Hi,

Two new videos of Episteme project have been published

https://www.gsi.dit.upm.es/index.php/canalgsi.html?lang=e

             Carlos A.

Reading on Thursday April 4 delayed at 12:00, on the B-225 defends his final project Adrian Perez, you're all invited.

Title: DATA MINING APPLIED TO FAULT PREDICTION IN A RAILWAY SYSTEM MAINTENANCE

Author: Adrián Pérez Orozco

Summary:

This work presents the results Trainmining project, conducted by the Intelligent Systems Group with Thales Spain. The project consists on the Development and implementation of a system failure prediction for a network of railway maintenance, by applying mining techniques datos.En Specifically, the project aims to be able to predict future events in the network rail (for alerts and failures of various systems) based on events that have occurred so far. The project uses SPADE algorithm to obtain alarm prediction rules, and has developed a prototype for the evaluation of real-time dicas rules.

Published the video of idea visualisation for THOFU project at GSI channel 

https://www.gsi.dit.upm.es/index.php/es/canalgsi.html

More info about the idea visualisation is available at:

http://www.gi2mo.org/2013/03/idea-relationship-visualisation-with-gi2mo-technologies/

Tomorrow 2oth February at 17:00 Adam defends his phD

Title:  Semantic Technologies in Idea Management Systems: A Model for Interoperability, Linking and Filtering

Author: Adam Westerski

Time: 17:00

Place: Salón de Grados

Abstract

Idea Management Systems are web applications that implement the notion of open innovation though crowdsourcing. Typically, organizations use those kind of systems to connect to large communities in order to gather ideas for improvement of products or services. Originating from simple suggestion boxes, Idea Management Systems advanced beyond collecting ideas and aspire to be a knowledge management solution capable to select best ideas via collaborative as well as expert assessment methods. In practice, however, the contemporary systems still face a number of problems usually related to information overflow and recognizing questionable quality of submissions with reasonable time and effort allocation. This thesis focuses on idea assessment problem area and contributes a number of solutions that allow to filter, compare and evaluate ideas submitted into an Idea Management System. With respect to Idea Management System interoperability the thesis proposes theoretical model of Idea Life Cycle and formalizes it as the Gi2MO ontology which enables to go beyond the boundaries of a single system to compare and assess innovation in an organization wide or market wide context. Furthermore, based on the ontology, the thesis builds a number of solutions for improving idea assessment via: community opinion analysis (MARL), annotation of idea characteristics (Gi2MO Types) and study of idea relationships (Gi2MO Links). The main achievements of the thesis are: application of theoretical innovation models for practice of Idea Management to successfully recognize the differentiation between communities, opinion metrics and their recognition as a new tool for idea assessment, discovery of new relationship types between ideas and their impact on idea clustering. Finally, the thesis outcome is establishment of Gi2MO Project that serves as an incubator for Idea Management solutions and mature open-source software alternatives for the widely available commercial suites. From the academic point of view the project delivers resources to undertake experiments in the Idea Management Systems area and managed to become a forum that gathered a number of academic and industrial partners.

Estáis todos invitados a la lectura

CALISTA project begins, TEC2012-32457, "Agent Technologies and Engineering Services Diagnostics and Configuration of Home Network using a Mobile Phone", awarded by the Ministry of Economy and Competitiveness Project Subrograma unoriented Fundamental Research , lasting from 2013 to 2016.
Project Summary
The network technology is increasingly penetrating in homes that already have delhogar networks formed by different network devices (cameras, storage units, video grabadoresde, ...). However, homeowners often do not have the knowledge to manage the network técniconecesario, assist in fault diagnosis and repair, or configurarsus services.
The purpose of the project is to apply CALISTA semantic technologies, engineering services and development desistemas multiagent diagnostic system, configuration and network management delhogar. The project will build that even in cases of lack of access to broadband network (ADSL, FTTH), the user has an alternative access to the 3G mobile network through your phone, your phone or tablet yque are natural user interfaces .
The purpose of the project will be achieved through the development of the following scientific objectives:
1. Research techniques cooperative fault diagnosis under uncertainty. In the diagnosis proyectopretendemos investigate cooperative, combining systems and Bayesian razonamientosemántico mulitagente and in two additional scenarios: (i) between different users using elsistema, so that will extend the knowledge base diagnostic causal model and (ii) between the user and the operator, thanks to the availability of the TID and IAP EPOs elsistema improving fault diagnosis of a qualified operator with user feedback.
2. Research techniques and building configuration in-home service deespecificación techniques based on their semantic representation.
3. Research on proactive network management by personal agents that facilitate execution of other orders and notify the user of potential hazards or task to be performed and not estánautomatizadas. This objective explores the definition of a personal agent architecture dotadode communication capabilities in natural language. The focus of the research will investigate elrazonamiento agent to give explanations to the user based on commonsense reasoning using, and the discovery of useful information available on the internet.

Name of course or activity: Agent Based Social Simulation
Name (in English): Agent Based Social Simulation
Number totales1 credits: 4
Objectives
The study and understanding of complex adaptive systems, such as networks or our own society, is extremely difficult. This course presents the foundations of a new discipline, Agent Based Social Simulation, which aims to model and understand these systems. The key of this discipline is the study of the behavior of isolated members of society, or agents, are not sufficient to derive group behaviors derived from these. Simulation techniques can: analyze the evolution of society as a whole from the interactions of individual agents with other agents and their environment predict the evolution of the system under different parameters, and evaluate training or other systems that must adapt to changing one of these complex systems. Some examples of complex systems to be discussed in the course are: the spread of computer viruses, rumors spread on Twitter, and evaluate different evacuation plans in a building with a society of workers.
The course aims to provide an overview of current solutions for social simulations.
The course will follow a practical approach.
The detailed objectives of the course are:
Learn techniques for agent-based social simulation and its application to network management
Learn to develop a simulation model of social
Learning to reason about the results of a social simulation
Methodology: Theoretical classes and online, through distance learning platform Moodle. Laboratory practical classes
Students to whom it may concern (or level courses that must be): Students from all courses with Java programming experience
Background information (recommended): Basic knowledge of Eclipse IDE.
Number of places: 60
Number theory credits: 1.5 Number of practical credits: 2.5
Dates: Courses shall (18/02/13, 25/02/13, 04/02/13, 11/03/13, 18/03/12, 25/03/13, 01/05/13). Practices remotely with final presentation in class.
Hours: Monday from 14.00 to 16.00
Evaluation: Personal practice at the end of the course
Date of examination (if any): No examination
Program:

• T1. Introduction to social simulation.
• T2. Social Simulation Models.
• T3. MASON environment.
• T4. Case Study. Spread of a computer virus.
• T5. Case Study. Spread tweets.
• T6. Case Study. Evacuation of a building.
• P1. Practical development of social simulation system.Coordinator: Carlos Angel Iglesias Fernández

Teachers participating:

• Emilio Serrano
• Alvaro Carrera
• Miguel Coronado