Robust NIRS models for non-destructive prediction of postharvest fruit ripeness and quality in mango

Rungpichayapichet, Parika; Mahayothee, Busarakorn; Nagle, Marcus; Khuwijitjaru, Pramote; Müller, Joachim

doi:10.1016/j.postharvbio.2015.07.006

Cited by 108 publications

(53 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Vásquez-Caicedo et al (2005) proposed a ripening index (RPI) for mango ripeness, combining the fruit firmness with sugar acid ratio. A vast range of RPI values were reported in many studies (Blanes et al, 2015;Kienzle et al, 2012;Rungpichayapichet et al, 2016). Even negative RPI values were found for ripe fruits in our preliminary study (Nambi et al, 2015).…”

Section: Introductionsupporting

confidence: 42%

“…But these studies did not propose any consolidated model or index to quantify or predict ripeness level. Saranwong et al (2004) and Rungpichayapichet et al (2016) reported on the prediction of ripeness and eating quality of mangoes using NIR spectroscopy. All these methods cannot be used as a ready reckoner with minimum inputs, and they need high cost instruments like NIR spectrometer and complex algorithms.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Comprehensive ripeness-index for prediction of ripening level in mangoes by multivariate modelling of ripening behaviour

Nambi

Thangavel

Manickavasagan

et al. 2017

International Agrophysics

View full text Add to dashboard Cite

A b s t r a c t. Prediction of ripeness level in climacteric fruits is essential for post-harvest handling. An index capable of predicting ripening level with minimum inputs would be highly beneficial to the handlers, processors and researchers in fruit industry. A study was conducted with Indian mango cultivars to develop a ripeness index and associated model. Changes in physicochemical, colour and textural properties were measured throughout the ripening period and the period was classified into five stages (unripe, early ripe, partially ripe, ripe and over ripe). Multivariate regression techniques like partial least square regression, principal component regression and multi linear regression were compared and evaluated for its prediction. Multi linear regression model with 12 parameters was found more suitable in ripening prediction. Scientific variable reduction method was adopted to simplify the developed model. Better prediction was achieved with either 2 or 3 variables (total soluble solids, colour and acidity). Cross validation was done to increase the robustness and it was found that proposed ripening index was more effective in prediction of ripening stages. Three-variable model would be suitable for commercial applications where reasonable accuracies are sufficient. However, 12-variable model can be used to obtain more precise results in research and development applications.

show abstract

Section: Introductionsupporting

confidence: 42%

Section: Introductionmentioning

confidence: 99%

Comprehensive ripeness-index for prediction of ripening level in mangoes by multivariate modelling of ripening behaviour

Nambi

Thangavel

Manickavasagan

et al. 2017

International Agrophysics

View full text Add to dashboard Cite

show abstract

“…An efficient histogram analysis 62 algorithm was proposed for real-time automated fruit surface quality evaluation (Zhang et al 63 2014a and 2014b). Internal quality attributes of mango were accurately predicted by short-wave 64 near-infrared spectroscopy and Fruit ripeness classification by NIRS calibrations showed 65 accuracies between 59 and 88% (Rungpichayapichet et al, 2016). An appropriately crafted 66 mixture of fifteen different visual features was used in their computer vision based date 67…”

Section: Introduction 28mentioning

confidence: 94%

Automatic quality and moisture evaluations using Evolution Constructed Features

Zhang

Lee

Lillywhite

et al. 2017

Computers and Electronics in Agriculture

View full text Add to dashboard Cite

12Many quality evaluation tasks that are complicated and unique to specialty crops are often 13 carried out manually by human experts by visually inspecting product appearances. This labor-14 intensive process usually depends greatly on experienced workers and lacks verification efficiency. 15Automating these tasks not only reduces the processing time, improves the verification accuracy, 16 but also reduces the labor costs. This study is conducted to explore the feasibility of using our 17 recently developed Evolution-Constructed Feature (ECO-Feature) to automatically evaluate the 18 quality of agricultural products. Three feature descriptors are added to the original ECO-Feature 19 algorithm to reduce its dimensionality and improve training efficiency. This paper uses date fruit, 20 cashews, pistachios, and almonds as examples to demonstrate the performance of the proposed 21 algorithm for quality and moisture evaluations. The proposed method is proven accurate, 22 effective and has been implemented and deployed for commercial production for the date 23

show abstract

“…More recently, a portable Luminar 5030 NIR was used by Jha et al () to assess a maturity index estimated based on SSC, DM, and TA in seven mango varieties. Rungpichayapichet, Mahayothee, Nagle, Khuwijitjaru, and Müller () used a portable VIS‐NIR photo‐diode array spectrometer (HandySpec Field 1000, tec5AG) to study mango fruit quality and maturity and good results were reported for SSC prediction, standard error of prediction (SEP) of 1.2% and a correlation coefficient ( R 2 ) of 0.90, for firmness prediction (SEP of 4.22 N and R 2 of 0.82), and for TA prediction (SEP of 0.38% and R 2 of 0.74). Marques, Freitas, Pimentel, and Pasquini () studying ‘Tommy Atkins’ mangoes used a portable MicroNIR 1700 to predict SSC, DM, TA, and firmness with low root mean square error of prediction (RMSEP), 0.92°Brix, 0.51%, 0.17%, and 12.2 N, respectively.…”

Section: Introductionmentioning

confidence: 99%

Cold storage of ‘Palmer’ mangoes sorted based on dry matter content using portable near infrared (VIS-NIR) spectrometer

Neto

Leite

Oliveira

et al. 2018

J Food Process Preserv

View full text Add to dashboard Cite

The objective of this study was to use dry matter (DM) calibration models to sort ‘Palmer’ mangoes prior cold storage and to evaluate the physiological and chemical changes during the storage period. PLS model developed with fruit from 2015/2016 season was not adequate to predict DM content in fruit from 2016/2017 (not adjusted R2). Therefore, VIS‐NIR spectra from 2016/2017 season were incorporated into data set and a new model was developed (RMSEcv of 10.5 g.kg−1, RnormalP2 of 0.75). With the new model, ‘Palmer’ mangoes were sorted into two maturity stages (150 g.kg−1 and 110 g.kg−1) which resulted in quality differences mainly in relation to DM and SSC. Portable VIS‐NIR spectrometer can be used to sort fruit according to maturity stages based on DM content and this classification affect fruit quality during cold storage as fruit with higher DM (150 g.kg−1) presented better quality than fruit with lower DM (110 g.kg−1). Practical applications Although results can be found regarding the use of portable NIR spectrometers to estimate maturity in mango fruit, there are no studies stating the use of this method to sort fruit prior cold storage. Our results highlight that portable VIS‐NIR spectrometer can be used to sort fruit according to maturity stages based on dry matter (DM) content and this classification affects fruit quality during cold storage as fruit with higher DM (150 g.kg−1) presented better quality than fruit with lower DM (110 g.kg−1) at the end of the storage period.

show abstract

Robust NIRS models for non-destructive prediction of postharvest fruit ripeness and quality in mango

Cited by 108 publications

References 40 publications

Comprehensive ripeness-index for prediction of ripening level in mangoes by multivariate modelling of ripening behaviour

Comprehensive ripeness-index for prediction of ripening level in mangoes by multivariate modelling of ripening behaviour

Automatic quality and moisture evaluations using Evolution Constructed Features

Cold storage of ‘Palmer’ mangoes sorted based on dry matter content using portable near infrared (VIS-NIR) spectrometer

Contact Info

Product

Resources

About