Generating Synthetic Fermentation Data of Shindari, a Traditional Jeju Beverage, Using Multiple Imputation Ensemble and Generative Adversarial Networks
Source abstract
Abstract
Fermentation is an age-old technique used to preserve food by restoring proper microbial balance. Boiled barley and nuruk are fermented for a short period to produce Shindari, a traditional beverage for the people of Jeju, South Korea. Shindari has been proven to be a drink of multiple health benefits if fermented for an optimal period. It is necessary to predict the ideal fermentation time required by each microbial community to keep the advantages of the microorganisms produced by the fermentation process in Shindari intact and to eliminate contamination. Prediction through machine learning requires past data but the process of obtaining fermentation data of Shindari is time consuming, expensive, and not easily available. Therefore, there is a need to generate synthetic fermentation data to explore various benefits of the drink and to reduce any risk from overfermentation. In this paper, we propose a model that takes incomplete tabular fermentation data of Shindari as input and uses multiple imputation ensemble (MIE) and generative adversarial networks (GAN) to generate synthetic fermentation data that can be later used for prediction and microbial spoilage control. For multiple imputation, we used multivariate imputation by chained equations and random forest imputation, and ensembling was done using the bagging and stacking method. For generating synthetic data, we remodeled the tabular GAN with skip connections and adapted the architecture of Wasserstein GAN with gradient penalty. We compared the performance of our model with other imputation and ensemble models using various evaluation metrics and visual representations. Our GAN model could overcome the mode collapse problem and converged at a faster rate than existing GAN models for synthetic data generation. Experiment results show that our proposed model executes with less error, is more accurate, and generates significantly better synthetic fermentation data compared to other models.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Spectroscopy and Chemometric Analyses · Advanced Chemical Sensor Technologies · Food Quality and Safety Studies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computer Engineering, Jeju National University, 102 Jejudaehak-ro, Jeju-si 63243, Korea
Funding
Korea Institute for Advancement of Technology
References (34)
Show source-provided references
1. Hyun, S.B., and Hyun, C.G. (2020). Anti-Inflammatory Effects and Their Correlation with Microbial Community of Shindari, a Traditional Jeju Beverage. Fermentation, 6.10.3390/fermentation6030087 ↗
2. Lactic acid bacteria as functional starter cultures for the food fermentation industry10.1016/j.tifs.2003.09.004 ↗
3. Endemic foodborne botulism among Alaska Native persons—Alaska, 1947–200710.1093/cid/ciq240 ↗
4. Hartmann, K.G., Schirrmeister, R.T., and Ball, T. (2018). EEG-GAN: Generative adversarial networks for electroencephalograhic (EEG) brain signals. arXiv.
5. Oord, A.v.d., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., Kalchbrenner, N., Senior, A., and Kavukcuoglu, K. (2016). Wavenet: A generative model for raw audio. arXiv.
6. Golany, T., Radinsky, K., and Freedman, D. (2020, January 12–18). SimGANs: Simulator-Based Generative Adversarial Networks for ECG Synthesis to Improve Deep ECG Classification. Proceedings of the International Conference on Machine Learning, Vienna, Austria.
7. DoseGAN: A generative adversarial network for synthetic dose prediction using attention-gated discrimination and generation10.1038/s41598-020-68062-7 ↗
8. Automatic classification of heartbeats using ECG morphology and heartbeat interval features10.1109/TBME.2004.827359 ↗
9. Eduardo, A., Aidos, H., and Fred, A. (2017, January 24–26). ECG-based biometrics using a deep autoencoder for feature learning-an empirical study on transferability. Proceedings of the International Conference on Pattern Recognition Applications and Methods, Porto, Portugal.10.5220/0006195404630470 ↗
10. Bishop, C.M. (2006). Pattern Recognition and Machine Learning, Springer.
11. Rajpurkar, P., Hannun, A.Y., Haghpanahi, M., Bourn, C., and Ng, A.Y. (2017). Cardiologist-level arrhythmia detection with convolutional neural networks. arXiv.
12. Adaptive neuro-fuzzy inference system for classification of EEG signals using wavelet coefficients10.1016/j.jneumeth.2005.04.013 ↗
13. Prasad, G.K., and Sahambi, J. (2003, January 15–17). Classification of ECG arrhythmias using multi-resolution analysis and neural networks. Proceedings of the TENCON 2003, Conference on Convergent Technologies for Asia-Pacific Region, Bangalore, India.
14. Kachuee, M., Fazeli, S., and Sarrafzadeh, M. (2018, January 4–7). Ecg heartbeat classification: A deep transferable representation. Proceedings of the 2018 IEEE International Conference on Healthcare Informatics (ICHI), New York, NY, USA.10.1109/ICHI.2018.00092 ↗
15. Deep learning approach for active classification of electrocardiogram signals10.1016/j.ins.2016.01.082 ↗
16. Choi, E., Biswal, S., Malin, B., Duke, J., Stewart, W.F., and Sun, J. (2017). Generating multi-label discrete patient records using generative adversarial networks. arXiv.
17. Torfi, A., and Beyki, M. (2019). Generating Synthetic Healthcare Records Using Convolutional Generative Adversarial Networks, Virginia Tech.
18. Jordon, J., Yoon, J., and van der Schaar, M. (May, January 30). PATE-GAN: Generating synthetic data with differential privacy guarantees. Proceedings of the International Conference on Learning Representations, Vancouver, BC, Canada.
19. Narváez, P., and Percybrooks, W.S. (2020). Synthesis of Normal Heart Sounds Using Generative Adversarial Networks and Empirical Wavelet Transform. Appl. Sci., 10.10.3390/app10197003 ↗
20. Aznan, N.K.N., Atapour-Abarghouei, A., Bonner, S., Connolly, J.D., Al Moubayed, N., and Breckon, T.P. (2019, January 14–19). Simulating brain signals: Creating synthetic eeg data via neural-based generative models for improved ssvep classification. Proceedings of the 2019 International Joint Conference on Neural Networks (IJCNN), Budapest, Hungary.
21. A novel approach to create synthetic biomedical signals using BiRNN10.1016/j.ins.2020.06.019 ↗
22. Multiple Imputation Ensembles (MIE) for dealing with missing data10.1007/s42979-020-00131-0 ↗
23. Mice: Multivariate imputation by chained equations in R
24. Random forest missing data algorithms10.1002/sam.11348 ↗
25. Tukey, J.W. (1977). Exploratory Data Analysis, Addison-Wesley. Reading.
26. (2020, January 10). Ensemble Methods: Bagging, Boosting and Stacking. Available online: https://towardsdatascience.com/ensemble-methods-bagging-boosting-and-stacking-c9214a10a205.
27. Generative adversarial nets
28. Brenninkmeijer, B., de Vries, A., Marchiori, E., and Hille, Y. (2019). On the Generation and Evaluation of Tabular Data Using GANs. [Master’s Thesis, Radboud University].
29. Xu, L., and Veeramachaneni, K. (2018). Synthesizing tabular data using generative adversarial networks. arXiv.
30. Arjovsky, M., Chintala, S., and Bottou, L. (2017). Wasserstein gan. arXiv.
31. Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., and Courville, A.C. (2017, January 4–9). Improved training of wasserstein gans. Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, CA, USA.
32. Bootstrapping and multiple imputation ensemble approaches for classification problems10.3233/JIFS-182656 ↗
33. Hazra, D., and Byun, Y.C. (2020). SynSigGAN: Generative Adversarial Networks for Synthetic Biomedical Signal Generation. Biology, 9.10.3390/biology9120441 ↗
34. Electrocardiogram generation with a bidirectional LSTM-CNN generative adversarial network