Towards Versatile Electronic Nose Pattern Classifier for Black Tea Quality Evaluation: An Incremental Fuzzy Approach

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

doi:10.1109/tim.2009.2016874

Cited by 52 publications

(14 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Metal oxide gas sensors are commonly used in electronic noses for various applications including pork adulteration [16] quality control [17,10] and as a formaldehyde sensor [18]. Sensing materials used in metal oxide sensor are Tin dioxide [SnO 2 ] and tungsten trioxide [WO 3 ] as both materials are claimed to be highly sensitive to various types of volatile compounds.…”

Section: Sensor Selectionmentioning

confidence: 99%

See 1 more Smart Citation

Rapid lard identification with portable electronic nose

Latief¹,

Khorsidtalab²,

Saputra³

et al. 2017

IOP Conf. Ser.: Mater. Sci. Eng.

View full text Add to dashboard Cite

Section: Sensor Selectionmentioning

confidence: 99%

“…They also play an important role in food industry. Some of the applications of electronic noses include detecting different flavours of milk [6,7], meat [8,9], tea [10], spoiled beef [11] and spoiled fish [12].…”

Section: Introductionmentioning

confidence: 99%

Rapid lard identification with portable electronic nose

Latief¹,

Khorsidtalab²,

Saputra³

et al. 2017

IOP Conf. Ser.: Mater. Sci. Eng.

View full text Add to dashboard Cite

“…Classification of some liquids, such as beer, alcohol and sesame oil, has been undertaken in other studies with good results [8][9][10]. Moreover, the authors of [11][12][13][14][15][16] have classified other products, such as black tea, coffee beans, green coffee, instant coffee, and rice varieties.…”

Section: Introductionmentioning

confidence: 99%

E-nose application to food industry production

Chilo

Pelegrí-Sebastiá

Cupane³

et al. 2016

IEEE Instrum. Meas. Mag.

View full text Add to dashboard Cite

Food companies worldwide must constantly engage in product development to stay competitive, cover existing markets, explore new markets, and meet key consumer requirements. This ongoing development places high demands on achieving quality at all levels, particularly in terms of food safety, integrity, quality, nutrition, and other health effects. Food product research is required to convert the initial product idea into a formulation for upscaling production with ensured significant results. Sensory evaluation is an effective component of the whole process. It is especially important in the last step in the development of new products to ensure product acceptance. In that stage, measurements of product aroma play an important role in ensuring that consumer expectations are satisfied. To this end, the electronic noses (enose) can be useful tools to achieve this purpose. The e-nose is a combination of various sensors used to detect gases by generating signals for an analysis system. Our research group has investigated the scent factor in some foodstuff and attempted to develop e-noses based on low-cost technology and compact size. In this paper, we present a summary of our research to date on applications of e-noses in the food industry.

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%

“…While incremental learning has been used and proposed in other fields [11,63 12, 13, 9, 10], its intrinsic advantages have been scarcely exploited in the field 64 of food analysis and chemometrics [14,15,16,17,18,19]. Bhattacharyya et 65 al.…”

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

Towards Versatile Electronic Nose Pattern Classifier for Black Tea Quality Evaluation: An Incremental Fuzzy Approach

Cited by 52 publications

References 25 publications

Rapid lard identification with portable electronic nose

Rapid lard identification with portable electronic nose

E-nose application to food industry production

Incremental model learning for spectroscopy-based food analysis

Contact Info

Product

Resources

About