ARAndre Braga Reis

Andre Braga Reis

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Andre Braga Reis has a total of 21 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • A privacy‐focused approach for anomaly detection in IoT networks

    by Pedro Martins, André B. Reis, Paulo Salvador, Susana Sargento

    Summary: IoT devices present a series of liabilities to administrators that aim for fully secure networks. Owing to their heterogeneity and limited processing power, administrators often implement monitoring mechanisms to prevent unauthorized use of resources and data exfiltration. However, most approaches allow for easy discrimination of private behavioral patterns of its users or nodes by their MAC or IP addresses. Inferring data exchange patterns at the physical layer is a more complex task, as a single signal power indicator may correspond to a mixture of simultaneous data transmissions. This article proposes privacy‐focused mechanisms by resorting to physical layer data analysis and one‐class classification models to perform anomaly detection in IoT networks. We present a full processing pipeline that considers the signal that identifies and models patterns on the channel activity and silence periods. We train our models with data captured from interactions with an Amazon Echo with devices generating background noise and test them against a similar scenario with a tampered network node periodically uploading data. Our data show that the best performing model, kernel density estimation, is able to detect anomalies with a 99% precision rate, even surpassing the tested neural networks approaches. We also propose a framework that aims to deploy validated models into production IoT environments. We designed an end‐to‐end data flow that autonomously extracts data and classifies them at the anomaly detection server. The envisioned components were designed to be horizontally scaled for a myriad of data streams and machine learning algorithms working in parallel.


  • Open Access

    Performance Analysis of Geiger–Müller and Cadmium Zinc Telluride Sensors Envisaging Airborne Radiological Monitoring in NORM Sites

    by Jorge Borbinha, Yuriy Romanets, Pedro Teles, José Corisco, Pedro Vaz, Diogo Carvalho, Yoeri Brouwer, Raul Luís, Luís Pinto, Alberto Vale, et al.

    Radiological monitoring is fundamental for compliance with radiological protection policies in the aftermath of radiological events, such as nuclear accidents, terrorism, and out-of-commission uranium mines. An effective strategy for radiation monitoring is to use radiation detectors coupled with Unmanned Aerial Vehicles (UAVs), enabling for quicker surveillance of large areas without involving the need of human presence in the target area. The main aim of this study was to formulate the parameters for a UAV flight strategy in preparation for future field measurements using Geiger–Muller Counters (GMC) and Cadmium Zinc Telluride (CZT) spectrometers. As a proof of concept, the prepared flight strategy will be used to survey out-of-commission uranium mines in northern Portugal. Procedures to assure the calibration of the CZT and verification of the GMCs were conducted, as well as a sensitivity analysis of the sensors considering different acquisition times, distance to source, and detector response time. This article reports specific parameters, such as UAV distance to ground, time of exposition, speed, and the methodology to perform the identification and calculate the activity of possible radioactive sources. An effective flight strategy is also presented, aiming to use radiation detectors coupled with UAVs to undertake extensive monitoring of areas with enhanced levels of environmental radiation, which is of prime importance due to the lasting hazardous effects of enhanced environmental radiation in the nearby ecosystem and population.


  • Forest Fire Monitoring Through a Network of Aerial Drones and Sensors

    by D. Simoes, A. Rodrigues, A. B. Reis, S. Sargento

    With the technological advances in recent years, elements such as aerial drones and its sensors are becoming increasingly accessible, smaller, transportable and also more stable in flight. Aerial drone fleets are ideally suited to monitor an active forest fire and to support firefighting teams on duty. In this paper we propose a system to support fire monitoring, built using a Flying Ad-hoc Network (FANET) and Unmanned Aerial Vehicles (UAVs), commonly called aerial drones, focused on collecting data from firefighters on duty, in wildfires' context. This system provides the sensing of a fire perimeter, and monitors and follows the firefighters while they are on duty. This system is validated both through simulation and through real-life experiments performed with a FANET of three UAVs. The results obtained in these experiments show that the proposed algorithms have good performance, and that the corresponding system is able to support the firefighting mission in an autonomous approach.


  • Improving the QoE of OTT Multimedia Services in Wireless Scenarios

    by Andre Dias, Andre B. Reis, Susana Sargento

    One of the goals of an operator is to improve the Quality of Experience (QoE) of a client in networks where Over-the-top (OTT) content is being delivered, as the Internet has now become the ‘de facto‘ path for video transmission, with video data representing over 75% of the entire network traffic, and the users’ desires to consume more content continuing to show exponential growth. This paper proposes a new approach to improve the clients’ QoE by using network awareness models as a way to forecast the number of future video content chunks to be cached. Once cached, these chunks become closer to the client, which mitigates the consequences of suboptimal network performance on bitrate-adaptive HTTP video streaming. Two prefetching approaches are proposed: an Analytic Hierarchy Process (AHP) through a weighted function on the measured quality of service metrics, and a Neural Network to estimate and maximize the user experience without the normal service delivery degradation. Our evaluation shows that AHP provides a suboptimal behavior under constrained bandwidth, while a neural network model is able to infer network behavior and predict an optimized MOS, allowing it to better optimize the caching system and the required prefetching to adequately improve QoE.


  • Open Access

    Smarter Cities With Parked Cars as Roadside Units

    by Andre Braga Reis, Susana Sargento, Ozan K. Tonguz

    Real-time monitoring of traffic density, road congestion, public transportation, and parking availability are key to realizing the vision of a smarter city and, with the advent of vehicular networking technologies, such as IEEE 802.11p and WAVE, this information can now be gathered directly from the vehicles in an urban area. To act as a backbone to the network of moving vehicles, collecting, aggregating, and disseminating their information, the use of parked cars has been proposed as an alternative to costly deployments of fixed roadside units. In this paper, we introduce novel mechanisms for parking vehicles to self-organize and form efficient vehicular support networks that provide widespread coverage to a city. These mechanisms are innovative in their ability to keep the network of parked cars under continuous optimization, in their multi-criteria decision process that can be focused on key network performance metrics, and in their ability to manage the battery usage of each car, rotating roadside unit roles between vehicles as required. We also present the first comprehensive study of the performance of such an approach, via realistic modeling of mobility, parking, and communication, through simulations, and an experimental verification of concepts that are key to self-organization. Our analysis brings strong evidence that parked cars can serve as an alternative to fixed roadside units, and organize to form networks that can support smarter transportation and mobility.


  • Open Access

    Smarter Cities with Parked Cars as Roadside Units

    by Andre B. Reis, Susana Sargento, Ozan K. Tonguz

    Real-time monitoring of traffic density, road congestion, public transportation, and parking availability are key to realizing the vision of a smarter city and, with the advent of vehicular networking technologies such as IEEE 802.11p and WAVE, this information can now be gathered directly from the vehicles in an urban area. To act as a backbone to the network of moving vehicles, collecting, aggregating, and disseminating their information, the use of parked cars has been proposed as an alternative to costly deployments of fixed Roadside Units. In this paper, we introduce novel mechanisms for parking vehicles to self-organize and form efficient vehicular support networks that provide widespread coverage to a city. These mechanisms are innovative in their ability to keep the network of parked cars under continuous optimization, in their multi-criteria decision process that can be focused on key network performance metrics, and in their ability to manage the battery usage of each car, rotating roadside unit roles between vehicles as required. We also present the first comprehensive study of the performance of such an approach, via realistic modeling of mobility, parking, and communication, thorough simulations, and an experimental verification of concepts that are key to self-organization. Our analysis brings strong evidence that parked cars can serve as an alternative to fixed roadside units, and organize to form networks that can support smarter transportation and mobility.

  • Parked Cars are Excellent Roadside Units

    by Andre B. Reis, Susana Sargento, Ozan K. Tonguz

    A comprehensive implementation of the envisioned traffic safety and efficiency applications of the IEEE 802.11p and Wireless Access for Vehicular Environments (WAVE) standards assume the premise of the use of Dedicated Short-Range Communications (DSRC) technology both as on-board units and as roadside units (RSUs). The high cost associated with RSUs, however, has so far prevented massive deployment of RSUs. Finding alternative solutions to this longstanding problem is therefore very important. In this paper, we propose a self-organizing network approach to using parked cars in urban areas as RSUs. This self-organizing network approach enables parked cars to create coverage maps based on received signal strength and make important decisions, such as if and when a parked car should serve as an RSU. Our results show the feasibility and cost-effectiveness of the proposed approach, which is able to provide excellent coverage using only a small fraction of the cars parked in a city.


  • Open Access

    Parked Cars are Excellent Roadside Units

    by Andre B. Reis, Susana Sargento, Ozan K. Tonguz

    A comprehensive implementation of the envisioned traffic safety and efficiency applications of the IEEE 802.11p and WAVE standards assume the premise of the use of DSRC technology both as on-board units (OBUs) and as Roadside Units (RSUs). The high cost associated with RSUs, however, has so far prevented massive deployment of RSUs. Finding alternative solutions to this longstanding problem is therefore very important. In this paper, we propose a self-organizing network approach to using parked cars in urban areas as RSUs. This self-organizing network approach enables parked cars to create coverage maps based on received signal strength and make important decisions, such as if and when a parked car should serve as an RSU. Our results show the feasibility and cost-effectiveness of the proposed approach, which is able to provide excellent coverage using only a small fraction of the cars parked in a city.