ESTG - Comunicações em conferências e congressos internacionais
URI permanente para esta coleção:
Navegar
Entradas recentes
- It Is the Time for Portuguese Texts!Publication . Craveiro, Olga; Macedo, Joaquim; Madeira, HenriqueIn this work, we introduce a software testbed for temporal processing of Portuguese texts, composed by several building blocks: identification, classification and resolution of temporal expressions and temporal text segmentation. Starting from a simple document, we can reach a set of temporally annotated segments, which enables the establishment of relationships between words and time. This temporally enriched information is then placed into an Information Retrieval system. This work represents a step forward for Portuguese language processing, with notorious lack of tools. Its main novelty is temporal segmentation of texts. Even with target application in temporal aware Information Retrieval, the described software tools can be used in other application scenarios.
- A European Portuguese Children Speech Database for Computer Aided Speech TherapyPublication . Lopes, Carla, Alexandra Calado Lopes; Veiga, Arlindo; Perdigão, FernandoThis paper introduces a European Portuguese speech database containing spoken material recorded from children. The need for such database arose from the need of train phone models for the development of a computer aided speech therapy system. Articulatory disorders affect a significant number of children in pre-school age. We propose a system intended to assist and reinforce the conventional speech therapy programs. Through the systematic use of games, it learns the phones where the child has more difficulty to pronounce. The child is then taken to train the production of those phones by playing games. Another interest of a children speech database is that accurate children's phone recognition is only possible using training data that reflects the population of users. It is a difficult task due to the high pitch of children's speech
- A survey on HDR visualization on mobile devicesPublication . Magalhães, Luis; Bessa, Maximino; Urbano, Carlos; Melo, Miguel; Peres, Emanuel; Chalmers, Alan; Pasi SaarikkoThere is a vast body of literature concerning the capture, storing, transmission and display of High Dynamic Range (HDR) imaging. Nevertheless, there are few works that try to address the problem of getting HDR on mobile devices. Their hardware limitations, such as processing power, storage space, graphics capabilities and screen characteristics, transform that problem in a big challenge. However, since more and more HDR content is being produced and given that in a few years it can become a standard, it is necessary to provide the means to visualize HDR images and video on mobile devices. The main goal of this paper is to present a survey on HDR visualization approaches and techniques developed specifically for mobile devices. To understand what are the main challenges that need to be addressed in order to visualize HDR on mobile devices, an overview of their main characteristics is given. The very low dynamic range of most of mobile devices' displays implies that a tone mapping operator (TMO) must be applied in order to visualize the HDR content. The current status of the research on TMO will be presented and analyzed, a special attention will be given to the ones that were developed taking in account the limited characteristics of the mobile devices' displays. Another important issue is visualization quality assessment, meaning visualize HDR content without losing the main characteristics of the original HDR content. Thus, evaluation studies of HDR content visualization on mobile devices will be presented and their results analyzed.
- High Performance Antennas for Early Fire Detection Wireless Sensor Networks at 2.4 GHzPublication . Oliveira, Tiago E. S.; Reis, João R.; Vala, Mário; Caldeirinha, Rafael F. S.In this paper, high performance antennas are pro-posed for massive deployment of wireless sensor networks (WSN) for early fire dectection in forested areas. A differential slotted microstrip patch antenna and a Quasi-Yagi microstrip antenna are proposed to be implemented in a WSN at 2.4 GHz (ISM band). Firstly, a microstrip Quasi-Yagi antenna has been studied and optimised to operate at 2.4 GHz, which is sough to be deployed as part of a sectorized base-station. The antenna is comprised of one reflector and six directors around a microstrip patch to create an end-fire radiation pattern. According to simulations, the optimised antenna reaches a gain of 9.41 dBi and a half-power beamwidth of 70° at 2.44 GHz, with a operating frequency band from 2.27 to 2.83 GHz. For the sensor node, a very small differential slotted microstrip patch antenna is proposed, which has been redesigned and optimised to operate at 2.4 GHz. The proposed design takes advantage of slotted resonant elements in order to reduce the overall size of the antenna. Simulation results ensure a realised gain of 4.15 dBi at 2.44 GHz and an operating frequency band from 2.37 to 2.5 GHz. The results present in this paper were performed by using the simulation software CST-MWS.
- Establishing a consistent training set with available low resolution ancillary dataPublication . Fonta, Cidália C.; Dinis, Joel; Gonçalves, Luisa M. S.; Caetano, MárioThe aim of this work is to establish consistent training sets using available low resolution ancillary data from the study area, which may be land cover maps with low spatial resolution. An initial training set is formed by a set of points randomly chosen from the land cover classes existing in the ancillary data. In a first phase some initial improvement of the training sets is done using the Normalized Difference Vegetation Index (NDVI). Three approaches are then tested to improve the initial training set using respectively the Maximum Likelihood Classifier, a classifier based on Dempster-Shafer theory and another based on the Mahalanobis distance. The degrees of certainty and uncertainty obtained with the soft classifier associated to each class is used to eliminate from the training set pixels that are not representative of the classes or identify new more reliable training pixels. A subsequent classification of the entire scene is made with the reference datasets obtained with the different approaches and the accuracy of the results tested building a confusion matrix and computing the User's, Producer's and Overall Accuracy. The proposed methodology is applied to a case study.
- A Physical Tuneable Wooden Pole Fence for Radio Transparency ControlPublication . Tribovane, Bruno A.; Caldeirinha, Rafael F. S.This paper presents modelling and measurement results of a highly sustainable fence made of circular section timber of low industrial processing for electromagnetic transparency control. Detailed studies on the dependence of the physical attributes of the fence and their impact on the electro-magnetic shielding effectiveness, will be presented. These include the parametrisation of poles' spacing and radius in a single layer configuration, that provides optimal configurations for transparency capabilities of the fence in a simulation environment at the frequency range of 0.3 to 10 GHz. Results show how increasing the spacing between centre of poles and reducing the radius can be fine-tuned to optimise shielding effectiveness for increased radio transparency.
- Exploring Pareto scale mixturesPublication . Felgueiras, Miguel; Santos, RuiPareto scale mixtures can be used to obtain distributions with heavier tails. An explanation of this model properties is provided, together with a discussion about the parameters estimation. Finally, a real data application is presented, consisting in the larger earthquakes seismic moment modeling.
- Discrete Compound Tests and Dorfman’s Methodology in the Presence of MisclassificationPublication . Santos, Rui; Martins, João Paulo; Felgueiras, MiguelCompound tests can be used to save resources for classification or estimation purposes in clinical trials and quality control. Nevertheless, the methodologies that are usually applied are restricted to qualitative group tests. Moreover, when quantitative compound tests are applied the problem is to ascertain whether the amount of some substance of any individual in the group is greater or lower than a prefixed threshold. An overview of the applications of the discrete compound tests highlights the advantages (to save resources) and disadvantages (higher probability of misclassification), and suggests criteria to assess the suitability of applying Dorfman’s methodology.
- Evaluation of seismic vulnerability assessment parameters for Portuguese vernacular constructions with nonlinear numerical analysisPublication . Ortega, Javier; Vasconcelos, Graça; Correia, Mariana; Rodrigues, Hugo; Lourenço, Paulo B.; Varum, HumbertoConsidering that vernacular architecture may bear important lessons on hazard mitigation and that well-constructed examples showing traditional seismic resistant features can present far less vulnerability than expected, this study aims at understanding the resisting mechanisms and seismic behavior of vernacular buildings through detailed finite element modeling and nonlinear static (pushover) analysis. This paper focuses specifically on a type of vernacular rammed earth constructions found in the Portuguese region of Alentejo. Several rammed earth constructions found in the region were selected and studied in terms of dimensions, architectural layout, structural solutions, construction materials and detailing and, as a result, a reference model was built, which intends to be a simplified representative example of these constructions, gathering the most common characteristics. Different parameters that may affect the seismic response of this type of vernacular constructions have been identified and a numerical parametric study was defined aiming at evaluating and quantifying their influence in the seismic behavior of this type of vernacular buildings. This paper is part of an ongoing research which includes the development of a simplified methodology for assessing the seismic vulnerability of vernacular buildings, based on vulnerability index evaluation methods.
- Hybrid channel-object approach for cinema post-production using particle systemsPublication . Fonseca, Nuno; Fonseca, NunoParticle systems are a new sound design approach that is receiving some attention from the cinema community due to the ability to handle thousands of sound sources simultaneously. Unfortunately, current immersive object-based audio formats are not prepared for such scale, forcing sound designers to use traditional channel-based audio approaches. This paper presents a hybrid approach that tries to merge the advantages of both object-based audio and channel-based audio. By using audio-objects with static positions, a high number of virtual "speaker channels" can be created, adding more space resolution than traditional channel-based formats, and allowing the mix of thousands of sounds. The proposed method can be used not only with particle systems software, but also on object-based audio down-mixing processes or even in high-demanding audio post-production workflows.