Browsing by Author "Troncoso-Pastoriza, Francisco"

Now showing 1 - 8 of 8
  • No Thumbnail Available
    Item
    Beamforming techniques for passive radar: an overview
    (MDPI (Multidisciplinary Digital Publishing Institute), 2023-03-24) Núñez-Ortuño, José M.; González-Coma, José P.; Nocelo López, Rubén; Troncoso-Pastoriza, Francisco; Álvarez-Hernández, María
    Passive radar is an interesting approach in the context of non-cooperative target detection. Because the signal source takes advantage of the so-called illuminator of opportunity (IoO), the deployed system is silent, allowing the operator cheap, portable, and practically undetectable deployments. These systems match perfectly with the use of antenna arrays to take advantage of the additional gains provided by the coherent combination of the signals received at each element. To obtain these benefits, linear processing methods are required to enhance the system’s performance. In this work, we summarize the main beamforming methods in the literature to provide a clear picture of the current state of the art. Next, we perform an analysis of the benefits and drawbacks and explore the chance of increasing the number of antenna elements. Finally, we identify the major challenges to be addressed by researchers in the future.
  • No Thumbnail Available
    Item
    IoT-based platform for automated IEQ spatio-temporal analysis in buildings using machine learning techniques
    (Automation in Construction, 2022-07) Troncoso-Pastoriza, Francisco; Martínez-Comesaña, Miguel; Ogando-Martínez, Ana; López-Gómez, Javier; Eguía-Oller, Pablo; Febrero-Garrido, Lara
    Providing accurate information about the indoor environmental quality (IEQ) conditions inside building spaces is essential to assess the comfort levels of their occupants. These values may vary inside the same space, especially for large zones, requiring many sensors to produce a fine-grained representation of the space conditions, which increases hardware installation and maintenance costs. However, sound interpolation techniques may produce accurate values with fewer input points, reducing the number of sensors needed. This work presents a platform to automate this accurate IEQ representation based on a few sensor devices placed across a large building space. A case study is presented in a research centre in Spain using 8 wall-mounted devices and an additional moving device to train a machine learning model. The system yields accurate results for estimations at positions and times never seen before by the trained model, with relative errors between 4% and 10% for the analysed variables.
  • No Thumbnail Available
    Item
    Photovoltaic power prediction using artificial neural networks and numerical weather data
    (Sustainability (Switzerland), 2020-12-02) Gómez-López, Javier; Troncoso-Pastoriza, Francisco; Granada-Álvarez, Enrique; Ogando-Martínez, Ana; Febrero-Garrido, Lara; Orosa-García, José Antonio
    The monitoring of power generation installations is key for modelling and predicting their future behaviour. Many renewable energy generation systems, such as photovoltaic panels and wind turbines, strongly depend on weather conditions. However, in situ measurements of relevant weather variables are not always taken into account when designing monitoring systems, and only power output is available. This paper aims to combine data from a Numerical Weather Prediction model with machine learning tools in order to accurately predict the power generation from a photovoltaic system. An Artificial Neural Network (ANN) model is used to predict power outputs from a real installation located in Puglia (southern Italy) using temperature and solar irradiation data taken from the Global Data Assimilation System (GDAS) sflux model outputs. Power outputs and weather monitoring data from the PV installation are used as a reference dataset. Three training and testing scenarios are designed. In the first one, weather data monitoring is used to both train the ANN model and predict power outputs. In the second one, training is done with monitoring data, but GDAS data is used to predict the results. In the last set, both training and result prediction are done by feeding GDAS weather data into the ANN model. The results show that the tested numerical weather model can be combined with machine learning tools to model the output of PV systems with less than 10% error, even when in situ weather measurements are not available.
  • No Thumbnail Available
    Item
    Posicionamiento de blancos marítimos en radar pasivo basado en redes DVB-T de frecuencia única
    (X Congreso Nacional de I+D en Defensa y Seguridad (DESEi+d 2023), 2023) Núñez-Ortuño, José M.; González-Coma, José P.; Nocelo López, Rubén; Troncoso-Pastoriza, Francisco; Álvarez-Hernández, María
    El radar pasivo es una tecnología de baja probabilidad de detección en auge dentro del ámbito militar y de defensa que permite identificar amenazas y estimar su distancia y velocidad biestáticas a partir de la señal emitida por iluminadores de oportunidad. Sin embargo, la distancia biestática estimada por un radar pasivo es una distancia ambigua definida por un elipsoide cuyos focos son el iluminador de oportunidad y el propio radar pasivo. Esta ambigüedad se incrementa al utilizar iluminadores de oportunidad que trabajan exactamente en la misma frecuencia dando lugar a blancos fantasma. En este artículo, se presenta un demostrador de radar pasivo biestático basado en señales de televisión digital terrestre (DVB-T) operando en redes de frecuencia única (SFN) para vigilancia marítima. Este trabajo se focaliza en posicionar unívocamente sobre un mapa blancos marítimos usando un array lineal de antenas que combinado con técnicas de beamforming permite estimar el ángulo de llegada de la emisión principal.
  • No Thumbnail Available
    Item
    Prediction of building’s thermal performance using LSTM and MLP neural networks
    (Applied Sciences (Switzerland), 2020-11-01) Martínez-Comesaña, Miguel; Febrero-Garrido, Lara; Troncoso-Pastoriza, Francisco; Martínez-Torres, Javier
    Accurate prediction of building indoor temperatures and thermal demand is of great help to control and optimize the energy performance of a building. However, building thermal inertia and lag lead to complex nonlinear systems is difficult to model. In this context, the application of artificial neural networks (ANNs) in buildings has grown considerably in recent years. The aim of this work is to study the thermal inertia of a building by developing an innovative methodology using multi-layered perceptron (MLP) and long short-term memory (LSTM) neural networks. This approach was applied to a public library building located in the north of Spain. A comparison between the prediction errors according to the number of time lags introduced in the models has been carried out. Moreover, the accuracy of the models was measured using the CV(RMSE) as advised by AHSRAE. The main novelty of this work lies in the analysis of the building inertia, through machine learning algorithms, observing the information provided by the input of time lags in the models. The results of the study prove that the best models are those that consider the thermal lag. Errors below 15% for thermal demand and below 2% for indoor temperatures were achieved with the proposed methodology.
  • No Thumbnail Available
    Item
    Sistema de perturbación (spoofing) para receptores GPS embarcados
    (XI Congreso Nacional de I+D en Defensa y Seguridad (DESEi+d 2024), 2024) Núñez-Ortuño, José M.; Troncoso-Pastoriza, Francisco
    Las pruebas de perturbación y suplantación de señal GNSS realizadas por el CUD-ENM en buques de la Armada y aeronaves del Ejército del Aire han revelado vulnerabilidades en estos sistemas, afectando tanto a equipos de navegación como a otros sistemas no previstos. El CUD-ENM ha desarrollado LOKI, un sistema capaz de realizar ataques de jamming y spoofing en múltiples bandas y constelaciones, suplantando posición y tiempo GPS con precisión. Esta herramienta permite evaluar y catalogar la resiliencia de los equipos receptores GPS y sistemas dependientes a bordo de los buques de la Armada. El sistema LOKI ha participado en las maniobras NEMO-22, MARSEC-22/23/24 y MINEX-23/24, creando ambientes GNSS degradados en los que se han realizado ataques efectivos sobre más de 15 unidades navales y aeronaves propias y de la coalición. En esta comunicación se describe la arquitectura software y hardware del sistema desarrollado, así como sus principales características.
  • No Thumbnail Available
    Item
    Sistema multiestático para la suplantación (spoofing) de señales GPS
    (X Congreso Nacional de I+D en Defensa y Seguridad (DESEi+d 2023), 2023) Núñez-Ortuño, José M.; González-Coma, José P.; Nocelo López, Rubén; Troncoso-Pastoriza, Francisco; Álvarez-Hernández, María
    Actualmente, los sistemas y plataformas que emplean nuestras Fuerzas Armada, tienen gran dependencia de datos procedentes de fuentes GNSS (Global Navigation Satellite System). En un ataque tradicional de suplantación (spoofing) de señales de sistemas GNSS, la emisión de las señales suele realizarse desde un mismo punto, radiando una señal que resulta ser el agregado de las señales que emitirían los satélites suplantados de la constelación original en la ZOI (Zona de Interés). Este tipo de ataque resulta fácilmente detectable en el emplazamiento de la víctima mediante el empleo de técnicas de DOA (Direction of Arrival) por cualquier equipo de guerra electrónica moderno o una antena CRPA (Controlled Reception Pattern Antenna). Una de las técnicas que complican la detección en este tipo de escenario es la de realizar un ataque simultáneo desde varias ubicaciones (ataque multiestático). El demostrador que se presenta en este trabajo, permite realizar este tipo de ataque que, ejecutado desde varios nodos atacantes de manera sincronizada, complica la detección de un ataque de GNSS Spoofing.
  • No Thumbnail Available
    Item
    Use of optimised MLP neural networks for spatiotemporal estimation of indoor environmental conditions of existing buildings
    (Building and Environment, 2021-11) Martínez-Comesaña, Miguel; Ogando-Martínez, Ana; Troncoso-Pastoriza, Francisco; López-Gómez, Javier; Febrero-Garrido, Lara; Granada-Álvarez, Enrique
    Controlling the indoor environmental quality in real time is essential for the health, well-being and productivity of occupants of a building. In recent years, research has focused on improving monitoring devices and strategies and developing techniques for estimating indoor conditions. The use of machine learning algorithms in this context has increased considerably. However, monitoring data in real time from large multizone working areas is challenging. The aim of this work is to provide an interpolation methodology based on the use of optimised multilayered perceptron neural networks to estimate the indoor environmental conditions of a building in real time. These estimations are obtained without the need for neither monitoring in the occupied working area nor human intervention and considering low-cost sensors. The neural network is optimised by implementing the multiobjective genetic algorithm NSGA-II to find the best architecture in terms of error and complexity. This method was applied to the building of a research centre in north-western Spain, where interpolated values for indoor air temperature, relative humidity and CO2 concentration were obtained. The results of this case study yielded relative errors close to 6% for temperature, 5% for relative humidity, and 12% for CO2 concentration. These values validate the methodology developed for the estimation of indoor environmental conditions and the contribution of this research to the improvement of the monitoring and control of the indoor environmental quality of a building.