Prediction by a Hybrid of Wavelet Transform and Long-Short-Term-Memory Neural Network

Data originating from some specific fields, for in-stance tourist arrivals, may exhibit a high degree of fluctuations as well as non-linear characteristics due to time varying behaviors. This paper proposes a new hybrid method to perform prediction for such data. The proposed hybrid model of wavelet transform and long-short-term memory (LSTM) recurrent neural network (RNN) is able to capture non-linear attributes in tourist arrival time series. Firstly, data is decomposed into constitutive series through wavelet transform. The decomposition is expressed as a function of a combination of wavelet coefficients, which have different levels of resolution. Then, LSTM neural network is used to train and simulate the value at each level to find the bias vectors and weighting coefficients for the prediction value. A sliding windows model is employed to capture the time series nature of the data. An evaluation is conducted to compare the proposed model with other RNN algorithms, i.e., Elman RNN and Jordan RNN, as well as the combination of wavelet transform with each of them. The result shows that the proposed model has better performance in terms of training time than the original LSTM RNN, while the accuracy is better than the hybrid of wavelet-Elman and the hybrid of wavelet-Jordan.

[1]  Prasanta K. Jana,et al.  Efficient task scheduling algorithms for heterogeneous multi-cloud environment , 2015, 2014 International Conference on Advances in Computing, Communications and Informatics (ICACCI).

[2]  Kai Chen,et al.  A LSTM-based method for stock returns prediction: A case study of China stock market , 2015, 2015 IEEE International Conference on Big Data (Big Data).

[3]  Seoung Bum Kim,et al.  Time series forecasting based on wavelet filtering , 2015, Expert Syst. Appl..

[4]  Sorin Moga,et al.  A wavelet based prediction method for time series , 2010 .

[5]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[6]  Luis F. Ortega.  A Neuro-wavelet Method for the Forecasting of Financial Time Series , 2012 .

[7]  Jürgen Schmidhuber,et al.  Learning Precise Timing with LSTM Recurrent Networks , 2003, J. Mach. Learn. Res..

[8]  Kyoji Kawagoe,et al.  A similarity search method of time series data with combination of Fourier and wavelet transforms , 2002, Proceedings Ninth International Symposium on Temporal Representation and Reasoning.

[9]  Zhiping Lin,et al.  Predicting time series with wavelet packet neural networks , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[10]  Fionn Murtagh,et al.  On neuro-wavelet modeling , 2004, Decis. Support Syst..

[11]  Prasanta K. Jana,et al.  A multi-objective task scheduling algorithm for heterogeneous multi-cloud environment , 2015, 2015 International Conference on Electronic Design, Computer Networks & Automated Verification (EDCAV).

[12]  Z. Zainuddin,et al.  Improving the Convergence of the Backpropagation Algorithm Using Local Adaptive Techniques , 2007, International Conference on Computational Intelligence.

[13]  T. Yahagi,et al.  Nonlinear time series prediction using wavelet networks with Kalman filter based algorithm , 2005, 2005 IEEE International Conference on Industrial Technology.

[14]  T. Chai,et al.  Root mean square error (RMSE) or mean absolute error (MAE)? – Arguments against avoiding RMSE in the literature , 2014 .

[15]  Longsheng Cheng,et al.  Financial Crisis Dynamic Prediction Based on Sliding Window Technology and Mahalanobis-Taguchi System , 2011, 2011 International Conference of Information Technology, Computer Engineering and Management Sciences.

[16]  Li Pan,et al.  Predicting Short-Term Traffic Flow by Long Short-Term Memory Recurrent Neural Network , 2015, 2015 IEEE International Conference on Smart City/SocialCom/SustainCom (SmartCity).

[17]  Natasa Terzija,et al.  Robust digital image watermarking algorithms for copyright protection , 2006 .

[18]  Piotr Fryzlewicz,et al.  Forecasting non-stationary time series by wavelet process modelling , 2003 .

[19]  Andrew W. Senior,et al.  Long short-term memory recurrent neural network architectures for large scale acoustic modeling , 2014, INTERSPEECH.

[20]  Budi Rahmani.  Early Model of Traffic Sign Reminder Based on Neural Network , 2012 .

[21]  Jürgen Schmidhuber,et al.  Learning to forget: continual prediction with LSTM , 1999 .

[22]  Juan Zamora,et al.  A Wavelet-Based Method for Time Series Forecasting , 2012, 2012 31st International Conference of the Chilean Computer Science Society.

[23]  Uros Lotric.  Wavelet based denoising integrated into multilayered perceptron , 2004, Neurocomputing.

[24]  Mohammad Kazem Sheikh-El-Eslami,et al.  Price forecasting of day-ahead electricity markets using a hybrid forecast method , 2011 .

[25]  Martin Reczko,et al.  Bidirectional Long Short-Term Memory Networks for Predicting the Subcellular Localization of Eukaryotic Proteins , 2007, IEEE ACM Trans. Comput. Biol. Bioinform..

[26]  D. Shah,et al.  Efficient Implementations of Discrete Wavelet Transforms Using Fpgas , 2011 .

[27]  Weria Khaksar,et al.  An artificial neural network hybrid with wavelet transform for short-term wind speed forecasting: A preliminary case study , 2015, 2015 International Conference on Science in Information Technology (ICSITech).