Silvia Jiménez-Fernández | Universidad de Alcalá (original) (raw)
Papers by Silvia Jiménez-Fernández
Conference proceedings, Aug 1, 2007
Remote patient monitoring in e-Health is everyday closer to be a mature technology / service. How... more Remote patient monitoring in e-Health is everyday closer to be a mature technology / service. However, there is still a lack of development in areas such as standardization of the sensor's communication interface, integration into Electronic Healthcare Record systems or incorporation in ambient-intelligent scenarios. This work identifies a set of use cases involved in the personal monitoring scenario and highlights the related features and functionalities, as well as the integration and implementation difficulties found when these are to be implemented in a system based on the ISO/IEEE11073 (X73) standard. It is part of a cooperative research effort devoted to the development of an end-to-end standards-based telemonitoring solution. Standardization committees are working towards adapting the X73 standard to this emerging personal health devices market and use case identification is essential to direct these revisions.
Conference proceedings, Aug 1, 2007
This paper presents a proof-of-concept design of a patient monitoring solution for Intensive Care... more This paper presents a proof-of-concept design of a patient monitoring solution for Intensive Care Unit (ICU). It is end-to-end standards-based, using ISO/IEEE 11073 (X73) in the bedside environment and EN13606 to communicate the information to an Electronic Healthcare Record (EHR) server. At the bedside end a plug-and-play sensor network is implemented, which communicates with a gateway that collects the medical information and sends it to a monitoring server. At this point the server transforms the data frame into an EN13606 extract, to be stored on the EHR server. The presented system has been tested in a laboratory environment to demonstrate the feasibility of this end-to-end standardsbased solution. I. INTRODUCTION NTENSIVE Care Units (ICUs) have been in last decades [1]-[3] the main bedside environment of hospitals where advances in technology have implied important changes in the Medical Devices (MDs), computers and sensors at the Point of Care (PoC). These devices acquire huge amounts of very valuable information, without the need for manually writing down each measurement, contributing to solutions based on the Electronic Healthcare Record (EHR) [4]-[6]. The communications within components of a patient monitoring system, and inter-system coordination become now very important in exploiting all the possibilities offered by the information gathered [7]-[9]. However, different manufacturers use their own software and communication protocols; building proprietary solutions that can only work alone or inside single-vendor equipment. As pointed out at the EMBS06 [10], a standardized communication framework is necessary in order to solve the interoperability problem that now emerges. Two of the standards with research interest nowadays are ISO/IEEE 11073 for PoC-MDs Communications (also known as X73) [11], and EN13606 for EHR communication [12]; a brief overview can be found in [13]. X73 is a family of standards Manuscript received April 16, 2007. This research work has been partially supported by projects TSI2005-07068-C02-01 and TSI2004-04940-C02-01 from Ministerio de Educación y Ciencia (Spanish Government), and a personal grant to both M.
IEEE Transactions on Biomedical Engineering, Dec 1, 2013
This paper addresses two key technological barriers to the wider adoption of patient telemonitori... more This paper addresses two key technological barriers to the wider adoption of patient telemonitoring systems for chronic disease management, namely usability and sensor device interoperability. As a great percentage of chronic patients are elderly patients as well, usability of the system has to be adapted to their needs. This paper identifies (from previous research) a set of design criteria to address these challenges, and describes the resulting system based on a wireless sensor network, and including a node as a custom-made interface that follows usability design criteria stated. This system has been tested with 22 users (mean age 65) and evaluated with a validated usability questionnaire. Results are good and improve those of other systems based on TV or smartphone. Our results suggest that user interfaces alternative to TVs and smartphones could play an important role on the usability of sensor networks for patient monitoring. Regarding interoperability, only very recently a standard has been published (2010, ISO IEEE 11073 Personal health devices) that can support the needs of limited computational power environments typical of patient monitoring sensor networks.
2022 IEEE Congress on Evolutionary Computation (CEC), Jul 18, 2022
There are several technologies for providing broadband services over wireless and cellular networ... more There are several technologies for providing broadband services over wireless and cellular networks. The fundamental one in the evolution from 3G to 4G is probably the High Speed Downlink Packet Access (HSPA) technology. There are many works in the literature tackling the problem of HSPA performance and capacity. Most of the developed techniques involving HSPA capacity are related to the system operation. This approach is specially useful when the network planner tries to evaluate how the system works, however, it is not the case when the mobile network operator is doing the business plan and whise to evaluate the return of investment. This paper provides a simple and novel methodology for estimating the additional investment required to provide High Speed Down-link Packet Access (HSDPA) in a 3G mobile network given a user service profile. This method is useful for techno-economic studies for mobile operators, consulting firms and national regulatory agencies.
Applied Soft Computing, Aug 1, 2012
This paper presents a hybrid evolutionary programming approach to solve the worst case tolerance ... more This paper presents a hybrid evolutionary programming approach to solve the worst case tolerance design problem (WCTDP) in magnetic devices. The hybrid algorithm is formed by a basic evolutionary programming approach, mixed with a gradient-guided local search. Two different local searches procedures are tested in the paper, both specially designed to be effective in the WCTDP. Simulations on an example in the design of a magnetic circuit and comparison with several existing bio-inspired heuristics are carried out, and have shown the goodness of our algorithm.
Computer Applications in Engineering Education, Jan 21, 2014
This paper presents an educational software tool to teach Artificial Intelligence (AI) techniques... more This paper presents an educational software tool to teach Artificial Intelligence (AI) techniques, specifically Hyper-heuristics, to Engineering students. This tool is based on the "Bubble Breaker" puzzle, an addictive game consisting in an M Â M matrix of colored bubbles. These balls, when forming sets of two or more same colored balls, can be popped and cleared out. Thus, this puzzle can be solved by setting many different low-level heuristics and applying a global search procedure (i.e., evolutionary algorithm) that conforms a robust hyper-heuristic technique. The hyper-heuristic decides what low-level heuristics are the best, and the sequential way in which they have to be applied to gain the highest score. This approach has proven an interesting method to teach AI techniques, since simple heuristics, evolutionary algorithms, and its combination are studied in an increasing manner.
In this paper we propose an approach for feature selection in a problem of significant wave heigh... more In this paper we propose an approach for feature selection in a problem of significant wave height prediction, to improve the exploitation of marine energy. The method that we present, a Grouping Genetic Algorithm - Extreme Learning Machine approach (GGA-ELM), mainly tries to improve the prediction performance of the regressors, providing more effective predictors and good performance in the final significant wave height prediction. In this method, the GGA looks for several subsets of features, and the ELM provides the fitness of the algorithm, through its accuracy on significant wave height prediction. The GGA is able to evolve different groups of features in parallel, which may improve the performance of the prediction obtained. After the feature selection process with the GGA-ELM, the final results are obtained by applying an ELM and also by a Support Vector Regressor algorithm, both working on the best GGA groups of features previously evolved. In the experimental part of the paper, we show the performance of the proposed approach in a real problem of significant wave height prediction at the West Coast of the USA, using variables directly obtained from several measuring buoys.
Computer Applications in Engineering Education, Oct 10, 2012
Mobile communications have become one of the key points in the development of Information Society... more Mobile communications have become one of the key points in the development of Information Society. Therefore the market demands to qualify engineers with a good formation on this topic, and more specifically related with good knowledge about the design and deployment of mobile and wireless networks and services of different technologies. For this reason most of the graduate and post‐graduate programs in Electrical and Electronic engineering studies consider at least one specific subject focused on mobile communications. However, the large number of concepts and the different existing technologies could make this subject very difficult for the student. This article presents a software tool for the design of second and third generation radio access networks, which makes easier the understanding and application of theoretical concepts, giving the student a more practical and realistic view of the subject. Furthermore as this tool has been applied for the regulation on mobile communications in different countries, the students can get some practical knowledge about the work in mobile communications in real world applications. © 2012 Wiley Periodicals, Inc. Comput Appl Eng Educ 23:1–12, 2015; View this article online at wileyonlinelibrary.com/journal/cae; DOI 10.1002/cae.21570
Expert Systems With Applications, 2013
Electromagnetic pollution due to mobile telephony is one of the most concerning problems arising ... more Electromagnetic pollution due to mobile telephony is one of the most concerning problems arising since the spreading of this technology. Different studies have shown the relationship between continuous exposition to electromagnetic fields and different kinds of pathologies. Despite this, the electromagnetic danger for exposition is not taken into account in recent mobile network deployments. In this paper we propose a novel evolutionary algorithm for mobile networks deployment, which takes into account the control of the electromagnetic emission from the base stations as one of the key design parameters. The proposed evolutionary approach is a variable-length algorithm, able to produce solutions with different number of base stations. We detail the encoding, operators and a repairing procedure applied to obtain good solutions in terms of coverage, cost and electromagnetic pollution. The algorithm has been tested in a real problem of mobile network deployment in Alcalá de Henares, Madrid, Spain, and compare with a greedy (constructive) approach and a meta-heuristic algorithm (Harmony Search), obtaining very good results.
Transactions on Emerging Telecommunications Technologies, Nov 30, 2013
Mobile technology is currently one of the main pillars of worldwide economy. The constant evoluti... more Mobile technology is currently one of the main pillars of worldwide economy. The constant evolution that mobile communications have undergone in the last decades, due to the appearance of new services and new technologies such as UMTS/HSPA and LTE, has contributed to achieve this position in global economy. However, due to the crisis of the sector in the last five years, mobile operator's revenues and investments have been reduced. Thus, mobile network operators tend to exploit the existing infrastructure at maximum possible, trying to use the existing network in the most efficient way. In this paper, a novel bio-inspired algorithm, the coral reef optimization algorithm (CRO) is introduced to minimize a network deployment investment cost problem. This is carried out by means of optimizing the user demand of different services offered by mobile operators over the available technologies in the market, namely the Optimal Service Distribution Problem (OSDP). The CRO is a recently proposed meta-heuristic based on the computer simulation of corals reproduction and reefs' formation. In this paper, this algorithm has been tested on several OSDP scenarios in Spain, observing a significant reduction (up to 400 Me) on the total investment costs associated to the Radio Access Network deployment. We compare the performance of the CRO approach with that of a classical (experience-based) services distribution, and with alternative meta-heuristics techniques, obtaining good results in all cases.
Applied Energy, 2012
This paper presents an evolutionary algorithm for wind speed reconstruction from synoptic pressur... more This paper presents an evolutionary algorithm for wind speed reconstruction from synoptic pressure patterns. The algorithm operates in a search space formed by grids of pressure measures, and must classify the different situations into classes, in such a way that a measure of wind speed in a given point is minimized among patterns assigned to the same class. Then, each class is assigned a mean wind speed and direction, so the wind speed reconstruction is possible for a new grid of synoptic pressures. In this paper we present the problem model and the specific description of the evolutionary algorithm proposed to solve the problem. We also show the good performance of the proposed method in the reconstruction of the average wind speed in six wind towers in Spain. The proposed method is applicable to wind speed reconstruction or reconstruction of wind missing data of wind series, specially when there is no other variable or related measure available.
Energies, Nov 6, 2017
Wind Power Ramp Events (WPREs) are large fluctuations of wind power in a short time interval, whi... more Wind Power Ramp Events (WPREs) are large fluctuations of wind power in a short time interval, which lead to strong, undesirable variations in the electric power produced by a wind farm. Its accurate prediction is important in the effort of efficiently integrating wind energy in the electric system, without affecting considerably its stability, robustness and resilience. In this paper, we tackle the problem of predicting WPREs by applying Machine Learning (ML) regression techniques. Our approach consists of using variables from atmospheric reanalysis data as predictive inputs for the learning machine, which opens the possibility of hybridizing numerical-physical weather models with ML techniques for WPREs prediction in real systems. Specifically, we have explored the feasibility of a number of state-of-the-art ML regression techniques, such as support vector regression, artificial neural networks (multi-layer perceptrons and extreme learning machines) and Gaussian processes to solve the problem. Furthermore, the ERA-Interim reanalysis from the European Center for Medium-Range Weather Forecasts is the one used in this paper because of its accuracy and high resolution (in both spatial and temporal domains). Aiming at validating the feasibility of our predicting approach, we have carried out an extensive experimental work using real data from three wind farms in Spain, discussing the performance of the different ML regression tested in this wind power ramp event prediction problem.
Journal of Wind Engineering and Industrial Aerodynamics, May 1, 2013
The real operation of a wind farm implies the solution of many different problems related to wind... more The real operation of a wind farm implies the solution of many different problems related to wind speed at a wind farm location site. Wind speed prediction and wind series reconstruction are the two examples of important problems tackled in wind farm management and prospection. Usually, wind speed prediction and reconstruction of wind series are carried out in wind farms using data from in situ measuring towers, usually named as Measure-Correlate-Predict methods (MCP). MCP processes consist, therefore, in the wind speed prediction or reconstruction from neighbor stations, using different methods. In this paper, we tackle the special case of real MCP operations in wind farms, in which the algorithms to reconstruct or predict the wind series must be extremely fast in order to be useful. We present the application of two state-of-the-art neural networks which have shown a very fast training time, with an excellent performance in terms of accuracy. Specifically, we show the application of Group Method of Data Handling and Extreme Learning Machines in the MCP reconstruction and prediction of wind speed series, in a real wind farm in Spain. A comparison in terms of computation time and accuracy with alternative algorithms in the literature is also carried out. Finally, we show a real implementation of the Group Method of Data Handling (GMDH) and Extreme Learning Machine (ELM) in a software in use for real MCP operations in wind farms.
Renewable Energy, Oct 1, 2017
Energies, Aug 2, 2016
Classification problems and their corresponding solving approaches constitute one of the fields o... more Classification problems and their corresponding solving approaches constitute one of the fields of machine learning. The application of classification schemes in Renewable Energy (RE) has gained significant attention in the last few years, contributing to the deployment, management and optimization of RE systems. The main objective of this paper is to review the most important classification algorithms applied to RE problems, including both classical and novel algorithms. The paper also provides a comprehensive literature review and discussion on different classification techniques in specific RE problems, including wind speed/power prediction, fault diagnosis in RE systems, power quality disturbance classification and other applications in alternative RE systems. In this way, the paper describes classification techniques and metrics applied to RE problems, thus being useful both for researchers dealing with this kind of problem and for practitioners of the field.
IEEE/ACM Transactions on Audio, Speech, and Language Processing
In this article, we propose a novel flexible architecture, with different algorithmic procedures,... more In this article, we propose a novel flexible architecture, with different algorithmic procedures, for effective story segmentation of broadcast news from subtitle files. The proposed system exploits spatial and temporal distance, as well as sentence similarity, to classify different stories in news broadcasts. The computational algorithms which form the architecture mainly focus on each sentence's features (temporal distance, spatial distance, and semantic similarity), and are combined to build an overall classifier. The first algorithm in the architecture focuses on the segmentation task, detecting boundaries between news. The second and third algorithms identify high semantic correlation between pieces of text, whether they are consecutive in space or not. Video Text Track (VTT) subtitle files are used to evaluate the performance of the proposed approach, although any file format that includes temporal information could also be considered. These VTT files may contain text errors and inaccuracies, and the proposed algorithms have been designed to deal with noisy content.
Conference proceedings, Aug 1, 2007
Remote patient monitoring in e-Health is everyday closer to be a mature technology / service. How... more Remote patient monitoring in e-Health is everyday closer to be a mature technology / service. However, there is still a lack of development in areas such as standardization of the sensor's communication interface, integration into Electronic Healthcare Record systems or incorporation in ambient-intelligent scenarios. This work identifies a set of use cases involved in the personal monitoring scenario and highlights the related features and functionalities, as well as the integration and implementation difficulties found when these are to be implemented in a system based on the ISO/IEEE11073 (X73) standard. It is part of a cooperative research effort devoted to the development of an end-to-end standards-based telemonitoring solution. Standardization committees are working towards adapting the X73 standard to this emerging personal health devices market and use case identification is essential to direct these revisions.
Conference proceedings, Aug 1, 2007
This paper presents a proof-of-concept design of a patient monitoring solution for Intensive Care... more This paper presents a proof-of-concept design of a patient monitoring solution for Intensive Care Unit (ICU). It is end-to-end standards-based, using ISO/IEEE 11073 (X73) in the bedside environment and EN13606 to communicate the information to an Electronic Healthcare Record (EHR) server. At the bedside end a plug-and-play sensor network is implemented, which communicates with a gateway that collects the medical information and sends it to a monitoring server. At this point the server transforms the data frame into an EN13606 extract, to be stored on the EHR server. The presented system has been tested in a laboratory environment to demonstrate the feasibility of this end-to-end standardsbased solution. I. INTRODUCTION NTENSIVE Care Units (ICUs) have been in last decades [1]-[3] the main bedside environment of hospitals where advances in technology have implied important changes in the Medical Devices (MDs), computers and sensors at the Point of Care (PoC). These devices acquire huge amounts of very valuable information, without the need for manually writing down each measurement, contributing to solutions based on the Electronic Healthcare Record (EHR) [4]-[6]. The communications within components of a patient monitoring system, and inter-system coordination become now very important in exploiting all the possibilities offered by the information gathered [7]-[9]. However, different manufacturers use their own software and communication protocols; building proprietary solutions that can only work alone or inside single-vendor equipment. As pointed out at the EMBS06 [10], a standardized communication framework is necessary in order to solve the interoperability problem that now emerges. Two of the standards with research interest nowadays are ISO/IEEE 11073 for PoC-MDs Communications (also known as X73) [11], and EN13606 for EHR communication [12]; a brief overview can be found in [13]. X73 is a family of standards Manuscript received April 16, 2007. This research work has been partially supported by projects TSI2005-07068-C02-01 and TSI2004-04940-C02-01 from Ministerio de Educación y Ciencia (Spanish Government), and a personal grant to both M.
IEEE Transactions on Biomedical Engineering, Dec 1, 2013
This paper addresses two key technological barriers to the wider adoption of patient telemonitori... more This paper addresses two key technological barriers to the wider adoption of patient telemonitoring systems for chronic disease management, namely usability and sensor device interoperability. As a great percentage of chronic patients are elderly patients as well, usability of the system has to be adapted to their needs. This paper identifies (from previous research) a set of design criteria to address these challenges, and describes the resulting system based on a wireless sensor network, and including a node as a custom-made interface that follows usability design criteria stated. This system has been tested with 22 users (mean age 65) and evaluated with a validated usability questionnaire. Results are good and improve those of other systems based on TV or smartphone. Our results suggest that user interfaces alternative to TVs and smartphones could play an important role on the usability of sensor networks for patient monitoring. Regarding interoperability, only very recently a standard has been published (2010, ISO IEEE 11073 Personal health devices) that can support the needs of limited computational power environments typical of patient monitoring sensor networks.
2022 IEEE Congress on Evolutionary Computation (CEC), Jul 18, 2022
There are several technologies for providing broadband services over wireless and cellular networ... more There are several technologies for providing broadband services over wireless and cellular networks. The fundamental one in the evolution from 3G to 4G is probably the High Speed Downlink Packet Access (HSPA) technology. There are many works in the literature tackling the problem of HSPA performance and capacity. Most of the developed techniques involving HSPA capacity are related to the system operation. This approach is specially useful when the network planner tries to evaluate how the system works, however, it is not the case when the mobile network operator is doing the business plan and whise to evaluate the return of investment. This paper provides a simple and novel methodology for estimating the additional investment required to provide High Speed Down-link Packet Access (HSDPA) in a 3G mobile network given a user service profile. This method is useful for techno-economic studies for mobile operators, consulting firms and national regulatory agencies.
Applied Soft Computing, Aug 1, 2012
This paper presents a hybrid evolutionary programming approach to solve the worst case tolerance ... more This paper presents a hybrid evolutionary programming approach to solve the worst case tolerance design problem (WCTDP) in magnetic devices. The hybrid algorithm is formed by a basic evolutionary programming approach, mixed with a gradient-guided local search. Two different local searches procedures are tested in the paper, both specially designed to be effective in the WCTDP. Simulations on an example in the design of a magnetic circuit and comparison with several existing bio-inspired heuristics are carried out, and have shown the goodness of our algorithm.
Computer Applications in Engineering Education, Jan 21, 2014
This paper presents an educational software tool to teach Artificial Intelligence (AI) techniques... more This paper presents an educational software tool to teach Artificial Intelligence (AI) techniques, specifically Hyper-heuristics, to Engineering students. This tool is based on the "Bubble Breaker" puzzle, an addictive game consisting in an M Â M matrix of colored bubbles. These balls, when forming sets of two or more same colored balls, can be popped and cleared out. Thus, this puzzle can be solved by setting many different low-level heuristics and applying a global search procedure (i.e., evolutionary algorithm) that conforms a robust hyper-heuristic technique. The hyper-heuristic decides what low-level heuristics are the best, and the sequential way in which they have to be applied to gain the highest score. This approach has proven an interesting method to teach AI techniques, since simple heuristics, evolutionary algorithms, and its combination are studied in an increasing manner.
In this paper we propose an approach for feature selection in a problem of significant wave heigh... more In this paper we propose an approach for feature selection in a problem of significant wave height prediction, to improve the exploitation of marine energy. The method that we present, a Grouping Genetic Algorithm - Extreme Learning Machine approach (GGA-ELM), mainly tries to improve the prediction performance of the regressors, providing more effective predictors and good performance in the final significant wave height prediction. In this method, the GGA looks for several subsets of features, and the ELM provides the fitness of the algorithm, through its accuracy on significant wave height prediction. The GGA is able to evolve different groups of features in parallel, which may improve the performance of the prediction obtained. After the feature selection process with the GGA-ELM, the final results are obtained by applying an ELM and also by a Support Vector Regressor algorithm, both working on the best GGA groups of features previously evolved. In the experimental part of the paper, we show the performance of the proposed approach in a real problem of significant wave height prediction at the West Coast of the USA, using variables directly obtained from several measuring buoys.
Computer Applications in Engineering Education, Oct 10, 2012
Mobile communications have become one of the key points in the development of Information Society... more Mobile communications have become one of the key points in the development of Information Society. Therefore the market demands to qualify engineers with a good formation on this topic, and more specifically related with good knowledge about the design and deployment of mobile and wireless networks and services of different technologies. For this reason most of the graduate and post‐graduate programs in Electrical and Electronic engineering studies consider at least one specific subject focused on mobile communications. However, the large number of concepts and the different existing technologies could make this subject very difficult for the student. This article presents a software tool for the design of second and third generation radio access networks, which makes easier the understanding and application of theoretical concepts, giving the student a more practical and realistic view of the subject. Furthermore as this tool has been applied for the regulation on mobile communications in different countries, the students can get some practical knowledge about the work in mobile communications in real world applications. © 2012 Wiley Periodicals, Inc. Comput Appl Eng Educ 23:1–12, 2015; View this article online at wileyonlinelibrary.com/journal/cae; DOI 10.1002/cae.21570
Expert Systems With Applications, 2013
Electromagnetic pollution due to mobile telephony is one of the most concerning problems arising ... more Electromagnetic pollution due to mobile telephony is one of the most concerning problems arising since the spreading of this technology. Different studies have shown the relationship between continuous exposition to electromagnetic fields and different kinds of pathologies. Despite this, the electromagnetic danger for exposition is not taken into account in recent mobile network deployments. In this paper we propose a novel evolutionary algorithm for mobile networks deployment, which takes into account the control of the electromagnetic emission from the base stations as one of the key design parameters. The proposed evolutionary approach is a variable-length algorithm, able to produce solutions with different number of base stations. We detail the encoding, operators and a repairing procedure applied to obtain good solutions in terms of coverage, cost and electromagnetic pollution. The algorithm has been tested in a real problem of mobile network deployment in Alcalá de Henares, Madrid, Spain, and compare with a greedy (constructive) approach and a meta-heuristic algorithm (Harmony Search), obtaining very good results.
Transactions on Emerging Telecommunications Technologies, Nov 30, 2013
Mobile technology is currently one of the main pillars of worldwide economy. The constant evoluti... more Mobile technology is currently one of the main pillars of worldwide economy. The constant evolution that mobile communications have undergone in the last decades, due to the appearance of new services and new technologies such as UMTS/HSPA and LTE, has contributed to achieve this position in global economy. However, due to the crisis of the sector in the last five years, mobile operator's revenues and investments have been reduced. Thus, mobile network operators tend to exploit the existing infrastructure at maximum possible, trying to use the existing network in the most efficient way. In this paper, a novel bio-inspired algorithm, the coral reef optimization algorithm (CRO) is introduced to minimize a network deployment investment cost problem. This is carried out by means of optimizing the user demand of different services offered by mobile operators over the available technologies in the market, namely the Optimal Service Distribution Problem (OSDP). The CRO is a recently proposed meta-heuristic based on the computer simulation of corals reproduction and reefs' formation. In this paper, this algorithm has been tested on several OSDP scenarios in Spain, observing a significant reduction (up to 400 Me) on the total investment costs associated to the Radio Access Network deployment. We compare the performance of the CRO approach with that of a classical (experience-based) services distribution, and with alternative meta-heuristics techniques, obtaining good results in all cases.
Applied Energy, 2012
This paper presents an evolutionary algorithm for wind speed reconstruction from synoptic pressur... more This paper presents an evolutionary algorithm for wind speed reconstruction from synoptic pressure patterns. The algorithm operates in a search space formed by grids of pressure measures, and must classify the different situations into classes, in such a way that a measure of wind speed in a given point is minimized among patterns assigned to the same class. Then, each class is assigned a mean wind speed and direction, so the wind speed reconstruction is possible for a new grid of synoptic pressures. In this paper we present the problem model and the specific description of the evolutionary algorithm proposed to solve the problem. We also show the good performance of the proposed method in the reconstruction of the average wind speed in six wind towers in Spain. The proposed method is applicable to wind speed reconstruction or reconstruction of wind missing data of wind series, specially when there is no other variable or related measure available.
Energies, Nov 6, 2017
Wind Power Ramp Events (WPREs) are large fluctuations of wind power in a short time interval, whi... more Wind Power Ramp Events (WPREs) are large fluctuations of wind power in a short time interval, which lead to strong, undesirable variations in the electric power produced by a wind farm. Its accurate prediction is important in the effort of efficiently integrating wind energy in the electric system, without affecting considerably its stability, robustness and resilience. In this paper, we tackle the problem of predicting WPREs by applying Machine Learning (ML) regression techniques. Our approach consists of using variables from atmospheric reanalysis data as predictive inputs for the learning machine, which opens the possibility of hybridizing numerical-physical weather models with ML techniques for WPREs prediction in real systems. Specifically, we have explored the feasibility of a number of state-of-the-art ML regression techniques, such as support vector regression, artificial neural networks (multi-layer perceptrons and extreme learning machines) and Gaussian processes to solve the problem. Furthermore, the ERA-Interim reanalysis from the European Center for Medium-Range Weather Forecasts is the one used in this paper because of its accuracy and high resolution (in both spatial and temporal domains). Aiming at validating the feasibility of our predicting approach, we have carried out an extensive experimental work using real data from three wind farms in Spain, discussing the performance of the different ML regression tested in this wind power ramp event prediction problem.
Journal of Wind Engineering and Industrial Aerodynamics, May 1, 2013
The real operation of a wind farm implies the solution of many different problems related to wind... more The real operation of a wind farm implies the solution of many different problems related to wind speed at a wind farm location site. Wind speed prediction and wind series reconstruction are the two examples of important problems tackled in wind farm management and prospection. Usually, wind speed prediction and reconstruction of wind series are carried out in wind farms using data from in situ measuring towers, usually named as Measure-Correlate-Predict methods (MCP). MCP processes consist, therefore, in the wind speed prediction or reconstruction from neighbor stations, using different methods. In this paper, we tackle the special case of real MCP operations in wind farms, in which the algorithms to reconstruct or predict the wind series must be extremely fast in order to be useful. We present the application of two state-of-the-art neural networks which have shown a very fast training time, with an excellent performance in terms of accuracy. Specifically, we show the application of Group Method of Data Handling and Extreme Learning Machines in the MCP reconstruction and prediction of wind speed series, in a real wind farm in Spain. A comparison in terms of computation time and accuracy with alternative algorithms in the literature is also carried out. Finally, we show a real implementation of the Group Method of Data Handling (GMDH) and Extreme Learning Machine (ELM) in a software in use for real MCP operations in wind farms.
Renewable Energy, Oct 1, 2017
Energies, Aug 2, 2016
Classification problems and their corresponding solving approaches constitute one of the fields o... more Classification problems and their corresponding solving approaches constitute one of the fields of machine learning. The application of classification schemes in Renewable Energy (RE) has gained significant attention in the last few years, contributing to the deployment, management and optimization of RE systems. The main objective of this paper is to review the most important classification algorithms applied to RE problems, including both classical and novel algorithms. The paper also provides a comprehensive literature review and discussion on different classification techniques in specific RE problems, including wind speed/power prediction, fault diagnosis in RE systems, power quality disturbance classification and other applications in alternative RE systems. In this way, the paper describes classification techniques and metrics applied to RE problems, thus being useful both for researchers dealing with this kind of problem and for practitioners of the field.
IEEE/ACM Transactions on Audio, Speech, and Language Processing
In this article, we propose a novel flexible architecture, with different algorithmic procedures,... more In this article, we propose a novel flexible architecture, with different algorithmic procedures, for effective story segmentation of broadcast news from subtitle files. The proposed system exploits spatial and temporal distance, as well as sentence similarity, to classify different stories in news broadcasts. The computational algorithms which form the architecture mainly focus on each sentence's features (temporal distance, spatial distance, and semantic similarity), and are combined to build an overall classifier. The first algorithm in the architecture focuses on the segmentation task, detecting boundaries between news. The second and third algorithms identify high semantic correlation between pieces of text, whether they are consecutive in space or not. Video Text Track (VTT) subtitle files are used to evaluate the performance of the proposed approach, although any file format that includes temporal information could also be considered. These VTT files may contain text errors and inaccuracies, and the proposed algorithms have been designed to deal with noisy content.