Electronic nose for black tea quality evaluation by an incremental RBF network

Tudu, Bipan; Jana, Arun; Metla, A.; Ghosh, Devanita; Bhattacharyya, Nabarun; Bandyopadhyay, Rajib

doi:10.1016/j.snb.2009.02.025

Cited by 104 publications

(60 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In India, one of the principal problems encountered for evaluating black tea is that as tea industries are spread over dispersed locations and quality of tea varies considerably on agroclimatic condition, type of plantation, season of flush, and method of manufacturing [17]. To avoid differences, in this study we used for the entire project the same tea.…”

Section: Brewed Teamentioning

confidence: 99%

Iron-Polyphenol Interaction Reduces Iron Bioavailability in Fortified Tea: Competing Complexation to Ensure Iron Bioavailability

Dueik

Chen

Diósady

2017

Journal of Food Quality

View full text Add to dashboard Cite

Tea seems to be like a logical substrate for iron fortification; however, its fortification with iron presents technical challenges as tea polyphenols form a blue complex with iron that makes both of them unavailable for absorption. The objective of this work was to develop an effective technology, to prevent the interaction of iron and polyphenols by using EDTA as a competing complexing agent. Fortified tea was prepared from premix, prepared by spraying iron and sodium EDTA into tea leaves. Iron concentration in tea was adjusted to 5 mg/cup. Iron content was measured by AAS and the iron-polyphenol complex by spectrophotometry at 560 nm. Sensory evaluation was carried out in order to determine if fortification affects the properties of tea. A molar ratio of 1 : 2 Fe : EDTA was able to avoid complex formation and provide 4 mg of iron per cup of brewed tea. The fortified tea had a similar colour and flavour as ordinary tea, without the development of off-flavours. However, fortified tea with a ratio lower than 1 : 2 had a darker colour and off-flavours. By the addition of EDTA in a molar ratio ≥1 : 2, it is possible to produce an iron fortified tea without the formation of off-flavours.

show abstract

Section: Brewed Teamentioning

confidence: 99%

Iron-Polyphenol Interaction Reduces Iron Bioavailability in Fortified Tea: Competing Complexation to Ensure Iron Bioavailability

Dueik

Chen

Diósady

2017

Journal of Food Quality

View full text Add to dashboard Cite

show abstract

“…Instrumental evaluation of black tea is quite complex because of presence of many compounds and therefore it is being distinguished by tea tasters on their scores [1,8]. Impedance tongue are sensor array for qualitative and quantitative analysis and it is used to differentiate basic standard taste.…”

Section: Preliminary Of Svmmentioning

confidence: 99%

“…Instrumental evaluation [1] of quality of black tea is quite complicated because of the presence of immeasurable compounds and their multidimensional influence in determining the final quality of tea. Many experienced tea tasters are employed for gradation of tea on the basis of their scores [2], this method is subjective and a low-cost equipment is desired in the tea industry.…”

Section: Introductionmentioning

confidence: 99%

Survey on Tea Discriminator

Gupta¹,

Shukla²

2015

IJCA

View full text Add to dashboard Cite

A number of beverages viz. hard drink, soft drink, packet juice, tea are being used around the globe having different chemical compositions. Organoleptic Systems are being used for a variety of detection tasks from checking quality of food products to medicinal diagnosis by detecting chemical compositions. The entire organoleptic system, from sample delivery stage to classification stage, is usually optimized to a particular problem domain in order to provide suitable sensing performance. The optimization of sample preparation, signal processing, feature extraction, classifier are as important as choice of sensors within the array in enhancing the performance of the organoleptic system because presence of irrelevant features increases the dimensionality of the search space, which can do reverse effect on the accuracy of the Pattern Recognition (PARC) techniques.Tea in present world is the most popular beverage having enormous global marketing. Various researchers have made a number of efforts to correlate tea quality with its chemical composition which led to many humanoid errors and may vary from person to person. This problem can be solved by using an instrument called "Electronic Tongue (i-tongue)". It is developed to reduce human sensory test panels, get accurate measurement of taste, prepare optimized development time and cost. This system analyses liquid including an array of non-specific chemical sensors with partial specificity for different component in liquid samples and appropriate pattern recognition capable of recognizing the qualitative and quantitative composition of sample and complex solutions. A number of attempts have been performed using sensor array and electrochemical techniques such as Cyclic Voltammetry, Potentiometry and Conductivity to classify different types of tea.

show abstract

“…While extensive research 13 has been done to create models under controlled conditions, for a small problem 14 or dataset, the applicability of those models in real world -e.g. in food testing 15 in the food industry or in routine analysis in a regulated testing laboratory- 16 is very scarce. This is due to the overfitting of the model to the calibration 17 set when only one instrument, one analytical laboratory or, in general, one set 18 of assumptions are taken into consideration to create the models.…”

mentioning

confidence: 99%

Incremental model learning for spectroscopy-based food analysis

Diaz-Chito

Georgouli

Koidis

et al. 2017

Chemometrics and Intelligent Laboratory Systems

View full text Add to dashboard Cite

In this paper we propose the use of incremental learning for creating and improving multivariate analysis models in the field of chemometrics of spectral data.As main advantages, our proposed incremental subspace-based learning allows creating models faster, progressively improving previously created models and sharing them between laboratories and institutions without requiring transferring or disclosing individual spectra samples. In particular, our approach allows to improve the generalization and adaptability of previously generated models with a few new spectral samples to be applicable to real-world situations. The potential of our approach is demonstrated using vegetable oil type identification based on spectroscopic data as case study. Results show how incremental models maintain the accuracy of batch learning methodologies while reducing their computational cost and handicaps.

show abstract

Electronic nose for black tea quality evaluation by an incremental RBF network

Cited by 104 publications

References 20 publications

Iron-Polyphenol Interaction Reduces Iron Bioavailability in Fortified Tea: Competing Complexation to Ensure Iron Bioavailability

Iron-Polyphenol Interaction Reduces Iron Bioavailability in Fortified Tea: Competing Complexation to Ensure Iron Bioavailability

Survey on Tea Discriminator

Incremental model learning for spectroscopy-based food analysis

Contact Info

Product

Resources

About