Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 11
Encontrada(s) 1 página(s)

e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Contribución de congreso (ConferenceOutput)

A semi-supervised learning approach to study the energy consumption in smart buildings

  • Quintero Gull, Carlos
  • Aguilar Castro, José Lisandro|||0000-0003-4194-6882
  • Rodríguez Moreno, María Dolores|||0000-0002-7024-0427
IEEE Symposium Series on Computational Intelligence (IEEE SSCI 2021), 05/12/2021-07/12/2021., In this work, we use the semi-supervised LAMDA-HSCC algorithm for characterizing the energy consumption in smart buildings, which can work with labeled and unlabeled data. Particularly, it uses the LAMDA-RD approach for the clustering problem and the LAMDA-HAD approach for the classification problem. Additionally, this algorithm uses three submodels for merging, partition groups (classes/cluster) and migrating individuals from a group to another. For the performance evaluation, several datasets of energetic consumption are used, with different percent of labeled data, showing very encouraging results according to two metrics in the semi-supervised context., European Commission, Agencia Estatal de Investigación, Junta de Comunidades de Castilla-La Mancha
e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Contribución de congreso (ConferenceOutput)

Autonomous cycle of data analysis tasks for scheduling the use of controllable load appliances using renewable energy

  • Aguilar Castro, José Lisandro|||0000-0003-4194-6882
  • Giraldo, Juan
  • Zapata, Manuela
  • Jaramillo, Andrés
  • Zuluaga, Luis
  • Rodríguez Moreno, María Dolores|||0000-0002-7024-0427
International Conference on Computational Science and Computational Intelligence, 15/12/2021-17/12/2021, Estados Unidos., With the arrival of smart edifications with renewable energy generation capacities, new possibilities for optimizing the use of the energy network appear. In particular, this work defines a system that automatically generates hours of use of the controllable load appliances (washing machine, dishwasher, etc.) within these edifications, in such a way that the use of renewable energy is maximized. To achieve this, we are based on the hypothesis that depending on the climate, a prediction can be made of how much energy will be generated and, according to the behavior of the users, the energy demand required by these appliances. Following this hypothesis, we build an autonomous cycle of data analysis tasks composed of three tasks, two tasks for estimating the required load (demand) and the renewable energy produced (supply), coupled with a scheduling task to generate the plans of use of appliances. The results indicate that it is possible to carry out optimal scheduling of the use of appliances, but that they depend on the quality of the predictions of supply and demand., European Commission, Agencia Estatal de Investigación, Junta de Comunidades de Castilla-La Mancha
e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Contribución de congreso (ConferenceOutput)

High-order input-reflectionless quasi-elliptic-type wideband bandpass filter using dual-mode slotline resonator

  • Yang, Li|||0000-0002-1264-4810
  • Psychogiou, Dimitra
  • Gómez García, Roberto|||0000-0001-9132-6927
2022 Asia-Pacific Microwave Conference (APMC), 29 November to 02 December 2022, Yokohama, Japan., A high-order input-reflectionless quasi-elliptic-type wideband bandpass filter (BPF) that exploits a complementary-diplexer-based topology is reported. Firstly, a fourth-order wideband microstrip-to-microstrip vertical transition employing a dual-mode slotline resonator as the reflective-type BPF channel is designed. It features a sharp-rejection BPF response with two close-to-passband transmission zeros (TZs). To attain broadband input-reflectionless behavior, a shunt resistively-terminated microstrip π-shape network is used as the absorptive bandstop-filter (BSF) channel. The RF theoretical operational principle of the conceived broadband BPF is detailed. Compared to prior-art high-order input-/two-port-reflectionless wideband BPFs, the proposed BPF features not only improved passband flatness at the passband edges, but also relatively-high stopband power-attenuation levels and power-absorption ratios. For experimental-validation purposes, a two-layer fourth-order BPF microstrip prototype centered at 1 GHz is developed and tested., European Commission, Agencia Estatal de Investigación
e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Contribución de congreso (ConferenceOutput)

Planar high-order broad-band bandpass filters based on two-stage quadrature couplers and their digital modeling

  • Yang, Li|||0000-0002-1264-4810
  • Martínez Piqueras, Gaspar
  • Muñoz Ferreras, José María|||0000-0003-1929-3934
  • Gómez García, Roberto|||0000-0001-9132-6927
2022 24th International Microwave and Radar Conference (MIKON), 12-14 September 2022, Gdansk, Poland., Planar two-stage branch-line directional power couplers are applied in this paper to the design of transversalsignal-interference high-order wide-band bandpass filters (BPFs) with very-sharp-rejection characteristics. In comparison with the previously-reported experimental BPF demonstrators of their precursors—i.e., those using transversal filtering sections (TFSs) with one-stage branch-line couplers loaded by longer dissimilar stubs—, an enlarged-bandwidth passband with a higher number of in-band reflection zeros and lower amplitude variation can be obtained. Moreover, multiple transmission zeros (TZs) can be created in the out-of-band region owing to the intrinsic signal-energy cancelation phenomena of the transversal signal-interference philosophy, which result in highselectivity filtering capabilities. As further conceptual understanding of the devised two-stage-coupler signal-interference BPFs, a digital-modeling interpretation for various illustrative synthesis examples is provided. In addition, for experimentalvalidation purposes, single- and two-TFS-based microstrip prototypes of wide-band BPFs centered at 2 GHz are manufactured and characterized. In these circuits, inter-digital-type input/output feeding sections are co-integrated. They allow to extend the lower/upper stopband bandwidths with regard to those inherent to their isolated two-stage-coupler-based TFSs., Agencia Estatal de Investigación, European Commission
e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Contribución de congreso (ConferenceOutput)

Model Guided Road Intersection Classification

  • Ballardini, Augusto Luis|||0000-0001-6688-5081
  • Hernández Saz, Álvaro|||0000-0002-3779-6474
  • Sotelo Vázquez, Miguel Ángel|||0000-0001-8809-2103
2021 IEEE Intelligent Vehicles Symposium (IV), 11/07/2021-17/07/2021, Nagoya, Japón., Understanding complex scenarios from in-vehicle cameras is essential for safely operating autonomous driving systems in densely populated areas. Among these, intersection areas are one of the most critical as they concentrate a considerable number of traffic accidents and fatalities. Detecting and understanding the scene configuration of these usually crowded areas is then of extreme importance for both autonomous vehicles and modern Advanced Driver Assistance Systems (ADAS), aimed at preventing road crashes and increasing the safety of Vulnerable Road Users (VRU). This work investigates how to classify intersection areas from RGB images using well-consolidated neural network approaches along with a method to enhance the results based on the teacher/student training paradigm. An extensive experimental activity aimed at identifying the best input configuration and evaluating different network parameters on both the well-known KITTI dataset and the new KITTI-360 sequences shows that our method outperforms current state-of-the-art intersection classification approaches on per-frame basis, proving the effectiveness of the proposed learning scheme., European Commission
e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Contribución de congreso (ConferenceOutput)

A multi-label approach for diagnosis problems in energy systems using LAMDA algorithm

  • Quintero Gull, Carlos
  • Aguilar Castro, José Lisandro|||0000-0003-4194-6882
  • Rodríguez Moreno, María Dolores|||0000-0002-7024-0427
2022 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), 18-23 July 2022, Italia., In this paper, we propose a supervised multilabel algorithm called Learning Algorithm for Multivariate Data Analysis for Multilabel Classification (LAMDA-ML). This algorithm is based on the algorithms of the LAMDA family, in particular, on the LAMDA-HAD (Higher Adequacy Grade) algorithm. Unlike previous algorithms in a multi-label context, LAMDA-ML is based on the Global Adequacy Degree (GAD) of an individual in multiple classes. In our proposal, we define a membership threshold (Gt), such that for all GAD values above this threshold, it implies that an individual will be assigned to the respective classes. For the evaluation of the performance of this proposal, a solar power generation dataset is used, with very encouraging results according to several metrics in the context of multiple labels., European Commission, Agencia Estatal de Investigación, Junta de Comunidades de Castilla-La Mancha
e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Contribución de congreso (ConferenceOutput)

Input-absorptive high-order wideband balun bandpass filters with quasi-elliptic-type response

  • Yang, Li|||0000-0002-1264-4810
  • Gómez García, Roberto|||0000-0001-9132-6927
2022 52th European Microwave Conference (EuMC), 27-29 September 2022, Milan, Italy., A class of input-reflectionless high-order wideband balun bandpass filters (BPFs) with quasi-elliptic-type response are reported. They consist of two main circuit parts: 1) a three-port reflective-type high-order balun BPF network and 2) a resistivelyterminated microstrip T-junction that is shunt connected at the unbalanced port. The reflective-type balun BPFs developed with 5th- and 6th-order Chebyshev equal-ripple responses are firstly described. By replacing the last two virtually-short-circuit-ended quarter-wavelength transmission-line (TL) stubs with opencircuit-ended half-wavelength TL stubs, their balun counterparts with two close-to-passband transmission zeros (TZs) are then presented. As design example, a 5th-order input-reflectionless quasi-elliptic-type wideband balun BPF is theoretically discussed. Furthermore, for experimental-validation purposes, a proof-ofconcept two-layer microstrip prototype of 5th-order balun BPF is simulated and tested. Its measured metrics are 2.05-GHz center frequency, 3-dB fractional bandwidth of 63.61% for the two output ports, input-power-matching levels higher than 10 dB, and stopband-power-rejection levels above 26.1 dB from DC to 5 GHz., European Commission, Agencia Estatal de Investigación
e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Contribución de congreso (ConferenceOutput)

Analysis of customer energy consumption patterns using an online fuzzy clustering technique

  • Aguilar Castro, José Lisandro|||0000-0003-4194-6882
  • Quintero Gull, Carlos
  • Rodríguez Moreno, María Dolores|||0000-0002-7024-0427
  • Viera, Juan
2022 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), 18/07/2022-23/07/2022, Italia., Currently, there is a high rate of generation of new information about the Energy Consumption of customers. It is important the traceability of its consumption pattern evolution to determine in real-time the services of a smart energy management system. This paper analyses the evolution of the Energy Consumption Pattern of customers using the Learning Algorithm for Multivariable Data Analysis (LAMDA). LAMDA is a fuzzy approach for supervised and unsupervised learning, based on the calculation of the Global Adequacy Degree (GAD) of one individual to a class/cluster, through the contributions of all its descriptors. LAMDA can create new classes/clusters after the training stage (online learning). If an individual does not have enough similarity to the preexisting classes/clusters, it is evaluated with respect to a threshold called the Non-Informative Class (NIC) to define if it is a new class/cluster. Particularly, the algorithm of the LAMDA family used in this paper is LAMDA-RD (Robust Distance). In the paper is analyzed the patterns of the initial grouping of the data, as well as, the patterns through their evolution (traceability). For the analysis of the patterns different metrics are considers: Calinski- Harabasz Index and Silhouette Score., European Commission, Agencia Estatal de Investigación, Junta de Comunidades de Castilla-La Mancha
e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Contribución de congreso (ConferenceOutput)

Multilayered balanced wideband bandpass filter with high filtering selectivity

  • Yang, Li|||0000-0002-1264-4810
  • Gómez García, Roberto|||0000-0001-9132-6927
2021 IEEE MTT-S International Microwave Filter Workshop (IMFW), 17-19 Nov. 2021, Peruggia, Italy., A type of multilayered balanced wideband bandpass filter (BPF) with high filtering selectivity is presented. It is composed of two back-to-back cascaded microstrip-tomicrostrip vertical transitions using slotline stepped-impedance resonators (SIRs). Under differential-mode excitation, a sharprejection fifth-order wideband filtering transfer function with two paired close-to-passband transmission zeros can be attained in the proposed balanced BPF. Moreover, high common-mode suppression levels within the differential-mode passband range are achieved. For experimental-demonstration purposes, a microstrip prototype of the devised balanced wideband BPF architecture is developed and tested. It exhibits a measured differential-mode fifth-order high-selectivity wideband filtering response with center frequency of 4.015 GHz, 3-dB fractional bandwidth of 38.06%, and minimum in-band power-insertionloss level of 0.947 dB. The common-mode suppression levels are above 20 dB from 2.075 to 5.588 GHz., European Commission, Agencia Estatal de Investigación
e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Contribución de congreso (ConferenceOutput)

Two-layered microstrip diplexer based on high-selectivity wideband bandpass filters

  • Yang, Li|||0000-0002-1264-4810
  • Gómez García, Roberto|||0000-0001-9132-6927
2022 IEEE Radio and Wireless Symposium (RWS), 16-19 Jan. 2022, Las Vegas, NV, USA., This paper presents a microstrip diplexer based on two high-selectivity wideband bandpass filters (BPFs) in a twolayered structure. Both the lower and upper channels are designed with third-order microstrip-to-microstrip vertical transitions using open-circuit-ended slotline stepped-impedance resonators (SIRs). Specifically, open-circuit-ended microstrip lines on the top and bottom layers for the lower channel are employed, whereas the upper channel is equipped with short-circuit-ended ones. Thus, owing to the slotline SIRs, two close-to-passband transmission zeros (TZs) leading to sharp-rejection capabilities for both BPF channels are attained. The theoretical foundations and RF operating principles of the devised diplexer are discussed in detail. For practical-validation purposes, a two-layered microstrip wideband diplexer prototype is designed, simulated, and tested. It features two three-pole high-selectivity filtering responses for the measured lower and upper channels that are centered at 1.52 GHz and 2.76 GHz, and exhibit 3-dB fractional bandwidths of 60% and 24.93%, respectively., European Commission, Agencia Estatal de Investigación
e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Contribución de congreso (ConferenceOutput)

CMRNet: camera to LiDAR-map registration

  • Cattaneo, Daniele
  • Vaghi, Matteo
  • Ballardini, Augusto Luis|||0000-0001-6688-5081
  • Fontana, Simone
  • Sorrenti, Domenico Giorgio
  • Burgard, Wolfram
IEEE Conference on Intelligent Transportation Systems - ITSC 2019, 27-30/10/2019, Auckland, Nueva Zelanda., In this paper we present CMRNet, a realtime approach based on a Convolutional Neural Network (CNN) to localize an RGB image of a scene in a map built from LiDAR data. Our network is not trained in the working area, i. e., CMRNet does not learn the map. Instead it learns to match an image to the map. We validate our approach on the KITTI dataset, processing each frame independently without any tracking procedure. CMRNet achieves 0.27m and 1.07° median localization accuracy on the sequence 00 of the odometry dataset, starting from a rough pose estimate displaced up to 3.5m and 17°. To the best of our knowledge this is the first CNN-based approach that learns to match images from a monocular camera to a given, preexisting 3D LiDAR-map., European Commission