Academic Supervisor:
Ainhoa Rezola

department:
Electrical and Electronic Engineering

Description and objectives:

This project embarks on the cutting edge of technology in collaboration with the Massachusetts Institute of Technology (MIT). It focuses on exploring revolutionary chipless technology for the Internet of Things (IoT), with particular emphasis on frequency coded (FC) chipless tags. These tags, recognized for their economic attractiveness and sensing capabilities, present challenges in terms of sensing and processing.

The proposal involves the use of a device known as Software-Defined Radio (SDR) to carry out measurements and collect data from the tags. The project proposes to apply signal processing techniques with the goal to improve the quality of the information obtained. Also, the potential of Machine Learning (ML) algorithms will be explored to classify more efficiently these tags, thus improving the identification capability.

It is important to note that the reader required for these tasks has already been previously developed, so the main focus will be on the measurement, processing and classification phases. The importance of antennas, fundamental elements in wireless communications, will also be addressed, contributing to the improvement of signal quality and, therefore, to the efficiency of the system.

Academic Supervisor:
Enrique Castaño Carmona

Division CEIT:
Advance Powder Metallurgy and Laser Manufacturing Group

area thematic:
Computing, modeling and simulation

Description and objectives:
The machining of materials using ultra-short pulse lasers is a very recent technology development and opens multiple possibilities in the field of functional surfaces, such as low friction coefficient surfaces in wind turbines or anti-icing surfaces in aeronautics. 

Currently, Ceit is leading a European project in which one of its objectives is to develop a simulation software for the machining process with this subject of lasers. The mathematical modeling of the process is already well advanced, as well as its numerical implementation.
The task of this PFG will be to design and develop the graphical interface with the Username of the simulation program so that its use is easy and intuitive. The student will apply and extend his knowledge of Python programming, GUI (Graphic User Interface) and design UX/UI (User Experience/User Interface) to achieve an interface that allows Username an attractive experience of the simulation program.

Academic Supervisor:
Santiago Figueroa Lorenzo

Division CEIT:
ICT Division. Group of data analysis and Information Management

area thematic:
development software development, DevOps.

Description:
In the DevOps world, it is critical to deploy infrastructure as code (IaC), as it provides a way to automate infrastructure management and provisioning. For this purpose, one of the most popular tools is Terraform, which allows deploying infrastructure to a wide range of providers in a simple and effective way. On the other hand, in most of the projects where this methodology is applied, it is essential to have virtual machines dedicated to development, which have a lifespan equal to that of project or some phase of project. In this case, the machines will be created on a Proxmox server. In order to manage these virtual machines using Terraform, it is necessary to build an API with the financial aid of Swagger (OpenAPI) that allows to connect it with the Proxmox server.

Objectives:
Develop the API to be able to automate the creation and deletion of these machines; learning along the project tools such as Jira, Gitlab/Github, Swagger, Terraform or Proxmox.

Academic Supervisor:
Santiago Figueroa Lorenzo

Division CEIT:
ICT Division. Group of data analysis and Information Management

area Thematic:
5G, development software, Cloud Computing.

Description:
The project has as goal to design and implement a network 5G platform based on Amarisoft and Open Source MANO (OSM) to deliver Network-as-a-Service (NaaS) services. The platform will provide an API using Swagger, which will enable the deployment and management of core topic components of the network 5G, including 5G cores, gnB, VMs, UE, a Prometheus server and Kubernetes related resources. This solution will enable agile and flexible deployment of 5G services, improving the efficiency and adaptability of network.

Objectives: 

• Design and implement a 5G network using the Amarisoft solution, which enables wireless connection of 5G devices and provides optimal performance of the network.

• Use Open Source MANO (OSM) as the orchestrator of the network, to facilitate the implementation and management of the network 5G resources.

• Apply the Network-as-a-Service (NaaS) concept to offer network services on demand, allowing users to consume resources and capabilities from network in a flexible and scalable manner.

• Develop an API using Swagger for managing and deploying components of the network 5G, including 5G cores, gnB, VMs, UE, a Prometheus server and Kubernetes related resources.

Academic Supervisor:
Santiago Figueroa Lorenzo

Division CEIT:
ICT Division. Group of data analysis and Information Management

area thematic:
development Software, Security.

Description and Objectives:
CI/CD is increasingly popular in embedded software development . However, projects are often constrained in a way that they are not in the development of applications (e.g., web). In addition to the physical and computational limitations of the target hardware platform, there are market limitations. The embedded software market has unique requirements security, privacy, and extremely long life cycles (e.g., products can remain on the market for decades). At the level of development, embedded software is not much different than development from typical applications (e.g., web), requiring IDEs, compilers, static and dynamic analysis and dynamics tools. However, the tools typically address architectures on which they work (host vs. target environment). Compiler-level automation uses the same techniques, but when code execution is involved, the host/target barrier becomes significant. Code execution automation requires special support development of software. Software test automation is more challenging due to the complexity of initiating and testing on embedded targets, not to mention the limited limited access to the target hardware that software teams have. This project, aims to carry out a first approach to the basic development CI/CD on embedded systems. Thus, given a basic development in C/C++, it is intended to pass this code through stages of testing, security checks and compilation (CI), to then perform an automated submission on a device (e.g. a microcontroller), but not before also performing functional testing (CD).

Academic Supervisor:
Santiago Figueroa Lorenzo 

Division CEIT:
ICT Division. Group of data analysis and Information Management 

area subject:
Machine Learning, Security. 

Description and objectives:
Anomaly detection plays a critical role in countless different fields. In an increasingly connected world, early identification of unusual activity has become a priority for businesses and organizations. Advances in Machine Learning have revolutionized the way we approach anomaly detection, enabling the identification of unwanted patterns more effectively and efficiently. Therefore, this project seeks the development and verification of these cutting-edge algorithms.

Tasks:

• Bibliographic review and selection of algorithms to be implemented.

• Model implementation.

• Evaluation and comparison of the performance of the developed algorithms.

• Interpretation of results.

Academic Supervisor:
Santiago Figueroa Lorenzo

Division CEIT:
ICT Division. Group of data analysis and Information Management

area subject:
Security, development software, Authentication, FIDO2, Authorization, Oauth2.

Description and objectives:
The use of passwords as an element of authentication of the systems, present weaknesses, related to the limited human capacity to retain long chains of characters, at the same time that it is susceptible to different types of attacks such as brute force attacks. This has gradually led to the emergence of tools and schemes that complement the exclusive use of passwords. By default, an authentication system must be composed of "something we know", for example, a password or a PIN code, "something we possess", for example, a card from credit or an RSA token, or "something we are" (biometric authentication), such as the shape of our hand or fingerprint.

This project consists of implementing a biometric authentication system based on the FIDO 2 standard, which leads to the design and implementation of a wallet for credential storage that interacts with an authentication and authorization system composed of Identity Providers, Policy Enforcement Points (PEP) Proxies and Authorization Servers.

Academic Supervisor:
Santiago Figueroa Lorenzo

Division CEIT:
ICT Division. Group of data analysis and Information Management

area thematic:
development Software, Security.

Description and objectives:
MLOps makes reference letter to the practices and techniques used to streamline and manage the lifecycle of machine learning models in production environments. It combines software engineering, data engineering, and operations principles to ensure efficient and reliable deployment, monitoring, and management of ML models at scale. However, current MLOps tools lack a component core topic: modern, powerful and up-to-date algorithms. Therefore, one of the main objectives of this project will be the integration of ML algorithms that can be verified and integrated into an MLOps flow. The MLOps flow will use KubeFlow for deploying a Kubernetes cluster, MinIO for object storage and Kubeflow for ML pipelines and model inference. Once the MLOps flow is implemented, the second part of project will focus on development security testing on the generated CI/CD pipelines.

Academic Supervisor:
Santiago Figueroa Lorenzo

Division CEIT:
ICT Division. Group of data analysis and Information Management

area thematic:
development Software, Privacy, Code Automation, Containers.

Description and objectives:
Fides is an open source privacy management platform for enforcing privacy standards at the code level. Fides tools allows to tag system privacy features, orchestrate programmatic rights enforcement and audit staff identifiable information stored in all systems and application infrastructures. Fides in turn supports all major privacy regulations (e.g. GDPR, CCPA and LGPD), and standards such as ISO 19944 by default.

This project seeks the automated implementation of the Fides platform in a practical use case, so that a consistent and versioned definition of the privacy features and resources of this system can be created and used as part of a CI/CD pipeline to process privacy requests.

Academic Supervisor:
Santiago Figueroa Lorenzo

Division CEIT:
ICT Division. Group of data analysis and Information Management

area thematic:
development Software, Security.

Description and Objectives:
Much of cybersecurity performance begins with proper risk assessment. For this reason, Cybersecurity Risk Assessment Tools (CRATs) are widely used today. For example, NIST recommends tools such as FacilityCyber for industrial environments. The main shortcomings associated with these tools are that many of them are passive, i.e., the enterprise fills out extensive forms to obtain information from the network and the assets, from which it performs the asset risk analysis. This scenario makes the result not 100% reliable. On the other hand, we have tools with an active behavior, i.e. that integrate services from finding, from which they are able to analyze vulnerabilities and the current establishment of the structure of the network (e.g. the tool FOCA). However, these tools do not integrate the risk analysis characteristic of passive tools, in addition to not being able to define zones and behaviors from an existing network in a way that reduces the exposed surface of assets. This project aims to develop a CRAT for industrial environments and, therefore, based on the rule IEC 62443, able to solve the mentioned problems.

Academic Supervisor:
Santiago Figueroa Lorenzo

Division CEIT:
ICT Division. Group of data analysis and Information Management

area thematic:
development Software, Security.

Description and objectives:
Monitoring and observability tools are widely used nowadays to have a control of the processes running in our Kubernetes cluster. Most of these tools only provide basic monitoring and observability of the Kubernetes cluster, but few of them apply detection and countermeasure. This scenario makes the ability to monitor the protection of a cluster against attacks very difficult leave. On the other hand, we have tools that offer finding of attacks and alerts, but without applying any countermeasure on it. This project has as goal the development of an alert, finding and countermeasure tool for industrial environments, and the integration of this tool with third party tools, capable of solving the above mentioned problems. These functionalities should be integrated into a custom Kubernetes cluster to monitor and protect the cluster from external attacks.

Academic Supervisor:
Santiago Figueroa Lorenzo

Division CEIT:
ICT Division. Group of data analysis and Information Management

area Thematic:
5G, Kubernetes, Cloud Computing, Virtualization.

Description and Objectives:
The adoption of Cloud Native in 5G telecom systems has been identified as a good candidate to reduce cost, improve system agility and the role of 5G services. Based on the 3GPP standard, the European Telecommunications Standards Institute (ETSI) has published the reference letter architecture of NFV tailored to Cloud Native environments and to enhance the framework of NFV, including, containers, load balancers and other elements as part of the architecture of reference letter.

This work pursues the validation of container technology on the MANO platform hosted at ETSI, in a CN environment, so that the results obtained in the work can help to encourage users and operators to use KNFs and thus taking advantage of container technologies.

Academic Supervisor:
Xabier Zubizarreta Iriarte.

Division CEIT:
data analysis and information management.

area subject:
Systems engineering.

Description and objectives:
Dynamic modeling of large systems (e.g., digital twins of a railway infrastructure - or a water system) is highly complex and consists of a number of sub-models (in the case of railroads, e.g., turnouts, tracks, vehicles, etc.) that are built using various methodologies and simulation software.

These digital twins represent a breakthrough in the development and optimization of new infrastructures, reducing costs by being able to replace physical subsystems with their digital twin, and thus sweeping a much larger number of configurations and parameter spaces at a much lower cost.

The main challenges for the efficient development of digital twins are their high complexity, computational cost and heterogeneity of simulation tools used. The task of this PFG will be to develop a modular and highly scalable digital twin modeling system to reduce the impact of the three factors mentioned above. For this purpose, it is foreseen to make use of highly parallelizable computational tools together with a container subject that encodes and standardizes the execution of the submodels of a digital twin.

Academic Supervisor:
Paul Zabalegui 

Division CEIT:
Transportation and sustainable mobility

area subject:
Telecommunication engineering

Description and objectives:
The use of positioning systems is becoming more and more common in the daily life of both people and companies, which integrate them in their systems as core topic pieces when it comes to want a safety and efficiency Degree that meets market expectations. In this sense, the major players in the railway sector (CAF, Thales, SNCF, Siemens, etc.) are devoting great efforts to the precise and continuous positioning of their trains. 

As its positioning systems are mainly based on GPS/GNSS technologies, the main challenge for challenge is to locate the receivers in indoor environments, where the satellite signal is degraded. Currently, Ceit is involved in a major European initiative that seeks to develop total positioning systems that work both indoors and outdoors, and that do so accurately and continuously, in order to reach the highest level of maturity on the road to the autonomous train Degree .

The task of this PFG would be to design and implement a WiFi-based positioning system that operates indoors and can be further merged with GPS/GNSS technologies. 

Academic Supervisor:
Paul Zabalegui 

Division CEIT:
Transportation and sustainable mobility

area subject:
Telecommunication engineering

Description and objectives:
The use of positioning systems is becoming more and more common in the daily life of both people and companies, which integrate them in their systems as core topic pieces when it comes to want a safety and efficiency Degree that meets market expectations. In this sense, the major players in the railway sector (CAF, Thales, SNCF, Siemens, etc.) are devoting great efforts to the precise and continuous positioning of their trains. 

As its positioning systems are mainly based on GPS/GNSS technologies, the main challenge for challenge is to locate the receivers in indoor environments, where the satellite signal is degraded. Currently, Ceit is involved in a major European initiative that seeks to develop total positioning systems that work both indoors and outdoors, and that do so accurately and continuously, in order to reach the highest level of maturity on the road to the autonomous train Degree .

The task of this PFG would be to conduct a study of the use of 5G technology for indoor positioning and to implement a 5G-based positioning algorithm that makes use of synthetic signals simulated using Matlab.

Academic Supervisor:
Paul Zabalegui 

Division CEIT:
Transportation and sustainable mobility

area subject:
Telecommunication engineering

Description and objectives:
The use of positioning systems is becoming more and more common in the daily life of both people and companies, which integrate them in their systems as core topic pieces when it comes to want a safety and efficiency Degree that meets market expectations. In this sense, the major players in the railway sector (CAF, Thales, SNCF, Siemens, etc.) are devoting great efforts to the precise and continuous positioning of their trains. 

As its positioning systems are mainly based on GPS/GNSS technologies, a major challenge for challenge is to obtain continuous centimeter accuracies on a global basis. Currently, Ceit is involved in a major European initiative to develop total positioning systems that are capable of locating trains ultra-precisely on their mission statement along the tracks, in order to reach the highest Degree of maturity on the road to the autonomous train.

The task of this GFP would be to implement an algorithm for decoding HAS augmentation signals from Galileo satellites for ultra-precise positioning, and its application to an already functional Matlab positioning algorithm based on GPS/GNSS signals.

Academic Supervisor:
Yuemin Ding

department Tecnun:
Electrical and Electronic Engineering

area thematic:
Telecommunication

Description and objectives:

Online monitoring and data collection in ultra-remote areas is specifically meaningful to investigate the local characteristics of climate change, biodiversity evolution, etc. It is also very important to prevent huge disasters, such as wildfires. However, online monitoring and data collection in ultra-remote areas have been challenging during the past decades. A major challenge is the lack of digital infrastructure for communication and data collection. However, the emerging satellite networking (such as Starlink) and low-power and long-distance IoT (such as MIoTy) technologies enable an alternate solution for online monitoring and data collection. The aim of this project is to develop a system based on satellite networks and low-power and long-distance IoT to enable online monitoring and data collection in ultra-remote areas.

Academic supervisor:

Íñigo Adín

Division CEIT:

ICT Division

area thematic:

IoT, communications, low power, Bluetooth.

Description and objectives:

This project proposes the evaluation of Bluetooth 5.1 technology in its modality Long Range for use in industrial environments. The aim here is to see the possibilities of this longer range version to compete in IoT technologies to be installed in production plants or in remote sensors, with range for the admissible meters in this case.

The aim is to evaluate this technology using evaluation boards and configuring the elements at FW and SW level to measure the signal quality in parameters potentially useful in industrial applications (time of flight, data rate, packet error rate, etc.). To do this, a search for these evaluation boards will be proposed and programming will be required using the admissible interfaces in each case.

Academic supervisor:

Itxaro Errandonea

Division CEIT:

data analysis and Information Management

area thematic:

Control

Description and objectives:

In many industrial processes there are variables that, being of great interest for decision making, cannot be measured directly by sensors. However, sometimes these variables can be observed indirectly by relating them to other measurable variables. The Kalman filter is precisely an observer that allows observing non-measurable variables using dynamic mathematical models involving measurable and non-measurable variables.

The task of this GFP will be to use a simulator of a water treatment plant to develop an observer capable of estimating in real time the concentration of ammonium and nitrate in the plant. Matlab/Simulink and/or Python will be used to realize the project .

Academic supervisor:

Itxaro Errandonea

Division CEIT:

data analysis and Information Management

area thematic:

Artificial Intelligence

Description and objectives:

Classical automatic control is giving way to new, more sophisticated control techniques based on artificial intelligence, such as Reinforcement Learning techniques.

The task of this PFG will be to use a water treatment plant simulator and apply Reinforcement Learning techniques to design an automatic control strategy that adjusts the oxygen level to keep the ammonium level close to a setpoint of reference letter. Matlab/Simulink and/or Python will be used to perform the project .

Academic supervisor:

Itxaro Errandonea

Division CEIT:

data analysis and Information Management

area thematic:

Artificial Intelligence

Description and objectives:

Many real industrial processes can be mathematically formulated using complex mechanistic models composed of nonlinear differential equations. Although these models are very useful for carrying out studies of design and operation, their handicap is their high computational cost which makes them unfeasible for use in real time decision making.

With the advent of Deep Learning techniques, proposals have emerged to reduce the complexity of these models and thus the computational cost. The task of this PFG will be to use the technique known as "physics informed neural networks" to obtain a reduced model of a water treatment plant. The Python environment will be used to carry out the project .

Academic supervisor:

Itxaro Errandonea

Division CEIT:

data analysis and Information Management

area thematic:

Artificial Intelligence

Description and objectives:

Water treatment plants are subject to increasingly stringent operational requirements requirements. It is no longer sufficient to comply with the quality of the treated water, but it is also necessary to do so with the minimum energy consumption. To achieve this, the operators of these processes need to have adequate information to enable them to make better decisions.

The task of this PFG would be to use an already developed WWTP simulator to generate data sets that collect its historical operation. These data sets will then be used to evaluate different Machine Learning classification algorithms with the goal in order to predict the operational state of the process. The algorithms will be programmed in Python.

Academic supervisor:

Leticia Zamora Cadenas - Iker Aguinaga Hoyos.

Division CEIT:

Information and Communication Technologies. Intelligent Systems for Industry 4.0 Group.

area thematic:

Telecommunication/Industrial Engineering

Description and objectives:

Indoor location systems are a booming element in recent years. Whether using radiofrequency technologies, inertial sensors or artificial vision systems, the location of objects or people in interior spaces is an element core topic in many applications (tracking of parts, access to security areas, tracking of people, augmented reality, etc.).

To determine and evaluate the accuracy of a location system, the most common method is to measure guide a number of control points or tests in a controlled environment to determine the accuracy of the system. However, this subject measurement is always subject to measurement errors, human error, and the impossibility of tracking a moving element in real time. Another widespread option, especially when the accuracy is to be evaluated dynamically, is to resort to cost-effective systems that allow the creation of the real path or "ground truth", such as, for example, vision tracking systems. However, it is not always possible to deploy this type of system subject , or the economic means to do so are not always available. Therefore, being able to evaluate the accuracy of indoor positioning systems at a low cost is still a problem that researchers and companies are trying to solve.

Currently Ceit has a line of research associated with positioning systems for indoor spaces, in which it works with various companies to provide solutions to their needs. This is why the need for a ground truth system that is easy to install and not too expensive was born.

The task of this GFP would be to develop a ground truth system, using virtual/augmented reality systems, for subsequent use in evaluating the accuracy of the proprietary indoor location system Ceit. HTC Vice, Oculus Quest and Hololens 2 hardware are available for the development of this system using the Unity3D programming platform. The candidate must have programming skills in C# or similar languages such as C++ or Java.

Academic supervisor:

Emilio Sánchez Tapia

Division CEIT:

Information and communications technologies. Intelligent Systems for Industry 4.0 Group. Vision and Robotics Subgroup

area thematic:

Robotics Engineering

Description and objectives:

Industry 4.0 has paved the way for multiple forms of automation that have as goal improve productivity and optimize work processes. In this context, the aim is to develop an intelligent mobile manipulator: a new robot subject that integrates the technology of an autonomous mobile robot and a highly efficient collaborative robotic arm capable of performing various operations.

The idea of project is to develop a robot that can move, detect and avoid obstacles, explore its environment to recognize objects through artificial vision and perform part handling tasks, being able to interact with operators. With the idea of implementing a digital transformation model , required today in real factory environments, robots, control elements, sensors and other onboard elements will be connected to each other through a digital platform to control the process in real time and from anywhere.

Currently CEIT has already developed a first working prototype (see figure below).

The task of this GFP would be the programming under ROS-2 of a sequence of tasks for the robot to interact with a classic robotic cell. The specific case to be developed will be for the robot to go to a archive of parts to be processed, bring them to the cell, wait for their processing and take them to another storeroom of already sorted parts.

Under this simple task, the concepts of:

• Collaborative mobile robotics
• Machine tending
• Control in force
• Problem of synchronisation of two automatic devices

Programming skills in C/C++, Python or java-script are required.

Academic supervisor:

Diego Borro

Division CEIT:

Intelligent Systems for Industry 4.0

area thematic:

Telecommunication Systems Engineering

Description and objectives:

Copernicus is the world's largest Earth observation programme to date. The programme is a joint initiative of the European Commission and the European Space Agency (ESA) to build an autonomous Earth observation system. The Copernicus programme relies on a family of satellites called Sentinel, owned by the European Union and developed to meet the needs of the Copernicus services and their users.

Every object on the Earth's surface reflects and absorbs energy in a variety of ways. The spectral signature represents the unique way in which a surface reflects the sun's energy, within the electromagnetic spectrum. In addition, spectral signatures are typically characterized on an X-axis (wavelength) and Y-axis (percent reflectance) graph so that different surfaces have different spectral signatures.

Currently there are a multitude of data, tools and software,... to access and process satellite data. The goal of this PFG would be to access multispectral information from a certain area of the planet and process it to obtain certain information such as changes in land cover, algae growth in the water, different types of crops, or the amount of urban development in a area. The specific information needed depends on the application and will be defined when the PFG starts.

The student will not start from scratch as a PFM has been defended and has made a study of the art of all existing technologies and tools.

Academic supervisor:

Íñigo Adín.

department Tecnun/Division CEIT:

CEIT. ICT Division

area thematic:

Positioning and communications

Description and objectives:

This project tries to propose novel techniques to achieve indoor and outdoor positioning by means of opportunity signals in combination with GNSS satellite signals (GPS, Galileo, etc.). The current trend is to merge the GNSS signal with inertial sensors and vision and radar based sensors for precise guidance. However, there are less expensive techniques using signals already present in the spectrum and application environment that can be useful. Wifi, Bluetooth beacons can be used as anchors and by fingerprinting techniques based on the received power, accuracies of the order of a few meters can be achieved. However, the new 5G, with higher frequency spectra and smaller cells can be useful for positioning by signal arrival time. There are also constellations of commercial satellites in low orbits that emit signals that can also be used for this purpose.

The goal is to establish the techniques used in each case and to estimate the achievable accuracies.