Search

Recent advancements in communication technology have transformed the way the industrial system works. This digitalization has improved the way of communication between different actors involved in cyber physical production systems (CPPS), such as users, suppliers, and manufacturers, thus making the whole process transparent. The utilization of emerging new technologies in CPPS can cause vulnerable spots that can be exploited by attackers to launch sophisticated distributed denial of service (DDoS) attacks, hence threatening the availability of the production systems. Existing machine learning based intrusion detection systems (IDS) often rely on unrealistic datasets for training and validation, thus missing the crucial testing phase with real-time scenarios. The results generated by the ML models are based on predictions at each flow level and cannot provide summarized information about malicious entities. To address this limitation, this study proposed an efficient IDS system that uses both rule-based detection and ML-based approaches to detect DDoS attacks damaging the infrastructure of CPPS. For training and validation of the system, we use real-time network traffic extracted from a real industrial scenario, referred to as Farm-to-Fork (F2F) supply chain system. Both, attacks and normal traffic were captured, and bidirectional features were extracted through CIC-FLOWMETER. We make use of 8 ML supervised and unsupervised approaches to detect the malicious flows; and then a rule-based detection mechanism is used to calculate the frequency of the malicious flows and to assign different severity levels based on the computed frequency. The overall results show that supervised models outperform unsupervised approaches and achieve an accuracy 99.97% and TPR 99.96%. Overall, the weighted accuracy when tested and deployed in a real-time scenario is around 98.71%. The results prove that the system works better when considering real-time scenarios and provides comprehensive, This work was supported in part by European Union’s Horizon Europe (PHOENi2X) under Grant 101070586, in part by the Spanish Ministry of Science and Innovation funded by MCIN/AEI/10.13039/501100011033 under Grant PID2021-124463OB-I00, in part by ERDF a way of making Europe, and in part by the Catalan Government under Contract 2021 SGR 00326., Peer Reviewed, Postprint (published version)

The upcoming sixth-generation (6G) networks are expected to be more heterogeneous, scalable, reliable, secure and energy-efficient. 6G services and applications will benefit from the fast data transmission rates, global coverage, precise positioning, and widespread intelligence capabilities provided by 6G technology. In this complex scenario, new attack surfaces and vectors will emerge, due to the distributed, disaggregated, dynamic, programmable and open nature of the entire end-to-end 6G infrastructure along with the fragmentation of data, as well as the need for supporting cross-platforms interoperability, making the application of security and trust fundamentally challenging. To securely manage services in the future 6G mobile networks along with the set of functions ruling its management, conceptual work is needed to defining functional blocks supporting a secure end-to-end 6G systems management. This is especially critical in handling specific functionalities, such as network disaggregation, risk and threats business impact, energyefficiency, self-configuration or dynamic discovery. This paper positions an innovative 6G security services management architecture, which builds on a set of innovative building blocks, leveraging key technologies, such as AI-assisted models and Digital Twin, while enabling a human-centric approach toward an end-to-end security solution. Two canonical workflows along with two illustrative application scenarios are proposed, Light Rail Transit and Extended Reality, to conceptually highlight the proposed architecture impact and its expected benefits when high bandwidth, ultra-low latency, and secure communications are required., This work was supported by the European union’s Horizon Europe, under the project HORSE, Grant 101096342. The work of Eva Rodriguez and Xavi Masip-Bruin was supported in part by the Spanish Ministry of Science and Innovation funded by MCIN/AEI/10.13039/501100011033 and ERDF: A way of making Europe under Grant PID2021-124463OB-I00, and in part by the Catalan Government under Contract 2021 SGR 00326., Peer Reviewed, Postprint (published version)

Títol alternatiu emprat a la intranet docent de l'EPSEVG: "Disseny d'un planificador de rutes personalitzades pel benchmarking de pacients respiratoris", El present Treball Final de Grau té com a objectiu desenvolupar un sistema de caracterització i avaluació de rutes per a pacients respiratoris de l'Hospital Clínic de Barcelona mitjançant una aplicació web que permet, tant a metges com a pacients, interactuar de manera eficient. A través d’aquest sistema, es pretén proporcionar una eina que permeti l'assignació de rutes d'acord amb l'estat físic i les condicions particulars de cada pacient, promovent una millora en la qualitat de vida i en la gestió de les activitats físiques recomanades pels especialistes. El projecte s’estructura en les següents fases principals: la realització i implementació d'equacions matemàtiques per al càlcul de l'esforç; el disseny i desenvolupament de l'aplicació web, la programació i integració d'un model d'intel·ligència artificial i la validació dels resultats obtinguts. La plataforma desenvolupada utilitza un mapa mundial interactiu en el qual el metge pot seleccionar el punt d'origen i un punt de destí de qualsevol ruta que desitgin consultar, a qualsevol ciutat del món. La dificultat de cada ruta es calcula mitjançant un conjunt d’equacions matemàtiques progressivament més complexes que consideren diversos factors, com la distància de la ruta, la inclinació del terreny i totes les característiques individuals del pacient (gènere, pes, alçada, edat i fins i tot estat físic i patologies). Es recorre a una fórmula matemàtica o una altra en funció dels paràmetres que el metge vulgui utilitzar, que poden ser més o menys. El sistema inclou un model de xarxa neuronal creat amb TensorFlow, que permet estimar amb major precisió l'esforç requerit per a cada ruta, incorporant variables addicionals com l’estat de salut i la quantitat de patologies del pacient, com s’ha apuntat anteriorment. D'aquesta manera, s’aconsegueix una avaluació molt precisa i personalitzada del nivell de dificultat que suposa realitzar una ruta per a cada pacient en particular., El presente Trabajo Final de Grado tiene como objetivo desarrollar un sistema de caracterización y evaluación de rutas para pacientes respiratorios del Hospital Clínic de Barcelona mediante una aplicación web que permite tanto a médicos como a pacientes interactuar de manera eficiente. A través de este sistema, se pretende proporcionar una herramienta que facilite la asignación de rutas de acuerdo con el estado físico y las condiciones particulares de cada paciente, promoviendo una mejora en la calidad de vida y en la gestión de las actividades físicas recomendadas por los especialistas. El proyecto se estructura en las siguientes fases principales: la realización e implementación de ecuaciones matemáticas para el cálculo del esfuerzo, el diseño y desarrollo de la aplicación web, la programación e integración de un modelo de inteligencia artificial y la validación de los resultados obtenidos. La plataforma desarrollada utiliza un mapa mundial interactivo en el que el médico puede seleccionar el punto de origen y un punto de destino de una ruta – cualquiera que quieran consultar -. La dificultad de cada ruta se calcula mediante un conjunto de ecuaciones matemáticas progresivamente más complejas que consideran diversos factores como la distancia de la ruta, la inclinación del terreno y todas las características individuales del paciente - género, peso, altura, edad e incluso estado físico y patologías -. Se recurre a una fórmula matemática u otra en función de los parámetros que el médico quiera utilizar, que pueden ser más o menos. El sistema incluye un modelo de red neuronal, creado con TensorFlow, que permite estimar con mayor precisión el esfuerzo requerido para cada ruta, incorporando variables adicionales como el estado de salud y la cantidad de patologías del paciente, como se ha apuntado anteriormente. De esta manera, se logra una evaluación muy precisa y personalizada del nivel de dificultad que supone realizar una ruta para cada paciente en particular., The purpose of this Thesis is to develop a system for the characterization and evaluation of routes for respiratory patients of the Hospital Clínic de Barcelona through a web application that allows both doctors and patients to interact efficiently. The aim of this system is to provide a tool that facilitates the assignment of routes according to the physical condition and particular circumstances of each patient, promoting an improvement in quality of life and in the management of physical activities recommended by specialists. The Thesis is structured into the following main phases: the design and implementation of mathematical equations to calculate physical effort, the design and development of the web application, the programming and integration of an artificial intelligence model, and the validation of the results obtained. The developed platform uses an interactive world map where doctors can select the origin and destination of any route they wish to analyse. The difficulty of each route is calculated through a set of progressively more complex mathematical equations that take into account various factors, such as the route distance, terrain slope, and all the individual characteristics of the patient (gender, weight, height, age, as well as physical condition and pathologies). Different mathematical formulas are applied depending on the number of parameters the doctor wishes to use. The system includes a neural network model created with TensorFlow, which allows for more precise estimation of the effort required for each route, incorporating additional variables such as the patient’s health status and number of pathologies, as previously indicated. This way, a highly precise and personalized evaluation of the level of difficulty required to complete a route is achieved for each specific patient. The results obtained show that the system is capable of classifying and characterizing routes effectively, providing doctors with a tool that assists them.

Aquest projecte descriu el disseny i desenvolupament d'un sistema IoT modular per monitoritzar el creixement de plantes, utilitzant un microcontrolador ESP32 i diversos sensors. S'han estudiat diverses opcions de microcontroladors i sensors. Amb aquesta informació, s'ha creat un prototip físic del dispositiu amb diversos sensors. Les dades es recullen i s'emmagatzemen en una plataforma al núvol que garanteix la seguretat i privacitat de la informació. A més, s'ha desenvolupat un model de machine learning per predir dades de sensors no inclosos, entrenat amb dades generades sintèticament que imiten patrons ambientals reals. També s'ha utilitzat un model IA per generar resums en llenguatge natural a partir de les dades recollides. El sistema permet el registre i autenticació d'usuaris mitjançant una aplicació mòbil desenvolupada durant el projecte, que també permet la configuració del dispositiu ESP32 i la lectura de les dades obtingudes d'aquest., Este proyecto describe el diseño y desarrollo de un sistema IoT modular para monitorear el crecimiento de plantas, utilizando un microcontrolador ESP32 y diversos sensores. Se ha estudiado diversas opciones de microcontroladores y sensores. Utilizando esta información, se ha creado un prototipo físico del dispositivo con varios sensores. Los datos se recogen y se almacenan en una plataforma en la nube que garantiza la seguridad y privacidad de la información. Además, se desarrolló un modelo de machine learning para predecir datos de sensores no incluidos, entrenado con datos generados sintéticamente que imitan patrones ambientales reales. También se uso un modelo IA para generar resúmenes en lenguaje natural a partir de los datos recopilados. El sistema permite el registro y autentificación de usuarios utilizando una aplicación móvil desarrollada durante el proyecto, que también permite la configuración del dispositivo ESP32 y la lectura de los datos obtenidos de este., This project describes the design and development of a modular IoT system for monitoring plant growth, utilizing an ESP32 microcontroller and various sensors. Various microcontroller and sensor options have been studied. Using this information, a physical prototype of the device was created, incorporating multiple sensors. Data is collected and stored on a cloud platform that ensures the security and privacy of the information. Additionally, a machine learning model was developed to predict data from sensors not included in the prototype. This model was trained with synthetically generated data that simulates real environmental patterns. An AI model was also used to generate natural language summaries from the collected data. The system allows for user registration and authentication through a mobile application developed during the project, which also facilitates the configuration of the ESP32 device and access to the data it collects.

© 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., This paper presents an approach for anomaly detection and forecasting that aims to protect the integrity and operational continuity of IoT critical infrastructure, specifically for a railway use case. This system is designed to monitor in real-time the sensor data to detect any deviations that may indicate a potential data tampering attack or a sensor malfunction. This early identification and notification of such anomalies is crucial for preventing unauthorized access and mitigating the risks associated with data tampering attacks. The proposed system is comprises of two primary components: a forecasting component and an anomaly detection component. The Forecasting Component uses a Long Short-Term Memory (LSTM) model to predict future sensor values, while the Anomaly Detection Component employs the Tukey's fence method to identify sensor measurements that significantly deviate from normal behaviour. A railway use case is included to demonstrate the practical application of the deep learning framework. These components were evaluated and both demonstrated excellent performance. The Forecasting Component provided highly accurate predictions of future sensor values, while the Anomaly Detection Component effectively identified deviations from normal patterns. The evaluation results confirmed the system's ability to detect significant anomalies and its capability to maintain operational integrity and security in IoT critical infrastructures., The work leading to this publication was partly funded by the European Union’s Horizon Europe under project PHOENi2X, Grant Agreement no. 101070586. For UPC authors this work is partially co-funded by the Spanish Ministry of Science and Innovation under grant PID2021-124463OBI00 funded by MCIN/AEI/10.13039/501100011033 and by ERDF A way of making Europe, as well as by the Catalan Government under contract 2021 SGR 00326., Peer Reviewed, Postprint (published version)

Títol alternatiu emprat a la intranet de l'EPSEVG: "Tecnologia blockchain per l’autenticació de dispositius “un-trusted” IoT ", Aquest treball final de grau ens mostra una manera per solucionar un aspecte negatiu dels dispositius IoT com és poder confiar en la integritat de les dades proporcionades. Aquest problema el podrem solucionar aplicant un mètode d’ autenticació de dispositius d’una forma segura i original fent ús d’eines de codi obert com el marc de treball de cadena de blocs Hyperledger Fabric, la qual servirà per emmagatzemar les dades per futures autenticacions de dispositius. S’empraran proves zkp més específicament zk-snark, utilitzant la llibreria libsnark, per la autenticació de dispositius de forma segura fent ús del protocol HTTPS per la comunicació entre el dispositiu i l’aplicació creada per comunicar-se amb la cadena de blocs. Per poder construir un escenari realista, hi ha una xarxa Docker on es troben els components de la cadena de blocs simbolitzant així un entorn empresarial. Per altra banda hi ha la simbolització d’un dispositiu IoT que es comunica amb l’aplicació per realitzar peticions que seran ateses. Si el dispositiu està registrat al sistema serà autenticat i podrà accedir de manera segura a la informació. La solució aportada és robusta i segura i pot ser aplicada en múltiples àmbits on es requereix una autenticació fiable., Este trabajo final de grado nos muestra una forma para solucionar un aspecto negativo de los dispositivos IoT como es poder confiar en la integridad de los datos proporcionados. Este problema se podrá solucionar aplicando un método de autenticación de dispositivos de una forma segura y original haciendo uso de herramientas de código abierto como el marco de trabajo de cadena de bloques Hyperledger Fabric, que servirá para almacenar los datos para futuras autenticaciones de dispositives. Se utilizarán pruebas de conocimiento cero (zkp) más específicamente zk-snark, utilizando la librería libsnark, para la autenticación de dispositivos de forma segura, haciendo uso del protocolo HTTPS para la comunicación entre el dispositivo y la aplicación creada para comunicarse con la cadena de bloques. Para poder construir un escenario realista, existe una red Docker donde se encuentran los componentes de la cadena de bloques, simbolizando de esta manera un entorno empresarial. Por otra parte, existe la simulación de un dispositivo IoT que se comunica con la aplicación para realizar peticiones que serán atendidas. Si el dispositivo está registrado en el sistema, será autenticado y podrá acceder de forma segura a la información. La solución aportada es robusta y segura y puede aplicarse en muchos ámbitos distintos donde se requiera una autenticación fiable., My end of degree thesis aims at showing a way to solve a negative aspect of IoT devices which is the need to be able to trust the integrity of the data provided. We are able to solve this problem by applying a method of device authentication in a secure and original way while using open-source tools such as the Hyperledger Fabric blockchain framework, which is used to store de data for future authentications of devices. ZKP tests will be used, specifically ZK-snark, and the libsnark library, to authenticate devices safely using the HTTPS protocol for the communication between the device and the application created to communicate with the blockchain. To build a realistic scenario, there is a Cocker network where the blockchain components are located, symbolizing in this way an enterprise environment. On the other hand, there is the symbolization of a IoT device that communicates with the application to make requests that will be answered. If the device is registered in the system, it will be authenticated and will have a secure access to the information requested. The solution provided is robust and secure and can be applied in various areas where reliable authentication is required.

The full deployment of sixth-generation (6G) networks is inextricably connected with a holistic network redesign able to deal with various emerging challenges, such as integration of heterogeneous technologies and devices, as well as support of latency and bandwidth demanding applications. In such a complex environment, resource optimization, and security and privacy enhancement can be quite demanding, due to the vast and diverse data generation endpoints and associated hardware elements. Therefore, efficient data collection mechanisms are needed that can be deployed at any network infrastructure. In this context, the network data analytics function (NWDAF) has already been defined in the fifth-generation (5G) architecture from Release 15 of 3GPP, that can perform data collection from various network functions (NFs). When combined with advanced machine learning (ML) techniques, a full-scale network optimization can be supported, according to traffic demands and service requirements. In addition, the collected data from NWDAF can be used for anomaly detection and thus, security and privacy enhancement. Therefore, the main goal of this paper is to present the current state-of-the-art on the role of the NWDAF towards data collection, resource optimization and security enhancement in next generation broadband networks. Furthermore, various key enabling technologies for data collection and threat mitigation in the 6G framework are identified and categorized, along with advanced ML approaches. Finally, a high level architectural approach is presented and discussed, based on the NWDAF, for efficient data collection and ML model training in large scale heterogeneous environments., This work was supported in part by the HORSE Project funded by the Smart Networks and Services Joint Undertaking (SNS JU) through the European Union’s Horizon Europe Research and Innovation Program under Grant 101096342 (www.horse-6g.eu)., Peer Reviewed, Postprint (published version)

Despite the large impact chronic obstructive pulmonary disease (COPD) that has on the population, the implementation of new technologies for diagnosis and treatment remains limited. Current practices in ambulatory oxygen therapy used in COPD rely on fixed doses overlooking the diverse activities which patients engage in. To address this challenge, we propose a software architecture aimed at delivering patient-personalized edge-based artificial intelligence (AI)-assisted models that are built upon data collected from patients’ previous experiences along with an evaluation function. The main objectives reside in proactively administering precise oxygen dosages in real time to the patient (the edge), leveraging individual patient data, previous experiences, and actual activity levels, thereby representing a substantial advancement over conventional oxygen dosing. Through a pilot test using vital sign data from a cohort of five patients, the limitations of a one-size-fits-all approach are demonstrated, thus highlighting the need for personalized treatment strategies. This study underscores the importance of adopting advanced technological approaches for ambulatory oxygen therapy., This research was funded by the Spanish Ministry of Science, Innovation and Universities and FEDER, grant number PID2021-124463OB-100, and by the AGAUR Catalan Agency, grant number 2021_SGR_00326., Peer Reviewed, Postprint (published version)

El mundo digital se ha convertido en un campo de batalla en constante evolución, que, junto a los ataques cibernéticos, cada vez más sofisticados y multifacéticos, acechan a empresas, gobiernos e individuos por igual. Las amenazas se multiplican exponencialmente, creando un panorama de ciberseguridad en constante cambio y desafío. A medida que la digitalización avanza y la generación de datos aumenta exponencialmente en nuestra vida cotidiana, la seguridad de la información emerge como una preocupación crítica. La ineludible necesidad de proteger los activos digitales y robustecer la infraestructura frente a una constante evolución de las amenazas cibernéticas se posiciona como una prioridad irrefutable. En este contexto, el presente Trabajo Final de Grado (TFG) se propone abordar estos desafíos mediante una investigación exhaustiva, un diseño meticuloso y una implementación rigurosa de una solución integral de ciberseguridad enfocada en el ámbito de las redes y de la inteligencia artificial. Se plantea la creación de un Sistema de Detección de Intrusiones de Red con Inteligencia Artificial (NIDS-AI - Network Intrusion Detection System with Artificial Intelligence), diseñado con el objetivo de fortalecer la seguridad tanto en entornos empresariales como personales. Este sistema se sustenta en modelos de aprendizaje automático, siguiendo un proceso que abarca desde la recolección, análisis y preprocesamiento de datos hasta el entrenamiento, selección, validación y evaluación de modelos. La implementación de este enfoque implica el uso de diversas técnicas y algoritmos, empleando datos no supervisados proveniente de un entorno local en tiempo real como datos supervisados proveniente de fuentes abiertas, como Kaggle o la Universidad de Nueva Gales del Sur, que incluyen diversas clases de ataques y datos benignos. Los algoritmos con las mejores precisiones en la detección de ataques serán seleccionados para integrarse en el NIDS-AI. Para la representación visual de los, El món digital s'ha convertit en un camp de batalla en constant evolució, que, juntament amb els atacs cibernètics, cada cop més sofisticats i multifacetics, aguaiten empreses, governs i individus per igual. Les amenaces es multipliquen exponencialment, creant un panorama de ciberseguretat en constant canvi i desafiament. A mesura que la digitalització avança i la generació de dades augmenta exponencialment a la nostra vida quotidiana, la seguretat de la informació emergeix com una preocupació crítica. La necessitat ineludible de protegir els actius digitals i enfortir la infraestructura davant d'una constant evolució de les amenaces cibernètiques es posiciona com una prioritat irrefutable. En aquest context, aquest Treball Final de Grau (TFG) es proposa abordar aquests desafiaments mitjançant una investigació exhaustiva, un disseny meticulós i una implementació rigorosa d'una solució integral de ciberseguretat enfocada a l'àmbit de les xarxes i de la intel·ligència artificial. Es planteja crear un Sistema de Detecció d'Intrusions de Xarxa amb Intel·ligència Artificial (NIDS-AI - Network Intrusion Detection System with Artificial Intelligence), dissenyat amb l'objectiu d'enfortir la seguretat tant en entorns empresarials com personals. Aquest sistema se sustenta en models d'aprenentatge automàtic, seguint un procés que abasta des de la recol·lecció, anàlisi i preprocessament de dades fins a l'entrenament, selecció, validació i avaluació de models. La implementació d'aquest enfocament implica l'ús de diverses tècniques i algorismes, emprant dades no supervisades provinents d'un entorn local en temps real com dades supervisades provinents de fonts obertes, com Kaggle o la Universitat de Nova Gal·les del Sud, que inclouen diverses classes de atacs i dades benignes. Els algoritmes amb les millors precisions en la detecció d'atacs seran seleccionats per integrar-se al NIDS-AI. Per a la representació visual de les dades obtingudes, es desenvoluparà un tauler de control qu, The digital world has become a constantly evolving battlefield, which, along with increasingly sophisticated and multifaceted cyber attacks, stalk companies, governments and individuals alike. Threats are multiplying exponentially, creating an ever-changing and challenging cybersecurity landscape. As digitalization advances and data generation increases exponentially in our daily lives, information security emerges as a critical concern. The unavoidable need to protect digital assets and strengthen infrastructure in the face of a constant evolution of cyber threats is positioned as an irrefutable priority. In this context, this Final Degree Project (TFG) aims to address these challenges through exhaustive research, meticulous design and rigorous implementation of a comprehensive cybersecurity solution focused on the field of networks and artificial intelligence. The creation of a Network Intrusion Detection System with Artificial Intelligence (NIDS-AI - Network Intrusion Detection System with Artificial Intelligence) is proposed, designed with the objective of strengthening security in both business and personal environments. This system is based on machine learning models, following a process that ranges from data collection, analysis and preprocessing to training, selection, validation and evaluation of models. The implementation of this approach involves the use of various techniques and algorithms, using unsupervised data from a local environment in real time as well as supervised data from open sources, such as Kaggle or the University of New South Wales, which include various kinds of attacks and benign data. The algorithms with the best accuracies in detecting attacks will be selected to be integrated into the NIDS-AI. For the visual representation of the data obtained, a control panel will be developed that will allow the visualization of the different categories for the different traffic flows. Regarding infrastructure, the implementation of NIDS-AI will be

This paper introduces a cutting-edge data architecture designed for a smart advertising context, prioritizing efficient data flow and performance, robust security, while guaranteeing data privacy and integrity. At the core of this study lies the application of federated learning (FL) as the primary methodology, which emphasizes the authenticity and privacy of data while promptly discarding irrelevant or fraudulent information. Our innovative data model employs a semi-random role assignment strategy based on a variety of criteria to efficiently collect and amalgamate data. The architecture is composed of model nodes, data nodes, and validator nodes, where the role of each node is determined by factors such as computational capability, interconnection quality, and historical performance records. A key feature of our proposed system is the selective engagement of a subset of nodes for modeling and validation, optimizing resource use and minimizing data loss. The AROUND social network platform serves as a real-world case study, illustrating the efficacy of our data architecture in a practical setting. Both simulated and real implementations of our architecture showcase its potential to dramatically curtail network traffic and average CPU usage, while preserving the accuracy of the FL model. Remarkably, the system is capable of achieving over a 50% reduction in both network traffic and average CPU usage even when the user count escalates by twenty-fold. The click rate, user engagement, and other parameters have also been evaluated, proving that the proposed architecture’s advantages do not affect the smart advertising accuracy. These findings highlight the proposed architecture’s capacity to scale efficiently and maintain high performance in smart advertising environments, making it a valuable contribution to the evolving landscape of digital marketing and FL., This work has been supported by the Spanish Ministry of Science and Innovation under grant PID2021-124463OB-I00 funded by MCIN/AEI/10.13039/501100011033 and by ERDF A way of making Europe, and by the Catalan Government under contract 2021 SGR 00326. The corresponding author, R.S., gratefully acknowledges the Universitat Politècnica de Catalunya and Banco Santander for the financial support of his predoctoral grant FPI-UPC 2021, Peer Reviewed, Postprint (published version)

Aquest projecte sorgeix de la necessitat identificada per l'Associació l’AUBE de millorar l'eficiència en la prevenció d’incendis i la conservació dels espais naturals de la muntanya de la Picossa a Móra d'Ebre. L'objectiu principal és implementar tecnologies avançades per proporcionar informació en temps real que permeti una presa de decisions ràpida i efectiva. En la investigació es van comparar diversos controladors de dades, incloent la BBC Micro:bit, Arduino i Raspberry Pi, per determinar la seva adequació per a la recopilació i gestió de dades ambientals. Es va seleccionar la Micro:bit per la seva facilitat d'ús, cost baix i integració amb extensions com la Weather:bit i la Wappsto:bit, que permeten monitoritzar variables ambientals. Es van realitzar proves de cobertura en punts estratègics de la Ribera d’Ebre per assegurar la connectivitat de la tecnologia NB-IoT. Els resultats van mostrar una cobertura variable, amb zones de senyal forta i altres amb cobertura limitada, suggerint la necessitat d'implementar tecnologies satel·litals en àrees crítiques. La plataforma desenvolupada permet la recopilació de dades en temps real i ofereix una interfície d'usuari personalitzada per a una gestió eficient. Aquesta tecnologia no només millora la gestió ambiental, sinó que també té una dimensió educativa significativa. L'Associació l’AUBE utilitzarà aquesta plataforma en col·laboració amb escoles locals per conscienciar els estudiants sobre la preservació del medi ambient i l'ús de tecnologia sostenible. Els resultats del projecte demostren la viabilitat i eficàcia de la plataforma per a la monitorització ambiental en temps real. La integració de tecnologies IoT en la gestió mediambiental permet una resposta ràpida davant possibles incidències, millorant significativament la prevenció d'incendis i la conservació dels espais naturals. En conclusió, aquest projecte subratlla la importància i l'eficàcia de les noves tecnologies en la gestió mediambiental., Este proyecto surge de la necesidad identificada por la Asociación la AUBE de mejorar la eficiencia en la prevención de incendios y la conservación de los espacios naturales de la montaña de la Picossa en Móra d'Ebre.El objetivo principal es implementar tecnologías avanzadas para proporcionar información en tiempo real que permita una toma de decisiones rápida y efectiva. En la investigación se compararon varios controladores de datos, incluyendo la BBC Micro:bit, Arduino y Raspberry Pi, para determinar su adecuación para la recopilación y gestión de datos ambientales.Se seleccionó la Micro:bit por su facilidad de uso, coste bajo e integración con extensiones como la Weather:bit y la Wappsto:bit,que permiten monitorizar variables ambientales. Se realizaron pruebas de cobertura en puntos estratégicos de la Ribera de Ebro para asegurar la conectividad de la tecnología NB-IoT. Los resultados mostraron una cobertura variable, con zonas de señal fuerte y otras con cobertura limitada, sugiriendo la necesidad de implementar tecnologías satelitales en áreas críticas. La plataforma desarrollada permite la recopilación de datos en tiempo real y ofrece una interfaz de usuario personalizada para una gestión eficiente.Esta tecnología no sólo mejora la gestión ambiental,sino que también tiene una dimensión educativa significativa.La Asociación AUBE utilizará esta plataforma en colaboración con escuelas locales para concienciar a los estudiantes sobre la preservación del medio ambiente y el uso de tecnología sostenible. Los resultados del proyecto demuestran la viabilidad y eficacia de la plataforma para la monitorización ambiental en tiempo real.La integración de tecnologías IoT en la gestión medioambiental permite una respuesta rápida frente a posibles incidencias, mejorando significativamente la prevención de incendios y la conservación de los espacios naturales.En conclusión, este proyecto subraya la importancia y eficacia de las nuevas tecnologías en la gestión medioambiental, This project arises from the identified need by the Association l’AUBE to improve efficiency in fire prevention and the conservation of natural spaces in the Picossa mountain in Móra d'Ebre. The main objective is to implement advanced technologies to provide real-time information that allows for quick and effective decision-making. The investigation compared various data controllers, including the BBC Micro:bit, Arduino, and Raspberry Pi, to determine their suitability for environmental data collection and management. The Micro:bit was selected for its ease of use, low cost, and integration with extensions such as Weather:bit and Wappsto:bit, which enable monitoring of environmental variables. Coverage tests were conducted at strategic points in the Ribera d’Ebre to ensure the connectivity of NB-IoT technology. The results showed variable coverage, with areas of strong signal and others with limited coverage, suggesting the need to implement satellite technologies in critical areas. The developed platform allows real-time data collection and offers a customized user interface for efficient management. This technology not only improves environmental management but also has a significant educational dimension. The Association l’AUBE will use this platform in collaboration with local schools to raise students' awareness of environmental preservation and the use of sustainable technology. The project results demonstrate the feasibility and effectiveness of the platform for real-time environmental monitoring. The integration of IoT technologies in environmental management allows for a rapid response to possible incidents, significantly improving fire prevention and the conservation of natural spaces. In conclusion, this project highlights the importance and effectiveness of new technologies in environmental management.

To the editor: Physical capacity tests are used for the diagnosis, prognosis and monitoring of chronic respiratory diseases (CRD), such as Chronic Obstructive Pulmonary Disease (COPD) or Pulmonary Hypertension (PH).1 Among these tests, the most widely used is the 6-minute walking test (6MWT).2 Additionally, the guidelines highlight the need to continuously record biological signals, particularly oxygen saturation (SpO2), which has been shown to be a prognostic marker in CRD.2 [...], The study was supported by grants from Societat Catalana de Pneumologia (SOCAP) (ESTEVE TEIJIN/2021), PI17/1515 and PI21/0555 from the Instituto de Salud Carlos III (ISCiii), co-funded by the European Union (ERDF/ESF, ”A way to make Europe” “Investing in your future”) and Premi d’Innovació de l’Hospital Clínic de Barcelona (2021). For UPC authors this work has been supported by the Spanish Ministry of Science and Innovation under contract PID2021-124463OB-I00, the Catalan Government under contract 2021 SGR 00326 and the Catalan Department of Research and Universities., Peer Reviewed, Postprint (published version)

Chronic Respiratory Diseases (CRDs), including Chronic Obstructive Pulmonary Disease (COPD), pose significant global health challenges. Long-term oxygen therapy (LTOT) has been widely adopted to improve respiratory function and quality of life in CRD patients. However, current oxygen dosing approaches show several limitations, including inconvenience and mismatched oxygen flow rates according to patients' activity. To address these challenges, the design of Patient Specific Modeling (PSM) and the utilization of advanced technologies, such as artificial intelligence (AI), can be integrated towards a personalized oxygen dosing. This study presents a first draft of a conceptual architecture combining cloud and edge computing aimed at optimizing oxygen dosing based on individual patient data. The evaluation of sixty neural network architectures in a small-scale test has shown good results, with smaller networks generally outperforming larger ones. Further research is needed to design new testing procedures and explore optimal parameters for the neural networks, including a large patients' number., This work has been supported by the Spanish Ministry of Science and Innovation under grant PID2021-124463OB-I00 funded by MCIN/AEI/10.13039/501100011033 and by ERDF A way of making Europe, the Catalan Government under contract 2021 SGR 00326 and the Catalan Department of Research and Universities, Peer Reviewed, Postprint (author's final draft)

The rising popularity of mobile devices has driven the need for faster connection speeds and more flexible authentication and authorization methods. This project aims to develop and implement an innovative system that provides authentication and authorization for both the device and the user. It also facilitates real-time user re-authentication within the application, ensuring transparency throughout the process. Additionally, the system aims to establish a secure architecture that minimizes the computational requirements on the client's device, thus optimizing the device's battery life. The achieved results have demonstrated satisfactory outcomes, validating the effectiveness of the proposed solution. However, there is still potential for further improvement to enhance its overall performance.

El projecte consisteix en el desplegament d’un conjunt de dispositius IoT en una granja avícola amb l’objectiu de monitorar i controlar variables ambientals i operatives clau. Els dispositius inclouen sensors per mesurar el contingut de les sitges de pinso, la temperatura exterior i interior, la humitat relativa, la concentració de diòxid de carboni, la concentració d'amoníac, la il·luminació i el consum d'aigua. A més, s'implementa un dispositiu actuador capaç d'emular el control de la ventilació, la calefacció, els llums i les menjadores. Tots els dispositius estan connectats mitjançant un servidor central, on envien les dades llegides dels sensors, també és on s'allotja l'aplicació web desenvolupada que l'usuari pot utilitzar per consultar les dades llegides per cadascun dels sensors, planificar accions en l'actuador, configurar alarmes i enregistrar dades importants dels animals. A més, l'algorítmia de control desenvolupada és capaç de gestionar de manera autònoma l'IoT actuador per complir les lleis de benestar animal en funció de les dades recollides pels sensors. L’objectiu conceptual principal d’aquest projecte és facilitar als criadors el compliment de la legislació espanyola que controla les normes mínimes de benestar animal aplicables a les granges avícoles destinades a la producció de carn. Finalment, cadascun dels dispositius IoT del projecte s'ha desplegat amb èxit en un entorn real amb l'objectiu de validar-ne la funcionalitat., El proyecto consiste en el despliegue de un conjunto de dispositivos IoT en una granja avícola con el objetivo de monitorear y controlar variables ambientales y operativas clave. Los dispositivos incluyen sensores para medir el contenido de los silos de pienso, la temperatura exterior e interior, la humedad relativa, la concentración de dióxido de carbono, la concentración de amoníaco, la iluminación y el consumo de agua. Además, se implementa un dispositivo actuador capaz de emular el control de la ventilación, la calefacción, las luces y los comederos. Todos los dispositivos están conectados mediante un servidor central, al que le envían los datos leídos de los sensores, también es donde se aloja la aplicación web desarrollada que el usuario puede utilizar para consultar los datos leídos por cada uno de los sensores, planificar acciones en el actuador, configurar alarmas y registrar datos importantes de los animales. Además, la algoritmia de control desarrollada es capaz de gestionar de manera autónoma el IoT actuador para cumplir con las leyes de bienestar animal en función de los datos recogidos por los sensores. El objetivo conceptual principal de este proyecto es facilitar a los criadores el cumplimiento de la legislación española que controla las normas mínimas de bienestar animal aplicables a las granjas avícolas destinadas a la producción de carne. Finalmente, cada uno de los dispositivos IoT del proyecto se ha desplegado con éxito en un entorno real con el objetivo de validar su funcionalidad., The project consists of the deployment of a set of IoT devices in a poultry farm with the objective of monitoring and controlling key environmental and operational variables. The devices include sensors to measure the contents of the feed silos, the outside and inside temperature, relative humidity, carbon dioxide concentration, ammonia concentration, lighting and water consumption. In addition, an actuator device capable of emulating the control of ventilation, heating, lights and feeders is implemented. All the devices are connected through a central server, to which they send the data read from the sensors, it is also where the developed web application is hosted, which the user can use to consult the data read by each of the sensors, plan actions in the actuator, set alarms and record important animal data. In addition, the developed control algorithm is capable of autonomously managing the IoT actuator to comply with animal welfare laws based on the data collected by the sensors. The main conceptual objective of this project is to make it easier for breeders to comply with Spanish legislation that controls the minimum standards of animal welfare applicable to poultry farms for meat production. Finally, each of the IoT devices in the project has been successfully deployed in a real environment in order to validate its functionality.

Rapid development in the network infrastructure has resulted in sophisticated attacks which are hard to detect using typical network intrusion detection systems (NIDS). There is a strong need for efficient NIDS to detect these known attacks along with ever-emerging zero-day exploits. Existing NIDS are more focused on detecting known attacks using supervised machine learning approaches, achieving better performance for known attacks but poor detection of unknown attacks. Many NIDS have utilized the unsupervised approach, which results in better detection of unknown anomalies. In this paper, we proposed a Hybrid NIDS based on Semisupervised One-Class Support Vector Machine (OC-SVM) and Supervised Random Forest (RF) algorithms. This detection system has several stages. The First stage is based on OC-SVM, which filters benign and malicious traffic. The next stages use many parallel supervised models and an additional OC-SVM model to separate known and unknown attacks from malicious traffic. The previous process is done so that known attacks are classified by their type, and unknown attacks are detected. The proposed NIDS is tested on the standard public dataset CSE-CIC-IDS-2018. The evaluation results show that the system achieves a high accuracy, 99.45%, for detecting known attacks. Our proposed NIDS achieves an accuracy of 93.99% for unknown or zero-day attacks. The overall accuracy of the proposed NIDS is 95.95%. The system significantly improves the detection of known and unknown anomalies using a hybrid approach., This project has received funding from the European Union’s H2020 research and innovation programme under the grant agreement No. 952644, from the Spanish Ministry of Science and Innovation under contract PID2021-124463OB- I00, and from the Catalan Government under contract 2021 SGR 00326., Peer Reviewed, Postprint (author's final draft)

L'ISWT o "Incremental Shuttle Walk Test" és una prova de caminada incremental que es realitza en un recorregut de 10 metres. La velocitat de la marxa augmenta cada minut i finalitza quan el pacient es troba massa fatigat per continuar o no pot mantenir la velocitat requerida. En una fulla de treball, el metge encarregat de supervisar la prova ha d'anotar certes mesures abans,durant i després de la prova. Durant la prova, el responsable ha d'estar atent a cada pas que fa el pacient entre els cons i, després de cada minut, ha de recollir dades sobre la freqüència cardíaca i la saturació d'oxigen en sang. L'objectiu d'aquest projecte és intentar digitalitzar la prova de l'ISWT, dissenyant una solució que faci més fàcil la feina al personal mèdic i com a mínim mantingui o incrementar l'eficàcia de la recopilació de dades. Des del Craax, fa temps que treballen en col·laboració amb l'Hospital Clínic de Barcelona, i ja tenen un sistema muntat i diversos dispositius útils per a altres proves. Alguns d'aquests dispositius els tenim a disposició i al llarg d'aquesta memòria podrem veure com els analitzem i busquem la manera d'utilitzar-los en la nostra solució. Podrem veure com anem integrant els diferents elements per millorar la pràctica de la prova, permetent al personal que durant la prova només s'hagi d'encarregar de supervisar la recopilació de dades, a més d'una navegació a través de l'aplicació senzilla i suficient per recopilar totes les dades necessàries i útils per a la prova. Aplicant els diversos coneixements adquirits al llarg de la carrera universitària i amb l'ajuda de l'equip directiu, s'ha desenvolupat una solució final que es considera satisfactòria d'acord amb els objectius i ofereix resultats positius en la seva consideració d'utilitat per a futures millores., ISWT de “Incremental Shuttle Walk Test” es una prueba de caminata incremental realizada a lo largo de un recorrido de 10 metros. La velocidad de marcha incrementa a cada minuto y este finaliza en el caso que el paciente se encuentre demasiado fatigado como para continuar o en caso de que no pueda mantener la velocidad requerida. En una hoja de trabajo el médico encargado de monitorizar la prueba, ha de anotar ciertas medidas anteriores, durante y posteriores de la prueba. Durante la prueba, el encargado ha de estar pendiente a cada paso por los conos que realiza el paciente, y tras cada minuto recoger datos de frecuencia cardiaca y saturación de oxígeno en sangre. El objetivo de este proyecto es intentar digitalizar la prueba del ISWT, diseñando así, una solución capaz de facilitar el trabajo al personal médico y como mínimo manteniendo o mejorando la eficacia de la recogida de datos. Desde el Craax llevan tiempo trabajando conjuntamente con el Hospital Clínic de Barcelona, ya tienen un sistema montado y diferentes dispositivos útiles para otras pruebas. Algunos de ellos los tenemos a disposición y a lo largo de esta memoria podremos observar como lo analizamos y buscamos poder utilizarlos en nuestra solución. Podremos ver como vamos encajando los diferentes elementos para mejorar la práctica de la prueba, permitiendo al personal que, durante la prueba únicamente tenga que encargarse de monitorizar la recogida de datos, además de una navegación a lo largo de la app sencilla y suficiente para recabar todos los datos necesarios y útiles para la prueba. Aplicando diferentes conocimientos adquiridos durante el recorrido universitario y con la ayuda del equipo dirigente, se ha desarrollado una solución final a considerar satisfactorio conforme los objetivos y de resultado positivo en su consideración de utilidad para futuras mejoras., The ISWT or "Incremental Shuttle Walk Test" is an incremental walking test performed over a 10-meter course. The walking speed increases every minute and ends when the client becomes too fatigued to continue or is unable to maintain the required speed. On a worksheet, the person in charge of monitoring the test must record certain pre-, during and post-test measurements. During the test, the responsible person must pay attention to each step taken by the client between the cones (shuttle) and, after each minute, collect data on heart rate and blood oxygen saturation. The objective of this project is to attempt to digitize the ISWT by designing a solution that makes the work easier for medical personnel and, at a minimum, maintains or improves the effectiveness of data collection. From Craax, they have been working collaboratively with the Hospital Clínic de Barcelona for some time, and they already have a system and various devices useful for other tests. Some of these devices are available to us, and throughout this report, we can see how we analyze them and seek ways to use them in our solution. We will see how we are integrating the different elements to improve the practice of the test, allowing the personnel during the test to only focus on monitoring data collection, along with simple and sufficient navigation through the app to gather all the necessary and useful data for the test Applying various acquired knowledge throughout the university journey and with the assistance of the leadership team, a final solution has been developed that is deemed satisfactory according to the objectives and yields positive results in its consideration of utility for future improvements.

The rapid growth in the number of interconnected devices on the Internet (referred to as the Internet of Things—IoT), along with the huge volume of data that are exchanged and processed, has created a new landscape in network design and operation. Due to the limited battery size and computational capabilities of IoT nodes, data processing usually takes place on external devices. Since latency minimization is a key concept in modern-era networks, edge servers that are in close proximity to IoT nodes gather and process related data, while in some cases data offloading in the cloud might have to take place. The interconnection of a vast number of heterogeneous IoT devices with the edge servers and the cloud, where the IoT, edge, and cloud converge to form a computing continuum, is also known as the IoT-edge-cloud (IEC) continuum. Several key challenges are associated with this new computing systems’ architectural approach, including (i) the design of connection and programming protocols aimed at properly manipulating a huge number of heterogeneous devices over diverse infrastructures; (ii) the design of efficient task offloading algorithms aimed at optimizing services execution; (iii) the support for security and privacy enhancements during data transfer to deal with the existent and even unforeseen attacks and threats landscape; (iv) scalability, flexibility, and reliability guarantees to face the expected mobility for IoT systems; and (v) the design of optimal resource allocation mechanisms to make the most out of the available resources. These challenges will become even more significant towards the new era of sixth-generation (6G) networks, which will be based on the integration of various cutting-edge heterogeneous technologies. Therefore, the goal of this survey paper is to present all recent developments in the field of IEC continuum systems, with respect to the aforementioned deployment challenges. In the same context, potential limitations and future challenge, This work was partially supported by the project «Towards a functional continuum operating system (ICOS)» funded by the European Commission (Project code/Grant Number: 101070177, call for proposal: HORIZON-CL4-2021-DATA-01, funded under HE|HORIZON-RIA\HORIZON-AG). For the UPC author, this work has been also partially supported by the Spanish Ministry of Science and Innovation under grant PID2021-124463OB-I00, which is funded by MCIN/AEI/10.13039/501100011033 and by ERDF A way of making Europe., Peer Reviewed, Postprint (published version)

Aquest Research Café, dirigit a estudiants, professorat i personal investigador, tractarà sobre la intel·ligència artificial des de diferents àmbits, abordant aspectes com la seguretat, l’educació i el coneixement., Este Research Café, dirigido a estudiantes, profesorado y personal investigador, tratará sobre la inteligencia artificial desde distintos ámbitos, abordando aspectos como la seguridad, la educación y el conocimiento.

Treball desenvolupat en el marc del programa "European Project Semester"., The project aims to implement a way for a teleoperator to control an existing self-driving car if the autonomous driving algorithms fail to respond to the encountered situation. The project will rely on the existing code developed by the MechLab Team at the HTW in Dresden, who have converted a BMW i3 into a self-driving car using surround and proximity sensors and a homemade software that controls the vehicle's speed and steering. The car is also able to detect pedestrians and other obstacles thanks to a deep learning algorithm dedicated to this part. Teleoperation systems pose many challenges, such as providing the teleoperator with the same level of situational awareness as a driver in the car. The driver needs to focus more on the surroundings, and therefore teleoperated drivers will have to rest more often and take more breaks. To address this challenge, the teleoperation system will use high information density sensors, including LiDAR, radar, and ultrasonic sensors, to provide the driver with an overlay of detected obstacles and the predicted path, enhancing reality to compensate for latency in communication by taking some workload off the operator. Another big challenge is to switch between the autonomous and teleoperated driving modes, as there are different problems that can appear. Most noticeably, during the time it takes for the operator to get aware of the situation and respond to the call, the car must be able to safely stop and wait for instructions from the operator. The failure to do so could result in dangerous or even deadly situations for the autonomous vehicle’s occupants as well as for the other road users, who do not need to wait for the communication to be established. One of the last great challenges is allow stable and fast communication between the car and the teleoperator. This can be achieved by narrowing the data transmitted for example by reducing video quality in predefined cases, or by ensuring redundancy in the communication media., Incoming

Adversarial attacks are still effective in today's world. The main idea of the project is to give a review of cloud cybersecurity, an analysis of the different strategies to use AI in an offensive way, identification of a critical context where using AI may substantially impact increasing cybersecurity vulnerabilities and propose a solution to proactively mitigate the effects of such a non-desired use of AI.

Aquest projecte pretén aportar solucions a les ciutats que necessiten millorar alguns aspectes per adaptar-se als temps actuals. Al llarg d’aquest projecte es buscarà quines solucions es poden aplicar en funció del tipus de ciutat. Després es desenvoluparà una eina que permetrà a un usuari entendre la situació de la seva ciutat i els passos a seguir per acostar-se a un model de ciutat més intel·ligent, eficient i sostenible. L’ eina és una aplicació web que conté un qüestionari amb un conjunt de preguntes sobre la ciutat, que dona com a resultat un anàlisi del seu estat i exemples de millores que s’hi podrien aplicar., This project aims to provide solutions to cities that need to improve some aspects to adapt to current times. Throughout this project I will look at what solutions can be applied depending on the type of city. Afterwards, a tool will be developed that will allow a user to understand the situation of their city and the steps to follow to approach a smarter, more efficient and sustainable city model. The tool is a web application that contains a questionnaire with a set of questions about the city, which results in an analysis of its status and examples of improvements that could be applied.

Future data-intensive intelligent applications are required to traverse across the cloudto-edge-to-IoT continuum, where cloud and edge resources elegantly coordinate, alongside sensor networks and data. However, current technical solutions can only partially handle the data outburst associated with the IoT proliferation experienced in recent years, mainly due to their hierarchical architectures. In this context, this paper presents a reference architecture of a meta-operating system (RAMOS), targeted to enable a dynamic, distributed and trusted continuum which will be capable of facilitating the next-generation smart applications at the edge. RAMOS is domain-agnostic, capable of supporting heterogeneous devices in various network environments. Furthermore, the proposed architecture possesses the ability to place the data at the origin in a secure and trusted manner. Based on a layered structure, the building blocks of RAMOS are thoroughly described, and the interconnection and coordination between them is fully presented. Furthermore, illustration of how the proposed reference architecture and its characteristics could fit in potential key industrial and societal applications, which in the future will require more power at the edge, is provided in five practical scenarios, focusing on the distributed intelligence and privacy preservation principles promoted by RAMOS, as well as the concept of environmental footprint minimization. Finally, the business potential of an open edge ecosystem and the societal impacts of climate net neutrality are also illustrated., For UPC authors: this research was funded by the Spanish Ministry of Science, Innovation and Universities and FEDER, grant number PID2021-124463OB-100., Peer Reviewed, Postprint (published version)

© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., Fog computing is a recent paradigm leveraging available resources at the edge of the network intended to extend the traditional cloud model towards the novel cloud continuum computing model. Recognized the unstoppable growth of highly dynamic and heterogeneous edge devices, as well as the pop up of a large set of diverse and ever more demanding services, the selection of those edge resources best meeting service requirements while also matching the expected QoS guarantees is, with no doubt, a challenging task. This paper presents a rankbased model aimed at both evaluating edge nodes’ characteristics and selecting nodes best performing the controller role, whilst simultaneously satisfying the required QoS constraints, coining the so-called Control-as-a-Service concept. To that end, a yet simple prediction strategy, based on Dynamic Branch Prediction is introduced to avoid unnecessary controller exchanges and QoS degradation. In the performed experiments, the proposed method yielded a reduction in the number of exchanges when compared to a solution with no prediction, under different scenarios. Comparing distinct selection strategies, the proposed model presented an improvement in controller availability as well as in relevant controllers’ characteristics, such as battery and memory capacity., This work is supported by FAPEMIG, CNPq, and CAPES. For the UPC author this work was supported by FEDER under contract RTI2018-094532-B-I00., Peer Reviewed, Postprint (author's final draft)

Treball desenvolupat en el marc del programa "European Project Semester"., This report explains the process the team went through when designing and developing a smart bridge that integrates into a smart city. It was proposed by the CRAAX lab which is a research group based in UPC Vilanova. It consists of both students and researchers studying computer science and telecommunications. In the CRAAX lab, there is a smart city testbed, which is a miniature model of a smart city. A smart city uses a framework of information and communication technologies to create, deploy and promote development practices to address urban challenges and create a joined-up technologically enabled, and sustainable infrastructure. Our goal is to create a smart bridge concept and show its integration into the smart city and the benefits it has towards improving traffic flow. Simulations will be conducted using an online program called Flexsim to compare traffic flow in different street layouts; an intersection, a four-lane bridge, and a two-lane bridge. From these calculations, we can decide which bridge will be most suited for the smart city. In the smart bridge, there will be many smart features incorporated to enhance the bridge further. These include smart sensors, big data, VMS, and other smart features. The bridge’s concept will be communicated through the simulation programs and with detailed design sketches describing each smart feature’s layout and function., Incoming

FOOXYnet és una aplicació web, concretament, una xarxa social destinada a ser integrada amb el conjunt de projectes entre l'Hospital Clínic de Barcelona i el CRAAX de la UPC de Vilanova i la Geltrú. Aquests projectes tenen la intenció de facilitar al personal mèdic l'avaluació dels pacients amb problemes respiratoris mitjançant l'execució d'exercicis físics com serien caminades seguint unes rutes personalitzades per als pacients. Amb la intenció de ser un portal social on els pacients poden compartir amb altres pacients i discutir el progrés dels exercicis proposats pel personal mèdic, va néixer FOOXYnet. Amb aquest objectiu en ment, FOOXYnet es fa servir de les rutes creades pel projecte de DCRoutes, entre altres criteris, per recomanar activament possibles contactes i contingut que s'ajusta als seus interessos personals. S’espera que conjuntament amb el interès de la xarxa, el pacient també desenvolupi una motivació addicional per realitzar els exercicis recomanats i poder compatir els resultats amb els altres usuaris de la xarxa. I així, motivar a altres pacients a seguir el seu exemple. Aplicant tècniques avançades d’arquitectura de programari, i amb la utilització de tecnologies de desenvolupament web, s’ha confeccionat una xarxa social amb una gran capacitat de creixement que compleix amb els objectius plantejats., FOOXYnet es una aplicación web, concretamente, una red social destinada a integrarse con el conjunto de proyectos entre el Hospital Clínico de Barcelona y el CRAAX de la UPC de Vilanova y la Geltrú. Estos proyectos tienen la intención de facilitar al personal médico la evaluación de los pacientes con problemas respiratorios mediante la ejecución de ejercicios físicos cómo unas camidatas siguiendo una ruta creada y personalizada para el paciente Con la intención de ser un portal social donde los pacientes pueden compartir con otros pacientes y discutir el progreso de los ejercicios propuestos por personal médico, se creó FOOXYnet. Con este objetivo en mente, FOOXYnet se hace servir de las rutas creadas por el proyecto de DCRoutes, entre otros criterios, para recomendar activamente posibles contactos y contenido que se ajuste a sus intereses personales. Se espera que junto con el interés de la red, el paciente también desarrolle una motivación adicional para realizar los ejercicios recomendados y poder comparar los resultados con los otros usuarios. Y de esta manera, motivar a otros pacientes a seguir su ejemplo. Aplicando técnicas avanzadas de arquitectura de programación, y con la utilización de tecnologías de desarrollo web, se ha confeccionado una red social con una gran capacidad de crecimiento que cumple con los objetivos planteados., FOOXYnet is a web application, specifically, a social network designed to integrate with the set of projects between the Hospital Clinic of Barcelona and the CRAAX of the UPC of Vilanova i la Geltrú. These projects are intended to facilitate the medical staff the evaluation of patients with respiratory problems through the execution of physical exercises such as walks following a route created and customized for the patient. With the intention of being a social portal where patients can share with other patients and discuss the progress of the exercises proposed by medical staff, FOOXYnet was created. With this goal in mind, FOOXYnet makes use of the routes created by the DCRoutes project, among other criteria, to actively recommend potential contacts and content that matches their personal interests. It is expected that along with the interest of the network, the patient will also develop additional motivation to perform the recommended exercises and be able to compare the results with other users. And in this way, motivate other patients to follow suit. By applying advanced programming architecture techniques and using web development technologies, a social network has been created with a great capacity for growth that meets the objectives set.

The wide adoption of the recently coined fog and edge computing paradigms alongsideconventional cloud computing creates a novel scenario, known as the cloud continuum, whereservices may benefit from the overall set of resources to optimize their execution. To operatesuccessfully, such a cloud continuum scenario demands for novel management strategies, enablinga coordinated and efficient management of the entire set of resources, from the edge up to thecloud, designed in particular to address key edge characteristics, such as mobility, heterogeneity andvolatility. The design of such a management framework poses many research challenges and hasalready promoted many initiatives worldwide at different levels. In this paper we present the resultsof one of these experiences driven by an EU H2020 project, focusing on the lessons learnt from a realdeployment of the proposed management solution in three different industrial scenarios. We thinkthat such a description may help understand the benefits brought in by a holistic cloud continuummanagement and also may help other initiatives in their design and development processes., This research was funded by H2020 mF2C Project, grant number 730929, and for UPCauthors by the Spanish Ministry of Science, Innovation and Universities and FEDER, grant numberRTI2018-094532-B-I00., Peer Reviewed, Postprint (published version)

Smart environments rely on the cloud for most computation activities; however, leveraging the availability of resources at the edge could complement the cloud capabilities to provide a resources continuum spectrum that takes advantage of the benefits of both technologies, cloud and edge computing. In this scenario, applications are usually decomposed for execution in sets of tasks, which are in turn encapsulated into virtual components such as containers. Containers are lightweight implementations of virtual machines, improving efficiency and portability in distributed applications. Traditional containers scheduling in cloud is a well-known problem, but when the environment is heterogeneous, as it is in the scope of edge computing and edge-cloud systems, the problem becomes more challenging. In this paper we present the Concurrent Container Clusters Scheduling problem (C3S) aimed at optimizing the problem of placing containers in clusters of heterogeneous nodes satisfying a set of resource requirements, quality of service limitations, and considering additional stringent constraints in terms of applications execution in isolation for security guaranteeing. The C3S problem has been formulated using Integer Linear Programming with the dual objective of minimizing the number of applications rejected while minimizing the number of nodes used for computation. We have evaluated the optimality of this approach, analyzed the performance in terms of solving time and, finally, created a heuristic approach to solve the problem in realistic high demanding scenarios., Peer Reviewed, Postprint (author's final draft)

In order to address high latency issues that may arise when executing timecritical applications at the cloud side, the novel fog computing paradigm has emerged, thus enabling the execution of such applications within computation nodes present at the edge of the network. While executing such applications, a user may be moving in an area where a high number of heterogeneous fog nodes (FNs) co-exist. This makes the problem of selecting the most appropriate fog node to execute the user’s tasks challenging, especially since the set of visible FNs dynamically changes. Therefore, to deal with the uncertain and dynamic nature of such a fog computing environment, we model the FN selection problem using multi-armed bandits. However, standard solutions for the bandit problem are not tailored for scenarios with changing FN availabilities. In addition, since switching from one FN to the other causes a switching cost, such solutions lead to accumulating a high switching cost. Therefore, to address these issues, we first propose a block-based FN selection scheme, where switching among FNs is not allowed during a block of timeslots. We also propose a greedy approach, where FNs having a sufficiently good delay performance are selected in a greedy manner. Simulation results reveal that both approaches significantly improve the FN selection performance. In particular, we found that the blockbased selection results in the lowest switching costs, whereas the greedy selection achieves the best overall performance., Peer Reviewed, Postprint (author's final draft)

Treball desenvolupat en el marc del programa "European Project Semester"., The 2021 EPS spring team composed of Sem, Rebekka, Bogdan, Daniel and Laurent has been working on the project proposed by the CRAAX Lab. The initially proposed name of the project was “Design of an ad-hoc adaptable sensor system for the 6MWT”. Since the scope of the project partially changed since then, the name was changed to “Medical Automated Movement Detector (MedAMD)”. The challenge is to develop a product that simplifies different tests that physicians run to know the desaturation level in patients with hypoxia, an illness in which the blood doesn’t carry enough oxygen. The CRAAX Lab has as of today two working prototypes, each specifically designed for one test. Our objective is to develop a device that is able to function for a multitude of tests, therefore facilitating the testing. In order to achieve that, we combined the technology of two devices, built by the CRAAX team and modified them so it would send data about the different movements of the patients to an already existing app, by Bluetooth. The scope of this project encompassed the analysis of the existing prototypes, conceptualizing our device, creating the overall design of both the casing of the electronic components and the strapping system to hold our device in place and build a functioning electronic circuit with the required set of sensors. The tests we are aiming to facilitate with our device require the device to be either strapped to the patient or to a cone. Ideally our device would send the data recorded by the sensors to an already existing app, via Bluetooth. As we have not had access to the existing coding and do not possess the necessary skills to code it on our own, we consider the successful bluetooth connection of our device to a bluetooth testing app (Serial Bluetooth Terminal) a measure of success. A future step to fully implement this device would be the coding necessary for the communication with an app. To conclude, we have successfully printed the redesigned casing for the e, Incoming

Nowadays IoT devices are a huge trend, present in a lot of people's routine, companies, public facilities and so on. The main reason for their raising popularity is mainly the huge range of use cases in which they can take part. This TFM is aimed at proposing and implementing an architecture able to provide security by design (having security as a premise in each designing step) withholding IoT devices in a supply chain scenario. Blockchain is the cornerstone of this project, due to the beneficious qualities it provides in regard of security. The obtained results are majorly satisfactory, battery tests indicate the performance of the proposed architecture yielding positive results yet there is room for improvement debriefed in future work section., Hoy en día, los dispositivos IoT son una gran tendencia, presente en la rutina de muchas personas, empresas, instalaciones públicas, etc. La razón principal de su creciente popularidad es principalmente la amplia gama de casos de uso en los que pueden participar. Este TFM tiene como objetivo proponer e implementar una arquitectura capaz de brindar seguridad por diseño (teniendo la seguridad como premisa en cada paso del diseño) reteniendo dispositivos IoT en un escenario de cadena de suministro. Blockchain es la piedra angular de este proyecto, debido a las beneficiosas cualidades que proporciona en materia de seguridad. Los resultados obtenidos son ampliamente satisfactorios, las pruebas de batería indican que el rendimiento de la arquitectura propuesta arroja resultados positivos, sin embargo, hay margen de mejora en la sección de trabajo futuro., Actualment, els dispositius IoT són una tendència enorme, present en moltes rutines, empreses, espais públics, etc. El principal motiu de la seva popularitat és principalment l?enorme ventall de casos d?ús en que poden formar-ne part. Aquest TFM té com a objectiu proposar i implementar una arquitectura capaç de proporcionar seguretat mitjançant el disseny (tenint la seguretat com a premissa en cada pas de disseny) retenint dispositius IoT en un escenari de cadena de subministrament. Blockchain és la pedra angular d?aquest projecte, a causa de les qualitats beneficioses que proporciona en matèria de seguretat. Els resultats obtinguts són majoritàriament satisfactoris, vàries proves indiquen el rendiment de l?arquitectura proposada donant resultats positius, tot i que hi ha marge de millora mencionat en la secció "treball futur".

Smart advertising creates awareness about some offer with a more direct, personalized and interactive focus. In this area, AROUND is a social network aimed at providing smart advertising to suggest appealing business to their customers and friends. The AROUND system is supported by a sophisticated recommender system, which considers not only the customers historical behaviours, but also their current mood and accurate location. In such smart recommendation systems, the response time for the personalized advertising is critical for a successful users’ quality of experience. In this research work we first evaluate the current performance of the AROUND system in terms of processing and communication times considering that, nowadays, this social network has more than 3 million users. The current implementation of the system relies on the deployment of a network of beacons, and uses a domestic cloud provider as the main infrastructure. We show that when the number of concurrent requests becomes too high, the response time faces some limitations. In order to address this issue, we discuss several alternatives, and propose the use of an edge-based strategy as a solution for fast response time. In the experimental section, we measure the performance of the AROUND system, both in our current infrastructure at the cloud and with an edge-based approach, and show the additional advantages of leveraging the edge-based strategy even in the case of overloading the cloud capacity., This work has been supported by the Spanish Ministry of Science, Innovation and Universities and by the European Regional Development Fund (FEDER) under contract RTI2018-094532-B-I00., Peer Reviewed, Postprint (author's final draft)

As a result of advances in technology and highly demanding users expectations, more and more applications require intensive computing resources and, most importantly, high consumption of data distributed throughout the environment. For this reason, there has been an increasing number of research efforts to cooperatively use geographically distributed resources, working in parallel and sharing resources and data. In fact, an application can be structured into a set of tasks organized through interdependent relationships, some of which can be effectively executed in parallel, notably speeding up the execution time. In this work a model is proposed aimed at offloading tasks execution in heterogeneous environments, considering different nodes computing capacity connected through distinct network bandwidths, and located at different distances. In the envisioned model, the focus is on the overhead produced when accessing remote data sources as well as the data transfer cost generated between tasks at run-time. The novelty of this approach is that the mechanism proposed for tasks allocation is data-flow aware, considering the geographical location of both, computing nodes and data sources, ending up in an optimal solution to a highly complex problem. Two optimization strategies are proposed, the Optimal Matching Model and the Staged Optimization Model, as two different approaches to obtain a solution to the task scheduling problem. In the optimal model approach a global solution for all application’s tasks is considered, finding an optimal solution. Differently, the staged model approach is designed to obtain a local optimal solution by stages. In both cases, a mixed integer linear programming model has been designed intended to minimizing the application execution time. In the studies carried out to evaluate this proposal, the staged model provides the optimal solution in 76% of the simulated scenarios, while it also dramatically reduces the solving time with respect to o, Peer Reviewed, Postprint (author's final draft)

The specific demands of supply chains built upon large and complex IoT systems, make it a must to design a coordinated framework for cyber resilience provisioning, intended to guarantee trusted supply chains of ICT systems, built upon distributed, dynamic, potentially insecure, and heterogeneous ICT infrastructures. As such, the solution proposed in this paper is envisioned to deal with the whole supply chain system components, from the IoT ecosystem to the infrastructure connecting them, addressing security and privacy functionalities related to risks and vulnerabilities management, accountability, and mitigation strategies, as well as security metrics and evidence-based security assurance. In this paper, we present FISHY as a preliminary architecture that is designed to orchestrate existing and beyond state-of-the-art security appliances in composed ICT scenarios. To this end, the FISHY architecture leverages the capabilities of programmable networks and IT infrastructure through seamless orchestration and instantiation of novel security services, both in real-time and proactively. The paper also includes a thorough business analysis to go far beyond the technical benefits of a potential FISHY adoption, as well as three real-world use cases highlighting the envisioned benefits of a potential FISHY adoption., This research was funded by H2020 FISHY Project, grant number 952644, and for UPC authors by the Spanish Ministry of Science, Innovation and Universities and FEDER, grant number RTI2018-094532-B-I00., Peer Reviewed, Postprint (published version)

DCRoutes es una aplicación web, destinada a ser integrada en un proyecto colaborativo entre el CRAAX y el Hospital Clínic de Barcelona. Uno de los componentes de ese proyecto se centra en facilitar a los médicos, el hecho de poder evaluar a un conjunto de pacientes con problemas respiratorios, con el objetivo de que puedan mejorar su capacidad pulmonar tras una serie de ejercicios. DCRoutes en concreto, tiene como objetivo, ofrecer la posibilidad de crear rutas en una zona geográfica específica. Una vez se genera una ruta, el sistema automáticamente la analizará en base a un conjunto de aspectos como elevaciones, distancia, duración aproximada, etc.,para de esta manera asignar una dificultad a dicha ruta. Pensando en el esquema general del proyecto, una vez el doctor esté con un paciente para asignarle una ruta, podrá utilizar la solución propuesta en este proyecto para bien analizar las rutas ya creadas por otro doctor o por él mismo y reutilizar alguna ruta para asignarla a su paciente, o bien podrá crear nuevas rutas/zonas para poder adecuarse mejor a las necesidades de este. Así, las rutas podrían acomodar necesidades propias del paciente como por ejemplo, el hecho que al paciente le gustara realizar dichas rutas en su zona de residencia y que además el origen de las mismas fuera el domicilio particular del paciente.. Gracias a una serie de reuniones con el resto del equipo del CRAAX y los médicos del Clínic de Barcelona, hemos ido integrando nuevas ideas y el proyecto ha ido evolucionando con las diferentes versiones. Tras estos meses de trabajo y las reuniones realizadas, se considera el resultado final satisfactorio de acuerdo a los objetivos iniciales planteados., DCRoutes is a web application designed to integrate with a collaborative project between CRAAX and Hospital Clínic de Barcelona. The aim of the project is to facilitate the evaluation of patients with respiratory problems in order to improve their lung capacity by a series of exercises. DCRoutes' specific objective is to make it possible to create routes in certain zones saved in the system. Once a route is generated, the system automatically analyses it, based on a set of values such as elevation, distance, approximate duration and more. The final analysis serves to assign a suitable difficulty to the associated track. Regarding the general scheme of the project, the doctor assigning a route to the patient will use our system to analyse routes already created by himself or another doctor/physiotherapist, and he will subsequently allocate the selected route to the patient. Also, as a second option, the doctor is able to create new tracks or choose new zones so as to adjust the route according to the needs of the person. For instance, if the patient would like to carry out all the routes in his area of residence. In addition, the origin of each route is the house of the patient. Throughout the memory, every stage of the process is presented step by step, along with indicated new features implemented in each new version of the project. In addition, we briefly reflect on what these new features provide, both in terms of the usability of the application and the functionalities to improve the creation of exercises for the patients. Thanks to the series of meetings with the rest of the CRAAX team and the doctors at the Barcelona Clinic, we have integrated new ideas and the project has gradually evolved from implementing new features. After months of work and sessions held, the final result is considered satisfactory and useful for hospitals.

Treball desenvolupat en el marc del programa "European Project Semester"., This report presents the outcome of a study towards enhancing the performance of a smart car and the testbed. The conducted study involved the design of a smart car, that would drive by itself on a testbed. Literature review has shown that there are existing similar systems, in which the purpose was to enhance functionalities like lane control, drive control and obstacle avoidance. Combining the different functionalities enhancement, a final proposition design is stated for future work., Incoming

Better resource utilization is a continuous demand for smart computing paradigm. Fog-to-Cloud (F2C) is emerging to satisfy that need. Adopting machine-learning (ML) techniques help F2C to priorly forecast system resource usage and performance, for keeping its promise towards better resource management. Performing ML techniques for predicting the resource usage and performance needs historical data of system resources. Processing over that data for extracting the knowledge is one of the essential steps in ML techniques. Based on the obtained knowledge, prediction model is built to perform forecasting operation. This course can be done either in a logically centralized location (cloud) or distributed locations. Due to data privacy issues and bandwidth limitation, it is often an impractical and massively resource-consuming job to continuously send those historical data to the centralized location. Also, the local execution of these operations reduces service latency for any time-sensitive applications. Considering these and observing F2C computing facilities, we realize to build a new architectural framework for adaptively managing F2C resources. In this framework, we implemented a globally coordination-based distributed learning and prediction mechanism for accurately forecasting the resource usage (i.e., RAM, CPU, Disk) and execution-time (performance) for achieving some tasks. Finally, performing comparative tests between our proposed framework and centralized learning and prediction based computing framework, shows our proposed framework outperforms over the centralized framework, in terms of prediction accuracy. Also, we found that in our proposed framework, the overall bandwidth utilization reduces by one-third, and data transmission time becomes lower by half to the centralized framework., Postprint (published version)

Safety and security of Industrial Control Systems (ICS) applied in many critical infrastructures is essential. In these systems, hazards can be due either to system failure or cyber-attacks factors. Accurate hazard detection and reducing reconfiguration time after hazard is one of the most important objectives in these systems. One of the procedures that can reduce the reconfiguration time is determining the cause of hazards and, based on the aforementioned factors, adopting the best commands in reconfiguration time. However, it is difficult to differentiate between different types of hazard because their effects on the system can be similar. With the advent of IoT into ICS, known as IIoT, it has become possible to differentiate the hazards through the adoption of data from different IIoT sensors in the environment. In this article, we propose a risk management approach that identifies hazards based on the physical nature of these systems with the support from the IIoT. The identified hazards fall into four categories: stealthy attack, random attack, transient failure, and permanent failure. Then, the reconfiguration process is run based on the proposed differentiation, which provides a better performance and reconfiguration time. In the experimental section, a fluid storage system is simulated, showing 97% correct differentiation of hazards and reducing in 60% the lost time in the system recovery reconfiguration., This work is supported by the Spanish Ministry of Economy and Competitiveness and by the European Regional Development Fund under Contract RTI2018-094532-B-I00 (MINECO/FEDER)., Peer Reviewed, Postprint (published version)

The recent development of delay-sensitive applications has led to the emergence of the fog computing paradigm. Within this paradigm, computation nodes present at the edge of the network can act as fog nodes (FNs) capable of processing users' tasks, thus resulting in latency reductions compared to the existing cloud-based execution model. In order to realize the full potential of fog computing, new research questions have arised, mainly due to the dynamic and heterogeneous fog computing context. This thesis focuses on the following questions in particular: How can a user detect the presence of a nearby FN? How should a user on the move adapt its FN discovery strategy, according to its changing context? How should an FN be selected , in the case of user mobility and FN mobility? These questions will be addressed throughout the different contributions of this thesis. The first contribution consists in proposing a discovery solution allowing a user to become aware of the existence of a nearby FN. Using our solution, the FN advertizes its presence using custom WiFi beacons, which will be detected by the user via a scan process. An implementation of this approach has been developed and its evaluation results have shown that it results in a non-negligible energy consumption given its use of WiFi. This has led to our second contribution, which aims at improving the WiFi scan performed in our discovery approach, especially in the case of user mobility. At a first stage, this improvement consisted in embedding information about the topology of the FNs in the beacons the user receives from previous FNs. We have shown that by adapting the scan behavior based on this information, considerable energy savings can be achieved, while guaranteeing a high discovery rate. However, as this approach is associated with a restrictive FN topology structure, we proposed a different alternative, at a second stage. This alternative leverages the history of cellular context information as an in, El recent desenvolupament d'aplicacions IoT ha comportat l'aparició del paradigma de fog computing. Dins d'aquest paradigma, els nodes de càlcul presents a la vora de la xarxa poden actuar com a “fog nodes'' (FN) capaços de processar les tasques dels usuaris, produint així reduccions de latència en comparació amb el model d'execució basat en núvol. Per assolir tot el potencial del fog computing, han sorgit noves qüestions de recerca, principalment a causa del context dinàmic i heterogeni de fog computing. Aquesta tesi se centra especialment en les qüestions següents: Com pot un usuari detectar la presència d'un FN? Com hauria d’adaptar un usuari en moviment la seva estratègia de descobriment de FN, segons el seu context? Com s’ha de seleccionar un FN, en el cas de la mobilitat dels usuaris i la mobilitat FN? Aquestes preguntes s’abordaran al llarg de les diferents aportacions d’aquesta tesi. La primera contribució consisteix a proposar una solució de descobriment que permeti a l'usuari detectar l’existència d’un FN proper. Mitjançant la nostra solució, un FN anuncia la seva presència mitjançant beacons Wi-Fi personalitzats, que seran detectats per l'usuari mitjançant un procés d’exploració. S'ha desenvolupat una implementació d'aquest enfocament i els seus resultats d’avaluació han demostrat que resulta en un consum d'energia menyspreable donat el seu ús del Wi-Fi. Això ha suposat la nostra segona contribució, que té com a objectiu millorar l’exploració Wi-Fi, especialment en el cas de la mobilitat dels usuaris. En una primera fase, aquesta millora va consistir a incorporar informació sobre la topologia dels FN en les beacons que rep l'usuari dels FN anteriors. Hem demostrat que mitjançant l'adaptació del comportament d'escaneig basat en aquesta informació es pot aconseguir un estalvi considerable d’energia, alhora que es garanteix un índex elevat de descobriment. Tanmateix, com aquest enfocament s'associa a una estructura de topologia FN restrictiva, vam proposar u, Postprint (published version)

© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., Industrial control systems (ICS) are applied in many critical infrastructures. Reducing reconfiguration time after hazard leads to safety improvement, so it is one of the most important objectives in these systems. Hazards can be due to the “system failure” or “cyber-attacks” factors. One of the procedures that can reduce the reconfiguration time is determining as soon as possible the cause of hazards based on the above mentioned factors. Differentiation of attack from failure without redundant data in addition to data from the system sensors is not possible. With advent of the IoT as IIoT, a condition is developed to provide the required redundant data; however, by increasing the number of IIoT devices within a factory, the generated data volume becomes too large. In this paper we describe a fog-based approach applied in a factory to deal with such increasing complexity. We compare the proposed method with a traditional cloud-based solution. According to the results, the proposed method leads to a reduction of 60% lost time in the recovery reconfiguration step of the system., Peer Reviewed, Postprint (author's final draft)

Technology in the twenty-first century is rapidly developing and driving us into a new smart computing world, and emerging lots of new computing architectures. Fog-to-Cloud (F2C) is among one of them, which emerges to ensure the commitment for bringing the higher computing facilities near to the edge of the network and also help the large-scale computing system to be more intelligent. As the F2C is in its infantile state, therefore one of the biggest challenges for this computing paradigm is to efficiently manage the computing resources. Mainly, to address this challenge, in this work, we have given our sole interest for designing the initial architectural framework to build a proper, adaptive and efficient resource management mechanism in F2C. F2C has been proposed as a combined, coordinated and hierarchical computing platform, where a vast number of heterogeneous computing devices are participating. Notably, their versatility creates a massive challenge for effectively handling them. Even following any large-scale smart computing system, it can easily recognize that various kind of services is served for different purposes. Significantly, every service corresponds with the various tasks, which have different resource requirements. So, knowing the characteristics of participating devices and system offered services is giving advantages to build effective and resource management mechanism in F2C-enabled system. Considering these facts, initially, we have given our intense focus for identifying and defining the taxonomic model for all the participating devices and system involved services-tasks. In any F2C-enabled system consists of a large number of small Internet-of-Things (IoTs) and generating a continuous and colossal amount of sensing-data by capturing various environmental events. Notably, this sensing-data is one of the key ingredients for various smart services which have been offered by the F2C-enabled system. Besides that, resource statistical information i, La tecnologia del segle XXI avança ràpidament i ens condueix cap a un nou món intel·ligent, creant nous models d'arquitectures informàtiques. Fog-to-Cloud (F2C) és un d’ells, i sorgeix per garantir el compromís d’acostar les instal·lacions informàtiques a prop de la xarxa i també ajudar el sistema informàtic a gran escala a ser més intel·ligent. Com que el F2C es troba en un estat preliminar, un dels majors reptes d’aquest paradigma tecnològic és gestionar eficientment els recursos informàtics. Per fer front a aquest repte, en aquest treball hem centrat el nostre interès en dissenyar un marc arquitectònic per construir un mecanisme de gestió de recursos adequat, adaptatiu i eficient a F2C.F2C ha estat concebut com una plataforma informàtica combinada, coordinada i jeràrquica, on participen un gran nombre de dispositius heterogenis. La seva versatilitat planteja un gran repte per gestionar-los de manera eficaç. Els serveis que s'hi executen consten de diverses tasques, que tenen requisits de recursos diferents. Per tant, conèixer les característiques dels dispositius participants i dels serveis que ofereix el sistema és un requisit per dissenyar mecanismes eficaços i de gestió de recursos en un sistema habilitat per F2C. Tenint en compte aquests fets, inicialment ens hem centrat en identificar i definir el model taxonòmic per a tots els dispositius i sistemes implicats en l'execució de tasques de serveis. Qualsevol sistema habilitat per F2C inclou en un gran nombre de dispositius petits i connectats (conegut com a Internet of Things, o IoT) que generen una quantitat contínua i colossal de dades de detecció capturant diversos events ambientals. Aquestes dades són un dels ingredients clau per a diversos serveis intel·ligents que ofereix F2C. A més, el seguiment continu dels dispositius participants genera igualment una gran quantitat d'informació estadística. En particular, en tenir aquesta informació, es fa molt més fàcil conèixer la disponibilitat i la idoneïtat dels, Postprint (published version)

The evolution of the Internet of Things (IoT) is imposing many distinct challenges, particularly to guarantee both wide and global systems communication, and to ensure an optimal execution of services. To that end, IoT services must make the most out of both cloud and fog computing (turning into combined fog–cloud scenarios), which indeed requires novel and efficient resource management procedures to handle such diversity of resources in a coordinated way. Most of the related works that can be found in the literature focus on resource mapping for service-specific execution in fog–cloud; however, those works assume a control and management architecture already deployed. Interestingly, few works propose algorithms to set that control architecture, necessary to execute the services and effectively implement services and resource mapping. This paper addresses that challenge by solving the problem of optimal clustering of devices located at the edge of the network offering their resources to support fog computing while defining the control and management role of each of them in the architecture, in order to ensure access to management functions in combined fog–cloud¿ scenarios. In particular, we set out the Fog–Cloud Clustering (FCC) problem as an optimization problem, which is based on multi-objective optimization, including realistic, novel and stringent constraints; e.g., to improve the architecture’s robustness by means of a device acting as a backup in the cluster. We model the FCC problem as a Mixed Integer Linear Programming (MILP) formulation, for which a lower and an upper bound on the number of required clusters is derived. We also propose a machine learning-based heuristic that provides scalable and near-optimal solutions in realistic scenarios in which, due to the high number of connected devices, solving the MILP formulation is not viable. By means of a simulation study, we demonstrate the effectiveness of the algorithms comparing its results with those of M, Peer Reviewed, Postprint (author's final draft)

The fog/edge computing concept has set the foundations for the deployment of new services leveraging resources deployed at the edge paving the way for an innovative collaborative model, where end-users may collaborate with service providers by sharing idle resources at the edge of the network. Combined Fog-to-Cloud (F2C) systems have been recently proposed as a control strategy for managing fog and cloud resources in a coordinated way, aimed at optimally allocating resources within the fog-to-cloud resources stack for an optimal service execution. In this work, we discuss the unfeasibility of the deployment of a single control topology able to optimally manage a plethora of edge devices in future networks, respecting established SLAs according to distinct service requirements and end-user profiles. Instead, a multidimensional architecture, where distinct control plane instances coexist, is then introduced. By means of distinct scenarios, we describe the benefits of the proposed architecture including how users may collaborate with the deployment of novel services by selectively sharing resources according to their profile, as well as how distinct service providers may benefit from shared resources reducing deployment costs. The novel architecture proposed in this paper opens several opportunities for research, which are presented and discussed at the final section., This work was supported by the H2020 EU mF2C project, ref. 730929 and for UPC authors, also by the Spanish Ministry of Economy and Competitiveness and the European Regional Development Fund under contract RTI2018-094532-B-I00., Peer Reviewed, Postprint (author's final draft)

Treball desenvolupat en el marc del programa "European Project Semester"., In the future, many problems may develop due to the steadily increasing population. Some of these are already noticeable. In order to solve space shortages, traffic jams, air pollution, shortages in water, electricity and food supply and other burgeoning problems, infrastructures must be digital and intelligent at the same time. These adapted cities are called smart cities. However, just like with any innovation, research needs to be carried out prior to any implementation. It's for this reason that CRAAX, an architectural research center, has created a smart city test bench. This is a model smart city with multiple autonomous inputs (for example buildings and bridges) that test the communication management network CRAAX has been working on for the last two years. By adding more variables, they can thoroughly test their management system in a more realistic setting. The goal of our team is to continue their development by adding yet another variable, an automated parking garage with an RFID barrier, to the Smart City testbench that CRAAX is developing. We had to make sure the designs contained the requirements set by CRAAX. These requirements were: a lift for the RC cars, a barrier controlled by RFID and the parking structure needs to fit in limited space. In this report, the research, design, building and finishing of the project are described., Incoming

© 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes,creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works, The inherent mobility characterizing users in fog computing environments along with the limited wireless range of their serving fog nodes (FNs) drives the need for designing efficient mobility management (MM) mechanisms. This ensures that users' resource-intensive tasks are always served by the most suitable FNs in their vicinity. However, since MM decisionmaking requires control information which is difficult to predict accurately a-priori, such as the users' mobility patterns and the dynamics of the FNs, researchers have started to shift their attention towards MM solutions based on online learning. Motivated by this approach, in this paper, we consider a bandit learning model to address the mobility-induced FN selection problem, with a particular focus on scenarios with a high FN density. Following this approach, a software agent implemented within the user's device learns the FNs' delay performances via trial and error, by sending them the user's computation tasks and observing the perceived delay, with the goal of minimizing the accumulated delay. This task is particularly challenging when considering a high FN density, since the number of unknown FNs that need to be explored is high, while the time that can be spent on learning their performances is limited, given the user's mobility. Therefore, to address this issue, we propose to limit the number of explorations to a small subset of the FNs. As a result, the user can still have time to be served by the FN that was found to yield the lowest delay performance. Using real world mobility traces and task generation patterns, we found that it pays off to limit the number of explorations in high FN density scenarios. This is shown through significant improvements in the cumulative regret as well as the instantaneous delay, compared to the case where all newly-appeared FNs are explored., Peer Reviewed, Postprint (author's final draft)

© 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., The Fog-to-Cloud (F2C) paradigm is emerging to both provide higher functional efficiency for latency-sensitive services and also help modern computing systems to be more intelligent. As it is still in its infancy, the biggest challenge for this domain is to build a proper resource allocation technique as part of an efficient resource management module. The diversified and distributed nature of that paradigm creates some additional hurdles for choosing the appropriate resources for executing some tasks. Significantly, efficient resource consumption estimation and performance forecasting are core issues in the design and development of a proper and smart resource management mechanism for F2C systems. Considering this fact, in this paper, we aim at designing an architectural framework for a prediction-based resource management mechanism for F2C systems. The performance prediction is based on supervised machine learning technology. The proposal has been evaluated and validated by predicting the performance and resources usage of F2C resources through several tests. Primarily, we have run an image recognition application on different F2C resources and collected performance-related information and resource consumption information. Then, by adopting the multivariate regression methodology, we perform some standard machine learning techniques to predict the performance and estimate the resource consumption of the F2C resources. Finally, to justify the effectiveness of our proposal, we calculated the value of a cost function between estimated values and the real measured values., This work has been supported by the Spanish Ministry of Science, Innovation and Universities and the European Regional Development Fund (FEDER) under contract RTI2018- 094532-B-I00, and by the H2020 European Union mF2C project with reference 730929., Peer Reviewed, Postprint (author's final draft)

Several efforts are currently active in dealing with scenarios combining fog, cloud computing, out of which a significant proportion is devoted to control, and manage the resulting scenario. Certainly, although many challenging aspects must be considered towards the design of an efficient management solution, it is with no doubt that whatever the solution is, the quality delivered to the users when executing services and the security guarantees provided to the users are two key aspects to be considered in the whole design. Unfortunately, both requirements are often non-convergent, thus making a solution suitably addressing both aspects is a challenging task. In this paper, we propose a decoupled transversal security strategy, referred to as DCF, as a novel architectural oriented policy handling the QoS-Security trade-off, particularly designed to be applied to combined fog-to-cloud systems, and specifically highlighting its impact on the delivered QoS., Peer Reviewed, Postprint (published version)

Nowadays, by increasing the number of connected devices to Internet rapidly, cloud computing cannot handle the real-time processing. Therefore, fog computing was emerged for providing data processing, filtering, aggregating, storing, network, and computing closer to the users. Fog computing provides real-time processing with lower latency than cloud. However, fog computing did not come to compete with cloud, it comes to complete the cloud. Therefore, a hierarchical Fog-to-Cloud (F2C) continuum system was introduced. The F2C system brings the collaboration between distributed fogs and centralized cloud. In F2C systems, one of the main challenges is security. Traditional cloud as security provider is not suitable for the F2C system due to be a single-point-of-failure; and even the increasing number of devices at the edge of the network brings scalability issues. Furthermore, traditional cloud security cannot be applied to the fog devices due to their lower computational power than cloud. On the other hand, considering fog nodes as security providers for the edge of the network brings Quality of Service (QoS) issues due to huge fog device’s computational power consumption by security algorithms. There are some security solutions for fog computing but they are not considering the hierarchical fog to cloud characteristics that can cause a no-secure collaboration between fog and cloud. In this thesis, the security considerations, attacks, challenges, requirements, and existing solutions are deeply analyzed and reviewed. And finally, a decoupled security architecture is proposed to provide the demanded security in hierarchical and distributed fashion with less impact on the QoS., Hoy en día, al aumentar rápidamente el número de dispositivos conectados a Internet, el cloud computing no puede gestionar el procesamiento en tiempo real. Por lo tanto, la informática de niebla surgió para proporcionar procesamiento de datos, filtrado, agregación, almacenamiento, red y computación más cercana a los usuarios. La computación nebulizada proporciona procesamiento en tiempo real con menor latencia que la nube. Sin embargo, la informática de niebla no llegó a competir con la nube, sino que viene a completar la nube. Por lo tanto, se introdujo un sistema continuo jerárquico de niebla a nube (F2C). El sistema F2C aporta la colaboración entre las nieblas distribuidas y la nube centralizada. En los sistemas F2C, uno de los principales retos es la seguridad. La nube tradicional como proveedor de seguridad no es adecuada para el sistema F2C debido a que se trata de un único punto de fallo; e incluso el creciente número de dispositivos en el borde de la red trae consigo problemas de escalabilidad. Además, la seguridad tradicional de la nube no se puede aplicar a los dispositivos de niebla debido a su menor poder computacional que la nube. Por otro lado, considerar los nodos de niebla como proveedores de seguridad para el borde de la red trae problemas de Calidad de Servicio (QoS) debido al enorme consumo de energía computacional del dispositivo de niebla por parte de los algoritmos de seguridad. Existen algunas soluciones de seguridad para la informática de niebla, pero no están considerando las características de niebla a nube jerárquica que pueden causar una colaboración insegura entre niebla y nube. En esta tesis, las consideraciones de seguridad, los ataques, los desafíos, los requisitos y las soluciones existentes se analizan y revisan en profundidad. Y finalmente, se propone una arquitectura de seguridad desacoplada para proporcionar la seguridad exigida de forma jerárquica y distribuida con menor impacto en la QoS., Postprint (published version)

The final publication is available at ACM via http://dx.doi.org/10.1145/3326540, With the advent of fog and edge computing paradigms, computation capabilities have been moved toward the edge of the network to support the requirements of highly demanding services. To ensure that the quality of such services is still met in the event of users’ mobility, migrating services across different computing nodes becomes essential. Several studies have emerged recently to address service migration in different edge-centric research areas, including fog computing, multi-access edge computing (MEC), cloudlets, and vehicular clouds. Since existing surveys in this area focus on either VM migration in general or migration in a single research field (e.g., MEC), the objective of this survey is to bring together studies from different, yet related, edge-centric research fields while capturing the different facets they addressed. More specifically, we examine the diversity characterizing the landscape of migration scenarios at the edge, present an objective-driven taxonomy of the literature, and highlight contributions that rather focused on architectural design and implementation. Finally, we identify a list of gaps and research opportunities based on the observation of the current state of the literature. One such opportunity lies in joining efforts from both networking and computing research communities to facilitate future research in this area., Peer Reviewed, Preprint

In the recent years, the majority of the world’s Critical Infrastructures (CIs) have evolved to be more flexible, cost efficient and able to offer better services and conditions for business growth. Through this evolution, CIs and companies offering CI services had to adopt many of the recent advances CIPSEC-Enhancing Critical Infrastructure Protection of the Information and Communication Technologies (ICT) field. This rapid adaptation however, was performed without thorough evaluation of its impact on CIs’ security. It resulted into leaving CIs vulnerable to a new set of threats and vulnerabilities that impose high levels of risk to the public safety, economy and welfare of the population. To this extend, the main approach for protecting CIs includes handling them as comprehensive entities and offer a complete solution for their overall infrastructures and ICT systems (IT&OT departments). However, complete CI security solutions exist, in the form of individual products from IT security companies. These products, integrate only in-house designed and developed tools/solutions, thus offering a limited range of technical solutions. The main aim of CIPSEC is to create a unified security framework that orchestrates state-of-the-art heterogeneous security products to offer high levels of protection in IT (information technology) and OT (operational technology) departments of CIs, also offering a complete security ecosystem of additional services. These services include vulnerability tests and recommendations, key personnel training courses, public-private partnerships (PPPs), forensics analysis, standardization activities and analysis against cascading effects., Peer Reviewed, Postprint (published version)