ESTG - Comunicações em conferências e congressos internacionais
URI permanente para esta coleção:
Navegar
Entradas recentes
- Forensic Analysis of Tampered Digital PhotosPublication . Ferreira, Sara; Antunes, Mário; Correia, Manuel E.Deepfake in multimedia content is being increasingly used in a plethora of cybercrimes, namely those related to digital kidnap, and ransomware. Criminal investigation has been challenged in detecting manipulated multimedia material, by applying machine learning techniques to distinguish between fake and genuine photos and videos. This paper aims to present a Support Vector Machines (SVM) based method to detect tampered photos. The method was implemented in Python and integrated as a new module in the widely used digital forensics application Autopsy. The method processes a set of features resulting from the application of a Discrete Fourier Transform (DFT) in each photo. The experiments were made in a new and large dataset of classified photos containing both legitimate and manipulated photos, and composed of objects and faces. The results obtained were promising and reveal the appropriateness of using this method embedded in Autopsy, to help in criminal investigation activities and digital forensics.
- PrefacePublication . Rodrigues, Nuno; Mendes, DanielPresents the introductory welcome message from the conference proceedings. May include the conference officers' congratulations to all involved with the conference event and publication of the proceedings record.
- Defining Semantic Meta-hashtags for Twitter ClassificationPublication . Costa, Joana; Silva, Catarina; Antunes, Mário; Ribeiro, BernardeteGiven the wide spread of social networks, research efforts to retrieve information using tagging from social networks communications have increased. In particular, in Twitter social network, hashtags are widely used to define a shared context for events or topics. While this is a common practice often the hashtags freely introduced by the user become easily biased. In this paper, we propose to deal with this bias defining semantic meta-hashtags by clustering similar messages to improve the classification. First, we use the user-defined hashtags as the Twitter message class labels. Then, we apply the meta-hashtag approach to boost the performance of the message classification. The meta-hashtag approach is tested in a Twitter-based dataset constructed by requesting public tweets to the Twitter API. The experimental results yielded by comparing a baseline model based on user-defined hashtags with the clustered meta-hashtag approach show that the overall classification is improved. It is concluded that by incorporating semantics in the meta-hashtag model can have impact in different applications, e.g. recommendation systems, event detection or crowdsourcing.
- Attention-driven tile splitting method for improved efficiency of omnidirectional versatile video codingPublication . Carreira, J.; Faria, Sergio M. M. de; Tavora, Luis M. N.; Navarro, Antonio; Assuncao, Pedro A.A common approach used in omnidirectional video coding is based on frame splitting into tiles, allowing partial delivery of only the subset of tiles that is necessary to render the user’s current viewing region, defined as a specific viewport or Field-of-View (FoV). Since tiles can be independently encoded, such mechanism provides a flexible solution for encoding planar representations with ultra-high definition (UHD), such as the Equirectangular Projection (ERP), using Versatile Video Coding (VVC). By only selecting and transmitting the coded data that is required to render the necessary FoV, rather than the full 360°, a great deal of bandwidth can be saved. While current solutions are based on splitting the omnidirectional video frames into tiles of equal size, this paper proposes a new approach based on adaptive tile size, driven by visual attention. Those regions where the visual attention is higher are partitioned in smaller tiles to obtain higher bit rate granularity, allowing to decode the most frequent FoVs with minimum out-of-FoV pixels and reduced bandwidth. Optimal tile boundaries are found by solving a lagrangian minimisation problem with a cost function that achieves the best tradeoff between the standard deviation and the average attention-weighted bit rate per tile. The experimental results show that an average of 7.17% and 17.73% of bit rate savings is obtained in comparison with conventional tilling methods for the commonly used FoVs of 90° ×90° and 45° ×45°, respectively.
- Health Literacy of the Polytechnic of Leiria StudentsPublication . Ascenso, Rita Margarida Teixeira; Dias, Sara Simões; Luis, Luis; Gonçalves, DulceHealth Literacy (HL) has several definitions and numerous HL assessment tools. Several systematic reviews on HL identified tools for HL assessment. Health Literacy Survey with 47 questions (HLS-EU-Q47) for Europe was adapted for 16 questions (HLS-EU-Q16), and for only 6 questions (HLS-EU-Q6). These are already in Portuguese and have been used to assess HL since 2017. The studies involved the Portuguese population, and recently, in 2021, the HL evaluation in university students identified limitations in HL. The HLS-EU-Q16_Pt used showed adequate internal consistency (Cronbach's alpha = 0.778, [0.737, 0.816]). Among 251 students from the Polytechnic of Leiria there was a statistically significant association of HL scores with the health area, and more evident when students had a previous degree in health.
- Machine Learning Methods for Quality Prediction in Thermoplastics Injection MoldingPublication . Silva, Bruno; Sousa, João; Alenya, GuillemNowadays, competitiveness is a reality in all industrial fields and the plastic injection industry is not an exception. Due to the complex intrinsic changes that the parameters undergo during the injection process, it is essential to monitor the parameters that influence the quality of the final part to guarantee a superior quality of service provided to customers. Quality requirements impose the development of intelligent systems capable to detect defects in the produced parts. This article presents a first step towards building an intelligent system for classifying the quality of produced parts. The basic approach of this work is machine learning methods (Artificial Neural Networks and Support Vector Machines) and techniques that combine the two previous approaches (ensemble method). These are trained as classifiers to detect conformity or even defect types in parts. The data analyzed were collected at a plastic injection company in Portugal. The results show that these techniques are capable of incorporating the non-linear relationships between the process variables, which allows for a good accuracy (≈99%) in the identification of defects. Although these techniques present good accuracy, we show that taking into account the history of the last cycles and the use of combined techniques improves even further the performance. The approach presented in this article has a number of potential advantages for online predicting of parts quality in injection molding processes.
- Multiple Approaches to the Diagnosis of Attention Deficit Hyperactivity DisorderPublication . Rijo, Rui; Martinho, Ricardo; Ge, XiaochengStudies indicate that about 3-7% of school-age children have attention deficit hyperactivity disorder (ADHD). If these disorders are not diagnosed and treated early, its consequences can harshly impair the adult life of the individual. In this context, early diagnosis is critical. Clinical reasoning is a key contributor to the quality of health care. Clinical decisions at the policy level are made within a stochastic domain; decisions for individuals are usually more qualitative. In both cases, poor reasoning can result in an undesirable outcome. Clinical decisions are most typically communicated in a document through free text. Text has significant limitations (particularly ambiguity and poor structuring) whether used for analysis, or to explain the decision-making process. In safety engineering, similar problems are faced in conveying safety arguments to support certification. As a result, approaches have been developed to conveying arguments in ways which improve communication and which are more amenable to analysis. The Goal Structuring Notation (GSN) – a graphical argumentation notation for safety – was developed for those reasons. It has evolved to be one of the most widely used techniques for representing safety arguments. The use of text-mining techniques is another approach in the process of achieving or suggesting a diagnosis to the physician. This paper investigates the relative feasibility of these two approaches and discuss their complementation. Based on a case example, the benefits and problems of adopting GSN and ontology approach in clinical decision-making for ADHD are discussed and illustrated.
- Assessment of existing rc precast industrial buildings according with eurocode 8 - part 3Publication . Batalha, Nádia; Rodrigues, Hugo; Sousa, Romain; Varum, Humberto; Fernandes, PauloPrecast reinforced concrete (PRC) buildings are common in the Portuguese industrial park, as well as throughout Europe. In past earthquakes, namely in Italy and Turkey, this typology of buildings showed a poor performance, namely at structural level. One of the major concerns at structural level regards the connection between the beams and columns. In recent surveys at the Portuguese industrial buildings, it was observed that the buildings built before 1980 present, most of the times, only friction connections between beam and columns. This type of connection is pointed as one of the weakest structural system in this typology of structures and consequently led to serious local and global damage when subjected to seismic loads. Regarding this issue, it was considered appropriate and necessary the study of existing Portuguese buildings with this type of beam-to-column connection and compare it with the use of mechanical connections (dowels), which is a more common solution in the recent buildings. The seismic behaviour of two PRC buildings built with these two solutions was analysed considering nonlinear static and dynamic analyses addressing both global and local (connections) response parameters. When analysed in view of the seismic regulation for existing buildings (Eurocode 8 –Part 3), the results obtained show that, overall, this typology of buildings present an acceptable structural performance. Nonetheless, unsatisfactory performance was observed at the beam-to-column connection in one of the buildings built without steel dowels. The results presented in this study highlight the need to consider adequate models to simulate these connections in order to accurately represent the seismic behaviour on the structure and identify possible limitations in the use of nonlinear static procedures to assess the seismic performance of this typology of buildings. In general, the buildings in study, located in a region of moderate seismicity, exhibited a satisfactory behaviour. However particular attention should be paid to beam-to-column connections, especially in the case of friction connections. In this regard it is important to accurately represent in the model the mechanisms involved in the connections, particularly in buildings located in moderate to high seismic zones.
- Analysis of the influence of cladding panels in the seismic behaviour of a prc industrial buildingPublication . Ostetto, Liana; Sousa, Romain; Rodrigues, Hugo; Fernandes, PauloRecent reports on the latest earthquakes in Italy and Turkey have highlighted some critical problems in the connections of cladding panels on industrial precast reinforced concrete (PRC) structures. The panel connections did not perform as expected, causing non-structural damages and, in most cases, leading to the panels overturning. The damage and collapse of these elements may result in significant losses of human lives and large socio-economic impacts due to business interruption. Despite being demonstrated that cladding panels can have a significant contribution on seismic response, these elements are often considered as non-structural, ignoring the interaction with the RC frame, and considering that they do not influence the seismic behaviour. Making use of a simplified macro element, this study assesses the seismic capacity of commonly employed claddings-to-structure connections, as well as the interaction of the cladding panels with the PRC industrial buildings. The analyses were carried out considering a PRC building representative of the Portuguese industrial park, studied with and without cladding panels. The seismic behaviour of the structure are assess considering both non-linear static and dynamic procedures.
- An Approach to Assess the Performance of Mobile Applications: A Case Study of Multiplatform Development FrameworksPublication . Mota, Dany; Martinho, RicardoComparative studies between software multiplatform development frameworks lack a proper approach that can be replicated in future performance assessments. Moreover, there is still a deficit in performance comparison tools. Also, performance comparisons realized between mobile applications developed under these multiplatform frameworks should be done with applications running in Release Mode, which ends up not happening in most studies. The objective of this paper is thus to create a whole comparative process as correct and stable as possible, so that we can use it to safely assess performance of mobile applications developed with these frameworks. As a case study, we compare the well-known Flutter and React Native frameworks, and present the obtained results under the proposed approach. With this work, developers can not only assess both these particular frameworks, but also use the approach for further comparisons.