Advertisement

Neural Computing and Applications

, Volume 31, Supplement 2, pp 1165–1171 | Cite as

A recurrent Elman network in conjunction with an electronic nose for fast prediction of optimum fermentation time of black tea

  • S. Ghosh
  • B. Tudu
  • N. Bhattacharyya
  • R. BandyopadhyayEmail author
Original Article
  • 188 Downloads

Abstract

Tea industries enjoy a significant position in the socio-economic ladder for any demographics, especially in India who is the largest producer as well as consumer of the agro-product. While tea ranks only next to water in the pedigree of globally consumed beverages, the imperative fermentation stage in the processing of tea leaves is conventionally monitored through olfactory perception of tea tasters. Recent advances in the field of machine olfaction have witnessed the advent of electronic nose prototypes, which provide a scientific validation to the organoleptic estimations disseminated by the tasters. However, fermentation is a continuous process requiring constant monitoring whose successful completion relies heavily on identification of distinct aroma peaks emanated at optimum instants. Since the fermentation process is integral to the final quality, it is deemed beneficial if the optimum fermentation period can be predicted at an earlier stage. Such preemptive information can mitigate constant monitoring requirements and momentary concentration lapses. Recognizing the time series nature of the data generated during the fermentation process with an electronic nose prototype, we have implemented a recurrent Elman network to predict the optimum fermentation period for different black tea samples. The results showed that the prescribed network could predict the optimum period with confidence at the halfway of the process. The minimal error between the predicted and the actual fermentation period at the halfway point suggests that the proposed model can well be integrated with an electronic nose dedicated for monitoring the fermentation process.

Keywords

Tea fermentation Electronic nose Recurrent network Elman network Optimum fermentation time Sensors 

Notes

Acknowledgements

The authors are grateful to Dr. Anutosh Chatterjee, former scientist, Bose Institute, Kolkata, India, and Mr. Surajit Ghosh, eminent tea technologist for their valuable guidance and encouragement throughout the study. The authors are deeply indebted to all the Tea Industries where experiments were carried out. The work has been sponsored by the National Tea Research Foundation, Tea Board, Government of India.

Compliance with ethical standards

Conflict of interest

The authors declare that they have no competing interests.

References

  1. 1.
    Yohannes MF, Matsuda T (2016) Weather effects on household demand for coffee and tea in Japan. Agribusiness 32:33–44CrossRefGoogle Scholar
  2. 2.
    Rashid MH, Fardous Z, Chowdhury MAZ, Alam MK, Bari ML, Moniruzzaman M, Gan SH (2016) Determination of heavy metals in the soils of tea plantations and in fresh and processed tea leaves: an evaluation of six digestion methods. Chem Cent J 10(1–13):7CrossRefGoogle Scholar
  3. 3.
    Joshi R, Gulati A (2015) Fractionation and identification of minor and aroma-active constituents in Kangra orthodox black tea. Food Chem 167:290–298CrossRefGoogle Scholar
  4. 4.
    Samanta T, Cheeni V, Das S, Roy AB, Ghosh BC, Mitra A (2015) Assessing biochemical changes during standardization of fermentation time and temperature for manufacturing quality black tea. J Food Sci Technol 52:2387–2393CrossRefGoogle Scholar
  5. 5.
    Zhu YF, Chen JJ, Ji XM, Hu X, Ling TJ, Zhang ZZ, Bao GH, Wan XC (2015) Changes of major tea polyphenols and production of four new B-ring fission metabolites of catechins from post-fermented Jing-Wei Fu brick tea. Food Chem 170:110–117CrossRefGoogle Scholar
  6. 6.
    Owuor PO, Obanda M (1998) The changes in black tea quality due to variations of plucking standard and fermentation time. Food Chem 61:435–441CrossRefGoogle Scholar
  7. 7.
    Sharma P, Ghosh A, Tudu B, Sabhapondit S, Baruah BD, Tamuly P, Bhattacharyya N, Bandyopadhyay R (2015) Monitoring the fermentation process of black tea using QCM sensor based electronic nose. Sens Actuators B Chem 219:146–157CrossRefGoogle Scholar
  8. 8.
    Gao L, Bian M, Mi R, Hu X, Wu J (2016) Quality identification and evaluation of Pu-erh teas of different grade levels and various ages through sensory evaluation and instrumental analysis. Int J Food Sci Technol 51:1338–1348CrossRefGoogle Scholar
  9. 9.
    Bhattacharyya N, Seth S, Tudu B, Tamuly P, Jana A, Ghosh D, Bandyopadhyay R, Bhuyan M (2007) Monitoring of black tea fermentation process using electronic nose. J Food Eng 80:1146–1156CrossRefGoogle Scholar
  10. 10.
    Bhattacharyya N, Seth S, Tudu B, Tamuly P, Jana A, Ghosh D, Bandyopadhyay R, Bhuyan M, Sabhapandit S (2007) Detection of optimum fermentation time for black tea manufacturing using electronic nose. Sens Actuators B Chem 122:627–634CrossRefGoogle Scholar
  11. 11.
    Eklöv T, Johansson G, Winquist F, Lundström I (1998) Monitoring sausage fermentation using an electronic nose. J Sci Food Agric 76:525–532CrossRefGoogle Scholar
  12. 12.
    Bhattacharyya N, Tudu B, Jana A, Ghosh D, Bandhopadhyay R, Bhuyan M (2008) Preemptive identification of optimum fermentation time for black tea using electronic nose. Sens Actuators B Chem 131:110–116CrossRefGoogle Scholar
  13. 13.
    Sharma M, Ghosh D, Bhattacharyya N (2013) Electronic nose—a new way for predicting the optimum point of fermentation of black tea. Int J Eng Sci Invent 2:56–60Google Scholar
  14. 14.
    Rather AM, Agarwal A, Sastry VN (2015) Recurrent neural network and a hybrid model for prediction of stock returns. Expert Syst Appl 42:3234–3241CrossRefGoogle Scholar
  15. 15.
    Aizenberg I, Sheremetov L, Villa-Vargas L, Martinez-Muñoz J (2016) Multilayer neural network with multi-valued neurons in time series forecasting of oil production. Neurocomputing 175:980–989CrossRefGoogle Scholar
  16. 16.
    Peris M, Escuder-Gilabert L (2013) On-line monitoring of food fermentation processes using electronic noses and electronic tongues: a review. Anal Chim Acta 804:29–36CrossRefGoogle Scholar
  17. 17.
    Claveria O, Monte E, Torra S (2015) Tourism demand forecasting with neural network models: different ways of treating information. Int J Tour Res 17:492–500CrossRefGoogle Scholar
  18. 18.
    Tudu B, Ghosh S, Bag AK, Ghosh D, Bhattacharyya N, Bandyopadhyay R (2015) Incremental FCM technique for black tea quality evaluation using an electronic nose. Fuzzy Inf Eng 7:275–289CrossRefGoogle Scholar
  19. 19.
    Bhattacharyya N, Tudu B, Jana A, Ghosh D, Bandhopadhyay R, Saha AB (2008) Illumination heating and physical raking for increasing sensitivity of electronic nose measurements with black tea. Sens Actuators B Chem 131:37–42CrossRefGoogle Scholar
  20. 20.
    Wang LF, Lee JY, Chung JO, Baik JH, So S, Park SK (2008) Discrimination of teas with different degrees of fermentation by SPME–GC analysis of the characteristic volatile flavour compounds. Food Chem 109:196–206CrossRefGoogle Scholar

Copyright information

© The Natural Computing Applications Forum 2017

Authors and Affiliations

  • S. Ghosh
    • 1
  • B. Tudu
    • 1
  • N. Bhattacharyya
    • 2
  • R. Bandyopadhyay
    • 1
    Email author
  1. 1.Department of Instrumentation and Electronics EngineeringJadavpur UniversityKolkataIndia
  2. 2.Centre for Development of Advanced ComputingKolkataIndia

Personalised recommendations