Page 145 - Laboratorios, Equipos e Instalaciones en España disponibles para el Sector Ferroviario

KNOWLEDGE ENGINEERING & MACHINE LEARNING GROUP

DEPARTMENT OF COMPUTER SCIENCE

UNIVERSITAT POLITECNICA DE CATALUNYA

DESCRIPTION AND GOALS OF THE ORGANISATION

The main aim of the Knowledge Engineering and Machine Learning Group
(KEMLG) is the analysis, design, implementation and application of several
Artificial Intelligence techniques and methodologies to support the operation
or behaviour analysis of real-world complex systems or domains. The
research is focused on the analysis, design, management or supervision of
these domains, such as in healthcare, in environmental processes and
systems, in social and internet-based systems and in the industrial and
enterprise sectors.

AREAS OF ACTIVITY
t Ontologies, Social Networks & Knowledge Representation t Machine Learning
t Semantic Web & Intelligent Web Services t Software Agents & Multi-Agent Systems

t IDSS & Recommender Systems t Electronic Institutions
t IDSS & Recommender Systems t Grid Computing

TEST FACILITIES, EQUIPMENT, TYPES OF TESTING AND/OR TRI"LS

Data Science
* Intelligent Data Analysis & knowledge discovery from data regarding people mobility, trains system, etc. to improve the
performance (processes, flows, tasks, etc.).
* Raw Data/Social Network Data Visualization for detecting user profiles, behaviour patterns, operation situations of the
train/mobility systems, time trends, etc.
* Predictive Analytics for estimating several parameters of mobility, train systems, routing, etc.
Intelligent Decision Support Systems (IDSS) for process optimization.
* Estimates of the degree of crowding in stations and coaches based on activity analysis on social networks and/or raw
data.
* Real-time detection of unplanned events with affectation of urban mobility based on analysis of social network activity
(accident prediction of mass movements in sport events, etc.) or/and raw data.
* Real-time detection of the state of the city in relation to mobility indicators.
* Simulation of different scenarios based on the application of different mobility policies (eg. what if increase the capacity
of wagons?).
* Implementation of opportunistic recommenders for multi-modal mobility route planners.
* Finding successful solutions to complex real-world mobility/planning/routing/assignment problems.
* Operationalizing mobility policies and automatic generation of policy suggestions for the detected scenarios.
* Integration of data generated by social networks to complement those obtained by other means (raw data, etc.).
* Real-time detection of scenarios and exceptional situations which may affect mobility (accidents, crowding, delays)
Successful Stories.
* Integrated approach to multi-modal smart metropolitan mobility systems [SUstainable and PERsuasive Human Users
moBility in future cities, SUPERHUB EU Project, http://superhub-project.eu/].
* Intelligent Environmental Decision Support Systems (ATL-EDAR software) for supervising WWTP [SISLtech S.L
company spin-off from UdG-UPC http://sisltech net]

ADDRESS CONTACT PERSON
C/ Jordi Girona 1-3, 08034 Barcelona Dr. Miquel Sànchez-Marrè FiEMSs
UPC, Campus Nord, edificio OMEGA, despachos 201-207 Profesor Titular de Universidad
Tel.: +34 93 413 78 41 Tel.: +34 93 413 78 41
http://kemlg.upc.edu Email: miquel@cs.upc.edu