Publications

@article{JIMENEZ-NAVARRO24,

title = {Explaining deep learning models for ozone pollution prediction via embedded feature selection},

author = {M. J. Jiménez-Navarro and M. Martínez-Ballesteros and F. Martínez-Álvarez and G. Asencio-Cortés},

url = {https://www.sciencedirect.com/science/article/pii/S1568494624002783},

doi = {https://doi.org/10.1016/j.asoc.2024.111504},

year  = {2024},

date = {2024-04-04},

journal = {Applied Soft Computing},

volume = {157},

pages = {111504},

abstract = {Ambient air pollution is a pervasive global issue that poses significant health risks. Among pollutants, ozone (O3) is responsible for an estimated 1 to 1.2 million premature deaths yearly. Furthermore, O3 adversely affects climate warming, crop productivity, and more. Its formation occurs when nitrogen oxides and volatile organic compounds react with short-wavelength solar radiation. Consequently, urban areas with high traffic volume and elevated temperatures are particularly prone to elevated O3 levels, which pose a significant health risk to their inhabitants. In response to this problem, many countries have developed web and mobile applications that provide real-time air pollution information using sensor data. However, while these applications offer valuable insight into current pollution levels, predicting future pollutant behavior is crucial for effective planning and mitigation strategies. Therefore, our main objectives are to develop accurate and efficient prediction models and identify the key factors that influence O3 levels. We adopt a time series forecasting approach to address these objectives, which allows us to analyze and predict O3 future behavior. Additionally, we tackle the feature selection problem to identify the most relevant features and periods that contribute to prediction accuracy by introducing a novel method called the Time Selection Layer in Deep Learning models, which significantly improves model performance, reduces complexity, and enhances interpretability. Our study focuses on data collected from five representative areas in Seville, Cordova, and Jaen provinces in Spain, using multiple sensors to capture comprehensive pollution data. We compare the performance of three models: Lasso, Decision Tree, and Deep Learning with and without incorporating the Time Selection Layer. Our results demonstrate that including the Time Selection Layer significantly enhances the effectiveness and interpretability of Deep Learning models, achieving an average effectiveness improvement of 9% across all monitored areas.},

keywords = {deep learning, feature selection, time series, XAI},

pubstate = {published},

tppubtype = {article}

}

@article{GARCIA-SOTO24,

title = {Water consumption time series forecasting in urban centers using deep neural networks},

author = {C. G. García-Soto and J. F. Torres and M. A. Zamora-Izquierdo and J. Palma and A. Troncoso},

url = {https://link.springer.com/article/10.1007/s13201-023-02072-4},

doi = {https://doi.org/10.1007/s13201-023-02072-4},

year  = {2024},

date = {2024-01-12},

journal = {Applied Water Science},

volume = {14},

pages = {1-14},

abstract = {The time series analysis and prediction techniques are highly valued in many application felds, such as economy, medicine and biology, environmental sciences or meteorology, among others. In the last years, there is a growing interest in the sustainable and optimal management of a resource as scarce as essential: the water. Forecasting techniques for water management can be used for diferent time horizons from the planning of constructions that can respond to long-term needs, to the detection of anomalies in the operation of facilities or the optimization of the operation in the short and medium term. In this paper, a deep neural network is specifcally designed to predict water consumption in the short-term. Results are reported using the time series of water consumption for a year and a half measured with 10-min frequency in the city of Murcia, the seventh largest city in Spain by number of inhabitants. The results are compared with K Nearest Neighbors, Random Forest, Extreme Gradient Boosting, Seasonal Autoregressive Integrated Moving Average and two persistence models as naive methods, showing the proposed deep learning model the most accurate results.},

keywords = {deep learning, forecasting, time series},

pubstate = {published},

tppubtype = {article}

}

@article{TRONCOSO-GARCIA23b,

title = {Explainable hybrid deep learning and Coronavirus Optimization Algorithm for improving evapotranspiration forecasting},

author = {A. R. Troncoso-García and I. S. Brito and A. Troncoso and F. Mártinez-Álvarez},

url = {https://www.sciencedirect.com/science/article/pii/S0168169923007755},

doi = {https://doi.org/10.1016/j.compag.2023.108387},

year  = {2023},

date = {2023-11-08},

journal = {Computers and Electronics in Agriculture},

volume = {215},

pages = {108387},

abstract = {Reference evapotranspiration is a critical hydrological measurement closely associated with agriculture. Accurate forecasting is vital in effective water management and crop planning in sustainable agriculture. In this study, the future values of reference evapotranspiration are forecasted by applying a recurrent long shortterm memory neural network optimized using the Coronavirus Optimization Algorithm, a novel bioinspired metaheuristic based on the spread of COVID-19. The input data is sourced from the Sistema Agrometeorológico para a Gestão da Rega no Alentejo, in Portugal, with meteorological data such as air temperature or wind speed. Several baseline models are applied to the same problem to facilitate comparisons, including support vector machines, multi-layer perceptron, Lasso and decision tree. The results demonstrate the successful forecasting performance of the proposed model and its potential in this field. In turn, to gain deeper insights into the model’s inner workings, the SHapley Additive exPlanation tool is applied for explainability. Consequently, the study identifies the most relevant variables for reference evapotranspiration forecasting, including previously measured evapotranspiration values. Additionally, a univariable model is tested using historic evapotranspiration values as input, offering a comparable performance with a considerable reduction of computational time},

keywords = {deep learning, forecasting, precision agriculture, XAI},

pubstate = {published},

tppubtype = {article}

}

@article{HADJOUT23,

title = {Electricity consumption forecasting with outliers handling based on clustering and deep learning with application to the Algerian market},

author = {D. Hadjout and A. Sebaa and J. F. Torres and F. Mártinez-Álvarez},

url = {https://www.sciencedirect.com/science/article/abs/pii/S0957417423006255},

doi = {https://doi.org/10.1016/j.eswa.2023.120123},

year  = {2023},

date = {2023-10-01},

journal = {Expert Systems with Applications},

volume = {227},

pages = {120123},

abstract = {The reduction of electricity loss and the effective management of electricity demand are vital operations for production and distribution electricity enterprises. To achieve these goals, accurate forecasts of aggregate and individual electricity consumers are necessary. A novel multistep forecasting method is developed to forecast medium-term electricity consumption of the Algerian economic sector. The proposed method goes through the following three steps: cleaning steps, clustering steps and forecasting step of each cluster. The aim of the first step is to detect and then replace outliers. To complete the first phase, Robust Exponential and Holt-Winters Smoothing algorithms are adapted. Then, to carry out accurate forecasting at a lowest level, K-Shape and K-Means clustering methods are utilized to extract similarities and identify customer consumption patterns as a second step. The third step entails developing a deep learning model based on Gated Recurrent Units to forecast the electricity consumption in each cluster. To validate the proposed method, we compared our results to the most known methods in literature like Autoregressive Integrated Moving Average, Seasonal Grey Model, LSTM networks, Temporal Convolutional Networks and two ensemble models. The results of several experiments conducted with 2000 electricity consumers during 14 years from an Algeria province (Bejaia) demonstrate that the proposed method provides remarkable prediction performances. Thus, prediction performances of the K-Shape-based clustering method reach much higher prediction accuracy. According to the MAPE metric, the results of the best predictions are equal to 2.04%. It is also notable that 87% of the clients have a considerably low prediction error.},

keywords = {clustering, deep learning, energy, time series},

pubstate = {published},

tppubtype = {article}

}

@article{JIMENEZ-NAVARRO23c,

title = {A New Deep Learning Architecture with Inductive Bias Balance for Oil Temperature Forecasting},

author = {M. J. Jiménez-Navarro and M. Martínez-Ballesteros and F. Martínez-Álvarez and G. Asencio-Cortés},

url = {https://journalofbigdata.springeropen.com/articles/10.1186/s40537-023-00745-0},

doi = {https://doi.org/10.1186/s40537-023-00745-0},

year  = {2023},

date = {2023-05-28},

journal = {Journal of Big Data},

volume = {10},

pages = {80},

abstract = {Ensuring the optimal performance of power transformers is a laborious task in which the insulation system plays a vital role in decreasing their deterioration. The insulation system uses insulating oil to control temperature, as high temperatures can reduce the lifetime of the transformers and lead to expensive maintenance. Deep learning architectures have been demonstrated remarkable results in various fields. However, this improvement often comes at the cost of increased computing resources, which, in turn, increases the carbon footprint and hinders the optimization of architectures. In this study, we introduce a novel deep learning architecture that achieves a comparable efficacy to the best existing architectures in transformer oil temperature forecasting while improving efficiency. Effective forecasting can help prevent high temperatures and monitor the future condition of power transformers, thereby reducing unnecessary waste. To balance the inductive bias in our architecture, we propose the Smooth Residual Block, which divides the original problem into multiple subproblems to obtain different representations of the time series, collaboratively achieving the final forecasting. We applied our architecture to the Electricity Transformer datasets, which obtain transformer insulating oil temperature measures from two transformers in China. The results showed a 13% improvement in MSE and a 57% improvement in performance compared to the best current architectures, to the best of our knowledge. Moreover, we analyzed the architecture behavior to gain an intuitive understanding of the achieved solution.},

keywords = {deep learning, time series},

pubstate = {published},

tppubtype = {article}

}

@article{JIMENEZ-NAVARRO23b,

title = {PHILNet: A Novel Efficient Approach for Time Series Forecasting using Deep Learning},

author = {M. J. Jiménez-Navarro and M. Martínez-Ballesteros and F. Martínez-Álvarez and G. Asencio-Cortés},

url = {https://doi.org/10.1016/j.ins.2023.03.021},

doi = {https://www.sciencedirect.com/science/article/pii/S0020025523003183?via%3Dihub},

year  = {2023},

date = {2023-03-03},

journal = {Information Sciences},

volume = {632},

pages = {815-832},

abstract = {Time series is one of the most common data types in the industry nowadays. Forecasting the future of a time series behavior can be useful in planning ahead, saving time, resources, and helping avoid undesired scenarios. To make the forecasting, historical data is utilized due to the causal nature of the time series. Several deep learning algorithms have been presented in this area, where the input is processed through a series of non-linear functions to produce the output. We present a novel strategy to improve the performance of deep learning models in time series forecasting in terms of efficiency while reaching similar effectiveness. This approach separates the model into levels, starting with the easiest and continuing to the most difficult. The simpler levels deal with smoothed versions of the input, whereas the most sophisticated level deals with the raw data. This strategy seeks to mimic the human learning process, in which basic tasks are completed initially, followed by more precise and sophisticated ones. Our method achieved promising results, obtaining a 35% improvement in mean squared error and a 2.6 time decrease in training time compared with the best models found in a variety of time series.},

keywords = {deep learning, time series},

pubstate = {published},

tppubtype = {article}

}

@article{EJIGU23,

title = {A Bayesian Optimization-Based LSTM Model for Wind Power Forecasting in the Adama District, Ethiopia},

author = {E. T. Habtemariam and K. Kekeba and M. Martínez-Ballesteros and F. Mártinez-Álvarez},

url = {https://www.mdpi.com/1996-1073/16/5/2317},

doi = {https://doi.org/10.3390/en16052317},

year  = {2023},

date = {2023-02-19},

journal = {Energies},

volume = {16},

pages = {2317},

abstract = {Renewable energies such as solar and wind power have become promising sources of energy to address the increase in greenhouse gases caused by the use of fossil fuels and to resolve current energy crises. Integrating wind energy into a large-scale electric grid presents a significant challenge due to the high intermittency and nonlinear behavior of wind power. Accurate wind power forecasting is essential for safe and efficient integration into the grid system. Many prediction models have been developed to predict the uncertain and nonlinear time series of wind power, but most neglect the use of Bayesian optimization to optimize the hyperparameters while training deep learning algorithms. The efficiency of grid search strategies decreases as the number of hyperparameters increases, and computation time complexity becomes an issue. This paper presents a robust and optimized Long-Short Term Memory network for forecasting wind power generation in the day ahead in the context of Ethiopia's renewable energy sector. The proposal uses Bayesian optimization to find the best hyperparameter combination in a reasonable computation time. The results indicate that tuning hyperparameters using this metaheuristic prior to building deep learning models significantly improves the predictive performance of the models. The proposed models were evaluated using MAE, RMSE, and MAPE metrics and outperformed both the baseline models and the optimized Gated Recurrent Unit architecture.},

keywords = {deep learning, time series},

pubstate = {published},

tppubtype = {article}

}

@article{JIMENEZ-NAVARRO23a,

title = {From Simple to Complex: A Sequential Method for Enhancing Time Series Forecasting with Deep Learning},

author = {M. J. Jiménez-Navarro and M. Martínez-Ballesteros and F. Mártinez-Álvarez and A. Troncoso and G. Asencio-Cortés},

year  = {2023},

date = {2023-01-20},

journal = {Logic Journal of the IGPL},

volume = {in press},

abstract = {Time series forecasting is a well-known deep learning application field in which previous data are used to predict the future behavior of the series. Recently, several deep learning approaches have been proposed in which several nonlinear functions are applied to the input to obtain the output. In this paper, we introduce a novel method to improve the performance of deep learning models in time series forecasting. This method divides the model into hierarchies or levels from simpler to more complex ones. Simpler levels handle smoothed versions of the input, whereas the most complex level processes the original time series. This method follows the human learning process where general/simpler tasks are performed first, and afterward, more precise/harder ones are accomplished.Our proposed methodology has been applied to the LSTM architecture, showing remarkable performance in various time series. In addition, a comparison is reported including a standard LSTM and novel methods such as DeepAR, Temporal Fusion Transformer (TFT), NBEATS and Echo State Network (ESN).},

keywords = {deep learning, time series},

pubstate = {published},

tppubtype = {article}

}

@article{Melgar2023c,

title = {A novel semantic segmentation approach based on U-Net, WU-Net, and U-Net++ deep learning for predicting areas sensitive to pluvial flood at tropical area},

author = {L. Melgar-García and F. Martínez-Álvarez and D. T. Bui and A. Troncoso},

url = {https://www.tandfonline.com/doi/full/10.1080/17538947.2023.2252401},

doi = {https://doi.org/10.1080/17538947.2023.2252401},

year  = {2023},

date = {2023-01-01},

journal = {International Journal of Digital Earth},

volume = {16},

number = {1},

pages = {3661-3679},

keywords = {deep learning, natural disasters},

pubstate = {published},

tppubtype = {article}

}

@article{HADJOUT22,

title = {Electricity consumption forecasting based on ensemble deep learning with application to the Algerian market},

author = {D. Hadjout and J. F. Torres and A. Troncoso and A. Sebaa and F. Martínez-Álvarez},

url = {https://www.sciencedirect.com/science/article/pii/S0360544221033090},

doi = {https://doi.org/10.1016/j.energy.2021.123060},

year  = {2022},

date = {2022-03-15},

journal = {Energy},

volume = {243},

pages = {123060},

abstract = {The economic sector is one of the most important pillars of countries. Economic activities of industry are intimately linked with the ability to meet their needs for electricity. Therefore, electricity forecasting is a very important task. It allows for better planning and management of energy resources. Several methods have been proposed to forecast energy consumption. In this work, to predict monthly electricity consumption for the economic sector, we develop a novel approach based on ensemble learning. Our approach combines three models that proved successful in the field, namely: Long Short Term Memory and Gated Recurrent Unit neural networks, and Temporal Convolutional Networks. The experiments have been conducted with almost 2000 clients and 14 years of monthly electricity consumption from Bejaia, Algeria. The results show that the proposed ensemble models achieve better performance than both the company's requirements and the prediction of the traditional individual models. Finally, statistical tests have been carried out to prove that significance of the ensemble models developed.},

keywords = {deep learning, energy, time series},

pubstate = {published},

tppubtype = {article}

}

@article{TORRES22b,

title = {A deep LSTM network for the Spanish electricity consumption forecasting},

author = {J. F. Torres and F. Martínez-Álvarez and A. Troncoso},

url = {https://link.springer.com/article/10.1007/s00521-021-06773-2},

doi = {https://doi.org/10.1007/s00521-021-06773-2},

year  = {2022},

date = {2022-02-05},

journal = {Neural Computing and Applications},

volume = {34},

pages = {10533-10545},

abstract = {Nowadays, electricity is a basic commodity necessary for the well-being of any modern society. Due to the growth in electricity consumption in recent years, mainly in large cities, electricity forecasting is key to the management of an efficient, sustainable and safe smart grid for the consumer. In this work, a deep neural network is proposed to address the electricity consumption forecasting in the short-term, namely, a long short-term memory (LSTM) network due to its ability to deal with sequential data such as time-series data. First, the optimal values for certain hyper-parameters have been obtained by a random search and a metaheuristic, called coronavirus optimization algorithm (CVOA), based on the propagation of the SARS-Cov-2 virus. Then, the optimal LSTM has been applied to predict the electricity demand with 4-h forecast horizon. Results using Spanish electricity data during nine years and half measured with 10-min frequency are presented and discussed. Finally, the performance of the proposed LSTM using random search and the LSTM using CVOA is compared, on the one hand, with that of recently published deep neural networks (such as a deep feed-forward neural network optimized with a grid search) and temporal fusion transformers optimized with a sampling algorithm, and, on the other hand, with traditional machine learning techniques, such as a linear regression, decision trees and tree-based ensemble techniques (gradient-boosted trees and random forest), achieving the smallest prediction error below 1.5%.},

keywords = {deep learning, energy},

pubstate = {published},

tppubtype = {article}

}

@article{BUI22b,

title = {Deformation forecasting of a hydropower dam by hybridizing a Long Short-Term Memory deep learning network with the Coronavirus Optimization Algorithm},

author = {K.-T. T. Bui and J. F. Torres and D. Gutiérrez-Avilés and V. H. Nhu and F. Martínez-Álvarez and D. T. Bui},

url = {https://onlinelibrary.wiley.com/doi/abs/10.1111/mice.12810},

doi = {https://doi.org/10.1111/mice.12810},

year  = {2021},

date = {2021-11-24},

journal = {Computer-Aided Civil and Infrastructure Engineering},

volume = {37},

pages = {1368-1386},

abstract = {The safety operation and management of hydropower dam play a critical role in social-economic development and ensure people's safety in many countries; therefore, modeling and forecasting the hydropower dam's deformations with high accuracy is crucial. This research aims to propose and validate a new model based on deep learning long short-term memory (LSTM) and the coronavirus optimization algorithm (CVOA), named CVOA-LSTM, for forecasting the deformations of the hydropower dam. The second-largest hydropower dam of Vietnam, located in the Hoa Binh province, is focused. Herein, we used the LSTM to establish the deformation model, whereas the CVOA was utilized to optimize the three parameters of the LSTM, the number of hidden layers, the learning rate, and the dropout. The efficacy of the proposed CVOA-LSTM model is assessed by comparing its forecasting performance with state-of-the-art benchmarks, sequential minimal optimization for support vector regression, Gaussian process, M5' model tree, multilayer perceptron neural network, reduced error pruning tree, random tree, random forest, and radial basis function neural network. The result shows that the proposed CVOA-LSTM model has high forecasting capability (R2 = 0.874, root mean square error = 0.34, mean absolute error = 0.23) and outperforms the benchmarks. We conclude that CVOA-LSTM is a new tool that can be considered to forecast the hydropower dam's deformations.},

keywords = {deep learning, time series},

pubstate = {published},

tppubtype = {article}

}

@article{TORRES21,

title = {Deep Learning for Time Series Forecasting: A Survey},

author = {J. F. Torres and D. Hadjout and A. Sebaa and F. Martínez-Álvarez and A. Troncoso},

url = {https://www.liebertpub.com/doi/10.1089/big.2020.0159},

doi = {10.1089/big.2020.0159},

year  = {2021},

date = {2021-02-05},

journal = {Big Data},

volume = {9},

number = {1},

pages = {3-21},

abstract = {Deep learning, one of the most remarkable techniques of machine learning, has been a major success in many fields, including image processing, speech recognition, and text understanding. It is powerful engines capable of learning arbitrary mapping functions, not require a scaled or stationary time series as input, support multivariate inputs, and support multi-step outputs. All of these features together make deep learning useful tools when dealing with more complex time series prediction problems involving large amounts of data, and multiple variables with complex relationships. This paper provides an overview of the most common Deep Learning types for time series forecasting, Explain the relationships between deep learning models and classical approaches to time series forecasting. A brief background of the particular challenges presents in time-series data and the most common deep learning techniques that are often used for time series forecasting is provided. Previous studies that applied deep learning to time series are reviewed.},

keywords = {big data, deep learning, time series},

pubstate = {published},

tppubtype = {article}

}

@article{parra2021trust,

title = {A Trust-Based Methodology to Evaluate Deep Learning Models for Automatic Diagnosis of Ocular Toxoplasmosis from Fundus Images},

author = {R. Parra and V. Ojeda and J.L. Vázquez Noguera and M. García-Torres and J.C. Mello-Román and C. Villalba and J. Facon and F. Divina and O. Cardozo and V. Castillo},

doi = {10.3390/diagnostics11111951},

year  = {2021},

date = {2021-01-01},

journal = {Diagnostics},

volume = {11},

number = {11},

pages = {1951},

publisher = {Multidisciplinary Digital Publishing Institute pubstate = published},

keywords = {bioinformatics, deep learning, pattern recognition},

pubstate = {published},

tppubtype = {article}

}

@article{ayala2021technical,

title = {Technical analysis strategy optimization using a machine learning approach in stock market indices},

author = {J. Ayala and M. García-Torres and J.L. Vázquez Noguera and F. Gómez-Vela and F. Divina},

doi = {10.1016/j.knosys.2021.107119 volume=225},

year  = {2021},

date = {2021-01-01},

journal = {Knowledge-Based Systems},

pages = {107119},

publisher = {Elsevier pubstate = published},

keywords = {deep learning, pattern recognition},

pubstate = {published},

tppubtype = {article}

}

@article{DIVINA2020,

title = {Hybridizing deep learning and neuroevolution: Application to the Spanish short-term electric energy consumption forecasting},

author = {F. Divina and J. F. Torres and M. García-Torres and F. Martínez-Álvarez and A. Troncoso},

url = {https://www.mdpi.com/2076-3417/10/16/5487},

doi = {https://doi.org/10.3390/app10165487},

year  = {2020},

date = {2020-07-30},

journal = {Applied Sciences},

volume = {10},

number = {16},

pages = {5487},

abstract = {The electric energy production would be much more efficient if accurate estimations of the future demand were available, since these would allow allocating only the resources needed for the production of the right amount of energy required. With this motivation in mind, we propose a strategy, based on neuroevolution, that can be used to this aim. Our proposal uses a genetic algorithm in order to find a sub-optimal set of hyper-parameters for configuring a deep neural network, which can then be used for obtaining the forecasting. Such a strategy is justified by the observation that the performances achieved by deep neural networks are strongly dependent on the right setting of the hyper-parameters, and genetic algorithms have shown excellent search capabilities in huge search spaces. Moreover, we base our proposal on a distributed computing platform, which allows its use on a large time-series. In order to assess the performances of our approach, we have applied it to a large dataset, related to the electric energy consumption registered in Spain over almost 10 years. Experimental results confirm the validity of our proposal since it outperforms all other forecasting techniques to which it has been compared.},

keywords = {big data, deep learning, energy, time series},

pubstate = {published},

tppubtype = {article}

}

@article{MARTINEZ-ALVAREZ20,

title = {Coronavirus Optimization Algorithm: A bioinspired metaheuristic based on the COVID-19 propagation model},

author = {F. Martínez-Álvarez and G. Asencio-Cortés and J. F. Torres and D. Gutiérrez-Avilés and L. Melgar-García and R. Pérez-Chacón and C. Rubio-Escudero and A. Troncoso and J. C. Riquelme},

url = {https://www.liebertpub.com/doi/full/10.1089/big.2020.0051},

doi = {10.1089/big.2020.0051},

year  = {2020},

date = {2020-07-22},

journal = {Big Data},

volume = {8},

number = {4},

pages = {308-322},

abstract = {This work proposes a novel bioinspired metaheuristic, simulating how the coronavirus spreads and infects healthy people. From a primary infected individual (patient zero), the coronavirus rapidly infects new victims, creating large populations of infected people who will either die or spread infection. Relevant terms such as reinfection probability, super-spreading rate, social distancing measures or traveling rate are introduced into the model in order to simulate the coronavirus activity as accurately as possible. The infected population initially grows exponentially over time, but taking into consideration social isolation measures, the mortality rate and number of recoveries, the infected population gradually decreases. The Coronavirus Optimization Algorithm has two major advantages when compared to other similar strategies. Firstly, the input parameters are already set according to the disease statistics, preventing researchers from initializing them with arbitrary values. Secondly, the approach has the ability to end after several iterations, without setting this value either. Furthermore, a parallel multi-virus version is proposed, where several coronavirus strains evolve over time and explore wider search space areas in less iterations. Finally, the metaheuristic has been combined with deep learning models, in order to find optimal hyperparameters during the training phase. As application case, the problem of electricity load time series forecasting has been addressed, showing quite remarkable performance.},

keywords = {big data, deep learning, energy, time series},

pubstate = {published},

tppubtype = {article}

}

@article{TORRES19-1,

title = {Big data solar power forecasting based on deep learning and multiple data sources},

author = {J. F. Torres and A. Troncoso and I. Koprinska and Z. Wang and F. Martínez-Álvarez},

url = {https://onlinelibrary.wiley.com/doi/abs/10.1111/exsy.12394},

doi = {https://doi.org/10.1111/exsy.12394},

year  = {2019},

date = {2019-03-01},

journal = {Expert Systems},

volume = {36},

pages = {id12394},

keywords = {deep learning, energy, time series},

pubstate = {published},

tppubtype = {article}

}

@article{ICAE2018,

title = {A scalable approach based on deep learning for big data time series forecasting},

author = {J. F. Torres and A. Galicia and A. Troncoso and F. Martínez-Álvarez},

url = {https://content.iospress.com/articles/integrated-computer-aided-engineering/ica580},

doi = {10.3233/ICA-180580},

year  = {2018},

date = {2018-01-01},

journal = {Integrated Computer-Aided Engineering},

volume = {25},

number = {4},

pages = {335-348},

abstract = {This paper presents a method based on deep learning to deal with big data times series forecasting. The deep feed forward neural network provided by the H2O big data analysis framework has been used along with the Apache Spark platform for distributed computing. Since H2O does not allow the conduction of multi-step regression, a general-purpose methodology that can be used for prediction horizons with arbitrary length is proposed here, being the prediction horizon, h, the number of future values to be predicted. The solution consists in splitting the problem into h forecasting subproblems, being h the number of samples to be simultaneously predicted. Thus, the best prediction model for each subproblem can be obtained, making easier its parallelization and adaptation to the big data context. Moreover, a grid search is carried out to obtain the optimal hyperparameters of the deep learning-based approach. Results from a real-world dataset composed of electricity consumption in Spain, with a ten-minute frequency sampling rate, from 2007 to 2016 are reported. In particular, the accuracy and runtimes versus computing resources and size of the dataset are analyzed. Finally, the performance and the scalability of the proposed method is compared to other recently published techniques, showing to be a suitable method to process big data time series.},

keywords = {deep learning, energy, time series},

pubstate = {published},

tppubtype = {article}

}