Most mango farms classify the maturity stage manually by trained workers using external indicators such as size, shape, and skin color, which can lead to human error or inconsistencies. We developed four common machine learning (ML) classifiers, the k-mean, naïve Bayes, support vector machine, and feed-forward artificial neural network (FANN), all of which were aimed at classifying the ripeness stage of mangoes at harvest. The ML classifiers were trained on biochemical data and then tested on physical and electrical data.The performance of the ML models was compared using fourfold cross validation. The FANN classifier performed the best, with a mean accuracy of 89.6% for unripe, ripe, and overripe classes, when compared to the other classifiers.

We theoretically designed the Kretschmann configuration coupled plasmon-waveguide resonance (CPWR) sensors, composed of thin films of metal nitrides. The thicknesses of the layers of the CPWR sensors were optimized using a genetic algorithm. The optimized CPWR sensors were applied to simultaneously measure the thickness and refractive index (RI) of diamond-like carbon (DLC) films. The field profiles and the sensitivity of the CPWR sensors in response to thin DLC films were studied using the finite-different time-domain technique and the transfer matrix method. The genetic algorithm method predicted that the two-mode CPWR sensors could simultaneously analyze the thickness and RI of the DLC films as thin as 1.0 nm at a wavelength of 1550 nm. The simulations showed that the angular sensitivity toward the refractive index changes of the DLC films of the optimized CPWR sensors was comparable to that of traditional CPWR sensors.

No abstract