Finding an Accurate Early Forecasting Model from Small Dataset: A Case of 2019-nCoV Novel Coronavirus Outbreak

• Autores: Rubén González Crespo , Enrique Herrera Viedma , Nilanjan Dey, Simon James Fong, Gloria Li
• Localización: IJIMAI, ISSN-e 1989-1660, Vol. 6, Nº. 1, 2020, págs. 132-140
• Idioma: español
• DOI: 10.9781/ijimai.2020.02.002
• Enlaces
  • Texto completo (pdf)
• Dialnet Métricas: 6 Citas
• Resumen

  • Epidemic is a rapid and wide spread of infectious disease threatening many lives and economy damages. It is important to fore-tell the epidemic lifetime so to decide on timely and remedic actions. These measures include closing borders, schools, suspending community services and commuters. Resuming such curfews depends on the momentum of the outbreak and its rate of decay. Being able to accurately forecast the fate of an epidemic is an extremely important but difficult task. Due to limited knowledge of the novel disease, the high uncertainty involved and the complex societal-political factors that influence the widespread of the new virus, any forecast is anything but reliable. Another factor is the insufficient amount of available data. Data samples are often scarce when an epidemic just started. With only few training samples on hand, finding a forecasting model which offers forecast at the best efforts is a big challenge in machine learning. In the past, three popular methods have been proposed, they include 1) augmenting the existing little data, 2) using a panel selection to pick the best forecasting model from several models, and 3) fine-tuning the parameters of an individual forecasting model for the highest possible accuracy. In this paper, a methodology that embraces these three virtues of data mining from a small dataset is proposed. An experiment that is based on the recent coronavirus outbreak originated from Wuhan is conducted by applying this methodology. It is shown that an optimized forecasting model that is constructed from a new algorithm, namely polynomial neural network with corrective feedback (PNN+cf) is able to make a forecast that has relatively the lowest prediction error. The results showcase that the newly proposed methodology and PNN+cf are useful in generating acceptable forecast upon the critical time of disease outbreak when the samples are far from abundant.

• Referencias bibliográficas
  • “WHO | Novel Coronavirus – China”. WHO. Archived from the original on 23 January 2020. Retrieved 1 February 2020.
  • Cohen, Jon (January 2020). “Wuhan seafood market may not be source of novel virus spreading globally”. Science. doi:10.1126/science.abb0611....
  • “Statement on the second meeting of the International Health Regulations (2005) Emergency Committee regarding the outbreak of novel coronavirus...
  • Sparrow, Annie. “How China’s Coronavirus Is Spreading—and How to Stop It”. Foreign Policy. Archived from the original on 31 January 2020....
  • Croda, R. M. C., D. E. G. Romero, and S. O. C. Morales, “Sales Prediction through Neural Networks for a Small Dataset”, International Journal...
  • R. J. Hyndman, and A. V. Kostenko, “Minimum sample size requirements for seasonal forecasting models,” Foresight, vol. 6, pp. 12-15, 2007.
  • S. Ingrassia, and I. Morlini, “Neural network modeling for small datasets,” Technometrics, vol.47, no. 3, pp. 297-311, 2005.
  • A. Pasini, “Artificial neural networks for small dataset analysis.” Journal of thoracic disease, vol. 7, no. 5, pp- 953, 2015.
  • M. A. Lateh, A. K. Muda, Z. I. M. Yusof, N. A. Muda and M. S. Azmi, “Handling a Small Dataset Problem in Prediction Model by employ Artificial...
  • R. Andonie, “Extreme data mining: Inference from small datasets,” Int. J. Comput. Commun. Control, vol. 5, no. 3, pp. 280–291, 2010.
  • T. Shaikhina, N. A.Khovanova, “Handling limited datasets with neural networks in medical applications: A small-data approach”, Artificial...
  • J. F. Slifker and S. S. Shapiro, “The Johnson system: selection and parameter estimation,” Technometrics, vol. 22, no. 2, pp. 239–246, 1980
  • R. Adhikari, and R. K. Agrawal, “An introductory study on time series modeling and forecasting,” arXiv preprint arXiv:1302.6613, 2013.
  • A. Singh, and G. C. Mishra, “Application of Box-Jenkins method and Artificial Neural Network procedure for time series forecasting of prices,”...
  • Arun, V., M. Krishna, B. V. Arunkumar, S. K. Padma, and V. Shyam, “Exploratory Boosted Feature Selection and Neural Network Framework for...
  • A. G. Ivakhnenko (1970) “Heuristic Self-Organization in Problems of Engineering Cybernetics”. Automatica Vol. 6, pp.207–219.
  • A. G. Ivakhnenko, and A. A. Zholnarskiy, (1992) “Estimating the coefficients of polynomials in parametric GMDH algorithms by the improved...
  • S. K. Oh, W. Pedrycz, B. J. Park, “Polynomial neural networks architecture: analysis and design”, Computers & Electrical Engineering,...
  • A. Andoni, R. Panigrahy, G. Valiant, L. Zhang, “Learning Polynomials with Neural Networks”, Proceedings of the 31 st International Conference...
  • S. Fong, N. N. Zhou, R. K. Wong, X. S. Yang: Rare Events Forecasting Using a Residual-Feedback GMDH Neural Network. ICDM Workshops 2012: 464-473.
  • N. Dey, S. Fong, W. Song, K. Cho (2018) Forecasting Energy Consumption from Smart Home Sensor Network by Deep Learning. In: Deshpande A. et...
  • W. Waheeb, and R. Ghazali, Forecasting the Behavior of Gas Furnace Multivariate Time Series Using Ridge Polynomial Based Neural Network Models,...
  • S. K. Shevade, S. S. Keerthi, C. Bhattacharyya, K.R.K. Murthy: Improvements to the SMO Algorithm for SVM Regression. In: IEEE Transactions...
  • J. Su, H. Zhang, A fast decision tree learning algorithm, AAAI’06: Proceedings of the 21st national conference on Artificial intelligence...
  • Y. Wang, I. H. Witten: Induction of model trees for predicting continuous classes. In: Poster papers of the 9th European Conference on Machine...