Development of non-destructive system for estimating avocado quality parameters

México has established itself as a significant global exporter of avocados, owing to the surging demand for this highly sought-after fruit. In response to market requirements, the assurance of specific quality parameters during the harvesting and international transportation phases has become indispensable. However, the predominant techniques employed for the assessment of these critical quality attributes are often intrusive and labor-intensive, resulting in substantial economic losses. In this research, we propose a novel approach, Smart Platform for Avocado Inspection and Analysis (SPAIA), which leverages intelligent audio analysis to nondestructively estimate key avocado quality parameters. Our methodology comprises a multi-faceted process, encompassing the design and development of a specialized capture device, meticulous data collection, and the formulation of robust audio-based estimation and evaluation models. As a result, our research proposes new aFI, aFIsum indices from Audio Signal Processing (ASP) techniques, and a new spectrogram, a product of image processing techniques and Intelligent Audio Analysis (IAA). Finally, the non-destructive approach yielded remarkable results in the estimation of the avocado quality parameters Seed Weight (SW), Dry Matter Index (DMI), Ripeness State (RS) and Uniform Ripeness (UR). The best regression models achieved a Pearson’s correlation index of 0.988, while the classification models exhibited an accuracy of 0.960. These findings not only demonstrate the viability of SPAIA as an innovative tool but also highlight its potential to revolutionize the avocado industry by offering a more efficient and sustainable means of ensuring fruit quality throughout the entire production and distribution process. •Development of a non-destructive system for estimating avocado quality parameters.•Construction of database with characteristics and quality aspect of Hass avocados.•Design of percussion prototype for automatic audio and metadata collection.•Proposal of indexes for the intelligent acoustic analysis in fruits.