Time Series Prediction Using DBN and ARIMA

Hirata, Takaomi; Kuremoto, Takashi; Obayashi, Masanao; Mabu, Shingo; Kobayashi, Kunikazu

doi:10.1109/ccats.2015.15

Cited by 31 publications

(21 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Comparing to the conventional learning method of DBN, i.e., using Hinton's RBM unsupervised learning method [6] [8] and back-propagation (BP), the proposed method which used the reinforcement learning method SGA instead of BP showed its superiority according to the measure of the average prediction precision E 1 . Additionally, the result by the proposed method achieved the top of rank of all previous studies such as MLP with BP, the best prediction of CATS competition IJCNN'04 [5], the conventional DBNs with BP [8] [9], and hybrid models [10] [11]. The details are shown in Table 1.The optimal parameters obtained by random search method are shown in Table 2.…”

Section: Experiments Resultsmentioning

confidence: 82%

“…In [9] and [10], Kuremoto, Hirata, et al constructed a DBN with RBMs and a multi-layer perceptron (MLP) to improved the previous time series predictor with RBMs only. In this section, these conventional methods are introduced.…”

Section: Dbn With Bp Learning (The Conventional Method)mentioning

confidence: 99%

“…As a successful application, ANNs are utilized as time series predictors today [3]- [11]. Especially, a deep belief net (DBN) composed by restricted Boltzmann machines (RBMs) [6] and Multi-Layer Perceptron (MLP) [2] was proposed in [8]- [10] recently.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep Belief Network Using Reinforcement Learning and Its Applications to Time Series Forecasting

Hirata

Kuremoto

Obayashi

et al. 2016

Neural Information Processing

Self Cite

View full text Add to dashboard Cite

Abstract. Artificial neural networks (ANNs) typified by deep learning (DL) is one of the artificial intelligence technology which is attracting the most attention of researchers recently. However, the learning algorithm used in DL is usually with the famous error-backpropagation (BP) method. In this paper, we adopt a reinforcement learning (RL) algorithm "Stochastic Gradient Ascent (SGA)" proposed by Kimura & Kobayashi into a Deep Belief Nets (DBN) with multiple restricted Boltzmann machines instead of BP learning method. A longterm prediction experiment, which used a benchmark of time series forecasting competition, was performed to verify the effectiveness of the novel DL method.

show abstract

Section: Experiments Resultsmentioning

confidence: 82%

Section: Dbn With Bp Learning (The Conventional Method)mentioning

confidence: 99%

See 1 more Smart Citation

Deep Belief Network Using Reinforcement Learning and Its Applications to Time Series Forecasting

Hirata

Kuremoto

Obayashi

et al. 2016

Neural Information Processing

Self Cite

View full text Add to dashboard Cite

show abstract

“…This is also consistent with some other application results where the DBNs were trained without a mass of data. For example, in [49,50], the DBNs were applied to the time series prediction and the wind power prediction, which also do not have a large quantity of data. In both applications, the experimental results demonstrated that the DBN approach performs best compared with the traditional techniques.…”

Section: Resultsmentioning

confidence: 99%

Deep Belief Network Based Hybrid Model for Building Energy Consumption Prediction

Ding

et al. 2018

Energies

View full text Add to dashboard Cite

Abstract:To enhance the prediction performance for building energy consumption, this paper presents a modified deep belief network (DBN) based hybrid model. The proposed hybrid model combines the outputs from the DBN model with the energy-consuming pattern to yield the final prediction results. The energy-consuming pattern in this study represents the periodicity property of building energy consumption and can be extracted from the observed historical energy consumption data. The residual data generated by removing the energy-consuming pattern from the original data are utilized to train the modified DBN model. The training of the modified DBN includes two steps, the first one of which adopts the contrastive divergence (CD) algorithm to optimize the hidden parameters in a pre-train way, while the second one determines the output weighting vector by the least squares method. The proposed hybrid model is applied to two kinds of building energy consumption data sets that have different energy-consuming patterns (daily-periodicity and weekly-periodicity). In order to examine the advantages of the proposed model, four popular artificial intelligence methods-the backward propagation neural network (BPNN), the generalized radial basis function neural network (GRBFNN), the extreme learning machine (ELM), and the support vector regressor (SVR) are chosen as the comparative approaches. Experimental results demonstrate that the proposed DBN based hybrid model has the best performance compared with the comparative techniques. Another thing to be mentioned is that all the predictors constructed by utilizing the energy-consuming patterns perform better than those designed only by the original data. This verifies the usefulness of the incorporation of the energy-consuming patterns. The proposed approach can also be extended and applied to some other similar prediction problems that have periodicity patterns, e.g., the traffic flow forecasting and the electricity consumption prediction.

show abstract

“…As same as the RL method, SGA adopted to MLP, RBFN, and self-organized fuzzy neural network (SOFNN) [7]; the prediction precision of DBN utilized SGA may also be raised comparing to the BP learning algorithm. Furthermore, it is available to raise the prediction precision by a hybrid model which forecasts the future data by the linear model ARIMA at first and modifying the forecasting by the predicted error given by an ANN which is trained by error time series [13,14].…”

Section: Introductionmentioning

confidence: 99%

Training Deep Neural Networks with Reinforcement Learning for Time Series Forecasting

Kuremoto¹,

Hirata²,

Obayashi³

et al. 2019

Time Series Analysis - Data, Methods, and Applications

Self Cite

View full text Add to dashboard Cite

As a kind of efficient nonlinear function approximators, artificial neural networks (ANN) have been popularly applied to time series forecasting. The training method of ANN usually utilizes error back-propagation (BP) which is a supervised learning algorithm proposed by Rumelhart et al. in 1986; meanwhile, authors proposed to improve the robustness of the ANN for unknown time series prediction using a reinforcement learning algorithm named stochastic gradient ascent (SGA) originally proposed by Kimura and Kobayashi for control problems in 1998. We also successfully use a deep belief net (DBN) stacked by multiple restricted Boltzmann machines (RBMs) to realized time series forecasting in 2012. In this chapter, a stateof-the-art time series forecasting system that combines RBMs and multilayer perceptron (MLP) and uses SGA training algorithm is introduced. Experiment results showed the high prediction precision of the novel system not only for benchmark data but also for real phenomenon time series data.

show abstract

Time Series Prediction Using DBN and ARIMA

Cited by 31 publications

References 5 publications

Deep Belief Network Using Reinforcement Learning and Its Applications to Time Series Forecasting

Deep Belief Network Using Reinforcement Learning and Its Applications to Time Series Forecasting

Deep Belief Network Based Hybrid Model for Building Energy Consumption Prediction

Training Deep Neural Networks with Reinforcement Learning for Time Series Forecasting

Contact Info

Product

Resources

About