UNIVERSITY PARK, PA. – A team of researchers from Penn State Berks has developed a wearable device that can tell the difference between indoor and outdoor lighting. The team adds that the device could help scientists better understand the health benefits of outdoor lighting and, in the future, could lead to wearables that could encourage users to spend more time outdoors.
The researchers describe the wearable device in a recent issue of Hardware X. It contains sensors that can collect data about light sources, including wavelength and frequency data. They used a machine learning method known as an artificial neural network (ANN) to examine this data and determine whether the device was placed indoors or outdoors.
According to Matthew Rhudy, assistant professor of engineering, outdoor and indoor lighting have significant differences that sensors can detect. The sun emits large amounts of light in the ultraviolet spectrum, or UV light, he said. Interior lighting tends to be in the visible spectrum.
“We collected a lot of data with the sensor package,” said Rhudy. “We set up the sensors in different places and had data logged for about an hour in a wide variety of situations and under different lighting conditions. The UV index alone can tell it pretty well. If a significant UV index is found, there is a good chance you are outside. “
The light intensity, even when it is cloudy, and differences in color temperature are also signals of exposure to outdoor lighting. Current research suggests that exposure to natural light outdoors can have both psychological and physical health benefits, the researchers said. While scientists are currently studying these effects, they mainly rely on participants to record their own observations of when they are indoors or outdoors, which scientists refer to as self-reports.
According to the Penn State Berks team, self-reporting may not be as accurate as a wearable device that can accurately capture changes in lighting as well as exposure to the various light sources.
Initial tests of the device were performed by placing the device in fixed locations to collect light data for about an hour. Once the data was logged, the researchers used an ANN to classify the data as either indoor or outdoor lighting. To validate the device, the researchers placed the sensor package in a fixed location, indoors or outdoors, and collected data in different locations, at different times, and under different weather conditions. A total of 3640 indoor and 1368 outdoor samples were collected.
The Penn State Berks team used off-the-shelf equipment to develop a wearable device that could keep track of whether a person was exposed to indoor or outdoor lighting.
Interdisciplinary DIY approach
Rhudy said the team took a do-it-yourself approach to building the device, relying on readily available off-the-shelf components. The total cost was approximately $ 70 based on this approach, he added.
“I could see it could be made cheaper – especially if we could maybe work with an electronics company and mass-produce it,” he said.
The model is currently unable to transfer data, but future versions could be expanded to include wireless features such as Bluetooth.
According to Rhudy, the work would never have seen the light of day, so to speak, without Penn State Berks’ formal and informal support for interdisciplinary collaboration. Rhudy’s technical background needs to be complemented by the psychological and biomechanical expertise of his teammates, he said.
“These types of projects happen a lot on our campus,” said Rhudy. “When I started we had a group of new faculties – and there was already a group of faculty meetings – that formed a research group called the Human Movement Research Center, which is primarily a collaboration between kinesiology and engineering, but also has psychology members. The main idea is to study this human connection between mental health, physical health and the mechanics of the human body. ”
Rhudy, who in the past studied sensor and sensor design primarily for use in unmanned aircraft, added that these interdisciplinary connections can not only help fill knowledge gaps, but are also important for innovation itself.
“Just being in the same room with people from kinesiology and psychology and talking about the kind of work they do sparked ideas,” he said.
According to Rhudy, the next steps will be to investigate the possibilities of making this project a larger long-term project and raising additional outside funding.
Nathan Greenauer, Associate Professor of Psychology, and Catherine Mello, Assistant Professor of Psychology, worked with Rhudy.
The Institute for Computer and Data Science supported the work with a Seed Grant.