Cookies Policy
We use cookies to improve our site and your experience. By continuing to browse our site you accept our cookie policy. Find out More
Close
  • Menu
Facts & Numbers
000
Presentation

Artificial Intelligence and Decision Support

At LIAAD, we work on the very strategic area of Data Science, which has an increasing interest worldwide and is critical to all areas of human activity. The huge amounts of collected data (Big Data) and the ubiquity of devices with sensors and/or processing power offer opportunities and challenges to scientists and engineers. Moreover, the demand for complex models for objective decision support is spreading in business, health, science, e-government and e-learning, which encourages us to invest in different approaches to modelling.

Our overall strategy is to take advantage of the data flood and diversification, and to invest in research lines that will help reduce the gap between collected and useful data, while offering diverse modelling solutions.

At LIAAD, our fundamental scientific principals are machine learning, statistics, optimisation and mathematics.

Latest News
Computer Science

INESC TEC researcher publishes book through Springer-Verlag

Alberto Adrego Pinto, researcher at the Laboratory of Artificial Intelligence and Decision Support (LIAAD) of INESC TEC and professor at the Faculty of Sciences of the University of Porto, has recently published the second volume of the series "Modeling, Dynamics, Optimization and Bioeconomics", together with David Zilberman, of the University of California, Berkeley, USA.

17th January 2018

Caravana Tecnológica visits INESC TEC

On 16 November, INESC TEC received the Caravana Tecnológica (Technological Caravan) of the MTech Portugal 2017 initiative and, in particular, the group of companies that expressed interest in getting to know the institute, its centres and its work.

18th December 2017

Computer Science

Project MAESTRA concluded with rating of Excellent

European project MAESTRA (Learning from Massive, Incompletely annotated, and Structured Data), which had the collaboration of the Laboratory of Artificial Intelligence and Decision Support (LIAAD) of INESC TEC, received a final rating of Excellent.

19th October 2017

INESC TEC researcher edits new publication in Mathematical Economics

The scientific publisher Springer Verlag has just released the publication Trends in Mathematical Economics – Dialogues Between Southern Europe and Latin America, edited by Alberto Adrego Pinto, INESC TEC researcher, together with professors Elvio Accinelli Gamba, UALSP (Mexico), Athanasios N. Yannacopoulos, AUEB (Athens, Greece), and Carlos Hervés-Beloso, University of Vigo (Spain).

09th November 2016

Doctoral thesis developed at INESC TEC awarded in Brazil

Vinicius Souza of the Institute of Mathematics and Computer Sciences, University of São Paulo (ICMC-USP), has received the "Best PhD Thesis" award for work conducted at INESC TEC. He was awarded as part of a competition which awards the best theses and dissertations in Artificial Intelligence and Computer Science (CTDIAC).

25th October 2016

Interest Topics
030

Featured Projects

PERSONA

PERSONALIZAÇÃO E GESTÃO DE INFORMAÇÃO BASEADA EM DADOS CLIENTE

2017-2019

RECAP

Research on European Children and Adults born Preterm

2017-2021

SmartFarming-1

Ferramenta avançada para operacionalização da agricultura de precisão

2016-2018

PANACea

Perfis para Anomalias Consumo

2016-2017

BI4UP2

Business Intelligence (BI) Tool

2016-2017

Dynamics2

Dynamics, optimization and modelling

2016-2019

CORAL-TOOLS

CORAL – Sustainable Ocean Exploitation: Tools and Sensors

2016-2018

MarineEye

MarinEye - A prototype for multitrophic oceanic monitoring

2015-2017

FOUREYES

TEC4Growth - RL FourEyes - Intelligence, Interaction, Immersion and Innovation for media industries

2015-2018

NanoStima-RL5

NanoSTIMA – Advanced Methodologies for Computer-Aided Detection and Diagnosis

2015-2018

iMAN

iMAN - Intelligence for advanced Manufacturing systems

2015-2018

NanoStima-RL3

NanoSTIMA – Health data infrastructure

2015-2018

NanoStima-RL4

NanoSTIMA – Health Data Analysis & Decision

2015-2018

SMILES

SMILES - Smart, Mobile, Intelligent and Large scale Sensing and analytics

2015-2018

FOTOCATGRAF

Graphene-based semiconductor photocatalysis for a safe and sustainable water supply: an advanced technology for emerging pollutants removal

2015-2018

SEA

SEA-Sistema de ensino autoadaptativo

2015-2015

MAESTRA

Learning from Massive, Incompletely annotated, and Structured Data

2014-2017

BI4UP

Business Intelligence (BI) Tool

2014-2014

SIBILA

Towards Smart Interacting Blocks that Improve Learned Advice

2013-2015

SmartManufacturing

Smart Manufacturing and Logistics

2013-2015

SmartGrids

Smart Grids

2013-2015

Dynamics

Dynamics and Applications

2012-2015

e-Policy

Engineering for the Policy-making Life Cycle (ePolicy)

2011-2014

SIMULESP

Expert system to support network operator on real time decision

2011-2015

CRN

Trust-aware Automatic E-Contract Negotiation in Agent-based Adaptive Normative Environments

2010-2013

KDUS

Knowledge Discovery from Ubiquitous Data Streams

2010-2013

Palco3.0

Intelligent Web system to support the management of a social network on music

2008-2011

Argos-1

Wind power forecasting system

2008-2012

MOREWAQ

Monitoring and Forecasting of Water Quality Parameters

2008-2011

ORANKI

Resource-bounded outlier detection

2008-2011

Team
Publications

LIAAD Publications

View all Publications

2018

Preference rules for label ranking: Mining patterns in multi-target relations

Authors
de Sa, CR; Azevedo, P; Soares, C; Jorge, AM; Knobbe, A;

Publication
INFORMATION FUSION

Abstract
In this paper, we investigate two variants of association rules for preference data, Label Ranking Association Rules and Pairwise Association Rules. Label Ranking Association Rules (LRAR) are the equivalent of Class Association Rules (CAR) for the Label Ranking task. In CAR, the consequent is a single class, to which the example is expected to belong to. In LRAR, the consequent is a ranking of the labels. The generation of LRAR requires special support and confidence measures to assess the similarity of rankings. In this work, we carry out a sensitivity analysis of these similarity-based measures. We want to understand which datasets benefit more from such measures and which parameters have more influence in the accuracy of the model. Furthermore, we propose an alternative type of rules, the Pairwise Association Rules (PAR), which are defined as association rules with a set of pairwise preferences in the consequent. While PAR can be used both as descriptive and predictive models, they are essentially descriptive models. Experimental results show the potential of both approaches.

2018

Using metalearning for parameter tuning in neural networks

Authors
Félix, C; Soares, C; Jorge, A; Ferreira, H;

Publication
Lecture Notes in Computational Vision and Biomechanics

Abstract
Neural networks have been applied as a machine learning tool in many different areas. Recently, they have gained increased attention with what is now called deep learning. Neural networks algorithms have several parameters that need to be tuned in order to maximize performance. The definition of these parameters can be a difficult, extensive and time consuming task, even for expert users. One approach that has been successfully used for algorithm and parameter selection is metalearning. Metalearning consists in using machine learning algorithm on (meta)data from machine learning experiments to map the characteristics of the data with the performance of the algorithms. In this paper we study how a metalearning approach can be used to obtain a good set of parameters to learn a neural network for a given new dataset. Our results indicate that with metalearning we can successfully learn classifiers from past learning tasks that are able to define appropriate parameters. © 2018, Springer International Publishing AG.

2018

Iterated-greedy-based algorithms with beam search initialization for the permutation flowshop to minimise total tardiness

Authors
Fernandez Viagas, V; Valente, JMS; Framinan, JM;

Publication
EXPERT SYSTEMS WITH APPLICATIONS

Abstract
The permutation flow shop scheduling problem is one of the most studied operations research related problems. Literally, hundreds of exact and approximate algorithms have been proposed to optimise several objective functions. In this paper we address the total tardiness criterion, which is aimed towards the satisfaction of customers in a make-to-order scenario. Although several approximate algorithms have been proposed for this problem in the literature, recent contributions for related problems suggest that there is room for improving the current available algorithms. Thus, our contribution is twofold: First, we propose a fast beam-search-based constructive heuristic that estimates the quality of partial sequences without a complete evaluation of their objective function. Second, using this constructive heuristic as initial solution, eight variations of an iterated-greedy-based algorithm are proposed. A comprehensive computational evaluation is performed to establish the efficiency of our proposals against the existing heuristics and metaheuristics for the problem.

2018

Enhancing supply chain performance through supplier social sustainability: An emerging economy perspective

Authors
Mani, V; Gunasekaran, A; Delgado, C;

Publication
International Journal of Production Economics

Abstract

2017

Mitigation in the Very Short-term of Risk from Wind Ramps with Unforeseen Severity

Authors
Pinto, M; Miranda, V; Saavedra, O; Carvalho, L; Sumaili, J;

Publication
JOURNAL OF CONTROL AUTOMATION AND ELECTRICAL SYSTEMS

Abstract
This paper addresses a critical analysis of the impact of the wind ramp events with unforeseen magnitude in power systems at the very short term, modeling the response of the operational reserve against this type of phenomenon. A multi-objective approach is adopted, and the properties of the Pareto-optimal fronts are analyzed in cost versus risk, represented by a worst scenario of load curtailment. To complete this critical analysis, a study about the usage of the reserve in the event of wind power ramps is performed. A case study is used to compare the numerical results of the models based on stochastic programming and models that take a risk analysis view in the system with high level of wind power. Wind power uncertainty is represented by scenarios qualified by probabilities. The results show that the reliability reserve may not be adequate to accommodate unforeseen wind ramps and therefore the system may be at risk.

Supervised Theses

2016

A Performance dos Agentes de Seguros e a Diversidade de Parcerias: Modelos de Equações Estruturais e Análise de Redes Sociais

Author
Mónica Monteiro Chibante Sequeira

Institution
UP-FEP

2016

A Aceitação do Aplicativo Móvel “Cartão Continente” por Parte dos Clientes Sénior

Author
Paula Sofia da Cruz Ribeiro

Institution
UP-FEP

2016

Impacto de uma Ação de Merchandising em Farmácias

Author
Teresa Filipa Ferreira da Cunha Cruz e Sousa

Institution
UP-FEP

2016

Impacto dos Incidentes Críticos Negativos na Propensão para a Repetição e Divulgação de um Destino de Férias

Author
Teresa Maria Moura Quintas

Institution
UP-FEP

2016

Perceção da responsabilidade social nos estudantes de mestrados em economia e gestão

Author
Tânia Margarida Soares Castro Silva

Institution
UP-FEP

Facts & Figures

0R&D Employees

2017

28Academic Staff

2017