Publications

In this work, a novel distance estimation mechanism using received signal strength indication (RSSI) signals with ZigBee modules is designed, implemented and tested in several scenarios. This estimator was used for a research project focused on a wildlife behavioral classification system deployed in Doñana’s National Park. As a supporting feature for that project, this work was implemented for locating animal’s collars acting as wireless nodes in order to find those who went outside of the coverage area of the network or that were accidentally detached from animals. This work describes the system architecture and the implementation of a mobile assistant capable of recovering devices located beyond the coverage of the network. The analytical model needed for distance estimation and the signal filtering are described, as well as the difficulties that the researchers must deal when building robust location estimators. This theoretical model was applied to three different scenarios and tested with two validation experiments.

Non-verbal communication is essential in the communication process. This means that its lack can cause misinterpretations of the message that the sender tries to transmit to the receiver. With the rise of video calls, it seems that this problem has been partially solved. However, people with cognitive disorders such as those with some kind of Autism Spectrum Disorder (ASD) are unable to interpret non-verbal communication neither live nor by video call. This work analyzes the relationship between some physiological measures (EEG, ECG, and GSR) and the affective state of the user. To do that, some public datasets are evaluated and used for a multiple Deep Learning (DL) system. Each physiological signal is pre-processed using a feature extraction process after a frequency study with the Discrete Wavelet Transform (DWT), and those coefficients are used as inputs for a single DL classifier focused on that signal. These multiple classifiers (one for each signal) are evaluated independently and their outputs are combined in order to optimize the results and obtain additional information about the most reliable signals for classifying the affective states into three levels: low, middle, and high. The full system is carefully detailed and tested, obtaining promising results (more than 95% accuracy) that demonstrate its viability.

Cervical cancer is caused in the vast majority of cases by the human papilloma virus (HPV) through sexual contact and requires a specific molecular-based analysis to be detected. As an HPV vaccine is available, the incidence of cervical cancer is up to ten times higher in areas without adequate healthcare resources. In recent years, liquid cytology has been used to overcome these shortcomings and perform mass screening. In addition, classifiers based on convolutional neural networks can be developed to help pathologists diagnose the disease. However, these systems always require the final verification of a pathologist to make a final diagnosis. For this reason, explainable AI techniques are required to highlight the most significant data to the healthcare professional, as it can be used to determine the confidence in the results and the areas of the image used for classification (allowing the professional to point out the areas he/she thinks are most important and cross-check them against those detected by the system in order to create incremental learning systems). In this work, a 4-phase optimization process is used to obtain a custom deep-learning classifier for distinguishing between 4 severity classes of cervical cancer with liquid-cytology images. The final classifier obtains an accuracy over 97% for 4 classes and 100% for 2 classes with execution times under 1 s (including the final report generation). Compared to previous works, the proposed classifier obtains better accuracy results with a lower computational cost.

The use of deep learning solutions in different disciplines is increasing and their algorithms are computationally expensive in most cases. For this reason, numerous hardware accelerators have appeared to compute their operations efficiently in parallel, achieving higher performance and lower latency. These algorithms need large amounts of data to feed each of their computing layers, which makes it necessary to efficiently handle the data transfers that feed and collect the information to and from the accelerators. For the implementation of these accelerators, hybrid devices are widely used, which have an embedded computer, where an operating system can be run, and a field-programmable gate array (FPGA), where the accelerator can be deployed. In this work, we present a software API that efficiently organizes the memory, preventing reallocating data from one memory area to another, which improves the native Linux driver with a 85% speed-up and reduces the frame computing time by 28% in a real application.

Este articulo presenta la metodologia empleada para dotar a nuestros alumnos, alumnos de la asignatura Diseno con Microcontroladores en el contexto del Master de Ingenieria de Computadores y Redes de la Universidad de Sevilla, de la capacidad de disenar y desarrollar sistemas empotrados integrados con interfaz grafica. En la actualidad se ha extendido el uso de microcontroladores ARM de 32 bits, existiendo diversas familias y arquitecturas, ademas se han popularizado las pantallas basadas en la tecnologia OLED. Debido a esta popularidad, resulta muy interesante la combinacion de ambos dispositivos para la formacion de la integracion de sistemas empotrados con interfaz grafica, ya que asi se puede proporcionar una interactuacion entre este tipo de sistemas y los usuarios. Este modulo didactico ha sido bien acogido por el alumnado, ya que el manejo de los displays OLED les resulta muy atractivo y se plantean las tecnicas de programacion necesarias para la implementacion de interfaces graficas mas complejas.

Abstract Breast cancer is the most lethal type of cancer among women, one of the causes can be due to the lack of professionals to evaluate the results of medical images in time (Sharafaddini et al. Multimed Tools Appl, 1–112 2024). This problem is even greater in developing countries. In recent years, diagnostic tools based on artificial intelligence techniques have been developed to improve diagnosis time and results. In this work, we present a system that analyzes histopathological images obtained from breast tissue biopsies to design a classification system that distinguishes between benign and malignant tissue. To demonstrate that the proposed work is robust, multiple alternatives and combinations are studied to obtain the best cases. Finally, we compare the proposed approach with previous works. Furthermore, the developed system integrates explainable artificial intelligence techniques to produce a report to the physician, including a heat map with the areas the system has determined to be essential for classification.

Parkinson’s disease is one of the neurodegenerative conditions that has seen a significant increase in prevalence in recent decades. The lack of specific screening tests and notable disease biomarkers, combined with the strain on healthcare systems, leads to delayed detection of the disease, which worsens its progression. The development of diagnostic support tools can support early detection and facilitate timely intervention. The ability of Deep Learning algorithms to identify complex features from clinical data has proven to be a promising approach in various medical domains as support tools. In this study, we present an investigation of different architectures based on Gated Recurrent Neural Networks to assess their effectiveness in identifying subjects with Parkinson’s disease from gait records. Models with Long-Short term Memory (LSTM) and Gated Recurrent Unit (GRU) layers were evaluated. Performance results reach competitive effectiveness values with the current state-of-the-art accuracy (up to 93.75% (average ± SD: 86 ± 5%)), simplifying computational complexity, which represents an advance in the implementation of executable screening and diagnostic support tools in systems with few computational resources in wearable devices.

Falls are current events that can lead to severe injuries and even accidental deaths among the population, especially the elderly. Since them usually live alone and their contact with other people has decreased since pandemic, recent years studies have focused on automatic fall detection systems with wearable devices using machine learning algorithms. Overall, and according to other works, these systems can be classified as non-guided, if the machine learning model directly uses raw data without feature extraction, or as guided systems, if a previous step of feature extraction is needed to reduce complexity of the algorithm. However, no recommendations are made in the literature on which system could be more advantageous for detecting fall events. Therefore, in this work, a detailed comparison between both types of systems is carried out, using the same process for different machine learning models in order to obtain an accurate classification of activities of daily living, falling risks, and falls. This process includes the optimization of models' hyperparameters to obtain the best classifiers, followed by an assessment using common evaluation metrics, confusion matrices, ROC curves and execution times. Results show a better classification of models' three classes for the non-guided models. However, the guided models show more stable metrics and lower computational load.

In this demonstration we present a spiking neural network architecture for audio samples classification using SpiNNaker. The network consists of different leaky integrate-and-fire neuron layers. The connections between them are trained using firing rate based algorithms. Tests use sets of pure tones with frequencies that range from 130.813 to 1396.91 Hz. Audio signals coming from the computer are converted to spikes using a Neuromorphic Auditory Sensor and, after that, this information is sent to the SpiNNaker board through a PCB that translates from AER to 2-of-7 protocol. The classification output obtained in the spiking neural network deployed on SpiNNaker is then shown in the computer screen. Different levels of random noise are added to the original audio signals in order to test the robustness of the classification system.

FPGA devices have demonstrated to be one of the most popular prototyping solutions. N anoelectronics is one of the fields that can prototype its architectures in these devices. Many FPGA vendors have recently included embedded processors in their devices, such as Xilinx with ARM -Cortex A cores, together with programmable logic cells. These devices are known as Programmable System on Chip (PSoC). Their ARM cores (embedded in the processing system or PS) communicates with the programmable logic cells (PL) using ARM-standard interface buses. ARM proposed the Advanced Microcontroller Bus Architecture (AMBA) as an open-standard. Its third generation included the Advanced eXtensible Interface (AXI) to reach higher performances. In this paper we analyse the performance of exhaustive data transfers between PS and PL for a Xilinx Zynq FPGA in a co-design real scenario for Convolutional Neural Networks (CNN) accelerator. This CNN accelerator processes, in dedicated hardware, a stream of visual information from a neuromorphic visual sensor for classification. In the PS side, a Linux operating system is running, which recollects visual events from the neuromorphic sensor into a normalized frame, and then it transfers these frames to the CNN accelerator of multi-layered CNNs; and read results, using an AXI-DMA bus in a per-layer way. As these kind of accelerators try to process information as quick as possible, data bandwidth becomes critical. Maintaining a good balanced data throughput rate requires some considerations, such as data partitioning techniques to balance RX and TX transfers, or different transfer management techniques: polling versus dedicated interrupt-based kernel-level driver. For longer enough packets, the kernel-level driver solution improves global computation timings in a CNN classification example. Kernel-level driver ensures safer solutions and enables OS tasks, scheduling for better computation distribution.