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{PEREZ24,

title = {Pattern sequence-based algorithm for multivariate big data time series forecasting: Application to electricity consumption},

author = {R. Pérez-Chacón and G. Asencio-Cortés and A. Troncoso and F. Martínez-Álvarez},

url = {https://www.sciencedirect.com/science/article/pii/S0167739X23004752},

doi = {https://doi.org/10.1016/j.future.2023.12.021},

year  = {2024},

date = {2024-01-29},

journal = {Future Generation Computer Systems},

volume = {154},

pages = {397-412},

abstract = {Several interrelated variables typically characterize real-world processes, and a time series cannot be predicted without considering the influence that other time series might have on the target time series. This work proposes a novel algorithm to forecast multivariate big data time series. This new general-purpose approach consists first of a previous pattern recognition performed jointly using all time series that form the multivariate time series and then predicts the target time series by searching for similarities between pattern sequences. The proposed algorithm is designed to tackle multivariate time series forecasting problems within the context of big data. In particular, the algorithm has been developed with a distributed nature to enhance its efficiency in analyzing and processing large volumes of data. Moreover, the algorithm is straightforward to use, with only two parameters needing adjustment. Another advantage of the MV-bigPSF algorithm is its ability to perform multi-step forecasting, which is particularly useful in many practical applications. To evaluate the algorithm’s performance, real-world data from Uruguay’s power consumption has been utilized. Specifically, MV-bigPSF has been compared with both univariate and multivariate methods. Regarding the univariate ones, MV-bigPSF improved 12.8% in MAPE compared to the second-best method. Regarding the multivariate comparison, MV-bigPSF improved 44.8% in MAPE with respect to the second most accurate method. Regarding efficiency, the execution time of MV-bigPSF was 1.83 times faster than the second-fastest multivariate method, both in a single-core environment. Therefore, the proposed algorithm can be a valuable tool for practitioners and researchers working in multivariate time series forecasting, particularly in big data applications.},

keywords = {big data, energy, forecasting, time series},

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{MARTINEZ24,

title = {Emerging trends in big data analytics and natural disasters (Editorial)},

author = {F. Martínez-Álvarez and R. Scitovski and C. Rubio-Escudero and A. Morales-Esteban},

url = {https://www.sciencedirect.com/science/article/pii/S0098300423001693},

doi = {https://doi.org/10.1016/j.cageo.2023.105465},

year  = {2024},

date = {2024-01-01},

journal = {Computers and Geosciences},

volume = {182},

pages = {105465},

keywords = {big data, natural disasters, time series},

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{TRONCOSO-GARCIA23,

title = {A new approach based on association rules to add explainability to time series forecasting models},

author = {A. R. Troncoso-García and M. Martínez-Ballesteros and F. Mártinez-Álvarez and A. Troncoso},

url = {https://www.sciencedirect.com/science/article/pii/S1566253523000295},

doi = {10.1016/j.inffus.2023.01.021},

year  = {2023},

date = {2023-01-22},

journal = {Information Fusion},

volume = {94},

pages = {169-180},

abstract = {Machine learning and deep learning have become the most useful and powerful tools in the last years to mine information from large datasets. Despite the successful application to many research fields, it is widely known that some of these solutions based on artificial intelligence are considered black-box models, meaning that most experts find difficult to explain and interpret the models and why they generate such outputs. In this context, explainable artificial intelligence is emerging with the aim of providing black-box models with sufficient interpretability. Thus, models could be easily understood and further applied. This work proposes a novel method to explain black-box models, by using numeric association rules to explain and interpret multi-step time series forecasting models. Thus, a multi-objective algorithm is used to discover quantitative association rules from the target model. Then, visual explanation techniques are applied to make the rules more interpretable. Data from Spanish electricity energy consumption has been used to assess the suitability of the proposal.},

keywords = {association rules, time series, XAI},

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{jimenez2023,

title = {Streaming big time series forecasting based on nearest similar patterns with application to energy consumption},

author = {P. Jiménez-Herrera and L. Melgar-García and G. Asencio-Cortés and A. Troncoso},

url = {https://academic.oup.com/jigpal/advance-article-abstract/doi/10.1093/jigpal/jzac017/6534493?redirectedFrom=fulltext},

doi = {https://doi.org/10.1093/jigpal/jzac017},

year  = {2023},

date = {2023-01-01},

journal = {Logic Journal of the IGPL},

volume = {31},

number = {2},

pages = {255-270},

abstract = {This work presents a novel approach to forecast streaming big time series based on nearest similar patterns. This approach combines a clustering algorithm with a classifier and the nearest neighbors algorithm. It presents two separate stages: offline and online. The offline phase is for training and finding the best models for clustering, classification and the nearest neighbors algorithm. The online phase is to predict big time series in real time. In the offline phase, data are divided into clusters and a forecasting model based on the nearest neighbors is trained for each cluster. In addition, a classifier is trained using the cluster assignments previously generated by the clustering algorithm. In the online phase, the classifier predicts the cluster label of an instance, and the proper nearest neighbors model according to the predicted cluster label is applied to obtain the final prediction using the similar patterns. The algorithm is able to be updated incrementally for online learning from data streams. Results are reported using electricity consumption with a granularity of 10 minutes for 4-hour-ahead forecasting and compared with well-known online benchmark learners, showing a remarkable improvement in prediction accuracy.},

keywords = {energy, IoT, time series},

pubstate = {published},

tppubtype = {article}

}

@article{Melgar2023b,

title = {Identifying novelties and anomalies for incremental learning in streaming time series forecasting},

author = {L. Melgar-García and D. Gutiérrez-Avilés and C. Rubio-Escudero and A.Troncoso},

url = {https://www.sciencedirect.com/science/article/pii/S0952197623005109},

doi = {https://doi.org/10.1016/j.engappai.2023.106326},

year  = {2023},

date = {2023-01-01},

journal = {Engineering Applications of Artificial Intelligence},

volume = {123},

pages = {106326},

keywords = {energy, IoT, time series},

pubstate = {published},

tppubtype = {article}

}

@article{Melgar2023a,

title = {A novel distributed forecasting method based on information fusion and incremental learning for streaming time series},

author = {L. Melgar-García and D. Gutiérrez-Avilés and C. Rubio-Escudero and A. Troncoso},

url = {https://www.sciencedirect.com/science/article/pii/S1566253523000635},

doi = {https://doi.org/10.1016/j.inffus.2023.02.023},

year  = {2023},

date = {2023-01-01},

journal = {Information Fusion},

volume = {95},

pages = {163-173},

keywords = {energy, IoT, time series},

pubstate = {published},

tppubtype = {article}

}

@article{MOLINA22,

title = {DIAFAN-TL: An instance weighting-based transfer learning algorithm with application to phenology forecasting},

author = {M. Á. Molina and M. J. Jiménez-Navarro and R. Arjona and F. Mártinez-Álvarez and G. Asencio-Cortés},

url = {https://www.sciencedirect.com/science/article/pii/S0950705122008322},

doi = {https://doi.org/10.1016/j.knosys.2022.109644},

year  = {2022},

date = {2022-10-22},

journal = {Knowledge-Based Systems},

volume = {254},

pages = {109644},

abstract = {The agricultural sector has been, and still is, the most important economic sector in many countries. Due to advances in technology, the amount and variety of available data have been increasing over the years. However, compared to other economic sectors, there is not always enough quality data for one particular domain (crops, plantations, plots) to obtain acceptable forecasting results with machine learning algorithms. In this context, transfer learning can help extract knowledge from different but related domains with enough data to transfer it to a target domain with scarce data. This process can overcome forecasting accuracy compared to training models uniquely with data from the target domain. In this work, a novel instance weighting-based transfer learning algorithm is proposed and applied to the phenology forecasting problem. A new metric named DIAFAN is proposed to weight samples from different source domains according to their relationship with the target domain, promoting the diversity of the information and avoiding inconsistent samples. Additionally, a set of validation schemes is specifically designed to ensure fair comparisons in terms of data volume with other benchmark transfer learning algorithms. The proposed algorithm, DIAFAN-TL, is tested with a proposed dataset of 16 plots of olive groves from different places, including information fusion from satellite images, meteorological stations and human field sampling of crop phenology. DIAFAN-TL achieves a remarkable improvement with respect to 15 other well-known transfer learning algorithms and three nontransfer learning scenarios. Finally, several performance analyses according to the different phenological states, prediction horizons and source domains are also performed.},

keywords = {time series, transfer learning},

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{losada2022,

title = {Automatic Eligibility of Sellers in an Online Marketplace: A Case Study of Amazon Algorithm},

author = {A. Gómez-Losada and G. Asencio-Cortés and N. Duch-Brown},

url = {https://www.mdpi.com/2078-2489/13/2/44},

doi = {10.3390/info13020044},

year  = {2022},

date = {2022-01-01},

journal = {Information},

volume = {13},

number = {44},

pages = {1--16},

abstract = {Purchase processes on Amazon Marketplace begin at the Buy Box, which represents the buy click process through which numerous sellers compete. This study aimed to estimate empirically the relevant seller characteristics that Amazon could consider featuring in the Buy Box. To that end, 22 product categories from Italy’s Amazon web page were studied over a ten-month period, and the sellers were analyzed through their products featured in the Buy Box. Two different experiments were proposed and the results were analyzed using four classification algorithms (a neural network, random forest, support vector machine, and C5.0 decision trees) and a rule-based classification. The first experiment aimed to characterize sellers unspecifically by predicting their change at the Buy Box. The second one aimed to predict which seller would be featured in it. Both experiments revealed that the customer experience and the dynamics of the sellers’ prices were important features of the Buy Box. Additionally, we proposed a set of default features that Amazon could consider when no information about sellers was available. We also proposed the possible existence of a relationship or composition among important features that could be used for sellers to be featured in the Buy Box.},

keywords = {feature selection, time series},

pubstate = {published},

tppubtype = {article}

}

@article{castan2022,

title = {A new hybrid method for predicting univariate and multivariate time series based on pattern forecasting},

author = {M.A. Castán-Lascorz and P. Jiménez-Herrera and A. Troncoso and G. Asencio-Cortés},

url = {https://www.sciencedirect.com/science/article/pii/S0020025521012226?via%3Dihub},

doi = {10.1016/j.ins.2021.12.001},

year  = {2022},

date = {2022-01-01},

journal = {Information Sciences},

volume = {586},

pages = {611--627},

abstract = {Time series forecasting has become indispensable for multiple applications and industrial processes. Currently, a large number of algorithms have been developed to forecast time series, all of which are suitable depending on the characteristics and patterns to be inferred in each case. In this work, a new algorithm is proposed to predict both univariate and multivariate time series based on a combination of clustering, classification and forecasting techniques. The main goal of the proposed algorithm is first to group windows of time series values with similar patterns by applying a clustering process. Then, a specific forecasting model for each pattern is built and training is only conducted with the time windows corresponding to that pattern. The new algorithm has been designed using a flexible framework that allows the model to be generated using any combination of approaches within multiple machine learning techniques. To evaluate the model, several experiments are carried out using different configurations of the clustering, classification and forecasting methods that the model consists of. The results are analyzed and compared to classical prediction models, such as autoregressive, integrated, moving average and Holt-Winters models, to very recent forecasting methods, including deep, long short-term memory neural networks, and to well-known methods in the literature, such as k nearest neighbors, classification and regression trees, as well as random forest.},

keywords = {energy, pattern recognition, time series},

pubstate = {published},

tppubtype = {article}

}

@article{velazquez2022distribution,

title = {Distribution level Electric current consumption and meteorological data set of the East region of Paraguay},

author = {G. Velázquez and F. Morales and M. García-Torres and F. Gómez-Vela and F. Divina and J.L. Vázquez Noguera and F. Daumas-Ladouce and C. Ayala and D. Pinto-Roaand P. Gardel-Sotomayor},

url = {https://www.sciencedirect.com/science/article/pii/S2352340921009744},

doi = {10.1016/j.dib.2021.107699},

year  = {2022},

date = {2022-01-01},

journal = {Data in Brief},

volume = {40},

pages = {107699},

publisher = {Elsevier pubstate = published},

abstract = {This paper presents a data set with information on meteorological data and electricity consumption in the department of Alto Paraná, Paraguay. The meteorological data were registered every three hours at the Aeropuerto Guarani, Department of Alto Paraná, which belongs to the Dirección Nacional de Aeronáutica Civil of Paraguay. The final data consists of a total of 22.445 records of temperature, relative humidity, wind speed and atmospheric pressure. On the other hand, the electrical energy consumption data set contains a total of 1.848.947 records, all of them coming from the one hundred and fifteen feeders located throughout the Alto Paraná region of Paraguay. Electrical energy consumption data was provided by Administración Nacional de Electricidad (ANDE). The analysis of this data can yield insights regarding the energy consumption in the area.},

keywords = {energy, time series},

pubstate = {published},

tppubtype = {article}

}

@article{morales2022analysisb,

title = {Analysis of Electric Energy Consumption Profiles Using a Machine Learning Approach: A Paraguayan Case Study},

author = {F. Morales and M. García-Torres and G. Velázquez and F. Daumas-Ladouce and P. Gardel-Sotomayor and F. Gómez-Vela and F. Divina and J. L. Vázquez Noguera and C. Sauer Ayala and D. Pinto-Roa},

url = {https://www.mdpi.com/2079-9292/11/2/267},

doi = {10.3390/electronics11020267},

year  = {2022},

date = {2022-01-01},

journal = {Electronics},

volume = {11},

number = {2},

pages = {267},

abstract = {Correctly defining and grouping electrical feeders is of great importance for electrical system operators. In this paper, we compare two different clustering techniques, K-means and hierarchical agglomerative clustering, applied to real data from the east region of Paraguay. The raw data were pre-processed, resulting in four data sets, namely, (i) a weekly feeder demand, (ii) a monthly feeder demand, (iii) a statistical feature set extracted from the original data and (iv) a seasonal and daily consumption feature set obtained considering the characteristics of the Paraguayan load curve. Considering the four data sets, two clustering algorithms, two distance metrics and five linkage criteria a total of 36 models with the Silhouette, Davies–Bouldin and Calinski–Harabasz index scores was assessed. The K-means algorithms with the seasonal feature data sets showed the best performance considering the Silhouette, Calinski–Harabasz and Davies–Bouldin validation index scores with a configuration of six clusters.},

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

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{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}

}