Examinando por Autor "Arjona Aguilera, Laura"

Mostrando 1 - 3 de 3
  • Miniatura
    Ítem
    Automatic classification of the physical surface in sound uroflowmetry using machine learning methods
    (Springer Science and Business Media Deutschland GmbH, 2024) Álvarez Arteaga, Marcos Lázaro; Arjona Aguilera, Laura; Iglesias Martínez, Miguel E.; Bahillo, Alfonso
    This work constitutes the first approach for automatically classifying the surface that the voiding flow impacts in non-invasive sound uroflowmetry tests using machine learning. Often, the voiding flow impacts the toilet walls (traditionally made of ceramic) instead of the water in the toilet. This may cause a reduction in the strength of the recorded audio signal, leading to a decrease in the amplitude of the extracted envelope. As a result, just from analysing the envelope, it is impossible to tell if that reduction in the envelope amplitude is due to a reduction in the voiding flow or an impact on the toilet wall. In this work, we study the classification of sound uroflowmetry data in male subjects depending on the surface that the urine impacts within the toilet: the three classes are water, ceramic and silence (where silence refers to an interruption of the voiding flow). We explore three frequency bands to study the feasibility of removing the human-speech band (below 8 kHz) to preserve user privacy. Regarding the classification task, three machine learning algorithms were evaluated: the support vector machine, random forest and k-nearest neighbours. These algorithms obtained accuracies of 96%, 99.46% and 99.05%, respectively. The algorithms were trained on a novel dataset consisting of audio signals recorded in four standard Spanish toilets. The dataset consists of 6481 1-s audio signals labelled as silence, voiding on ceramics and voiding on water. The obtained results represent a step forward in evaluating sound uroflowmetry tests without requiring patients to always aim the voiding flow at the water. We open the door for future studies that attempt to estimate the flow parameters and reconstruct the signal envelope based on the surface that the urine hits in the toilet
  • Miniatura
    Ítem
    Dynamic and scalable strategies to lower the identification time and energy consumption in Aloha-based RFID anti-collision protocols
    (Universidad de Deusto, 2018-12-10) Arjona Aguilera, Laura; Landaluce, Hugo; Facultad de Ingeniería; Ingeniería para la Sociedad de la Información y Desarrollo Sostenible
    The fourth industrial revolution is coming, promising to bring together the worlds of production and network connectivity in an Internet of Things (IoT). One capable and feasible technology to build in intelligence to a product is Radio Frequency Identification (RFID) technology. This technology uses a spectrum of radio frequency to transfer the identification information between two communication devices: reader and tags. A remarkable characteristic of this technology is that it does not need a direct line of sight between the reader and the tags to establish communication. In addition, it is a low-intrusive technology, which can be easily adapted to the IoT paradigm. The core application of RFID technology is to read a code stored in the tags’ internal memory, which uniquely identifies them. Thus, tags can be attached to a large number of different items for numerous pplications, highlighting activity recognition, localization systems, tracking, and mobile sensing applications. The coexistence of several tags in the same identification zone of the reader provides RFID technology with a great flexibility at the expense of the tag collision problem. Tags share the same communication channel (the air) and may respond simultaneously to the same reader command, interfering and garbling their waveforms. The reader then is unable to interpret the information received from the tags, requiring tags to re-transmit their messages. As a result, tags collisions extend the time employed by the reader to identify the tag set and also the energy consumed in the process. Anti-collision protocols are then proposed to arbitrate the tags’ responses, with the main goal of maximizing the number of tags identified by a time unit and minimizing the energy consumed by the reader during the identification process. Most RFID manufacturers currently follow the EPCglobal Class 1 Generation 2 (EPC C1G2) standard. This standard employs the Slot Counter anticollision protocol, which belongs to the Dynamic Frame Slotted Aloha (DFSA) category. DFSA protocols are characterized by providing tags a set of time slots where tags must randomly choose one time slot to transmit their message. The main challenge that DFSA protocols aim to solve is determining the number of time slots that are contained in one set. The Slot Counter protocol follows a set of recommendations from the current standard to face this challenge, but the exact values of some configuration parameters are not specified. Furthermore, the Slot Counter protocol does not scale efficiently to large tag set sizes, because it presents a smooth behaviour. This lack of definition provides large improvement possibilities in the field of DFSA protocols. Consequently, many DFSA algorithms have recently appeared in the literature to improve the performance of the Slot Counter protocol. This dissertation provides a solution to the tag collision problem by proposing two dynamic and scalable strategies for DFSA protocols: fuzzy logic and tag estimation. These two strategies are then applied to a traditional DFSA protocol based on the current standard, resulting in four novel anticollision protocols. The proposed protocols improve the performance of existing DFSA protocols, including the Slot Counter, in terms of the tags identification time and the energy efficiency in passive RFID systems. Finally, a physical RFID experimentation system is presented to implement and evaluate user-configurable DFSA protocols based on EPC C1G2.
  • Miniatura
    Ítem
    Flow prediction in sound-based uroflowmetry
    (Nature Research, 2025-01-03) Álvarez Arteaga, Marcos Lázaro; Arjona Aguilera, Laura; Jojoa Acosta, Mario Fernando; Bahillo, Alfonso
    Sound-based uroflowmetry (SU) offers a non-invasive alternative to traditional uroflowmetry (UF) for evaluating lower urinary tract dysfunctions, enabling home-based testing and reducing the need for clinic visits. This study compares SU and UF in estimating urine flow rate and voided volume in 50 male volunteers (aged 18–60), with UF results from a Minze uroflowmeter as the reference standard. Audio signals recorded during voiding were segmented and machine learning algorithms (gradient boosting, random forest, and support vector machine) estimated flow parameters from three devices: Ultramic384k, Mi A1 smartphone, and Oppo smartwatch. The mean absolute error for flow rate estimation were 2.6, 2.5 and 2.9 ml/s, with R2 values of 84%, 83%, and 79%, respectively. Analysis of the Ultramic384k’s frequency range showed that the 0–8 kHz band contained 83% of significant components, suggesting higher sampling frequencies are unnecessary. A 1000 ms segment size was optimal for balancing computational efficiency and accuracy. Lin’s concordance coefficients for urine flow and voided volume using the smartwatch (0–8 kHz, 1000 ms) were 0.9 and 0.85, respectively, demonstrating that SU is a reliable, cost-effective alternative to UF for estimating key uroflowmetry parameters, with added patient convenience