Persona: Martín Gutiérrez, Sergio
Cargando...
Dirección de correo electrónico
ORCID
0000-0002-4118-0234
Fecha de nacimiento
Proyectos de investigación
Unidades organizativas
Puesto de trabajo
Apellidos
Martín Gutiérrez
Nombre de pila
Sergio
Nombre
8 resultados
Resultados de la búsqueda
Mostrando 1 - 8 de 8
Publicación Exploring IoT Vulnerabilities in a Comprehensive Remote Cybersecurity Laboratory(MDPI, 2023) Delgado, Ismael; San Cristóbal Ruiz, Elio; Martín Gutiérrez, Sergio; Robles Gómez, AntonioWith the rapid proliferation of Internet of things (IoT) devices across various sectors, ensuring robust cybersecurity practices has become paramount. The complexity and diversity of IoT ecosystems pose unique security challenges that traditional educational approaches often fail to address comprehensively. Current curricula may provide theoretical knowledge but typically lack the practical components necessary for students to engage with real-world cybersecurity scenarios. This gap hinders the development of proficient cybersecurity professionals capable of securing complex IoT infrastructures. To bridge this educational divide, a remote online laboratory was developed, allowing students to gain hands-on experience in identifying and mitigating cybersecurity threats in an IoT context. This virtual environment simulates real IoT ecosystems, enabling students to interact with actual devices and protocols while practicing various security techniques. The laboratory is designed to be accessible, scalable, and versatile, offering a range of modules from basic protocol analysis to advanced threat management. The implementation of this remote laboratory demonstrated significant benefits, equipping students with the necessary skills to confront and resolve IoT security issues effectively. Our results show an improvement in practical cybersecurity abilities among students, highlighting the laboratory’s efficacy in enhancing IoT security education.Publicación Security management on Arduino-based electronic devices(IEEE Xplore, 2023-05-01) Jorge Sainz-Raso; Martín Gutiérrez, Sergio; Gabriel Diaz; Manuel Castro; https://orcid.org/0000-0001-8055-7463; https://orcid.org/0000-0001-9246-351X; https://orcid.org/0000-0003-3559-4235Arduino has arisen as a very popular element among the devices, platforms and communication protocols that make up the Internet of Things (IoT). This popularity has grown because it is low-cost and flexible device but with a huge potential for home-made or educational electronic projects. However, due to the low-cost requirement design, this device has some hardware limitations and vulnerabilities that must be carefully studied for each project. This article analyzes different software and hardware vulnerabilities that can be found in different version of Arduino boards. Finally, some good practices and recommendations are presented in order to mitigate presented vulnerabilities.Publicación Overview of embedded systems to build reliable and safe ADAS and AD systems(IEEE (Institute of Electrical and Electronic Engineers), 2020-02) Belmonte, Francisco J; Martín Gutiérrez, Sergio; Sancristobal, Elio; Ruipérez Valiente, José A.; Castro, ManuelAutomotive industry is a key sector in developed countries, taking advantage from Electronic and Semiconductor industries, for which this work is focused on, including an overview of embedded systems and related technologies for Advanced Driver Assistance Systems (ADAS) development, end user applications and their implementation (SoCs, Application Processors-APs, MCUs, software and boards), manufacturers solutions, architectures, trends and other aspects (like methodologies) to improve functional safety, reliability and performances. The current status to permit the transition from ADAS to Autonomous Driving (AD) systems and Self-Driving Cars (SDC) is also explored.Publicación Human stability assessment and fall detection based on dynamic descriptors(Wiley, 2023-06-14) Gutiérrez, Jesús; Martín Gutiérrez, Sergio; Rodriguez, VictorFall detection systems use a number of different technologies to achieve their goals, contributing, this way, to better life conditions for the elderly community. The artificial vision is one of these technologies and, within this field, it has gained momentum over the course of the last few years as a consequence of the incorporation of different artificial neural networks (ANN’s). These ANN’s share a common characteristic, they are used to extract descriptors from images and video clips that, properly processed, will determine whether a fall has taken place. However, these descriptors, which capture kinematic features associated to the fall, are inferred from datasets recorded by young volunteers or actors who simulate falls. Given the well documented differences between these falls and the real ones concerns about system performances in the real-world, out of laboratory environments, are raised. This work implements an alternative approach to the classical use of kinematic descriptors. To do it, for the first time to the best of our knowledge, we propose the introduction of human dynamic stability descriptors used in other fields to determine whether a fall has taken place. These descriptors approach the human body in terms of balance and stability, this way, differences between real and simulated falls become irrelevant, as all falls are a direct result of a fail in the continuous effort of the body to keep balance, regardless of other considerations. The descriptors are determined by using the information provided by a neural network able to estimate the body center of mass and the feet projections onto the ground plane, as well as the feet contact status. The theory behind this new approach and its validity is studied in this article with very promising results, as it is able to match or over exceed the performances of previous systems using kinematic descriptors in laboratory conditions and, given the independence of this approach from the conditions of the fall, real or simulated, it has the potential to have a better behavior in the real-world than classic systems.Publicación Fall Detection in Low-illumination Environments from Far-infrared Images Using Pose Detection and Dynamic Descriptors(IEEE Xplore, 2024-03-18) Gutiérrez Brito, Jesús; Martín Gutiérrez, Sergio; Rodriguez, Victor; Albiol, Sergio; Plaza Agudo, Inmaculada; Medrano, Carlos; Martinez, JavierIn an increasingly aging world, the effort to automate tasks associated with the care of elderly dependent individuals becomes more and more relevant if quality care provision at sustainable costs is desired. One of the tasks susceptible to automation in this field is the automatic detection of falls. The research effort undertaken to develop automatic fall detection systems has been quite substantial and has resulted in reliable fall detection systems. However, individuals who could benefit from these systems only consider their use in certain scenarios. Among them, a relevant scenario is the one associated to semi-supervised patients during the night who wake up and get out of bed, usually disoriented, feeling an urgent need to go to the toilet. Under these circumstances, usually, the person is not supervised, and a fall could go unnoticed until the next morning, delaying the arrival of urgently needed assistance. In this scenario, associated with nighttime rest, the patient prioritizes comfort, and in this situation, body-worn sensors typical of wearable systems are not a good option. Environmental systems, particularly visual-based ones with cameras deployed in the patient's environment, could be the ideal option for this scenario. However, it is necessary to work with far-infrared (FIR) images in the low-light conditions of this environment. This work develops and implements, for the first time, a fall detection system that works with FIR imagery. The system integrates the output of a human pose estimation neural network with a detection methodology which uses the relative movement of the body's most important joints in order to determine whether a fall has taken place. The pose estimation neural networks used represent the most relevant architectures in this field and have been trained using the first large public labeled FIR dataset. Thus, we have developed the first vision-based fall detection system working on FIR imagery able to operate in conditions of absolute darkness whose performance indexes are equivalent to the ones of equivalent systems working on conventional RGB images.Publicación RGB-D-Fusion: Image Conditioned Depth Diffusion of Humanoid Subjects(IEEE Xplore, 2023-09-04) Kirch, Sascha; Olyunina, Valeria; Ondřej, Jan; Pagés, Rafael; Martín Gutiérrez, Sergio; Pérez Molina, Clara María; https://orcid.org/0000-0002-5578-7555; https://orcid.org/0009-0000-9766-5057; https://orcid.org/0000-0002-5409-1521; https://orcid.org/0000-0002-5691-9580We present RGB-D-Fusion, a multi-modal conditional denoising diffusion probabilistic model to generate high resolution depth maps from low-resolution monocular RGB images of humanoid subjects. Accurately representing the human body in 3D is a very active research field given its wide variety of applications. Most 3D reconstruction algorithms rely on depth maps, either coming from low-resolution consumer-level depth sensors, or from monocular depth estimation from standard images. While many modern frameworks use VAEs or GANs for monocular depth estimation, we leverage recent advances in the field of diffusion denoising probabilistic models. We implement a multi-stage conditional diffusion model that first generates a low-resolution depth map conditioned on an image and then upsamples the depth map conditioned on a low-resolution RGB-D image. We further introduce a novel augmentation technique, depth noise augmentation, to increase the robustness of our super-resolution model. Lastly, we show how our method performs on a wide variety of humans with different body types, clothing and poses.Publicación Easy Development of Industry 4.0 Remote Labs(MDPI, 2024) Rejón Gómez, Carlos; Martín Gutiérrez, Sergio; Robles Gómez, AntonioAcquiring hands-on skills is nowadays key for Engineers today in the context of Industry 1 4.0. However, it is not always possible to do this in person. Therefore, it is essential to be able to do 2 this from a remote location. To support the development of remote labs for experimentation, this work 3 proposes the development of an open Industry 4.0 remote platform, which can be easily configured 4 and scaled to develop new remote labs for IoT (Internet of Things), cybersecurity, perception systems, 5 robotics, AI (Artificial Intelligence), etc. Over time, these capabilities will enable the development of 6 sustainable Industry 4.0 remote labs. These labs will coexist on the same Industry 4.0 platform, as 7 our proposed Industry 4.0 remote platform is capable of connecting multiple heterogeneous types 8 of devices for remote programming. In this way, it is possible to easily design open remote labs for 9 the digital transition to Industry 4.0 in a standardized way, which is the main research goal of our 10 In4Labs project. Several users are already conducting a series of IoT experiments within our remote 11 Industry 4.0 platform, providing useful recommendations to be included in future versions of the 12 platform.Publicación Internet of Things Remote Laboratory for MQTT remote experimentation(Springer Link, 2023) Anhelo, Jesús; Robles Gómez, Antonio; Martín Gutiérrez, SergioRemote laboratories have matured substantially and have seen widespread adoption across universities globally. This paper delineates the design and implementation of a remote laboratory for Industry 4.0, specifically for Internet of Things. It employs Raspberry Pi and ESP8266 microcontrollers, to bolster online Internet of Things (IoT) learning and experimentation platforms. Such platforms hold significant value in delivering high-quality online education programs centered on IoT. Students have access to a web interface where they can write Arduino code to program the behavior of each one of the nodes of an Internet of Things scenario. This setup allows them to remotely program three NodeMCU boards in a manner akin to the usage of the Arduino IDE connected to an Arduino board locally. The system offers the ability to compile and upload code, complete with error notifications. Additionally, it furnishes several functionalities such as the ability to load new local code, save the authored code to one's personal computer, load predefined examples, access a serial monitor, and avail the Node Red platform. This amalgamation of features promises to offer a comprehensive and interactive remote learning experience for students engaging with IoT technologies.