Follow Us on Google News
A team of Pakistani scientists has made a significant scientific advancement by creating an artificial intelligence (AI)-based visual categorization approach that precisely determines the sweetness of native citrus fruits.
The National University of Sciences and Technology (NUST) National Centre of Robotics and Automation team, under the direction of Dr. Ayesha Zeb, successfully predicted fruit sweetness with an accuracy rate of over 80% without causing any harm to the fruit.
To conduct their experiment, the researchers selected 92 citrus fruits, including Blood Red, Mosambi, and Succari varieties, from a farm in the Chakwal district. They utilized a handheld spectrometer to obtain spectra, which are patterns obtained from the bouncing light, from marked regions on the fruits’ skin. The team employed near-infrared (NIR) spectroscopy, a technique that enables the analysis of non-visible light spectra, to examine the fruit samples. Of the 92 fruits, 64 were used for calibration and 28 for prediction via the spectrometer.
While the use of NIR spectroscopy in damage-free fruit classification is not new, the Pakistani team’s novel approach involved applying it to model the sweetness of local fruits. Additionally, they integrated artificial intelligence algorithms for direct classification of orange sweetness, resulting in improved accuracy.
Chemical and sensory testing are typically used to evaluate fruit sweetness. Brix, a measurement of total sugars, is used to assess how sweet oranges are, while titratable acidity (TA), a measure of citric acid, is used to determine how much of it is present. Peeling off samples from the designated spectroscopic zones, the scientists got reference values for Brix, TA, and fruit sweetness before building the AI model.
