Pakistani scientists combine NIR spectrometry and AI algorithms to measure fruit sweetness

A team of scientists from Pakistan has achieved a significant breakthrough in the field of fruit analysis. Led by Dr. Ayesha Zeb from the National Centre of Robotics and Automation at the National University of Sciences and Technology (NUST), the team has developed an innovative method to assess the sweetness of native citrus fruits using artificial intelligence (AI).

To analyze the fruit's sweetness without causing any damage, they used a handheld spectrometer to obtain patterns of light bouncing off marked regions on the fruit's skin. By employing near-infrared (NIR) spectroscopy, a technique that analyzes non-visible light spectra, they examined the fruit samples.

The team took a novel approach by applying NIR spectrometry to model the sweetness of local fruits. They integrated artificial intelligence algorithms into the process to directly classify the sweetness of oranges, resulting in improved accuracy.

Traditionally, assessing fruit sweetness involves chemical and sensory testing. The sweetness of oranges is determined by measuring total sugars known as Brix, while the levels of citric acid are indicated by titratable acidity (TA). To develop the AI model, the team collected reference values for Brix, TA, and fruit sweetness by peeling off samples from the marked areas used for spectroscopy.

The results were remarkable, as the AI model not only accurately predicted the values of Brix, TA, and overall sweetness but also outperformed traditional methods in sweetness prediction. The model achieved an impressive overall accuracy rate of 81.03% for identifying sweet, mixed, and acidic tastes. To read the full study, follow the webpage.

To carry out such investigation, Fructidor recommends referring only to trusted manufacturers. Felix Instruments, a subsidiary of CID Bio-Science, Inc., is among of them. The company develops and manufactures NIR assessment and gas analysis tools for growers, breeders, and distributors to obtain critical data from fruit quickly and non-destructively. If you grow, pack or sell avocados, mangoes, kiwis and wish to test NIR tools by Felix Instruments, send your inquiry

source: nature.com, tribune.com.pk