Using Fuzzy Logic to Increase Accuracy in Mango Maturity Index Classification: Approach for Developing a Portable Near-Infrared Spectroscopy Device
Open Access
Abstract
Grading is a decisive step in the successful distribution of mangoes to customers according to their preferences for the maturity index. A non-destructive method using near-infrared spectroscopy has historically been used to predict the maturity of fruit. This research classifies the maturity indexes in five classes using a new approach involving classification modeling and the application of fuzzy logic and indirect classification by measuring four parameters: total acidity, soluble solids content, firmness, and starch. These four quantitative parameters provide guidelines for maturity indexes and consumer preferences. The development of portable devices uses a neo spectra micro development kit with specifications for the spectrum of 1350–2500 nm. In terms of computer technology, this study uses a Raspberry Pi and Python programming. To improve the accuracy performance, preprocessing is carried out using 12 spectral transformation operators. Next, these operators are collected and combined to achieve optimal performance. The performance of the classification model with direct and indirect approaches is then compared. Ultimately, classification of the direct approach with preprocessing using linear discriminant analysis offered an accuracy of 91.43%, and classification of the indirect approach using partial least squares with fuzzy logic had an accuracy of 95.7%.Keywords
Funding Information
- Kementerian Keuangan Republik Indonesia (62/LPDP/2020)
This publication has 40 references indexed in Scilit:
- A local pre-processing method for near-infrared spectra, combined with spectral segmentation and standard normal variate transformationAnalytica Chimica Acta, 2016
- Maintaining mango (Mangifera indica L.) fruit quality during the export chainFood Research International, 2011
- Chemometric profiling of pre-climacteric Sri Lankan mango fruit (Mangifera indica L.)Food Chemistry, 2009
- Ensemble preprocessing of near-infrared (NIR) spectra for multivariate calibrationAnalytica Chimica Acta, 2008
- A fuzzy logic approach to experience-based reasoningInternational Journal of Intelligent Systems, 2007
- Multiplicative Scatter Correction during On-line Measurement with Near Infrared SpectroscopyBiosystems Engineering, 2007
- Prediction of mango eating quality at harvest using short-wave near infrared spectrometryPostharvest Biology and Technology, 2007
- Physical and mechanical properties of mango during growth and storage for determination of maturityJournal of Food Engineering, 2006
- The robust normal variate transform for pattern recognition with near-infrared dataAnalytica Chimica Acta, 1999
- Fuzzy sets as a basis for a theory of possibilityFuzzy Sets and Systems, 1999