Percorrer por autor "Chaves, Paulo"
A mostrar 1 - 6 de 6
Resultados por página
Opções de ordenação
- Enhanced AutomaticWildfire Detection System Using Big Data and EfficientNetsPublication . Fernandes, Armando; Utkin, Andrei; Chaves, PauloPrevious works have shown the effectiveness of EfficientNet—a convolutional neural network built upon the concept of compound scaling—in automatically detecting smoke plumes at a distance of several kilometres in visible camera images. Building on these results, we have created enhanced EfficientNet models capable of precisely identifying the smoke location due to the introduction of a mosaic-like output and achieving extremely reduced false positive percentages due to using partial AUROC and applying class imbalance. Our EfficientNets beat InceptionV3 and MobileNetV2 in the same dataset and achieved a true detection percentage of 89.2% and a false positive percentage of only 0.306% across a test set with 17,023 images. The complete dataset used in this study contains 26,204 smoke and 51,075 non-smoke images. This makes it one of the largest, if not the most extensive, datasets reported in the scientific literature for smoke plume imagery. So, the achieved percentages are not only among the best reported for this application but are also among the most reliable due to the extent and representativeness of the dataset.
- Indoor Position Method Using Wi-FiPublication . Fernandes, Luís; Barata, Fábio; Chaves, PauloThe main objective of this paper is to present an indoor position method, developed for museums and hospitals, in order to known the position of persons and equipments. The method is composed by a particle filter algorithm to be embedded in smartphones or tags. The main goal is to develop a light method to run by not very powerful microprocessors, energized by batteries. The position method presented is based on a Wi-Fi structure, to lighten the use of the communication network, the position is generated by each device from raw data received locally.
- LIF and SFS techniques for early detection of biofilms harmful for cultural heritagePublication . Utkin, A.B.; Chaves, Paulo; Fernades, L.; I.V., Pinto; Revez, M.J.Specific LIF (laser induced fluorescence) and SFS (spectral fluorescence signature) sensors have been developed for detecting biofilms colonizing the surface of cultural heritage artefacts. The sensors contribute to a large-scale monitoring and decision supporting system, which is being deployed for historical monument protection within the framework of the European project STORM.
- Modular buck-boost transformerless grid-tied inverter for low voltage solar panelsPublication . Nunes, Hugo; Pimenta, Nelson; Fernandes, Luís; Chaves, Paulo; Costa, J. M. DoresThis paper deals with a transformerless AC module for low DC voltage output photovoltaic solar panels. The DC to AC converter was designed to be a single-phase grid-tied inverter, and is based on a buck-boost topology with current mode control to shape the current and to adjust delivered power. The common ground node prevents voltage fluctuations and increases people´s safety. Low power inverters tend to be less efficient than larger ones and are prone to higher harmonic distortion. To overcome these drawbacks, special care was taken in designing the power stage, and harmonic compensation was included in the control stage. The inverter has MPPT capability and operates with unity power factor. Inverter´s operation is analysed, and some simulation results are presented. A 220Wp two-stage single-phase AC module prototype, with 240V and 50Hz sine-wave output, was build and connected to a low voltage photovoltaic solar panel. Experimental results for this plug-and-play converter are here presented.
- Pilot practical experiences and achieved resultsPublication . Boldrighinia, Francesca; Fort, Mercè López; Borghinia, Silvia; Brumb, Patricia; Chaves, Paulo; De Santisa, Anna; DeWit, Rosmarie; Giapitsogloue, Kostas; Magalhaes, Ana Patricia; Pinto, Inês Vaz; Revez, Maria João; Tanircanf, Gulum; Tatlasg, Nikolaos-Alexandros; Tzigounakie, Anastasia; Uckanf, Eren; Utkinh, Andrei Borissovitch; Williamsoni, Robert James; Kontogianni, Vasiliki
- Study on the Application of EfficientDet to Real-Time Classification of Infrared Images from Video SurveillancePublication . Mendes, Filipe; Fernades, Armando M.; Fernandes, Luis; Piedade, Fernando; Chaves, PauloThe monitoring of certain areas can be a tedious and non-interactive task that usually leads to some missed occurrences. With the development of object-detection models, this problem can be mitigated and reduced. In this paper, a rare application of EfficientDet model to the analysis of footage from an infrared camera in real-time is studied. The model will be used to detect deers, people and cars in images captured at the surroundings of a classified facility from where we do not yet have images available. Consequently, we show the process of creating the model and discuss the problems raised by the real-time performance limitations as well as by the available data limitations. The results obtained suggest that this kind of implementation has the potential to improve existing surveillance systems.