Pasar al contenido principal

LOCALIZACION Y DETECCION PARA SEGUIMIENTO DE MOVIMIENTO Y ACTIVIDAD DE PERSONAS

PID2021-122642OB-C41

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal para Impulsar la Investigación Científico-Técnica y su Transferencia
Subprograma Subprograma Estatal de Generación de Conocimiento
Convocatoria Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2021
Plan Estatal 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSIDAD DE ALCALA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 14
Encontrada(s) 1 página(s)

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

Evaluation of Spread-Spectrum Sequences in Ultrasonic Sonar for Indoor People Localization

  • García Requejo, Alejandro|||0000-0002-4955-8852
  • Pérez Rubio, María del Carmen|||0000-0001-8271-6843
  • Hernández Alonso, Álvaro|||0000-0001-9308-8133
  • Wright, William M. D.
  • Murano, Santiago Emmanuel Francis
2024 IEEE International Symposium on Medical Measurements and Applications (MeMeA), 26-28 June 2024, Eindhoven, Netherlands., Device-free localization (DFL) systems enable non-intrusive indoor human location without the need to wear a sensor or tag. This can be particularly helpful in healthcare and assisted living applications based on monitoring vulnerable people to improve their quality of life in their own home. For this purpose, this work presents a DFL system based on an ultrasonic asynchronous multistatic sonar, installed on the ceiling, consisting of four transmitters and a receiver that estimates the 3D position of a person's head. The emitted signals propagated through the indoor space are acquired by the receiver, which processes them by means of different proposed methods to estimate the position. Each transmitter emits spread-spectrum signal pulses with good cross-correlation properties, providing an update time of 300 ms and asynchronous operation. Kasami, Zadoff-Chu and orthogonal chirp emission sequences are analyzed by simulation and experimental results. Hence, it can be determined that Zadoff-Chu and chirp stand out due to their performance in terms of Doppler tolerance and accuracy, reaching mean absolute errors of 4.5 cm and 3.5 cm with standard deviations of 0.6 cm and 2 cm, respectively. On the other hand, Zadoff-Chu offers better correlation properties, while chirp provides higher data availability due to its better transducer adaptation., Agencia Estatal de Investigación, Universidad de Alcalá
e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Contribución de congreso (ConferenceOutput)

Preliminary Unknown Appliance Detection using Convolutional Variational Auto-Encoders for AAL

  • Diego Otón, Laura De|||0000-0002-4939-2987
  • Fuentes Jiménez, David|||0000-0001-6424-4782
  • Pizarro Pérez, Daniel|||0000-0003-0622-4884
  • Hernández Alonso, Álvaro|||0000-0001-9308-8133
  • Mari, Simone
  • Nieto Capuchino, Rubén|||0000-0002-8293-9665
2024 IEEE International Conference on Omni-layer Intelligent Systems (COINS), 29-31 July 2024, London, United Kingdom., The healthcare landscape is evolving, emphasising the importance of Active Assisted Living in addressing challenges presented by the ageing population. Integrating Non-Intrusive Load Monitoring provides insights into individual appliance usage patterns without additional sensors, enabling the detection of changes in daily activities that may reflect a person's health status. Within the effectiveness of this approach, adaptability is crucial as households evolve, discerning variations in energy consumption patterns caused by new or replaced electrical devices. For this reason, this work introduces a sophisticated hybrid approach combining deep learning and classic machine learning to classify household electrical loads and detect unknown loads using high-frequency electrical current signal data. Finally, while experimental results highlight areas for improvement, the findings suggest promising applications in household settings, marking a step forward in facing hurdles within the AAL context., Agencia Estatal de investigación, Universidad de Alcalá
e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Artículo científico (JournalArticle)

Combined infrared-ultrasonic positioning system to improve the data availability

  • Aparicio Esteve, Elena|||0000-0001-7886-312X
  • Ureña Ureña, Jesús|||0000-0003-1408-6039
  • Hernández Alonso, Álvaro|||0000-0001-9308-8133
  • Villadangos Carrizo, José Manuel|||0000-0001-5900-0978
This work was supported in part by MCIN/AEI/10.13039/501100011033 and EU “NextGenerationEU”/PRTR (ref. TED2021-131773B-I00) Proyectos, Many indoor positioning applications related to accurate monitoring and tracking targets require centimeter precision. Infrared (IR)- and ultrasound (US)-based systems represent a feasible approach providing high robustness against interference. Furthermore, their combination may achieve better performance by mitigating their complementary drawbacks, covering larger areas, and improving the availability of positioning measurements. In this context, this work presents the proposal and experimental evaluation of a tightly coupled fusion method that uses an extended Kalman filter (EKF) to merge an IR- and a US-based positioning system. An outlier detection method is considered to select measurements with an adequate performance. Experimental results reveal that the IR and US systems are unable to position in 4.08% and 26.06% of locations, whereas the combined IR -US system has 100% of availability. In addition, the merged solution achieves less than 4 cm of positioning error in 90% of cases, outperforming the IR and US systems when they work independently., Agencia Estatal de Investigación, Universidad de Alcalá, European Commission
e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Contribución de congreso (ConferenceOutput)

An encoder-decoder LSTM network for load forecasting in building power systems

  • Mari, Simone
  • Donato, Patricio
  • Hernández Alonso, Álvaro|||0000-0001-9308-8133
  • Fiorucci, Edouardo
2025 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), 19-22 May 2025, Chemnitz, Germany., Intelligent energy management systems have become a trending topic in the last decade, due to those challenges associated to climate change or energy shortages, among others. Efficient energy management and energy demand response are often related to the availability of accurate prediction models that may provide the expected energy consumption for a household or building early enough. For that purpose, deep learning and deep neural networks are already a suitable approach to deal with large datasets from a building energy consumption, thus making it feasible the definition and training of data-driven models. In this context, this work describes a novel encoder-decoder network based on LSTM (Long Short-Term Memory) layers that is capable of forecasting the weekly energy consumption of a public building, starting from the actual energy values from the previous week as well as from the information about the work days in that week. The proposal has been successfully validated in the School of Engineering from the National University of Mar Del Plata (Argentina), achieving a mean absolute error of 2.68 kW in the prediction of the active power of the building during a test period of eleven weeks., Agencia Estatal de Investigación
e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Artículo científico (JournalArticle)

Extracting daily routines from raw RSSI data

  • Montoliu, Raúl
  • Sansano Sansano, Emilio
  • Martínez García, Marina
  • Lluva Plaza, Sergio|||0000-0002-0050-2807
  • Jiménez Martín, Ana|||0000-0003-0713-0054
  • Villadangos Carrizo, José Manuel|||0000-0001-5900-0978
  • García Domínguez, Juan Jesús|||0000-0002-7121-8651
Detecting behavioral routines is an important research area with many implications in various practical applications. One such application involves studying the behavior of older adults residing in care homes. This paper proposes a comprehensive methodology for extracting and analyzing the daily routines of older adults in care homes. The methodology utilizes raw data comprising signal strength measurements obtained from smartwatches worn by six volunteers over five months. To establish the basis for estimating daily activities, fingerprint-based localization techniques are employed to track the minute-by-minute location of each volunteer. Subsequently, the activity performed by each volunteer is estimated for each day. Finally, the study estimates the probability of a user undertaking each one of the studied activities on a given weekday., Agencia Estatal de Investigación
e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Libro o Monografía (Book)

Centralized optical 3D positioning system for emitting tags

  • Aparicio Esteve, Elena|||0000-0001-7886-312X
  • Ureña Ureña, Jesús|||0000-0003-1408-6039
  • Hernández Alonso, Álvaro|||0000-0001-9308-8133
  • Moltó Orozco, David|||0000-0002-2790-3758
  • Villadangos Carrizo, José Manuel|||0000-0001-5900-0978
  • Cubero Vacas, Miguel
13th International Conference on Indoor Positioning and Indoor Navigation (IPIN2023), 25-28 September 2023, Nuremberg, Germany., The demand for accurate and reliable local positioning systems has grown rapidly with the increasing use of Location-Based Services (LBS). Emerging technologies such as optical, RF, acoustic, mechanical, and magnetic are feasible options for indoor positioning. Optical-based systems have gained attention due to the widespread LED lamp availability and centimeter-level accuracy. In this context, this work presents the implementation and validation of a centralized optical Local Positioning System (LPS) based on a set of mobile emitter LEDs and a minimum of two fixed receivers, enabling simultaneous position of all tags in the infrastructure (centralized approach). The system is designed for long-distance measurements, using Visible or Infrared Light signals. By incorporating geometric considerations into a Non-Linear Least Squares Estimator (NLSE), the system can estimate the 3D position of a mobile object (i.e. person, drone). The comparison of different deployments demonstrates that the proposed system estimates the 3D position with less than 4mm of error in 90% of cases when using four non-aligned receivers and a single LED., Agencia Estatal de Investigación, Universidad de Alcalá, Junta de Comunidades de Castilla-La Mancha, European Commission
e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Contribución de congreso (ConferenceOutput)

Conditioning stage of a QADA receiver for a large range IR positioning system

  • Ureña Ureña, Jesús|||0000-0003-1408-6039
  • Villadangos Carrizo, José Manuel|||0000-0001-5900-0978
  • Hernández Alonso, Álvaro|||0000-0001-9308-8133
  • Moltó Orozco, David|||0000-0002-2790-3758
  • Aparicio Esteve, Elena|||0000-0001-7886-312X
  • García García, Juan Carlos|||0000-0002-9367-9475
2024 IEEE International Instrumentation and Measurement Technology Conference (I2MTC 2024), 20-23 May 2024, Glasgow, United Kingdom., Optical positioning systems in the infrared or visible spectrum find application in the tracking of people or mobile vehicles in indoor spaces. A line of research proposes the use of LED emitters, acting as tags to be positioned, and quadrant receivers (QADA, Quadrant Photodiode Angular Diversity Aperture) located at known positions in the infrastructure. These systems can operate at a measurement rate that can reach some MHz at relatively low cost. Apart from the challenge of high-speed processing, they must also deal with low and changing signal-to-noise ratios (measurements at short and long distances, with different transmitter-receiver angle of view, etc.). This paper deals with the design of the analog conditioning stage of a QADA receiver taking into account that it must operate in a linear area with large dynamic signal margins and provide three outputs, one sum signal and two differential signals, that must be amplified with identical gain, as the performance of the triangulation algorithms used in positioning depends on this. Each signal has a transimpedance amplifier with continuous and low-frequency backlight cancellation. Furthermore, an automatic gain control with a large dynamic range is applied to the sum signal and the gain derived over time is used to manage two variable gain amplifiers for the other two differential signals. Some results are presented that show the performance of the system., Universidad de Alcalá, Agencia Estatal de Investigación, Junta de Comunidades de Castilla-La Mancha
e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Contribución de congreso (ConferenceOutput)

6-DoF optical positioning system with RSS-AoA measurements and Harmony Search refinement

  • Aparicio Esteve, Elena|||0000-0001-7886-312X
  • Moltó Orozco, David|||0000-0002-2790-3758
  • Hernández Alonso, Álvaro|||0000-0001-9308-8133
  • Ureña Ureña, Jesús|||0000-0003-1408-6039
IPIN-WCAL 2025 Indoor Positioning and Indoor Navigation - Workshop for Computing & Advanced Localization 2025, at the 15th International Conference on Indoor Positioning and Indoor Navigation (IPIN 2025), Tampere, Finland, September 15 - 18, 2025., Indoor localization is an ever-growing area of research, driven by applications such as autonomous robot navigation, cultural and commercial venue guidance, logistics, emergency response, and health monitoring of older adults. This paper presents a two-stage hybrid method for the full six degrees-of-freedom (6-DoF) pose estimation in optical indoor localization systems using a quadrant photodiode (QP) sensor. First, a geometric Angle-of-Arrival (AoA) algorithm estimates the receiver’s 3D position and yaw rotation using normalized energy ratios. Then, a Harmony Search (HS) algorithm refines this partial estimation to full 6-DoF by estimating the roll and pitch angles, while simultaneously refining all pose parameters through reprojection error minimization. The method is validated through simulations over a 2 × 2 × 1 m³ volume. Results show that the proposed approach significantly outperforms the AoA-only baseline. In scenarios with different orientations, the 90-th percentile position error drops from 0.61 m to 0.38 m in the x and y coordinates, and from 0.24 m to 0.20 m in the z one. Orientation errors in roll, pitch, and yaw are below 6.56°, 6.48°, and 1.03°, respectively., Agencia Estatal de Investigación
e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Artículo científico (JournalArticle)

Multisensory system for long-term activity monitoring to facilitate aging-in-place

  • Lluva Plaza, Sergio|||0000-0002-0050-2807
  • Jiménez Martín, Ana|||0000-0003-0713-0054
  • Gualda Gómez, David|||0000-0003-2071-6260
  • Villadangos Carrizo, José Manuel|||0000-0001-5900-0978
  • García Domínguez, Juan Jesús|||0000-0002-7121-8651
Demographic changes and an ageing population require more effective methods to confront the increased prevalence of chronic diseases which generate dependence in older adults as well as an important rise in social expenditure. The challenge is not only to increase life expectancy, but also to ensure that the older adults can fully enjoy that moment in their lives, living where they wish to (private home, nursing home, …). Physical activity (PA) is a representative parameter of a person’s state of health, especially when we are getting older, because it plays an important role in the prevention of diseases, and that is the reason why it is promoted in older adults. One of the goals of this work is to assess the feasibility of objectively measuring the PA levels of older adults wherever they live. In addition, this work proposes long-term monitoring that helps to gather daily activity patterns. We fuse inertial measurements with other technologies (WiFi- and ultrasonic-based location) in order to provide not only PA, but also information about the place where the activities are carried out, including both room-level location and precise positioning (depending on the technology used). With this information, we would be able to generate information about the person’s daily routines which can be very useful for the early detection of physical or cognitive impairment., Junta de Comunidades de Castilla-La Mancha, Agencia Estatal de Investigación, Universidad de Alcalá
e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Artículo científico (JournalArticle)

Ultrasonic Device-Free Localization System Using Orthogonal Chirp-Based Multistatic Sonar

  • García Requejo, Alejandro|||0000-0002-4955-8852
  • Pérez Rubio, María del Carmen|||0000-0001-8271-6843
  • Hernández Alonso, Álvaro|||0000-0001-9308-8133
  • Wright, William M. D.
This work was supported in part by MCIN/AEI/10.13039/501100011033 and EU “NextGenerationEU”/PRTR (ref. TED2021-131773B-I00), Indoor device-free localization (DFL) systems offer an alternative paradigm to traditional location, in which the target to be located does not need to carry any sensor, tag, or electronic device. In contrast to most popular DFL systems, which are based on radio frequency technologies, ultrasonic signals have been used in this work, due to their good accuracy results, to estimate the 3-D position of a person's head. For this purpose, a four-emitter and a single-receiver multistatic sonar installed overhead has been employed. The emission signals follow a time division orthogonal chirp division multiplexing (TD-OCDM) access technique to obtain a 300 ms update time and asynchronous operation. The signals propagated in the indoor space are acquired by the receiver and processed. A sign-data least mean square (SD-LMS) adaptive filter algorithm has been applied in order to remove the background components on the received signal. Then, a specific window from the resulting clean signal is employed to determine the reflected signal at the target time-of-arrival (ToA) by using an adaptive threshold. The ToA obtained, together with the direct path ToA between emitters and the receiver, provide ranges to compute the target location using a localization algorithm. A simulator was used to analyze the proposal, estimating the coverage area of the system at 3.14 m(2). Several experiments have been performed with a single user placing the multistatic sonar at heights of 2.60 and 2.80 m above the floor within the coverage area. The results achieved positioning errors lower than 9 cm for the 2.60-m height and 11.6 cm at 2.80 m in 90% of the cases., Agencia Estatal de Investigación
e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Artículo científico (JournalArticle)

HIFDA - High-Frequency Electrical Voltage and Current Signals from Household Appliances

  • Navarro Pérez, Víctor Manuel
  • Barragán Frías, Marta
  • Nieto Capuchino, Rubén|||0000-0002-8293-9665
  • Ureña Ureña, Jesús|||0000-0003-1408-6039
  • Hernández Alonso, Álvaro|||0000-0001-9308-8133
This work was supported in part by MCIN/AEI/10.13039/501100011033 and EU “NextGenerationEU”/PRTR (ref. TED2021-131773B-I00), The increasing demand for efficient energy management in smart grids has led to the development of various Non-Intrusive Load Monitoring (NILM) techniques. These aim to disaggregate energy consumption and classify appliances using data from a single-point smart meter at a household's grid mains. With the use of machine learning methods, NILM solutions increasingly rely on datasets for training and validation. While datasets like WHITED, BLOND, and UK-DALE provide insights into consumption patterns, they face limitations such as lack of steady-state data, complicated ground-truth or low sampling rates, which hinder detecting low-power appliances. High sampling rates, however, improve classification accuracy and enable identifying these devices. This study introduces the HIgh Frequency household electrical signals DAtaset (HIFDA), a high-frequency dataset capturing steady-state signals from 14 household appliances at 100 kSPS, including the empty grid. Data, collected via a custom System-on-Chip (SoC) device, focuses on active consumption and includes multiple time windows. HIFDA, hosted on Zenodo, ensures its suitability for modern NILM research and other applications., Agencia Estatal de Investigación
e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Libro o Monografía (Book)

High-rate acquisition system for an infrared LPS

  • Cubero Vacas, Miguel
  • Moltó Orozco, David|||0000-0002-2790-3758
  • Aparicio Esteve, Elena|||0000-0001-7886-312X
  • Hernández Alonso, Álvaro|||0000-0001-9308-8133
  • Villadangos Carrizo, José Manuel|||0000-0001-5900-0978
  • Ureña Ureña, Jesús|||0000-0003-1408-6039
2023 38th Conference on Design of Circuits and Integrated Systems (DCIS), 15-17 November 2023, Málaga, Spain., In the last years, the demand for positioning systems based on visible light, infrared light or, in general, optical signals has increased considerably due to their high accuracy and low cost compared to positioning systems based on other technologies, as well as their ease of integration due to their wide presence in domestic and industrial environments. The main constraint of these solutions is that the high speed of light makes the acquisition process complex. This work proposes a complete acquisition architecture for the twelve signals coming from four QADA (Quadrature Angular Diversity Aperture) photoreceptors, based on an analog front-end for signal conditioning at the input, an analog-to-digital converter, and a final digital stage using an FPGA for the acquisition of the data coming from the converter with high data rates up to 16.25 Msps. To verify the system performance, LS (Loosely Synchronized) sequences, often used in positioning systems, are emitted by a LED, and, later, they are acquired and digitally processed successfully by the proposed architecture in some preliminary experimental tests., Agencia Estatal de Investigación, Universidad de Alcalá, Junta de Comunidades de Castilla-La Mancha, European Science Foundation
e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Artículo científico (JournalArticle)

A comparison between autocorrelation- and crosscorrelation-based coarse frame synchronization schemes for OFDM-PLC systems

  • Colombo, Martín Alejandro
  • Ureña Ureña, Jesús|||0000-0003-1408-6039
  • Hernández Alonso, Álvaro|||0000-0001-9308-8133
  • Marziani, Carlos Manuel de
  • Mayosky, Miguel Ángel
Orthogonal frequency division multiplexing (OFDM)-based Power-Line Communications (PLC) systems are vulnerable to synchronization errors, and the particularities of the PLC channel affect the performance of the synchronization process. In this context, this work is focused on the initial pilot symbol detection, presenting a comparison between autocorrelation- (AC) and crosscorrelation (CC)-based timing metrics, which include the most common preamble-based synchronization strategies. Two robust timing metrics are defined and the effect of multipath, Colored Background Noise (CBN) and Impulsive Noise (IN) is theoretically evaluated on each. A detailed analysis of the probability distributions of the timing metrics is performed and primary detection thresholds and lower bounds for the symbol detection probability are derived. Simulations of the OFDM-PLC system are performed in order to validate the analysis, considering a statistic PLC channel model and different noise sources. Results show that the CBN and IN significantly degrade the timing metrics behavior, and that the CC-based timing metric is more robust to this worsening, thus achieving a better synchronization performance than the AC-based timing metric., Agencia Estatal de Investigación
e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Contribución de congreso (ConferenceOutput)

A configurable CORDIC and PSADIC fusion architecture for nonlinear edge-computing

  • Xie, M.
  • Yu, Ningmei
  • Tian, Dian
  • Zhang, J.
  • Hernández Alonso, Álvaro|||0000-0001-9308-8133
  • Ureña Ureña, Jesús|||0000-0003-1408-6039
2024 9th International Conference on Integrated Circuits and Microsystems (ICICM), 25-27 October 2024, Wuhan, China., The computation of some crucial and nonlinear functions on the edge has to consider the area and latency. The traditional coordinate rotation digital computer (CORDIC) systems are widely used for these key functions, such as the sine, cosine, or the square root. For the co-calculations of the division and the square root, CORDIC requires more iteration cycles and resources, whereas the power series approximate digital computer (PSADIC) approach can half the iteration cycles. In this context, a configurable CORDIC and PSADIC fusion architecture is proposed here for edge-computing. It integrates five modes of CORDIC and PSADIC to calculate some crucial nonlinear functions. Each mode is simulated and verified on software and hardware, achieving the mean relative error distance (MRED) lower than 10−4. Under the TSMC 40nm process, the area of proposed architecture is increased by 18.3% compared to the PSADIC one, but the five modes, including all the calculations from CORDIC and PSADIC, are implemented., Agencia Estatal de Investigación