Ensemble Deep Learning Models for Forecasting Cryptocurrency Time-Series

Livieris, Ioannis E.; Pintelas, Emmanuel G.; Stavroyiannis, Stavros; Pintelas, Panayiotis E.

doi:10.3390/a13050121

Cited by 94 publications

(52 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A common method for combining base models is averaging. Averaging has the advantage of reducing variance in the predictions based on the understanding that the based models will not make similar errors in their predictions [ 57 ]. It involves the generation and training of a specific number of models separately and combining them through the computation of the mean of the predicted class scores.…”

Section: Resultsmentioning

confidence: 99%

Health Condition Estimation of Bearings with Multiple Faults by a Composite Learning-Based Approach

Inyang

Petrunin

Jennions

2021

Sensors

View full text Add to dashboard Cite

Bearings are critical components found in most rotating machinery; their health condition is of immense importance to many industries. The varied conditions and environments in which bearings operate make them prone to single and multiple faults. Widespread interest in the improvements of single fault diagnosis meant limited attention was spent on multiple fault diagnosis. However, multiple fault diagnosis poses extra challenges due to the submergence of the weak fault by the strong fault, presence of non-Gaussian noise, coupling of the frequency components, etc. A number of existing convolutional neural network models operate on a distinct feature that is not enough to assure reliable results in the presence of these challenges. In this paper, extended feature sets in three homogenous deep learning models are used for multiple fault diagnosis. This ensures a measure of diversity is introduced to the health management dataset to obtain complementary solutions from the models. The outputs of the models are fused through blending ensemble learning. Experiments using vibration datasets based on bearing multiple faults show an accuracy of 98.54%, with an improvement of 2.74% in the overall effectiveness over the single models. Compared with other technologies, the results show that this approach provides an improved generalized diagnostic capability.

show abstract

Section: Resultsmentioning

confidence: 99%

Health Condition Estimation of Bearings with Multiple Faults by a Composite Learning-Based Approach

Inyang

Petrunin

Jennions

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…However, they do not evaluate whether the model properly fits the data while the residuals are usually dedicated to evaluating this. Therefore, we evaluated the forecasting reliability of the proposed models by examining for auto-correlation in the errors [35,36]. Figures 3-5 illustrate the autocorrelation function (ACF) diagram for Dez reservoir inflow forecasting by FSF-ARIMA model, RANN model, and Hybrid model, respectively.…”

Section: Resultsmentioning

confidence: 99%

“…Although the hybrid model outperformed the RANN and FSF-ARIMA models, the ACF plots revealed that all models were unable to make reliable forecasts. It is worth mentioning that employing a more advanced model such as long short-term memory (LSTM) and deep learning techniques like the Convolutional Neural Network (CNN), as well as their combination, CNN-LSTM [35,36], can improve the accuracy of forecasting. In addition, these new models have shown more reliable forecasts [35,36].…”

mentioning

confidence: 99%

“…It is worth mentioning that employing a more advanced model such as long short-term memory (LSTM) and deep learning techniques like the Convolutional Neural Network (CNN), as well as their combination, CNN-LSTM [35,36], can improve the accuracy of forecasting. In addition, these new models have shown more reliable forecasts [35,36]. Therefore, there are open avenues to compare the results of this study with LSTM and CNN-LSTM in future investigations.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Improving Daily Peak Flow Forecasts Using Hybrid Fourier-Series Autoregressive Integrated Moving Average and Recurrent Artificial Neural Network Models

Banihabib

Bandari

Valipour

2020

View full text Add to dashboard Cite

In multi-purpose reservoirs, to achieve optimal operation, sophisticated models are required to forecast reservoir inflow in both short- and long-horizon times with an acceptable accuracy, particularly for peak flows. In this study, an auto-regressive hybrid model is proposed for long-horizon forecasting of daily reservoir inflow. The model is examined for a one-year horizon forecasting of high-oscillated daily flow time series. First, a Fourier-Series Filtered Autoregressive Integrated Moving Average (FSF-ARIMA) model is applied to forecast linear behavior of daily flow time series. Second, a Recurrent Artificial Neural Network (RANN) model is utilized to forecast FSF-ARIMA model’s residuals. The hybrid model follows the detail of observed flow time variation and forecasted peak flow more accurately than previous models. The proposed model enhances the ability to forecast reservoir inflow, especially in peak flows, compared to previous linear and nonlinear auto-regressive models. The hybrid model has a potential to decrease maximum and average forecasting error by 81% and 80%, respectively. The results of this investigation are useful for stakeholders and water resources managers to schedule optimum operation of multi-purpose reservoirs in controlling floods and generating hydropower.

show abstract

“…Let us quote other relevant works. Shintate & Pichl (2019) , Ji, Kim & Im (2019) , Livieris et al (2020) , Lamothe-Fernández et al (2020) , and Chen, Li & Sun (2020) predicted Bitcoin price at different frequencies using several machine learning techniques and investigating the importance of the sample dimension. Greaves & Au (2015) investigated the predictive power of blockchain network-based features on the bitcoin price.…”

Section: Related Workmentioning

confidence: 99%

Predictions of bitcoin prices through machine learning based frameworks

Cocco¹,

Tonelli²,

Marchesi³

2021

PeerJ Computer Science

View full text Add to dashboard Cite

The high volatility of an asset in financial markets is commonly seen as a negative factor. However short-term trades may entail high profits if traders open and close the correct positions. The high volatility of cryptocurrencies, and in particular of Bitcoin, is what made cryptocurrency trading so profitable in these last years. The main goal of this work is to compare several frameworks each other to predict the daily closing Bitcoin price, investigating those that provide the best performance, after a rigorous model selection by the so-called k-fold cross validation method. We evaluated the performance of one stage frameworks, based only on one machine learning technique, such as the Bayesian Neural Network, the Feed Forward and the Long Short Term Memory Neural Networks, and that of two stages frameworks formed by the neural networks just mentioned in cascade to Support Vector Regression. Results highlight higher performance of the two stages frameworks with respect to the correspondent one stage frameworks, but for the Bayesian Neural Network. The one stage framework based on Bayesian Neural Network has the highest performance and the order of magnitude of the mean absolute percentage error computed on the predicted price by this framework is in agreement with those reported in recent literature works.

show abstract

Ensemble Deep Learning Models for Forecasting Cryptocurrency Time-Series

Cited by 94 publications

References 40 publications

Health Condition Estimation of Bearings with Multiple Faults by a Composite Learning-Based Approach

Health Condition Estimation of Bearings with Multiple Faults by a Composite Learning-Based Approach

Improving Daily Peak Flow Forecasts Using Hybrid Fourier-Series Autoregressive Integrated Moving Average and Recurrent Artificial Neural Network Models

Predictions of bitcoin prices through machine learning based frameworks

Contact Info

Product

Resources

About