<p>Today, measuring the concentration of various microRNAs in fruits has been introduced to model the storage conditions of agricultural products. However, there is a limiting factor in the extensive utilization of such techniques: the existing methods for measuring microRNA sequences, including PCR and microarrays, are time-consuming and expensive and do not allow for simultaneous measurement of several microRNAs. In this study, a biosensor based on the Förster resonance energy transfer (FRET) of fluorescence dyes that can lead to the hybridization of oligonucleotide probes labeled with such dyes by using an excitation wavelength has been used to simultaneously measure microRNAs. Three microRNA compounds, i.e., miRNA-164, miRNA-167, and miRNA-399a, which play significant roles in the postharvest characteristics of strawberry fruits were measured. The simultaneous measurement was performed using three fluorescence dyes which exert various emission wavelengths at 570, 596, and 670&#xa0;nm. In the following, machine learning methods including artificial neural networks (ANNs) and support vector machines (SVMs), with hyperparameter values optimized ​with the help of metaheuristic optimization algorithms, were used to predict the amount of mechanical loading on strawberry fruits and their storage period having the microRNA concentrations. The results showed that the SVM with Gaussian kernel, which was optimized by the Harris hawks optimization, is capable of predicting the mechanical stress and storage period of strawberry fruits with a coefficient of determination (<i>R</i>²) of 0.89 and 0.92, respectively. The findings of this study reveal the application of combining FRET-based biosensors and machine learning methods in fruit storage quality assessment.</p>