CIIC - Publicações em Atas de Conferências com Peer Review
Permanent URI for this collection
Browse
Recent Submissions
- Silhouette Enhancement in Light Field Disparity Estimation Using the Structure TensorPublication . Lourenço, Rui; Assunção, Pedro; Távora, Luís M.N.; Fonseca-Pinto, Rui; Faria, SergioThis paper presents a method to improve disparity maps computed from light field images using structure tensor methods, which tend to expand the borders of the occluding objects, enlarging their silhouette. The proposed method relies on the fact that such regions of the silhouette are defined by a mismatch between the disparity map edges, computed by the structure tensor, and those of the corresponding epipolar plane images (EPI) representing the light field. The proposed silhouette improvement method determines a correspondence between EPI edges and the disparity map edges, identifying the erroneous silhouette regions. The disparity map is corrected by using neighbouring values computed with high structure tensor reliability. The achieved results show that the disparity map is improved both around object edges and overall, reducing the MSE by 47.9% in comparison with other methods also based on the structure tensor.
- A Practical Solution for Automatic Service Discovery and Usage over Resource Poor Ad-hoc Sensor NetworksPublication . Costa, Nuno; Pereira, António; Serôdio, CarlosAd-hoc networks present new challenges due to its mobility, lack of infrastructure and resource limited devices. This means that service discovery (and usage) protocols targeted for traditional networks are not suitable for ad-hoc networks because they usually rely on the fixed and high availability characteristics of nodes to run important services. Ad-hoc networks need service discovery protocols compliant with its mobility and changing topology. In this paper we present a practical solution capable of provide automatic service discovery and usage over ad-hoc networks of resource poor sensor nodes. The solution was not developed from the ground-up. Instead, it was based on a (successfully) solution for traditional networks but then modified to address ad-hoc networks while keeping it original semantics.
- A Java Software Stack for Resource Poor Sensor Nodes: Towards Peer-to-Peer JiniPublication . Costa, Nuno; Pereira, António; Serôdio, CarlosSensor networks have been referred to as part of the background infrastructure required to achieve ubiquitous computing. This has recently promoted a considerable amount of attention from the research community that concluded that existing protocols and techniques for service discovery, such as JINI or UPnP are not suitable for the case of resource poor, battery-powered sensor nodes. We do not really agree with this approach. We think that those protocols could be a good starting point to "power-up" sensor nodes with poor resources for ubiquitous computing support. Starting from this principle and recognizing that existing sensor node system software is not suitable for our purpose, we decided to build a new sensor node software stack. The result was a stand-alone Java Virtual Machine, suitable for sensor nodes with poor resources, an implementation of the ubiquitous TCP/IP communication stack and Jini based middleware to achieve automatic service discover and usage. This software stack was tailored to perfectly fit in the state-of-the-art Mica2 class of sensor nodes.
- Solving a Realistic Location Area Problem Using SUMATRA Networks with the Scatter Search AlgorithmPublication . Luz, Sónia Maria Almeida da; Vega-Rodríguez, Miguel A.; Gómez-Pulido, Juan A.; Sánchez-Pérez, Juan M.This paper presents a new approach based on the Scatter Search (SS) algorithm applied to the Location Management problem using the Location Area (LA) scheme. The LA scheme is used to achieve the best configuration of the network partitioning, into groups of cells (location areas), that minimizes the costs involved. In this work we execute five distinct experiments with the aim of setting the best values for the Scatter Search parameters, using test networks generated with realistic data [1]. We also want to compare the results obtained by this new approach with those achieved through classical strategies, other algorithms from our previous work and also by other authors. The simulation results show that this SS based approach is very encouraging.
- IntelligentCart: Architecture of an Innovative System for the Acquisition of Products in Grocery StoresPublication . Santos, Diana S.S.; Pereira, António; Gonçalves, RamiroLarge grocery stores are nowadays used by millions of people for the acquisition of an enlarging number of products. Product acquisition represents a complex process that comprises time spent in corridors, product location and checkout queues. On the other hand, it is becoming increasingly difficult for retailers to keep their clients loyal and to predict their needs due to the influence of competition and the lack of tools that discriminate consumption patterns. In this article it is presented the proposal of an architecture and solution of an innovative system for the acquisition of products in grocery stores (IntelligentCart). The IntelligentCart explores emerging mobile technologies and automatic identification technologies (such as RFID) as a way to improve the quality of services provided by retailers and to augment the consumer value thus allowing to save time and money.
- Integration of Resource Poor Wireless Sensor Networks into Smart SpacesPublication . Costa, Nuno; Pereira, António; Serôdio, CarlosWireless Sensor networks (WSNs) have been referred to as one part of the background infrastructure required to achieve ubiquitous computing, where smart spaces are included. For instance, WSNs could be especially useful to compute the user context or even 'context' of mobile resources in general. To serve this purpose, wireless sensor network must expose some sort of service discovery and usage capability and be compatible with the nowadays ubiquitous technologies. In this paper we present a practical approach to bring WSNs, specially the ones built from resource poor sensor nodes, to participate into smart environments as ubiquitous devices. The approach addresses device heterogeneity, uses the state of the art and ubiquitous TCP/IP communication stack, is service driven and do not rely in any external resource rich device. As a result, we successfully created a Java based service discovery and usage protocol that is compliant with ad-hoc networks and resource constrained devices and a framework capable of produce the source and binary code ready to run on both resource constrained sensor nodes and PCs.
- Digital Forensic Artifacts of the Cortana Device Search Cache on Windows 10 DesktopPublication . Domingues, Patrício; Frade, MiguelMicrosoft Windows 10 Desktop edition has brought some new features and updated other ones that are of special interest to digital forensics analysis. The search box available on the taskbar, next to the Windows start button is one of these novelties. Although the primary usage of this search box is to act as an interface to the intelligent personal digital assistant Cortana, in this paper, we study the digital forensic artifacts of the search box on machines when Cortana is explicitly disabled. Specifically, we locate, characterize and analyze the content and dynamics of the JSON-based files that are periodically generated by the Cortana device search cache system. Forensically important data from these JSON files include the number of times each installed application has been run, the date of the last execution and the content of the custom jump list of the applications. Since these data are collected per user and saved in a resilient text format, they can help in digital forensics, mostly in assisting the validation of other sources of information.
- UAV Proposal for Real-Time Online Gaming to Reduce StressPublication . Safadinho, David; Ramos, João; Ribeiro, Roberto; Pereira, António Manuel de JesusSports practice is a common way people find to relieve the high stress levels. Sometimes it is impossible to move around and look for a place to do that, but the new technologies allow the practice of sports and recreational activities afar through the internet, in a comfortable way. The technological progress is responsible for the virtualization of many tasks. Nowadays, online multiplayer games try to be real, but they only focus on scenery virtualizations. As we know there already exists various UAV competitions, but sometimes, due to the many rules imposed by the aerial space, it isn't possible and safe to train when and where we want. To promote a better quality of life, it is being developed a platform with a totally distributed architecture based on the Internet of Drones concept, as it is shown in this article, that will allow the control of real unmanned aerial vehicles at anytime, from anywhere. The solution is composed by a high-scalability and a low-cost modeling system that will permit UAV users to practice their control skills in a comfortable and safe way. This interaction with a real vehicle will relieve the high stress levels caused by daily life.
- Digital Forensic Artifacts of FIDO2 Passkeys in Windows 11Publication . Domingues, Patricio; Frade, Miguel; Negrão, MiguelFIDO2’s passkey aims to provide a passwordless authentication solution. It relies on two main protocols – WebAuthn and CTAP2 – for authentication in computer systems, relieving users from the burden of using and managing passwords. FIDO2’s passkey leverages asymmetric cryptography to create a unique public/private key pair for website authentication. While the public key is kept at the website/application, the private key is created and stored on the authentication device designated as the authenticator. The authenticator can be the computer itself – same-device signing –, or another device – cross-device signing –, such as an Android smartphone that connects to the computer through a short-range communication method (NFC, Bluetooth). Authentication is performed by the user unlocking the authenticator device. In this paper, we report on the digital forensic artifacts left on Windows 11 systems by registering and using passkeys to authenticate on websites. We show that digital artifacts are created in Windows Registry and Windows Event Log. These artifacts enable the precise dating and timing of passkey registration, as well as the usage and identification of the websites on which they have been activated and utilized. We also identify digital artifacts created when Android smartphones are registered and used as authenticators in a Windows system. This can prove useful in detecting the existence of smartphones linked to a given individual.
- Evaluation of AI-based Malware Detection in IoT Network TrafficPublication . Prazeres, Nuno; Costa, Rogério Luís de C.; Santos, Leonel; Rabadão, CarlosInternet of Things (IoT) devices have become day-to-day technologies. They collect and share a large amount of data, including private data, and are an attractive target of potential attackers. On the other hand, machine learning has been used in several contexts to analyze and classify large volumes of data. Hence, using machine learning to classify network traffic data and identify anomalous traffic and potential attacks promises. In this work, we use deep and traditional machine learning to identify anomalous traffic in the IoT-23 dataset, which contains network traffic from real-world equipment. We apply feature selection and encoding techniques and expand the types of networks evaluated to improve existing results from the literature. We compare the performance of algorithms in binary classification, which separates normal from anomalous traffic, and in multiclass classification, which aims to identify the type of attack.