Ultrasound AI technology promotes food safety

Tōkai University and Fujitsu announced the successful development of a new technology for testing the freshness of Japanese frozen tuna. The joint research focuses on the development of new ultrasonic AI technology, which is the first in the world to measure the meat quality of frozen tuna without cutting or damaging the product. New technology offers a new way to check the quality of frozen tuna without compromising its value, and may help improve the trust and safety of global frozen tuna and other food distribution in the future.

The two parties introduced this joint research at the Ultrasound Research Society Technical Committee Meeting (hosted by IEICE) held in Hiroshima, Japan.

Japanese and global demand for tuna has increased significantly, with 15 countries catching and producing more than 50,000 tons of tuna in 2020. Demand for high-quality tuna for sashimi has set off a food craze.

Most wild-caught natural tuna is quickly frozen on commercial fishing vessels and then shipped through distributors to restaurants and supermarkets to consumers. However, the quality of tuna depends largely on the conditions under which it is caught and how it is handled throughout distribution.

Traditional methods of inspecting the freshness and meat quality of frozen tuna typically require inspectors to cut off the tail of the fish to visually inspect a cross-section of the tuna tail. Cutting off the tails of tuna often damages and reduces the value of the fish, while the process relies heavily on a limited number of trained experts to accurately conduct quality checks.

To find the best ultrasonic frequency for inspecting frozen tuna, Tokai University and Fujitsu conducted experiments at several wave frequencies. Tests have shown that ultrasound at relatively low frequencies (around 500kHz) produces the best results.

To identify possible indicators of insufficient freshness, the parties compared the ultrasonic waveforms of tuna samples with good and insufficient freshness to check whether there were differences in the waveforms due to the freshness of the samples. Tokai University and Fujitsu found that the reflection intensity in bone areas was particularly strong in tuna specimens that were not fresh enough. Based on these findings, the two parties created a machine learning model based on bone reflection waves in tuna specimens that can correctly check the freshness of frozen tuna with 70 to 80 percent accuracy.

In addition to waveforms that can be easily distinguished by the human eye, the newly developed AI technology is also able to identify differences in waveforms that are difficult to perceive with human vision.

In addition, Tokai University and Fujitsu will conduct trials using more tuna samples to improve the accuracy of the newly developed technology and further enhance its ability to detect other quality defects in frozen tuna, such as whether A blood clot or other pathology is present.

The two partners also plan to conduct field trials in marine product processing plants and conduct research to apply the technology to a wider range of areas, including animal husbandry, biological processing of frozen products fields and medical fields.

The above is the detailed content of Ultrasound AI technology promotes food safety. For more information, please follow other related articles on the PHP Chinese website!