INESC-ID

About: INESC-ID is a nonprofit organization based out in Lisbon, Portugal. It is known for research contribution in the topics: Field-programmable gate array & Control theory. The organization has 932 authors who have published 2618 publications receiving 37658 citations.

Automated two-way entrainment to improve spoken dialog system performance

Abstract: This paper proposes an approach to the use of lexical entrainment in Spoken Dialog Systems. This approach aims to increase the dialog success rate by adapting the lexical choices of the system to the user's lexical choices. If the system finds that the users lexical choice degrades the performance, it will try to establish a new conceptual pact, proposing other words that the user may adopt, in order to be more successful in task completion. The approach was implemented and tested in two different systems. Tests showed a relative dialog estimated error rate reduction of 10% and a relative reduction in the average number of turns per session of 6%.

FUZYE: A Fuzzy ${c}$ -Means Analog IC Yield Optimization Using Evolutionary-Based Algorithms

Abstract: This paper presents fuzzy ${c}$ -means-based yield estimation (FUZYE), a methodology that reduces the time impact caused by Monte Carlo (MC) simulations in the context of analog integrated circuits (ICs) yield estimation, enabling it for yield optimization with population-based algorithms, e.g., the genetic algorithm (GA). MC analysis is the most general and reliable technique for yield estimation, yet the considerable amount of time it requires has discouraged its adoption in population-based optimization tools. The proposed methodology reduces the total number of MC simulations that are required, since, at each GA generation, the population is clustered using a fuzzy ${c}$ -means (FCMs) technique, and, only the representative individual (RI) from each cluster is subject to MC simulations. This paper shows that the yield for the rest of the population can be estimated based on the membership degree of FCM and RIs yield values alone. This new method was applied on two real circuit-sizing optimization problems and the obtained results were compared to the exhaustive approach, where all individuals of the population are subject to MC analysis. The FCM approach presents a reduction of 89% in the total number of MC simulations, when compared to the exhaustive MC analysis over the full population. Moreover, a ${k}$ -means-based clustering algorithm was also tested and compared with the proposed FUZYE, with the latest showing an improvement up to 13% in yield estimation accuracy.

Spatial OLAP modeling: an overview base on spatial objects changing over time

Abstract: Enabling the decision making process to support spatial queries is not a trivial task. This task becomes even harder when using geographic information systems (GIS) with data warehouse (DW) because these two technologies are in general used separately. In general, a GIS solution handles spatial data without considering time constrains or without requiring the analyses of geometric shapes evolving over time. Temporal maps further raise difficulties on indexing issues and on the associated query mechanisms. On the other hand, a typical DW operates with non-spatial data for different time periods. It also does not support spatial data types, such as point, lines, and polygons. In this paper, we propose a multidimensional spatiotemporal data model to enable spatial analysis, in a context of evolving specifications. The proposed data model addresses the problem of spatial and temporal data integration by providing information to facilitate semantic interoperability and data analysis in a spatial DW that uniformly handles all types of data. Using a practical example in the field of land parcels, we evaluate the implementation of the model.

Using Fuzzy Fingerprints for Cyberbullying Detection in Social Networks

Abstract: As cyberbullying becomes more and more frequent in social networks, automatically detecting it and pro-actively acting upon it becomes of the utmost importance. In this work, we study how a recent technique with proven success in similar tasks, Fuzzy Fingerprints, performs when detecting textual cyberbullying in social networks. Despite being commonly treated as binary classification task, we argue that this is in fact a retrieval problem where the only relevant performance is that of retrieving cyberbullying interactions. Experiments show that the Fuzzy Fingerprints slightly outperforms baseline classifiers when tested in a close to real life scenario, where cyberbullying instances are rarer than those without cyberbullying.

An extended dynamic model of Lactococcus lactis metabolism for mannitol and 2,3-butanediol production

Abstract: Biomedical research and biotechnological production are greatly benefiting from the results provided by the development of dynamic models of microbial metabolism. Although several kinetic models of Lactococcus lactis (a Lactic Acid Bacterium (LAB) commonly used in the dairy industry) have been developed so far, most of them are simplified and focus only on specific metabolic pathways. Therefore, the application of mathematical models in the design of an engineering strategy for the production of industrially important products by L. lactis has been very limited. In this work, we extend the existing kinetic model of L. lactis central metabolism to include industrially relevant production pathways such as mannitol and 2,3-butanediol. In this way, we expect to study the dynamics of metabolite production and make predictive simulations in L. lactis. We used a system of ordinary differential equations (ODEs) with approximate Michaelis–Menten-like kinetics for each reaction, where the parameters were estimated from multivariate time-series metabolite concentrations obtained by our team through in vivo Nuclear Magnetic Resonance (NMR). The results show that the model captures observed transient dynamics when validated under a wide range of experimental conditions. Furthermore, we analyzed the model using global perturbations, which corroborate experimental evidence about metabolic responses upon enzymatic changes. These include that mannitol production is very sensitive to lactate dehydrogenase (LDH) in the wild type (W.T.) strain, and to mannitol phosphoenolpyruvate: a phosphotransferase system (PTSMtl) in a LDH mutant strain. LDH reduction has also a positive control on 2,3-butanediol levels. Furthermore, it was found that overproduction of mannitol-1-phosphate dehydrogenase (MPD) in a LDH/PTSMtl deficient strain can increase the mannitol levels. The results show that this model has prediction capability over new experimental conditions and offers promising possibilities to elucidate the effect of alterations in the main metabolism of L. lactis, with application in strain optimization.