Researchers at the University of Vaasa are exploring how packaging alone could function as a condition monitor using printing inks that change color when exposed to alterations in temperature or humidity.

According to the team, the combination of inks and artificial intelligence (AI) demonstrates how packaging can accurately detect signal changes without needing electronics.

“My research showed that traditional, simple computational methods work well for recognizing significant color differences. However, for subtle changes and varying conditions, the most effective methods were convolutional neural networks that are based on artificial intelligence,” the researchers noted.

Notably, the team found that convolutional neural networks excelled in the detection of subtle, fast-changing conditions, such as those indicated by functional printing inks that change color in response to environmental factors.

Being able to detect such changes rapidly promises to prevent food or pharmaceutical spoilage, waste and damage, the team reported.

The color change in printing ink is typically too subtle or occurs too quickly for current machine vision systems to detect reliably. Once the change becomes mechanically recognizable, the process may already be too advanced, or damage may have likely already taken place. However, with AI, recognition is faster and more accurate. As such, the technology promises to make it possible to use such printed indicators not only in factories but also on consumer goods, thus offering real-time feedback on product freshness and safety.

Such printed indicators could potentially be applied directly on packages along with regular labels at little cost, the team added.

“Expensive electronic measuring devices cannot be placed on, for example, a lettuce package, as it would constitute a large portion of the product’s price or could cause additional challenges for recycling. Printed indicators solve this problem,” the researchers added.

For the food industry, such indicators could be used to track shelf life with greater precision while health care providers could use the indicators to ensure proper storage of medicines, the team concluded.