Modern data mining tools in descriptive sensory analysis: A case study with a Random forest approach

Granitto, Pablo M.; Gasperi, F.; Biasioli, Franco; Trainotti, E.; Furlanello, Cesare

doi:10.1016/j.foodqual.2006.11.001

Cited by 51 publications

(43 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…RF graphical outputs are multidimensional scaling projections [35] of the data set that utilise a particular measure of distance among samples based on the internal assignation of classes in the RF ensemble. Granitto et al [36] discussed the use of this tool in the analysis of food data. The authors showed that RF visualisations can be very informative for discrimination tasks, as they use information about the real classes (opposite to PCA) and also can be less biased than other supervised visualisations (like LDA or PLS) because RF plots are based on unseen samples.…”

Section: Ptr-tof-ms Analysismentioning

confidence: 99%

PTR‐TOF‐MS and data‐mining methods for rapid characterisation of agro‐industrial samples: influence of milk storage conditions on the volatile compounds profile of Trentingrana cheese

et al. 2010

View full text Add to dashboard Cite

Proton transfer reaction-mass spectrometry (PTR-MS), a direct injection mass spectrometric technique based on an efficient implementation of chemical ionisation, allows for fast and high-sensitivity monitoring of volatile organic compounds (VOCs). The first implementations of PTR-MS, based on quadrupole mass analyzers (PTR-Quad-MS), provided only the nominal mass of the ions measured and thus little chemical information. To partially overcome these limitations and improve the analytical capability of this technique, the coupling of proton transfer reaction ionisation with a time-of-flight mass analyser has been recently realised and commercialised (PTR-TOF-MS). Here we discuss the very first application of this new instrument to agro-industrial problems and dairy science in particular. As a case study, we show here that the rapid PTR-TOF-MS fingerprinting coupled with data-mining methods can quickly verify whether the storage condition of the milk affects the final quality of cheese and we provide relevant examples of better compound identification in comparison with the previous PTR-MS implementations. In particular, 'Trentingrana' cheese produced by four different procedures for milk storage are compared both in the case of winter and summer production. It is indeed possible to set classification models with low prediction errors and to identify the chemical formula of the ion peaks used for classification, providing evidence of the role that this novel spectrometric technique can play for fundamental and applied agro-industrial themes.

show abstract

Section: Ptr-tof-ms Analysismentioning

confidence: 99%

PTR‐TOF‐MS and data‐mining methods for rapid characterisation of agro‐industrial samples: influence of milk storage conditions on the volatile compounds profile of Trentingrana cheese

et al. 2010

View full text Add to dashboard Cite

show abstract

“…Despite being popular in the machine learning, medicine and neuroscience literature, (Granitto et al, 2007;Lehmann et al, 2007), Random Forests is only slowly gaining prominence in ecology (Pal, 2005;Garzon et al, 2006;Prasad et al, 2006;De'ath, 2007). The approach presents a very promising technique for a wide range of environmental problems due to their flexibility, adaptability, interpretability and performance.…”

Section: Prediction Using Random Forestsmentioning

confidence: 99%

Incorporating uncertainty in gully erosion calculations using the random forests modelling approach

Kuhnert¹,

Kinsey-Henderson²,

Bartley³

et al. 2010

Environmetrics

View full text Add to dashboard Cite

SUMMARYGully erosion represents one of the greatest threats to agricultural watersheds around the world and this is exacerbated with continual changes to land practices and changing climatic condition at a temporal scale. Catchment based models which include gully erosion have received increased attention in recent years due to the impact of gully erosion on downstream water quality. These types of models take gully erosion calculated via a deterministic model at a particular spatial location, along with other measures of erosion to provide an end-ofcatchment load. Although seen as a major contributor to erosion in this type of modelling framework, the error surrounding the gully erosion calculation is ignored in the sediment model. We propose a methodology that investigates the error in the gully erosion model. The methodology uses Random Forests to predict gully density and its associated prediction error across a catchment using environmental variables, which are then incorporated into the gully erosion model. We demonstrate the approach using the Burdekin catchment in Queensland, Australia, where only a very small proportion of gullies ($0.88%) have been mapped. Our results cast doubt in the predictive ability of models of sediment transportation that use gully erosion where the error is estimated high.

show abstract

“…Besides the high cost, these techniques usually present long time delays, or require the use of several purification steps (Perez-Cachopilar, 2011;Nitra, 2011). Sensory analysis is another methodology used to evaluate the juice dilution; however, it usually requires a large number of variables and a trained team, which is generally very time consuming and presents high costs (Granitto et al 2007). Image analysis represents an important characterization technique in food science and technology (Fernandes et al 2013), not only due to its precision / accuracy, but also because of its non-invasive feature.…”

Section: Introductionmentioning

confidence: 99%

Use of image analysis for monitoring the dilution of Physalis peruviana pulp

Licodiedoff

Ribani

Camlofski

et al. 2013

Braz. arch. biol. technol.

View full text Add to dashboard Cite

The aim of this work was to develop linear models using the image analysis coupled with density measurements to monitor the dilution of the Physalis juice in the concentrations ranging from 0 to 100% in mass of juice pulp. A sample corresponding to 20% in the mass of juice pulp was for validating purposes and a prediction of 19.9±0.3%. The models with three parameters showed the best predictions, providing this technique with a promising future for the monitoring the dilution of fruit juices.

show abstract

Modern data mining tools in descriptive sensory analysis: A case study with a Random forest approach

Cited by 51 publications

References 22 publications

PTR‐TOF‐MS and data‐mining methods for rapid characterisation of agro‐industrial samples: influence of milk storage conditions on the volatile compounds profile of Trentingrana cheese

PTR‐TOF‐MS and data‐mining methods for rapid characterisation of agro‐industrial samples: influence of milk storage conditions on the volatile compounds profile of Trentingrana cheese

Incorporating uncertainty in gully erosion calculations using the random forests modelling approach

Use of image analysis for monitoring the dilution of Physalis peruviana pulp

Contact Info

Product

Resources

About