NATural Language Energy for Promoting CONSUMER Sustainable Behaviour
Principal Research: Gracián Triviño Barros Program: Horizon 2020 Partners: Ariosz Kft; ECSC; Valor, Desarrollo e Innovación (VDI); National Institute for consumer Research (SIFO); Ricerca sul Sistema Energetico (RSE); VaasaETT Oy Ab Ltd (VaasaETT); Strategic Design Scenarios SPRL (SDS); Draxis; ADICONSUM; Energy Saving Trust England
The residential energy consumption represents the 28% of total European Union (EU) and if we include consumption in office buildings this percentage increases to 40%, accounting for 36% of global CO2 emissions. Therefore, to achieve the ambitious goals set in the Europe 2020 strategy, which includes reducing by 20% the energy consumption and emissions of greenhouse gases, it is necessary to implement among consumers measures to promote a change in their consumption habits and a more sustainable use of energy at home. In this regard, previous studies have shown that initiatives based in providing user with regular personalized information about their consumption have great potential impact, and can reach reductions of between 5 and 20% in consumption.
The main objective of NATCONSUMERS project is to establish a comprehensive methodology for reducing electricity consumption in households based on the periodic provision of reports, personalized and in natural language, including direct actions to decrease consumption and therefore the cost of electricity bill. This summary will include information about consumption patterns, comparisons with historical data and clients with similar houses, and finally recommendations to adopt a more sustainable attitude. Within the energy slang such methods for modifying consumer behavior are known as indirect feedback.
The bases for the generation of such reports consist in a perfect characterization of European electricity consumers (type of housing and family, electricity uses, appliances and efficiency, consumption habits, attitudes, values ...), their classification into different groups and the intelligent analysis of their consumption data, provided by smart meters. The integration of user profile and smart meter data will provide the basis for the corresponding report. Also, another important task of the project is to analyze in detail the structure, content of these reports as well as the most appropriate communication channel (through the electricity bill, the web, social networks, specific app ..) or frequency of delivery, all based on the user clustering. As main results of the project three major deliverables will be obtained. On the one hand, an advanced segmentation of residential electricity consumers at European level; on the other, a set of computational tools for intelligent analysis of smart-data; finally, the main result of this work, a methodology for providing feedback, customized and easily understandable, to customers.
This coordination and support action (CSA) has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 657672. The multidisciplinary project team is made up of 10 organizations from 8 different European countries: five SMEs, three research institutes and two consumer associations, which encompass a wide variety of backgrounds, from sociologists, psychologists, to experts in the areas of energy and ICT.
ECSC acts as administrative coordinator of this network and technical leader of work package 5, in which the most important product of this activity will be generated, the feedback methodology. Also, the ECSC team takes an active role in the works related to the characterization of consumers and the development/application of computational tools for the intelligent analysis of smart meters.
More information at the project webpage (www.natconsumers.eu), Linkedin group (https://www.linkedin.com/grp/home?gid=8346421) and Twitter account (https://twitter.com/NATCONSUMERS?lang=es)
Intelligent Computational Tool for Forcasting Beef Quality
Meat is a very vulnerable product and any error in meat processing, packaging, distribution or at the point of sale will potentially affect its quality. Failure to detect a pathogen may have a dreadful effect on consumer’s perception and a negative impact on the industry. These problems are important to the meat industry since the freshness of the product is a quality attribute related to the final selling price.
In this context, during the project ECSC will study, design and develop an intelligent software for predicting the condition of beef. Initially, intelligent data processing techniques will be identified and applied to correlate variables measured in the laboratory and their impact on predicting the state of the meat. Then various machine learning methods will be designed to provide the best outputs of the system, this is the current quality of the meat and their lifetime for consumption, based on the inputs, data from laboratory or biosensors. Finally, and based on previous results, we will develop and validate with real data the most suitable method for real-time performance with defined inputs.
Asturias Programme 2014-2015
Principal Research: Sergio Damas Arroyo Funding Organization: Science, technology and innovation plan of the Asturias Principality Program: Asturias Programme 2014-2015 Partners: Proyectos individuales
Four different innovative projects were approved under the Asturias Programme by the corresponding regional organism. Following you could find the name and a brief description of their main goal.
1. Soft computing, agent-based modeling and dynamic systems for the management of the brand and marketing (grant code: CT14-05-2-04). The main objective of this project is the development of agent-based models, ABMs, for brand and competitive market systems. The global procedure for the modeling involves the use of techniques from fuzzy logic and system dynamic areas, calibration and validation using genetic algorithms and metaheuristics, development of simulation and optimization engines and finally the validation of the models in real scenarios.
2. Image analysis using Soft Computing (CT14-05-2-05). The main goal of this project is to extend our previous works in the image analysis field, generating frontier knowledge in the areas of fuzzy logic, evolutionary algorithms and metaheuristics, as well as go beyond the current image technologies in the market. Three scenarios will be studied in detail: medical image, forensic identification and wood quality control
3. Intelligent data analysis for industry and life sciences (CT14-05-2-06). The aim of this action is the design and development of data mining methods for: i) the analysis of neuronal signals (spikes) and the identification of assemblies involve in a specific process; ii) the study of fMRI images; and iii) the prediction of traffic patterns using GPS information. Moreover, APIs for the different developed tools will be generated.
4. Design of advanced fuzzy controllers (CT14-05-2-07). This project proposes the development of different methodologies and formalisms that allow advancing in the Control Theory. So, it involves the development of identification algorithms for piecewise bilinear models, the design of non lineal predictive controllers for tab systems and the definition of a methodology for the stability analysis of the controllers.
All these actions were approved within the “Programa Asturias 2014-2015” call by the Regional Ministry of Economy and Employment and are funded by the Principality of Asturias, through the 2013-2017 Science, Technology and Innovation Plan (grant code in project description), and the European Union, through the FEDER funds.
Support Tool for Strategic Decission Making about Corporate Identity
Principal Research: Manuel Chica Serrano Contracting Companies: Rod Brand Partners: Rod Brand, ECSC
Corporate image of a company represents the perception of the stakeholders of the entire organization. However, the valorization of this intangible parameter could last years when applying current methodologies in the case of a multinationals. The complexity of this analysis is due to the numerous variables that should be considered, their relationships as well as multiple audiences (consumers, employees, shareholders, suppliers, enterprise buyers, financial sector analysts, media or competitors) .
Identimod® roposes the development of intelligent methods that allow selecting the critical variables of the coorporative image system. This method uses as inputs the current variables, their systemic roles, cycles and the feedback existing at that time. The output will be a subset of variables which optimizes the system performance. The use of this software will catalyze the process of proposing and implementing actions to improve the image of a company or product., Within the scope of the porject, the ECSC works in modelling the variable selection problem, studies its implementation, and the testing using optimization algorithms
Agent-based modeling applications for the marketing sector
Principal Research: Manuel Chica Serrano Contracting Companies: Rod Brand consultants Partners: Rod Brand consultants, ECSC
This work consists in the development and validation of a model for the analysis of consumer buying behavior using “agent based modeling” techniques. The aim of this model is to simulate future scenarios that allow the evaluation and/or optimization of company marketing strategies.
Electricity in Natural Language
Principal Research: Gracián Triviño Barros Contracting Companies: HC Energía-EDP Partners: HC Energía-EDP, ECSC
Energy efficiency is the main measure that can reduce significantly emissions of greenhouse gases, and it be should be part of all mitigation policies. According to studies made by the International Energy Agency (IEA), the highest barrier that currently exists for the implementation of energy efficiency measures, with the technology currently available, is the lack of information that users have about their consumption, especially domestic users, and therefore the importance of efficient use. Based on this and taking advantage of legislative change that makes households to change their old meter by one that provides detailed hourly consumption statistics, Elenna2015 project promotes the development of a software tool capable of transforming the information provided by meters in simple text messages, meaningful and easily understandable by users. These messages, jointly with recommendations for an efficient consumption (also in text), will be included in the bimonthly bill sent to clients, with the ultimate goal of make aware users about their electricity demand. This work is the continuation of Ecofamilias project, which served for the realization of the first advances and also to identify certain obstacles that will be faced in this second phase of the project.
To achieve this overall objective, the ECSC will develop a dynamic granular linguistic model of power consumption for HC -EDP clients, which will be the engine for the generation of linguistic reports, and will refine the content of messages in order to increase its specific relevance for each consumer.
EPSRC and ESRC Centre for Doctoral Training on Quantification and Management of Risk & Uncertainty in Complex Systems & Environments
Principal Research: Christian Borgelt Program: - Partners: Universidad de Liverpool
CDT will address industrial and societal needs, at the local and global scales, which arise from the rapidly growing complexity of systems of various kinds, their environment and associated risks and uncertainties. It offers cutting-edge expertise and methodologies with which to quantify, mitigate and manage risk and uncertainty in many fields. To deal with that it counts with a multidisciplinary research team includes experts from architecture, engineering, environmental sciences, financial and actuarial mathematics, computer science, electrical engineering & electronics, economics and finance, social sciences and psychology.
CDT is established with the financial support of the UK’s Research Councils EPSRC and ESRC, the University of Liverpool and 36 industrial and academic partners. In the CDT, training will be provided for 76 PhDs over 8 years within a mathematical/scientific framework providing the essential tools needed to address multi-/inter-disciplinary problems of risk and uncertainty. The CDT is supported by 25 industrial partners, non-profit making foundations or national laboratories and 11 overseas university partners. Each PhD project will have at least two supervisors from different disciplines and will involve two six-month placements with partner organisations.
ECSC is one of the academic partners that support this initiative and it will receive PhD students under this programm as well as participate in different events organized by CDT.
This CDT is funded by the Research Councils UK, the University of Liverpool and a wide range of high profile industry partners, both local and international.
Principal Research: Luis Magdalena Layos Contracting Companies: HC COGENERACION Funding Organization: IDEPA Program: Innova 2012 Partners: HC Cogeneración, ECSC
Pregas project aims to optimize the utilization of Steelmaking Gas (GLD) and Coke Gas (GCK), generated by Arcelor, between the different options of use considering the different installation and supply requirements. These gases are used for generating electricity, that is placed in the network, and for producing steam which is supplied to Arcelor. The main requirements include that the start and stop processes of engines and boilers carry a cost and that the steam supply can not be interrupted, so a reduction in the use of GLD in boilers involves greater use of Natural Gas (GN), with the corresponding overrun.
To achieve this final goal it will be necessary to include a previous step of predicting the availability of gas for anticipating supply stops and the flow received on each time, with the incorporation of a gas meter as an element to smooth flow variations. For both stages, prediction and optimization, soft computing-based techniques will be applied which will determine the casting realization patterns, GLD production patterns associated with a casting as well as the different possibilities of action and assessment of their effects. During the last months of the project the developed algorithms will be validated and integrated, in the Sidergas factory of HC Cogeneracion, and a simple and intuitive user interface will be generated, providing easy handling for non-experts.
Parsing and multi-word expressions. Towards linguistic precision and computational efficiency in natural language processing
Principal Research: Gracián Triviño Barros Funding Organization: Seven framework programme Program: COST Actions Partners: 24 paises europeos se encuentran involucrados en esta acción COST
The Action, PARSEME, aims at increasing and enhancing the support of the European multilingual heritage from Information and Communication Technologies (ICT). This general aim is addressed through improving linguistic representativeness, precision and computational efficiency of Natural Language Processing (NLP) applications. The Action focuses on the major bottleneck of these applications: Multi-Word Expressions (MWEs), i.e. sequences of words with unpredictable properties such as "to count somebody in" or "to take a haircut". A breakthrough in their modelling and processing can only result from a coordinated effort of multidisciplinary experts in different languages.
Expected deliverables include enhanced language resources and tools, as well as recommendations of best practices for cutting-edge MWE-aware language models. It will pave the way towards competitive next generation text processing tools which will pay greater attention to language phenomena.
This project is funded by the European Union within the COST programme under the reference IC1207 COST Action
Prediction Model of Production in Wind Parks
Principal Research: Manuel Chica Serrano Contracting Companies: EDP renováveis Partners: EDP RENOWABLES EUROPE, ECSC
The objective of this project was to develop a robust and efficient system to improve production forecast in wind energy parks of the multinational EDP Renowables Europe.
Project work involved updating the forecast model generated in the past (1st phase), and the implementation and validation of the improved version in EDP Renowables Europe facilities. This second model took into account historical data of prediction, production and availability of multiple EDP wind farms. The analysis of the new data reestimated and adjusted the parameters of the old model, improving production forecasts. The new model was validated online in EDP offices.
Tool Shape Correction project
Principal Research: Christian Borgelt Contracting Companies: PMG Asturias Program: R&D Contract Partners: PMG Asturias
After defining the shape, sizes and powder composition of a new part, the shape and dimensions of the production tools have to be designed. In this project, we will use
detailed measurements of approximately 35 different references produced in the PMG plant in Mieres including data of the tools to produce them. This historical
record of the most parts and tools manufactured contains important knowledge waiting to be harnessed and utilized for more effective and efficient tool design. The
tool shape correction system that will be developed in this project can speed up the design process and increase its accuracy and robustness. This speed, reduced cost
and flexibility can provide an important competitive advantage to the plant of PMG in Asturias.
The ECSC will develop an algorithm that allows to quickly compute estimates from different sets of chosen reference parts together with an indication of their reliability, so that the design process becomes faster, more accurate, and more robust. The implementation of this algorithm in a software tool that will be used at PMG will be done in a second phase after the end of this first development project.
Simulation and optimization of commercial promotions using artificial intelligence techniques. Phase II
Principal Research: Wolfgang Trutschnig Contracting Companies: Alimerka, Nortia Inteligencia de Negocio Funding Organization: Science, technology and innovation plan of the Asturias Principality Program: Funding to companies for the development of R&D projects Partners: Alimerka, Nortia Inteligencia de Negocio
Supermarkets have based their competition strategy in high reductions of the prices. Prices are a key aspect for customers when deciding how to buy, and prices are conditioned by several factors, i.e., negotiations with suppliers. Therefore, companies need to be able to fast and efficient decision making, being aware of the potential consequences of such decisions.
In the first part of this project a “Simulator of Promotions” that allow predicting, simulating, and optimising the commercial impact of the promotions designed, before launching them, was developed.
In this second phase a set of algorithms will be generated with the purpose of massive and direct marketing. In the area of collective marketing new models and researches will be carried out to identify the effect of cannibalism in products, synergies between them and recommendations for the optimal advertisement of combination of products in the promotional brochure. Regarding individual marketing, recommendation algorithms will be studied for the promotion of product packs to specific groups of people and vice versa, to which person I have to offer a set of products. Additionally, in the last stage of the project new tools for the optimization of direct-mail advertising and supermarkets location will be tackled.
Medical imaging using bio-inspired and soft computing
Principal Research: Oscar Cordón Funding Organization: Seven framework programme Program: Marie Curie Initial Training Networks Partners: Universidad de Ghent, Universidad Libre de Bruselas, Universidad de Nottingham, Universidad de los Estudio de Parma, Universidad de Granada, Henesis, Universidad Clínica de Friburgo, Centro Internacional de Investigación Científica, General Electric Europa, Hospital Universitario Central de Asturias, Treelogic
Medical imaging is at the heart of many of today’s improved diagnostic and treatment technologies. Computer-based solutions are vastly more capable of both quantitative measurement of the medical condition and the pre-processing tasks of filtering, sharpening, and focusing image detail. Bio-inspired and Soft Computing techniques have been successfully applied in each of the fundamental steps of medical image processing and analysis (e.g. restoration, segmentation, registration or tracking). The natural partnership of humans and intelligent systems and machines in Medical imaging is to provide the clinician with powerful tools to take better decisions regarding diagnostic and treatment. The main goal of the “Medical Imaging using bio-inspired and soft computing” Initial Training Network is to create a training programme where 16 enrolled early-stage researchers will be exposed to a wide variety of Bio-Inspired and Soft Computing techniques, as well as to the challenge of applying them to different situations and problems within the different MI stages. The collaboration of experts from different areas will generate new and viable methods and solutions from the combined ideas of these communities. The presence of both research and technical partners in the network, including hospitals and companies, will provide the appropriate framework for application domain focused research. The trained young researchers will acquire a strong background for the development of intelligent systems based on Bio-Inspired and Soft Computing providing flexible application-oriented solutions to current Medical Imaging problems in the clinical and research field.
Optimization of the Gamonedo cheese tasting process for providing the guarantee of origin
Principal Research: Gil González-Rodríguez Contracting Companies: ALCE Calidad Funding Organization: Science, technology and innovation plan of the Asturias Principality Program: Research and development projects in companies
The evaluation of food products is a complex process that involves several scientific fields and sensory analysis plays an essential role. The sensory properties influence the choice and preferences of consumers therefore it is of great importance to develop methods to measure these characteristics more objectively. The sensory evaluation is even more important in products that have local singularities and are marketed under Protected Denominations of Origin.
In this project, we have redesigned the tasting process of Gamonedo cheese applying Soft Computing techniques for the acquisition and processing of data. A methodology has being developed to increase the reliability and efficiency of the tasting process and to reduce the time and resources used. The application of fuzzy logic has allowed the development of a flexible and adaptable method for other types of food products.
INNOVATIVE POPLAR LOW DENSITY STRUCTURAL PANEL
Principal Research: Enrique Ruspini Contracting Companies: - Funding Organization: Seven framework programme Program: FP7-Environment Partners: IMAL SRL, IBL SPA , CIAOTECH SRL, STELA LAXHUBER Gmbh, IDP Ingeniería y Arquitectura Iberia, S.L., Fundación para el Progreso del Soft Computing, Università degli Studi di Milano, CHIMAR HELLAS S.A.
I-PAN aims at providing novel and highly environmental friendly solutions in the field of the engineered wood based boards. I-PAN's main objective is the design of a breakthrough wood-made lightweight panel, adopting 50% of its volume recycled wood and for the remaining 50% poplar wood by using the upper part of the tree that is commonly underused. To this purpose, a novel manufacturing process will be designed and innovation to existing resins will be defined in order to require less energy during the drying and pressing process, minimizing VOC emission and reducing the overall cost of production.
In order to reach this goal, a consortium of 8 partners, coming from 4 different EU countries (Germany, Greece, Italy, Spain) and including 4 SMEs, 2 large industrial partners specialized in manufacturing wood-made panels and production of poplar made panels, a Research Centre and a University is involved.
ECSC researchers will participate in the development of a monitoring and control system, based in advanced vision and three-dimensional reconstruction techniques, for a optimal resin distribution during the blending process. Additionallly, they will be involved in construction of a vision system to control mat forming process
This project is co-funded by the European Commission within the FP7 (2007–2013) under the grant agreement no. 308630
Development of a platform based on soft computing techniques for programming wind power generation
Principal Research: Oscar Cordón Contracting Companies: Neo energía
Companies that manage wind farms should provide predictions of wind power generation as accurate as possible. However, this is a complex task that requires the integration of imprecise data from different sources. In this innovative project, the ECSC is developing a system to improve the production forecasts of wind farms of the multinational EDP Renovaveis. Soft computing techniques are being used to integrate real time information, historical data and expert knowledge to provide better predictions of wind energy production.
New methodologies and protocols of forensic identification by craniofacial superimposition
Principal Research: Sergio Damas Arroyo Funding Organization: Seven framework programme Program: SEC-2011.1.4-3 Advanced forensic framework - Coordination and Support Action Partners: European Centre for Soft Computing, Consorci di Ricerca Sistemi ad Agenti, Europaischer Ausschuss fur Rechtmedizin EV, University of Granada, Ministry of Public Security (Israel), Universidade de Coimbra, Ministerio del Interior (España)
The new methodologies and protocols of forensic identification by craniofacial superimposition (MEPROCS) project aims to propose a common EU framework to allow the extensive application of the craniofacial superimposition (CS) technique in practical forensic identification scenarios commonly tackled by the European scientific police units. This framework will include: i) the implementation of an existing semi-automatic method to assist the forensic experts in the application of the CS technique, resulting in a simple, quick, and systematic approach; ii) the definition of standard protocols at European level, leading to the objective application of the CS technique in different forensic identification scenarios; and iii) the specification of a forensic science methodology to provide an objective evaluation of the forensic identification results achieved by CS, avoiding particular assumptions that could bias the process. Hence, the project clearly promotes the validation and exchange of CS protocols and methodologies among different organisations.
The particular objectives of this project concern supporting the development of a trustable CS methodological framework by fulfilling requirements covering educational, technical, economic, social, and security aspects.
Development of an Intelligent System for the Prediction of Building and Demolition Waste
Principal Research: Luis Magdalena Layos Contracting Companies: AIE, Contemax, Duonet Funding Organization: Centre for technological and industrial development (CDTI) Program: Interempresas Partners: AIE (6 constructoras), Contemax, Duonet
The main objective of this project is the development of an expert system for the prevention, control, estimation and good practices in building waste management. We will create an easy to use and efficient tool that predicts the amount and kind of waste generated in building works, establishing the basis for action procedures at all the stakeholdersinvolved in its control levels (administration, building companies, and waste managers)
The final goal will be the obtaning of new algorithms for the analysis of building parameters and of information about the waste generated, which will be integrated in an intelligent system for the prediction and control of the waste.This system will easier the fulfillment of administrative regulations for the building sector defined in the RD 105/2008.
Operating of safety, intelligent and sustainable motorways
Principal Research: Luis Magdalena Layos Funding Organization: Spanish ministry of science and innovation Program: CENIT Partners: OHL Concesiones, Iridium, Abertis, Indra, SICE, Obrascón Huarte Lain, Dragados, Geocisa, GMV, Asfaltos Augusta, Hidrofersa, Siegrist y Moreno, PyG Estructuras Ambientales, CPS Ingenieros, Asociación Española de la Carretera, Torre de Comares.
The main objective of the project is to advance in the definition of the future motorways with a comprehensive approach from their design, construction, operation and maintenance to their deconstruction. Thus, we aim at achieving several objectives such as minimizing the environmental impact, increase users' benefit, avoiding interruptions for maintenance and traffic jams, and reduce circulation risks. The ECSC focuses its tasks in the development of a decision support system that will analyse the available information in order to determine the best actions to be carried out in each specific situation within the management of a motorway. The decision support system will take into account context data, behaviour models, expert knowledge, predictions systems, etc
Development of an intelligent tool to analyse electric consumption data
Principal Research: Christian Borgelt Contracting Companies: HC energía Funding Organization: Science, technology and innovation plan of the Asturias Principality Program: Research and development projects in companies
The energy companies are facing new challenges and environmental requirements. The HC Energia company, aware of this situation, has launched this project that aimed at promoting a more efficient energy consumption. The ECSC has applied intelligent data mining and computing with words techniques to improve the interpretability of the information registered by the electricity meters of “HC Energía”, developing a first prototype able to clearly and easily describes users their energetic consumption patterns. This intelligent tool provides HC Energía of information about each user energetic consumption, and therefore the company will be able to offer its customers advice to carry out a sustainable consumption, both from the economic and environmental point.
Technologies for automated and intelligent management of the future power distribution networks
Principal Research: Enrique Ruspini Contracting Companies: Indra Sistemas S.A Funding Organization: Spanish ministry of science and innovation Program: CENIT Partners: Unión Fenosa Distribución, Gas Natural, Indra, Sistemas Avanzados de Control, ZIV, DIMAT, NSysCom, Aplicaciones en Informática Avanzada, Answare Technologies, Visual Tools, Brainstorm Multimedia, Prodevelop, DiagnóstiQA, Omazabal y Cía
Currently we are attending to a new framework in the energy sector characterised by the boost of the energetic efficiency, the emergence of new customers (eg: electric vehicles) and new energy production systems, what are making necessary actions devoted to the integration of all these new elements and to demand management.
In this context, the objective if this project is the development of intelligent systems able to analyse data from different sources, to monitor and control the power grid, and to carry out efficient and safe management of the new energy requirements. The work of the ECSC in this project is focused on obtaining new algorithms for the optimization of supply and management recharging points for electric vehicles
Intelligent cab for road transport
Principal Research: Gracián Triviño Barros Funding Organization: Spanish ministry of science and innovation Partners: ESM, CEIT, LANDER, Universidad de Alcalá, ALSA, Universidad de Valencia, Universidad Rey Juan Carlos, Tecnum, Universidad Politécnica de Madrid
The main objective of this project is to design an intelligent cab for vehicles equipped with smart technologies, able to record and assess information parameters of the vehicle, of the infrastructure and the driver. In addition to the detection and identification of these data, a decision making system will be designed, for its application in vehicle reactions, warning management, communication systems and on-board information.
Within this project the ECSC is involved in the subproject "HITO: Human Interface Technology by Observation" in which, computing with words and perceptions techniques are being applied to the development of a system architecture and a user interface that allow the risk management while driving.
This project is supported by the European Regional Development Fund (ERDF).
Intelligent systems for capacities and operations optimization and rationalization in Tenneco Automotive company
Principal Research: Oscar Cordón Contracting Companies: Tenneco Automotive Funding Organization: Institute for the economic development of the Principality of Asturias (IDEPA) Program: Innova
Single and multiobjective metaheuristic techniques have been applied in the analysis and modelling of an automotive components manufacturing line of the Tenneco Automotive company. Thus we have developed a system to support plant managers on decision-making tasks related with planning and rescheduling the production, thereby improving the productive capacity of the company.
Abstraction, Synthesis, and Integration of Information for Human-Robot Teams
Principal Research: Enrique Ruspini Funding Organization: Spanish ministry of science and innovation Program: Fundamental Research Partners: Univ. de Alcalá (UAH; proyecto coordinado)
Researchers of the ECSC in colaboration with the Univerity of Alcalá are applying soft computing techniques, data collection/fusion, and information integration to develop concepts and algorithms for the generation of qualitative object descriptions easily understandable by humans and for the integration of those semantic descriptions into coherent, high-level, descriptions of situations, intentions, and plans. Results will be implemented in the testbed environments required to evaluate its practical applications, such as 3D mapping based on collaborative labelling for safe autonomous navigation or quick deployment of rescue teams under emergency situations.
New Developments on Soft Computing and Computer Vision Techniques in Forensic Identification
Principal Research: Sergio Damas Arroyo Contracting Companies: - Funding Organization: Spanish ministry of science and innovation Program: Fundamental Research Programme Partners: Proyecto coordinado. Subproyecto 1: UGR
As an outstanding result of previous projects (SOCOVIFI, reference TIN2006-00829 and to a lesser extent SIMMRA, reference TIN2009-07727 project), the researchers of the current coordinated project proposal developed an automatic procedure to support the forensic anthropologist in the application of the Craniofacial superimposition (CS) technique to human identification cases. The procedure considered the use of soft computing (SOCO) techniques, image registration methods and 3D skull modeling.
Despite the high success achieved by the designed CS framework, some aspects still need to be addressed to make it a computer-based system able to assist forensic experts in real identification cases. The aim of this SOCOVIFI2 coordinated project proposal is thus to extend the current procedure to develop an automatic, reliable, and robust computer-based solution to assist the expert in forensic identification by CS.
This global objective involves the following six research lines: i) modeling of all the sources of uncertainty inherently involved in the process; ii) development of objective and semi-automatic techniques for the validation of skull-face overlay and CS identification results, considering their application to multiple comparisons; iii) design of new camera models for specific scenarios; iv) automation of existing skeleton-based age estimation methods; v) development of a new 3D model reconstruction procedure able to deal with fragmented skulls; vi) development of a software demonstrator integrating all the latter methods; and vii) validation of the new techniques on real-world identification cases.
This project has received funding from the spanish Ministry of Economy and Competitiveness, within the non-oriented basic research programme (TIN2012-38525-C02-02), and from the European Union through ERDF funds.
Framework for Interactive-services Over Natural-conversational Agents
Principal Research: Gracián Triviño Barros Contracting Companies: ADELE Robots Funding Organization: Centre for technological and industrial development (CDTI) Program: NEOTEC Partners: ADELE Robots
According to Ray Kurzweil, renowned american scientist and inventor specializing in AI systems, robots revolution will be achieved in 2020 and it will be more significant than that produced by genetics and nanotecnolgy. However, much work need to be adressed due there is still a wide rejection in society concerning the use of robots. One of the main reasons for this rejection is the coldness and lack of empathy of current robotic systems. Therefore, a key factor for the success of robotic solutions is the implementation of emotional aspects in the interaction with people.
FIONA aims to catalyze the development of interaction features and capabilities that provide not only physical robots but also virtual assistants or avatars with a similar behaviour than humans. With this purpose a platform will be developed where different kind of organisations (universities, research centers, companies, etc..) will made available their advances and developments in this field in order to contribute to the goal of providing solutions that accomplish the needs of each specific customer.
Teh ECSC will apply Affective Computing and Computing with Perceptions techniques towards achieving this common goal.
Development of a Fuzzy Inferential System for the Quantification of Intangible Assets
Principal Research: José Maria Alonso Moral Contracting Companies: Vortica Funding Organization: Science, technology and innovation plan of the Asturias Principality Program: Support for the development of R & D projects by companies 2007-2013 Partners: Vortica
In this project we will adress the analysis and development of a system able to characterize and quantify subjective properties of products by applying fuzzy logic. The main aim of this project will be the development of an innovative methodology to evaluate the qualitative description of object’s intangible properties.
The approach will be based in emotional and psicological aspects related with Kansei Engineering, focusing in the quantitative description of the qualitative featuresof an object provided by the users. This will allow the integration of this kind of properties in the current generative design systems of the company Vortica, avoiding the re-design of all the productive process each time that a new product wants to be produced.
The final goal of this research work is to adapt the design of a product to the qualitative opinions of users'groups, which has been classified according several criteria in different potential customer groups.
Technologies to provide mobile services in the future intelligent universe
Principal Research: Oscar Cordón Contracting Companies: Treelogic Funding Organization: Spanish ministry of science and innovation Program: CENIT Partners: Telefónica investigación y desarrollo S.A., Telvent S.A., AT4 Wireless, iSOCO, Worldnet 21, Instalaciones Inabensa S.A., Treelogic, Caja Navarra, Sugar Factory, TB Solutions
The project aims to explore and maximize the exploitation of the capacities that mobile devices offer to individuals by means of the interaction with the environment, both from a personal and professional point of view. One of the main objectives of the project is the personalisation of the contents and the services offered to the users (trough their mobile devices) according to their interests and to the context (place, time, situation, etc.). The ECSC is designing the tools that will allow the identification of typical user behaviours. As a result, the offered services could be adapted to their preferences, and new services could be created to satisfy new detected needs.
Linguistic Description of Complex Phenomena
Principal Research: Gracián Triviño Barros Funding Organization: Spanish ministry of science and innovation Program: Fundamental Research Partners: Universidad de Santiago (proyecto coordinado)
The objective of the project is the design and development of a new family of computational systems capable of generating linguistic descriptions of complex phenomena.
This type of systems will be used in supervision and control applications and especially in the development of user interfaces based on the use of natural language.
On a theoretical level, we expect to make significant contributions in the research line of Computing with Words and Perceptions proposed by L.A. Zadeh. On the practical level, we will produce a methodology and various application prototypes that will represent the core for the industrial exploitation of the new methodology.
This project was cofunded by the Spanish Ministry of Economy and Competitiveness, through the 2011 Basic Research Programme (ref. TIN2011-29827-C02-01), as well as by the Economy and Employment office from the Principality of Asturias, through the 2013 Joint Financing Programme (ref. COF13-054)
Bisociation networks for creative information discovery
Principal Research: Christian Borgelt Funding Organization: Seven framework programme Program: Future and Emerging Technologies Partners: Universidad Konstanz (Alemania), Universidad del Ulster (Reino Unido), Instituto Josef Stefan (Eslovenia), Universidad Católica de Leuven (Bélgica), Universidad de Bristol (Reino Unido), Universidad Otto von Guericke de Magdeburgo (Alemania), Universidad de Helsinki (Finlandia)
The concept of association is at the heart of many of today's powerful ICT technologies such as information retrieval and data mining. These technologies typically employ association by similarity or co-occurrence to discover new information relevant to the evidence already known to the user. However, domains that are characterized by the need to develop innovative solutions require a form of creative information discovery from increasingly complex, heterogeneous and geographically distributed information sources. These domains, including design and engineering (drugs, materials, processes, devices), areas involving art (fashion and entertainment), and scientific discovery disciplines, require a different ICT paradigm that can help users to uncover, select, re-shuffle, and combine diverse contents to synthesize new features and properties leading to creative solutions. People working in these areas employ creative thinking to connect seemingly unrelated information, for example, by using metaphors or analogical reasoning. These modes of thinking allow the mixing of conceptual categories and contexts, which are normally separated. The functional basis for these modes is a mechanism called bisociation (see Arthur Koestler "The Act of Creation").
The goal of this project is to develop a fundamentally new ICT paradigm based on the concept of bisociation. The key vision of the project is to develop a bisociative information discovery framework and an implemented open-source platform for interactive and scalable processing of massive, dispersed collections of heterogeneous contents. The project will develop a novel knowledge representation formalism (a bisociation network) and a bisociative reasoning mechanism enabling information discovery from the resulting network, using novel graph analysis, visualization and explanation techniques.
Intelligent systems integrated in on board systems
Principal Research: Gracián Triviño Barros Contracting Companies: Treelogic Funding Organization: Science, technology and innovation plan of the Asturias Principality Program: Research and development projects in companies Partners: Treelogic
More information available soon
Advanced irrigation system based on artificial intelligence
Principal Research: José Maria Alonso Moral Contracting Companies: Treelogic Funding Organization: Institute for the economic development of the Principality of Asturias (IDEPA) Program: INNOVA
The objective of this project was to obtain an automatic irrigation system able to make intelligent decisions about the optimal irrigation of both arable lands and entertainment areas, such as golf courses. With this aim the ECSC has tried several concepts focused on the development of a system that estimates the real water needs using meteorological information, expert knowledge, and information about the environment. In addition, the application of artificial intelligence techniques will allow the system to act in autonomous way, providing great economic efficiency.
Real time video analysis for security applications
Principal Research: Sergio Damas Arroyo Contracting Companies: Treelogic Funding Organization: Science, technology and innovation plan of the Asturias Principality Partners: Treelogic
The increasing number of terrorist attacks, crimes committed by small organised gangs, and the vandalism in large cities, are one of the principal concerns of citizens and governments. In this context, is important the development and implementation of intelligent surveillance systems able to the “understand” what is happening. The main objective of this project is to investigate technologies for video analysis in real-time using semantic techniques and soft computing, and its application in smart surveillance systems in heterogeneous environments. The work the ECSC is focused in studying and selecting the most suitable Soft Computing techniques to achieve this aim.
Intelligent system for the efficient energy management in buildings
Principal Research: Gracián Triviño Barros Contracting Companies: Comasis Consultores S.L. Funding Organization: Xunta de Galicia
The increasing energy consumption and depletion of the fossil energy resources is causing negative impacts in the environment and the economy. Therefore, it is necessary to undertake measures that lead to the efficient management of the energy.
This project main objective is the development of an intelligent system that allows controlling the principal consumption points in a building (lighting, air conditioning, hot water, etc.), adapting them to the environmental conditions and trying to balance energy efficiency and energetic resources.
The ECSC research is focused in the obtaining of a cognitive architecture that integrates the interface with the operator, helping him to better be aware on real time of the system behaviour and to better decision making. This interface will allow to, in one hand, acquire the user wellness perception, by means of a language interaction, and in the other the transmission to the operator of this perception as well as other environment information, also using a language interaction. Therefore, he will be able to easy understand the state of the building and to efficient manage it.
Continuous Time Detection of Neuronal Assemblies and Spatio-Temporal Patterns in parallel spike trains
Principal Research: Christian Borgelt Contracting Companies: - Funding Organization: Spanish ministry of science and innovation Program: Basic Research Programme Partners: ECSC
Biological neural networks like the human brain are generally formed by millions or even billions of neurons—the elementary units of neural information processing. While the chemical and electrical signaling behavior on the level of individual neurons and their connections is fairly well understood in terms of voltage gradients, action potentials (spikes), neurotransmitters, excitatory and inhibitory synapses as the connection points between neurons etc., it is a topic of intense ongoing research how larger groups of neurons cooperate to process information and, more basically, how they represent (code) information (stimuli strengths etc.).
Unfortunately, classical detection methods become infeasible for the rich data that can be recorded nowadays due to a combinatorial explosion of the possible patterns to be tested for, a lack of reliable statistics, and a lack of appropriate analysis tools. This project aims at improving this situation by exploiting the progress made within the data mining community on the topic of frequent pattern mining, especially frequent item set mining, but also elements of fuzzy technology. The goal is to develop new and improved methods for these tasks, which are particularly geared to the special challenges one faces in parallel spike train analysis, therefore contributing to understand the principles of coordinated neural activity, neural coding and neural assemblies.
This project has received funding from the spanish Ministry of Economy and Competitiveness, within the non-oriented basic research programme (TIN2012-31372), and from the European Union through ERDF funds.
Auto-configurable robots for social services
Principal Research: Gracián Triviño Barros Funding Organization: Spanish ministry of industrie, tourism and commerce Program: Singular and strategic projects Partners: Treelogic, Fatronik, M-Bot Solutions, Omicron electronics, Bizintek innova, Verbio, Universidad de Deusto, Universidad de Extremadura, Universidad Politécnica de Cataluña, Alimerka, Hospital Comarcal Sant Antoni , Junta de Andalucía
The use of robots for services purposes has suffered a limited development comparing with the growing application of these systems in other industrial sectors. To overcome this existing gap, robots should show social aptitudes and be able to anticipate users' needs. The main challenge this project faces is to move from the current concept of social robots, focused on providing pre-established services and not easily re-configurable, towards the creation of intelligent systems, able to autoconfigurate and to autonomously modify its behaviour, by means of understanding and learning capacities, and human interaction.
In this context, the project, integrated by a consortium of 13 Spanish companies, R&D centres, universities, and hospitals, is developing new intelligent assistant robots able to provide personal services in different environments and situations. The ECSC is working in the design of computational tools to provide robots of empathy and improved communication skills. Thereby, we aim at increasing the social acceptance of assistant robots. The results obtained from this project will be validated in marketing and health environments.
This project (ref: TSI-020301-2009-27) is supported by the European Regional Development Fund (ERDF).
Development and applicability of predictve mathematical models of the food spoilage and pathogens
Principal Research: Christian Borgelt Contracting Companies: El Barquero, Friobas, Embutidos El Hórreo, Mariscos Oviñana Funding Organization: Science, technology and innovation plan of the Asturias Principality Program: Research and development projects in companies
Currently, the studies of the self life and the microbiological behaviour of food products require large numbers of tests, what involves high costs for companies, especially in the case of the development of innovative products. Therefore the food sector is very interested in reducing these testing costs without compromising safety or quality.
In this project, the ECSC has studied the viability of applying fuzzy statistics on the development of a methodology to estimate the shelf-life of different types of food products. The final goal of this study has been to establish the bases for obtaining a tool to be integrated in the food safety management system of the companies involved, improving the robustness of this process and increasing their competitiveness reducing logistic and analysis costs.
Natural Language Interaction Engine
Principal Research: Gracián Triviño Barros Contracting Companies: Treelogic Funding Organization: Science, technology and innovation plan of the Asturias Principality Partners: Sinerco
This project aims to increase the capacity of interaction of the machines performing oral and body language. The project's goal is to create Embodied Conversational Agents through speech and gesture features, using semantic technologies. Analysis of acoustic and visual signals will provide the knowledge of the scene that is taking place. The virtual agent will establish fluid and natural communication with people, adapting its behavior to the circumstances and characteristics of the user and its environment. In order to establish a relationship of empathy between the person and the machine, the virtual agent will be provided with different personalities, looks and gestures, so that the person always maintain a fluid dialogue and emotional interaction.
The ECSC works in tbe application of Computing wiht Words and Perception techniques in the extraction of caractheristics of the user and the environment, and in speech recognition.
Computing with Meanings for automatic teller machines
Principal Research: Gracián Triviño Barros Contracting Companies: Treelogic Funding Organization: Science, technology and innovation plan of the Asturias Principality Program: Research and development projects in companies
In this project we have worked on the development of a new generation of automatic teller machines that emulate a part of the interactions between the customers and the staff in bank offices. The main characteristics of these virtual assistants are, on the one hand the ability to understand language and to communicate using it, and in the other the empathy, reached by detecting intentions, needs and emotions of the user. We have also worked on the design of techniques that endow these assistants of capacity to learn and become adapted, and to recognize the user and provide him a more personalised assistance. Thus, interaction will be quite similar to the personal one, what will make easier the use of the services provided by these systems, overcoming its current limitations.
Combining soft computing techniques and statistical methods to improve data analysis solutions
Principal Research: Christian Borgelt Funding Organization: Seven framework programme Program: COST Action Partners: http://costsoftstat.softcomputing.es/members.html
22 countries participate in this COST action (European Cooperation in the field of Scientific and Technical Research) coordinated by the ECSC, which aims at reinforcing the dialogue between Soft Computing and Statistics scientific community, reaching important scientific and technical results.
The main objective of this project is to create improved tools for intelligent data analysis, able to be applied in both scientific and industrial fields that integrates the robustness of the statistical methods with the flexibility and the capacity to solve real problems of the Soft Computing.
Intelligent data analysis tool to improve the fabrication of new products
Principal Research: Gil González-Rodríguez Contracting Companies: PMG Asturias Powder Metal
In the field of industrial production a long and tedious process take place since a piece is designed until its fabrication starts. Using advance statistical techniques and artificial intelligence methods the ECSC has developed a tool that sistematises this process, providing experts of reliable indications about how to produce new car parts basing on historical data of reference pieces. Therefore the precision and robustness, has considerable increased, and thus the efficiency of the process.
Historical geomorphologic analysis of Asturias flooding areas: statistic and soft computing contributions
Principal Research: Gil González-Rodríguez Funding Organization: Science, technology and innovation plan of the Asturias Principality Program: Basic research project 2009 Partners: Indurot, Universidad de Oviedo
In this project we are applying fuzzy sets modelling techniques for developing a deep analysis of the experimental data obtained from mapping the flood areas in Asturias. Therefore, we aim at obtaining a system that allows, on one hand, to improve the understanding of the factors that explain floodings’ danger, and on the other to reduce the degree of experience required to perform the mapping of dangerous flooding areas, and the complexity of this task.
Soft Collaborative Intelligent Systems
Principal Research: Enrique Ruspini Funding Organization: Seven framework programme Program: Marie Curie-International Incoming Fellowship
We will investigate new research lines aimed at designing, understanding, and implementing collaborative information systems involving multiple interacting agents. The objectives of these studies will be, on one hand, robotic and sensor systems incorporating a large number of interacting agents and, on the other, distributed information systems incorporating sophisticated coordination and interaction tools. Soft-computing techniques will be applied to the design, analysis, and implementation of multiagent systems including hybrid systems where several human and autonomous agents collect, exchange, and process information to regulate system behaviour. The project plans to cover a wide range of applications such as manufacturing, scheduling, control, diagnosis, logistics, environmental emergency management, energy managing, and road traffic management. The project is based in a multidisciplinary approach that will integrate developments stemming from insights from a number of perspectives, notably biology, cognitive science, linguistics, economics, and social sciences.
Soft computing and computer vsion techniques in forensic identification
Principal Research: Oscar Cordón Funding Organization: Spanish ministry of science and innovation Program: Fundamental no orientated research 2006 Partners: Universidad de Granada
An automatic system to assist forensic anthropologists in the identification of dead bodies is being developed by means of the superimposition of 3D skulls’ images with photographs of the missing people. The use of bio-inspired algorithms and fuzzy systems allows that the identification process that takes more than twenty hours of an experienced professional could be carried out automatically by a computer in just two minutes.
Computing with words and perceptions in an intelligent environment
Principal Research: Gracián Triviño Barros Funding Organization: Spanish ministry of science and innovation Program: Fundamental not orientated research Partners: Universidad Politécnica de Madrid, Universidad Rey Juan Carlos y Universidad de Santiago
This is an interdisciplinary project involving basic research as well as the development of prototypes for specific applications in the area of Soft Computing.
The project is structured around the creation of a virtual entity that uses a network of sensors and actuators, and its ability to perform linguistic descriptions to operate as a computational assistant for the user of a monitoring and control system in an intelligent environment. We are focusing our efforts on the investigation of the use of words to create descriptions of the information obtained from these sensor networks. These descriptions will emphasize the relevant aspects of the physical system being analyzed taking into account the needs of the user at each instant in time. Thus, this virtual entity will be capable of producing to the user the impression of a communication with a mental and intentional being similar to him/her.
Soft analysis of crisp and imprecise experimental data
Principal Research: Gil González-Rodríguez Funding Organization: Spanish ministry of science and innovation Program: Fundamental not orientated research 2008 Partners: Universidad de Oviedo
The need to obtain objective conclusions from incomplete or imprecise information has opened different research directions along the last years. In particular, combining the modelling of the imprecise sample information in terms of fuzzy set valued data with the use of standard Statistical techniques for functional data analysis has been a very valuable strategy, though in some cases it was too restrictive and in disagreement with the imprecise nature of the involved data. In this project the research team is working on several alternatives that may help to overcome such inconveniency. Specifically, two basic problems will be addressed: Linear regression with imprecise data and ‘Fuzzy’ hypothesis testing. Furthermore, the development of soft techniques it is considered.
Consulting network for processes and relationships management
Principal Research: Oscar Cordón Funding Organization: MINISTRY OF INDUSTRY, ENERGY AND TOURISM Partners: Informática Gesfor, Telenium, Carver, Novadays, Atos Origin, Tecnocom, GMV Soluciones Globales de Internet, Paradigma Tecnológico, ESI Tecnalia, Universidad Politécnica de Madrid, Universidad de Alcalá
Eight companies, two universities and two research centres collaborate in this project to investigate, test and implement new technologies to process and manage professional relations within consulting companies. This project will develop tools to improve information flow and the creation of connections between the different stakeholders involved in their activities (customers, employees, suppliers, partners, etc).
The ECSC activities are focused on the application of intelligent data analysis techniques and fuzzy clustering to knowledge discovery, the extraction of relevant user's information and to provide personalised recommendations (e.g. creating links ad groups).
This project (ref: TSI-020301-2009-31) is supported by the European Regional Development Fund (ERDF).
New knowledge management tools in complex business organizations
Principal Research: Christian Borgelt Funding Organization: Spanish ministry of industrie, tourism and commerce Program: Profit 2007 Partners: Universidad Politécnica de Madrid, Idea Informatica
The objective of this project is the development of a knowledge management tool that facilitates the participation and collaboration between different members of a company in order to improve their effectiveness. In particular, the news tools will support both formal and informal structures of companies. ECSC focuses its research in the application of data mining and text mining technologies to generate virtual communities created by means of the compilation of the interests of the members of the organization. Soft Computing techniques will automate the identification and publication of relationships between users and contents.
Simulation and optimization of commercial promotions using artificial intelligence techniques
Principal Research: Wolfgang Trutschnig Contracting Companies: Alimerka y Nortia Funding Organization: Science, technology and innovation plan of the Asturias Principality Program: Funding to companies for the development of R&D projects
Supermarkets have based their competition strategy in high reductions of the prices. Prices are a key aspect for customers when deciding how to buy, and prices are conditioned by several factors, i.e., negotiations with suppliers. Therefore, companies need to be able to fast and efficient decision making, being aware of the potential consequences of such decisions.
In this project the ECSC is working with ALIMERKA supermarket in the development of automatic learning and prediction algorithms for obtaining a “Simulator of Promotions” that allow predicting, simulating, and optimising the commercial impact of the promotions designed, before launching them. We will consider sales, royalty and customers’ satisfaction. Furthermore, an expert system will be developed to recommend user the optimal combination of promotions considering variables such as season, profit margin or customers estimated response.
Application of fuzzy logic and evolutionary algorithms to visual science map mining
Principal Research: Prakash Shelokar Funding Organization: Spanish ministry of science and innovation Program: Juan de la Cierva
The main goal of this research project is to take a step ahead in the field of visual science map mining by means of advanced graph-based data mining techniques based on multi-objective metaheuristics, to analyze and compare the structure of scientific fields and research fronts in maps of the same (taken at different periods of time) or different domains (looking for similarities between different countries scientific productions).
This project is supported by the Spanish Ministry of Science and Innovation, by means of the Juan de la Cierva 2010 sub-programme, with a project reference: JCI-2010-07626.
Language learning by means of multiagent systems: Smart Bees
Principal Research: Sergio Guadarrama Funding Organization: Spanish ministry of science and innovation Program: Juan de la Cierva
Smart-Bees is a project driven by experiments where we want to study how machines can learn and communicate using linguistic descriptions from the perspective of Computing with Words.
For our experiments we are developing a web-based application for automatically creating natural language-based descriptions out of images. The system first learns descriptions provided by humans, and then uses computational intelligence and fuzzy logic to produce its own descriptions witthout human intervention.
Technological framework for cognitive technologies in industrial processes
Principal Research: Oscar Cordón Funding Organization: Spanish ministry of science and innovation Program: National programme of applied research 2009. Subprogramme technological centres Partners: Fundación LEIA
The objective of this project is to make a qualitative leap forward the maintenance, management, monitoring and operation of industrial processes by means of the development of cognitive tools that allow anticipating situations of breakdowns, maintenance requirements, etc. These new systems will provide more competitive manufacturing enterprises, mainly SMEs, through more efficient from an economic and energetic point, safer and friendly with the environment processes.
This project (ref: PID-020100-2009-7) is supported by the European Regional Development Fund (ERDF)
Single- and multi-objective metaheuristics for real-world applications: assembly line balancing, visual science map mining, and 3D forensic modeling
Principal Research: Oscar Cordón Funding Organization: Spanish ministry of science and innovation Program: Fundamental not orientated research Partners: Universidad de Granada
Many complex combinatorial and numerical optimization problems arise in human activities, such as economics (e.g., portfolio selection), industry (e.g., scheduling or logistics), or engineering (e.g., network routing), among many others. The impracticability to get optimal solutions for these kinds of problems in reasonable time using classical algorithmic techniques has caused the successful development of different approximate algorithm methodologies, called metaheuristics, in the last two decades, able to quickly provide high quality solutions to them.
The main aim of the current project is to take a step ahead on the solution of some specific complex real-world applications by means of metaheuristic algorithms. We will mainly focus on single- and multi-objective evolutionary and ant colony optimization algorithms, due these are the metaheuristics which seem to be better suited to solve the considered problems.