INESC TEC Repository
Not a member yet
2130 research outputs found
Sort by
mySense: A comprehensive data management environment to improve precision agriculture practices
No full textProcedural Modeling of Buildings Composed of Arbitrarily-Shaped Floor-Plans: Background, Progress, Contributions and Challenges of a Methodology Oriented to Cultural Heritage
Get PDFEvolutionary dynamics for the generalized Baliga–Maskin public good model
Get PDFThe problem of the consumption or provision of common and public goods is a well known and well studied problem in economic sciences. The nature of the problem is the existence of non-excludable externalities which gives rise to incentives to free-riding behaviour. There are several economical frameworks trying to deal with the problem such as coalition theory or mechanism design and implementation theory to ensure a Pareto efficient consumption or provision of such good. Baliga and Maskin considered an environmental game where several communities face a problem of pollution reduction. They show that all communities except one of them have incentives to act as a free-rider, i.e. only one community is willing to face the costs that air cleaning implies, namely the one with greatest preference for the good. In this work we introduce an adaptive evolutionary dynamics for the generalization of the Baliga–Maskin model to quasi-linear utility functions. We show that the Baliga–Maskin equilibrium is the only asymptotically stable dynamical equilibrium, all others being unstable. This result reasserts the problem of free-riding and externalities for the case of a common good in a dynamically/evolutionary setting, and reiterates the relevance of mechanism design and coalition formation in the context of dynamical models. © 201
CATARACTS: Challenge on automatic tool annotation for cataRACT surgery
No full textSurgical tool detection is attracting increasing attention from the medical image analysis community. The goal generally is not to precisely locate tools in images, but rather to indicate which tools are being used by the surgeon at each instant. The main motivation for annotating tool usage is to design efficient solutions for surgical workflow analysis, with potential applications in report generation, surgical training and even real-time decision support. Most existing tool annotation algorithms focus on laparoscopic surgeries. However, with 19 million interventions per year, the most common surgical procedure in the world is cataract surgery. The CATARACTS challenge was organized in 2017 to evaluate tool annotation algorithms in the specific context of cataract surgery. It relies on more than nine hours of videos, from 50 cataract surgeries, in which the presence of 21 surgical tools was manually annotated by two experts. With 14 participating teams, this challenge can be considered a success. As might be expected, the submitted solutions are based on deep learning. This paper thoroughly evaluates these solutions: in particular, the quality of their annotations are compared to that of human interpretations. Next, lessons learnt from the differential analysis of these solutions are discussed. We expect that they will guide the design of efficient surgery monitoring tools in the near future. © 2018 Elsevier B.V
Evolutionary Game Theory: A Generalization of the ESS Definition
Get PDFIn this paper, we study the concept of Evolutionarily Stable Strategies (ESSs) for symmetric games with n = 3 players. The main properties of these games and strategies are analyzed and several examples are provided. We relate the concept of ESS with previous literature and provide a proof of finiteness of ESS in the context of symmetric games with n = 3 players. We show that unlike the case of n = 2, when there are more than two populations an ESS does not have a uniform invasion barrier, or equivalently, it is not equivalent to the strategy performing better against all strategies in a neighborhood. We also construct the extended replicator dynamics for these games and we study an application to a model of strategic planning of investment. © 2019 World Scientific Publishing Company
Immersive 360° video user experience: impact of different variables in the sense of presence and cybersickness
Get PDFVirtual Reality (VR) has been recently gaining interest from researchers and companies, contributing to the development of the associated technologies that aim to transport its users to a virtual environment by the stimulation of their senses. Technologies such as Head-Mounted Displays (HMD), capable of presenting 360° video in 3D, are becoming affordable and, consequently, more common among the average consumer, potentiating the creation of a market for VR experiences. The purpose of this study is to measure the influence of (a) video format (2D/monoscopic vs 3D/stereoscopic), (b) sound format (2D/stereo vs 3D/spatialized), and (c) gender on users’ sense of presence and cybersickness, while experiencing a VR application using an HMD. Presence and cybersickness were measured using questionnaires as subjective measures. Portuguese versions of the Igroup Presence Questionnaire for presence and the Simulator Sickness Questionnaire for cybersickness were used. Results revealed no statistically significant differences between (a) VIDEO and (b) SOUND variables on both senses of presence and cybersickness. When paired with (a) VIDEO, the independent variable (c) Gender showed significant differences on almost all subscales of presence. Results suggest that the widely acknowledged differences in spatial ability between genders were a major factor contributing to this outcome. © 2017 Springer-Verlag GmbH German
Online inspection system based on machine learning techniques: real case study of fabric textures classification for the automotive industry
Get PDFThis paper focus on the classification, in real-time and under uncontrolled lighting, of fabric textures for the automotive industry. Many industrial processes have spatial constraints that limit the effective control of illumination of their vision based systems, hindering their effectiveness. The ability to overcome these problems using robust classification methods with suitable pre-processing techniques and choice of characteristics will increase the efficiency of this type of solutions with obvious production gains and thus economical. For this purpose, this paper studied and analyzed various pre-processing techniques, and selected the most appropriate fabric characteristics for the considered industrial case scenario. The methodology followed was based on the comparison of two different machine learning classifiers, ANN and SVM, using a large set of samples with a large variability of lightning conditions to faithfully simulate the industrial environment. The obtained solution shows the sensibility of ANN over SVM considering the number of features and the size of the training set, showing the better effectiveness and robustness of the last. The characteristics vector uses histogram equalization, Laws filter and Sobel filter, and multi-scale analysis. By using a correlation based method was possible to reduce the number of features used, achieving a better balanced between processing time and classification ratio. © 2016 Springer Science+Business Media New Yor
Accessible software development: a conceptual model proposal
Get PDFEqual access to all software and digital content should be a reality in the Digital Era. This argument is something defended both by existing regulations, norms and standards, and also business organizations and governments. Despite this acknowledgement, the reality is still far from the desired equality. For certain groups of disabled or impaired citizens, such as the visually impaired, the existence of e-accessibility compliance represents an opportunity to integrate, in a more simple and straightforward manner, their societies. Despite the existing poor results on e-accessibility compliance, the mentioned citizens insist on using digital devices in their daily lives. Even though, in the last decade, multiple standards and regulations have been published towards indicating how to develop accessible digital user interfaces, there are still two major issues surrounding its implementation: the complexity and disparity of the documents containing the abovementioned norms, and also the lack of e-accessibility know-how by software experts. With this in mind, a proposal for an accessible software development model that encompasses e-accessibility incorporation as one of the development process activities has been presented. This model might represent a very interesting support tool for software development organizations and a novel resource for learning and training institutions to be able to improve their computer science and informatics students' skills on e-accessibility
Collaborative immersive authoring tool for real-time creation of multisensory VR experiences
Get PDFWith the appearance of innovative virtual reality (VR) technologies, the need to create immersive content arose. Although there are already some non-immersive solutions to address immersive audio-visual content, there are no solutions that allow the creation of immersive multisensory content. This work proposes a novel architecture for a collaborative immersive tool that allows the creation of multisensory VR experiences in real-time, thus promoting the expeditious development, adoption, and use of immersive systems and enabling the building of custom-solutions that can be used in an intuitive manner to support organizations’ business initiatives. To validate the presented proposal, two approaches for the authoring tools (Desktop interface and Immersive interface) were subjected to a set of tests and evaluations consisting of a usability study that demonstrated not only the participants’ acceptance of the authoring tool but also the importance of using immersive interfaces for the creation of such VR experiences. © 2019, Springer Science+Business Media, LLC, part of Springer Nature