Prediction of Processing Tomato Peeling Outcomes

Abstract

Peeling outcomes of processing tomatoes were predicted using multivariate analysis of magnetic resonance (MR) images. Tomatoes were obtained from a whole‐peel production line. Each fruit was imaged using a 7‐tesla MR system, and a multivariate data set was created from 28 different images. After imaging, the fruits were individually tagged and processed in a pilot peeling system. An expert grader then assessed the peeling outcome for each fruit; outcomes included “whole peel,”“some skin attached” and seven others. The multivariate analysis techniques of partial least squares‐discriminant analysis (PLS‐DA) and soft independent modeling of class analogy (SIMCA) were used to predict peeling outcome from the 28 MR images. The PLS‐DA model for the “whole peel” (best) outcome correctly classified 81% of the fruit that were in this category. The SIMCA model performed well for rejecting non‐“whole peel” fruit but did not perform as well for identification of “whole peel” fruit. PRACTICAL APPLICATIONS Fruit processors seek methods for predicting the quality of their finished products from measurements of their raw materials (individual fruit). Such predictions will ensure optimal allocation and processing of each fruit, which will result in raw material cost savings, improved product quality, wastewater reduction and energy efficiency. In the case of processing tomatoes, peeling outcome is the metric of interest. This study demonstrates the feasibility of predicting final product quality using MR imaging of raw food materials.

Understanding Tomato Peelability

“…The method reported by Milczarek and McCarthy () is a practical option for researchers who have the budget to acquire radio frequency tagging equipment. The steps involved are: (1)Each fruit is individually tagged by injecting a numbered RFID chip (12‐mm length × 2‐mm diameter) through the stem scar, approximately 10 mm into the columella. (2)Fruits undergo the peeling process of choice. (3)The technician in charge of determining peeling outcome is able to identify the fruits by using a portable RFID reader. …”

“…Radio frequency ID (RFID) method. The method reported by Milczarek and McCarthy (2011) is a practical option for researchers who have the budget to acquire radio frequency tagging equipment. The steps involved are:…”

A pilot scale electrical infrared dry-peeling system for tomatoes: Design and performance evaluation

“…Small energy and carbon footprints, high water-use efficiency, wastewater management, and minimal chemical contamination have become critical factors in decision-making in terms of choices of food production and processing systems (Roy et al, 2009). In the fruit and vegetable industry, many unit operations such as peeling, blanching, and pasteurisation are energy-and water-intensive and result in huge amounts of wastewater with high salinity and organic loads (Das & Barringer, 2005;Milczarek & McCarthy, 2011;Pan, Li, Bingol, McHugh, & Atungulu, 2009;Rock, Yang, Goodrich-Schneider, & Feng, 2011;Setty, Vijayalakshimi, & Devi, 1993). The conventional peeling process is carried out using hot lye solution or pressurised steam.…”

A Quick Detection of Melamine Adulteration in Milk and Dairy Products Using First-Order Multivariate Calibration

“…Several multivariate calibration algorithms of handling spectroscopic, chromatographic and electrochemical data have been developed and used for quantification solutes in complex matrices (Brereton ). Partial least squares (PLS) and net analyte preprocessing‐partial least squares (NAP/PLS) have been applied for analyzing food, drugs and clustering processed foodstuffs (Al‐Degs ; Milczarek and McCarthy ; Bhaskar et al . ).…”