Principal researcher: Luis Magdalena
Contractor:Treelogic
Research units involved: Fundamentals of Soft Computing.
The objective of this project is to study the development of an autonomous irrigation management system that optimises the use of water by means of artificial intelligent techniques.
Principal researcher: Luis Magdalena
Support: Centre for the Development of Industrial Technology-CDTI (CENIT Programme)
Research units involved: Cognitive Computing/Applications of Fuzzy Logic and Evolutionary Algorithms/Intelligent Data Analysis and Graphical Models
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. Three central themes are going to be considered throughout the project: service quality, safety and sustainability. 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.
Principal researcher: Luis Magdalena
Support: Centre for the Development of Industrial Technology - CDTI (CENIT Programme)
Research units involved: Cognitive Computing/ Applications of Fuzzy Logic and Evolutionary Algorithms.
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 personalization 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 will design the tools that will allow the identification of the typical user behaviours. As a result, the offered services could be adapted to their preferences or needs, and new services could be created to satisfy new detected needs.
For more information click here (external link in spanish)
Principal researcher: Luis Magdalena
Support: Centre for the Development of Industrial Technology-CDTI (CENIT Programme)
Research unit involved: Applications of Fuzzy Logic and Evolutionary Algorithms/Intelligent Data Analysis and Graphical Models
In this project, we are developing a set of models, architectures and prototypes of a new industrial production paradigm based on knowledge. This new framework for the application of Cognitive Technologies in industrial production processes aims at introducing innovative methodologies for the maintenance, management, monitoring and operation of these processes. These new methodologies will improve the competitiveness of manufacturing companies, mainly SMEs, by means of more efficient processes (in economic and energetic terms) that are safer and environmentally friendlier.
Principal researcher: Gracián Triviño
Support: Ministry of Science and Innovation (Fundamental Research Programme)
Research units involved: Cognitive Computing/ Fundamentals of Soft Computing.
This is an interdisciplinary project involving basic research as well as the development of prototypes for specific applications in the area of Soft Computing. Its main objective is to contribute to the extension of Fuzzy Logic towards Computing with Words and Perceptions as suggested by Professor Zadeh. We will focus our efforts on investigating the use of words to create descriptions of the information obtained from complex sensor networks. These descriptions should emphasize the relevant aspects of the physical system being analyzed taking into account the needs of the user at each instant in time.
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. The main feature of this virtual entity is that it will be capable of producing to the user the impression of a communication with a mental and intentional being similar to him/her.
Principal researcher: Christian Borgelt
Contractor: HC Energía
Research units involved: Intelligent Data Analysis and Graphical Models/ Cognitive Computing.
The ECSC will employ data mining techniques to improve the interpretability of the information registered by the electricity meters of “HC Energía” and will develop a system that will describe the energetic consumption patterns in a clear and simple way to the users. The intelligent data analysis tools developed will permit to generate linguistic recommendations for the customers in order to help them to have a more efficient and environmentally-friendly energetic consumption.
Principal researcher: Gil González
Contractor: PMG Asturias Powder Metal
Research units involved: Intelligent Data Analysis and Graphical Models.
The objective of this project is to improve new products development process by means of advanced statistical techniques and artificial intelligent methods. The main objectives of this project are: (1) to develop data analysis methods that will mitigate the mathematical assumptions underlying current estimation process in order to capture the knowledge buried in the database of reference parts and tools, (2) to reduce the number of manual choices made by the tool designer based on his tacit knowledge in order to make the procedure more systematic and traceable, and (3) to provide an automatic tool that allows to quickly compute estimates from different sets of chosen reference products together with an indication of their reliability, so that the design process becomes faster, more accurate and more robust.
Principal researcher: Christian Borgelt
Support: Future and Emerging Technologies, 7º Framework Program, European Union.
Research units involved: Intelligent Data Analysis and Graphical Models.
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.
For more information click here (external link)
Principal researcher: Gracián Triviño
Contractor: Treelogic
Research units involved: Cognitive Computing
The project will develop a new generation of Automatic Teller Machines that will emulate a part of the interactions of customers with staff in bank offices. The advanced interface that combines infographic techniques to control a virtual assistant with computer vision techniques for facial costumer’s recognition and simulation of visual contact will create a sensation in the customer of a personalised attention similar to the interaction with a human. The interaction will be done by means of a spoken dialog between the customer and the virtual assistant that will overcome the limitations of current automatic dialog systems. ECSC will focus in the incorporation of Computing with Meanings into the virtual assistant. This approach allows structuring the semantic and pragmatic levels by implementing a flexible knowledge representation based in natural language.
Principal researcher: Christian Borgelt
Support: COST Action, European Union
Research units involved: Intelligent Data Analysis and Graphical Models.
The main objective of this COST action is to strengthen the dialogue between the statistics and soft computing research communities in order to cross-pollinate both fields and generate mutual improvement activities. Soft computing, as an engineering science, and statistics, as a branch of mathematics, emphasize different aspects of data analysis. Soft computing focuses on obtaining working solutions quickly, accepting approximations and unconventional approaches. Its strength lies in its flexibility to create models that suit the needs arising in applications (context of discovery, model generation). In addition, it emphasizes the need for intuitive and interpretable models, which are tolerant to imprecision and uncertainty. Statistics is more rigorous and focuses on establishing objective conclusions based on experimental data by analysing the possible situations and their (relative) likelihood (context of justification, model validation). It emphasizes the need for mathematical methods and tools to assess solutions and guarantee performance. Bringing the two fields closer together will enhance the robustness and generalisability of data analysis methods, while preserving the flexibility to solve real-world problems efficiently and intuitively.
For more information click the following links (external links):
http://www.cost.esf.org/domains_actions/ict/Actions/Data_Analysis_Solutions
Principal researcher: Óscar Cordón
Support: Ministry of Education and Science and the Regional Government of Andalusia
Research units involved: Applications of Fuzzy Logic and Evolutionary Algorithms.
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.
Principal researcher: Christian Borgelt
Support: PROFIT Project, Ministry of Industry, Tourism and Commerce.
Research units involved: Intelligent Data Analysis and Graphical Models/ Applications of Fuzzy Logic and Evolutionary Algorithms.
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.
Principal researcher: Óscar Cordón
Contractor: Tenneco Automotive Ibérica
Research units involved: Applications of Fuzzy Logic and Evolutionary Algorithms.
The aim of this project is to analyse and model an automotive components manufacturing line. A system to support managers’ planning decisions and production re-programming processes has been developed.
