to take do really well with the simple reminders like a little box of pills,” says Edwards. “But there is a growing population of individuals who take four, five, and six medications over the counter, prescription, in combination, with food, without food–and those are the people who would benefit most from a PlaceLab-like situation.”
As the first fully instrumented live-in laboratory, the PlaceLab also allows researchers to examine questions of privacy and security. Though every volunteer has the option to cover up a camera or delete data at any time, researchers have found that after a few days, most volunteers get used to the cameras and sensors and forget they are being monitored.
Only a handful of studies have been conducted so far, but the potential for new research is great. “We tried to make the lab as capable as we could,” says Larson. “You can’t predict what an MIT student will want to do.” – By Mara E. Vatz
This new data poisoning tool lets artists fight back against generative AI
The tool, called Nightshade, messes up training data in ways that could cause serious damage to image-generating AI models.
Rogue superintelligence and merging with machines: Inside the mind of OpenAI’s chief scientist
An exclusive conversation with Ilya Sutskever on his fears for the future of AI and why they’ve made him change the focus of his life’s work.
The Biggest Questions: What is death?
New neuroscience is challenging our understanding of the dying process—bringing opportunities for the living.
Driving companywide efficiencies with AI
Advanced AI and ML capabilities revolutionize how administrative and operations tasks are done.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.