Ofertas de proyectos

A list of issues hard to compute would include:

1. The computation of the partition function is NP-hard, involving an  exponential sum of terms
2. The exact computation of the derivative of the log-likelihood is  also NP-hard, since it contains the derivative of the partition function

Therefore, in practice we have to approximate both the computation of
the probabilities and several components of the learning process
itself. These drawbacks have prevented RBMs to show their real
potential as truly probabilistic models.

Currently, we are working on trying to improve several of the unsolved
issues related to RBMs:

1. - Mechanisms to control the learning process: www.lsi.upc.edu/~eromero/Publications/Downloads/2018-tnnls-stopcritRBM.pdf
2. Better approximations of the derivative of the log-likelihood: http://www.lsi.upc.edu/~eromero/Publications/Downloads/2019-nn-weightedCD.pdf
3. Efficient approximation of the partition function (work in progress)

These works have opened new lines of research, some of which can be
the topic of a Master's Thesis. The scope and degree of depth of the
work can be adapted to the estimated times to complete the Thesis. For
further details, contact Enrique Romero (eromero@cs.upc.edu).

A more detailed description of the project can be found in

https://www.cs.upc.edu/~eromero/Downloads/Retina-TFM-Project-01.pdf

The project is proposed in collaboration with Javier Zarranz Ventura
(Institut Clínic d'Oftalmologia, ICOF, Hospital Clínic de Barcelona, and
Institut d'Investigacions Biomèdiques August Pi I Sunyer, IDIBAPS),
which would provide a large annotated database to develop the project. For further information, please contact Alfredo Vellido (avellido@cs.
upc.edu) or Enrique Romero (eromero@cs.upc.edu).

La inteligencia artificial puede resultar una herramienta valiosa para mejorar la eficiencia, la precisión y la calidad de los procesos en la planta de producción de alimentos y para mejorar la valoración de la calidad del producto final. Se propone la introducción de tecnología NIR (Near Infrared Reflectance) y de otros sensores como sistema de control, monitoreo y predicción de la calidad de las elaboraciones en planta de producción de alimentos de forma automatizada. Por tanto, las herramientas de IA permitirán la mejora de la calidad de las elaboraciones, en un desarrollo en 3 fases dentro de la cadena:

(1) Modelado de materias primas en planta con el NIR (producto en fresco).

(2) Calidad asegurada en la elaboración de cremas, mediante monitoreo de procesos y corrección de parámetros de forma automatizada.

(3) Valoración de la calidad de producto final (nutricional, químico y sensorial) que percibe el consumidor.

Este proyecto se realiza en colaboración con IRTA Lleida y Ametller Origen.

Functional near-infrared spectroscopy (fNIRS) is a non-invasive neuroimaging technique that measures changes in oxygenated (HbO2) and deoxygenated hemoglobin (HbR) in the cerebral cortex. Due to its portability and low cost, fNIRS has been used in Brain-Computer Interface (BCI) applications, characterizing hemodynamic responses to varying stimuli, and investigating auditory and visual-spatial attention during Complex Scene Analysis (CSA). In this project, we want to design and implement an fNIRS study with a goal of studying the impact of neural and BCI outcomes to improving the training of LAI models' attention mechanism (e.g., Transformer attention) during reading comprehension tasks (e.g., the participants will be judging the quality of generated text). We want to demonstrate experimentally that augmenting a model with fNIRS data carries neural activity features complementing the information captured by the model and demonstrate that it improves the models' performance. To this end, we will have to collect data from participants and test how different Transformer models benefit from different types of fNIRS attention masks.

The candidate will:

• Carry out controlled studies and collect data from a number of participants.
• Try different approaches to incorporating fNIRS signal in the training process of DL/LLM models and compare against baselines/experiments (these should be replicated).
• Carry out ablation studies, personalisation techniques, error analyses, etc.
• Contribute to authoring a scientific article

Els detalls es donaran a l'alumne personalment

The optimization will ensure the cost and losses minimization while ensuring a safe integration of renewable energy (of variable nature) also considering the availability of flexible demand and energy storage systems. The use cases will include normal operation and also contingencies. The optimization will include security constrained optimal power flow. Some use cases will include large scale continental grids and potentially offshore wind power plants connected to offshore energy hubs. Other use cases will be focused on distribution networks.

MENA Business Investment Group is a multinational company dedicated to human resource consulting and selection at an
international level.
Aiming to create new business units based on new technologies, the company wants to develop an AI-based software
able to search for candidates in the different available databases, and communicate with potential candidates to validate
provided data.
In a second phase we also want to explore the possibility of an AI conducting a preliminary the interview with the possible candidates and prepare a final report on each candidate.

The project will explore different LLMs, both commercial and open source, develop a working interaction strategy
between the HR system and the LLM (either via prompting or instructing the model if needed), and compare their costs
and performance to establish the best option for the company's goals

This TFM is linked to an internship in the company:
https://borsapractiques.fib.upc.edu/ca/ofertes/oferta/2475?check_logged_in=1

Introducción

En situaciones de emergencias radiológicas, algunas áreas pueden ser inaccesibles o peligrosas para los equipos de intervención. En estos escenarios, la utilización de detectores de radiación montados sobre vehículos aéreos tripulados de forma remota es una solución que facilita su monitorización. Estos sistemas permiten obtener información del mapa radiológico sin exponer al personal de primera intervención y, al mismo tiempo, ayudan a una mejor toma de decisiones.

Por este motivo, en los últimos años, el desarrollo de sistemas de medida de la radiactividad mediante detectores de espectrometría gamma, adaptados para su instalación sobre vehículos aéreos no tripulados, y basados en hélices rotatorias (de aquí en adelante se utilizará la abreviación "drones"), se ha intensificado gracias también a los avances tanto de los detectores como de los drones.

En el proyecto europeo "Preparedness" (http://www.preparedness-empir.eu), desarrollado de 2017 a 2020, se caracterizaron y compararon diversos sistemas de espectrometría gamma instalados en drones que permitían la visualización en tiempo real de los mapas radiológicos en dos dimensiones (2D). El TFM que se propone pretende dar un paso adelante mediante el desarrollo y puesta en marcha de un sistema de medida de la radiactividad en el medio ambiente basado en un sistema de detección de espectrometría gamma instalado en un dron y con capacidad para realizar una construcción tridimensional (3D) del estado radiológico del escenario con la mayor rapidez posible. El sistema de visualización en 3D desarrollado, permitirá disponer de mapas radiológicos precisos en escenarios con geometrías complejas.

Dicho TFM es parte de un trabajo de investigación más grande que se enmarca en el proyecto de investigación financiado por el Consejo de Seguridad Nuclear gamma-dron y abarca los siguientes objetivos específicos:

O1) Optimizar la geometría del detector de espectrometría gamma seleccionado para su aplicación en medidas tridimensionales (3D) y su instalación en un dron.

O2) Calibrar y caracterizar el sistema de espectrometría gamma desarrollado en condiciones de laboratorio. 

O3) Elaborar los programas de cálculo para determinar las variables radiológicas que serán visualizadas.

O4) Desarrollar técnicas de reconstrucción 3D adaptativa para representar de forma realista y eficiente la geometría del terreno y la variabilidad inherente a dichos terrenos.

O5) Visualizar con la mayor rapidez posible las variables radiológicas en un mapa 3D del escenario del accidente en la estación de tierra. 

O6) Verificar el funcionamiento del sistema desarrollado mediante la realización de vuelos en campos aéreos de referencia.

O7) Demostrar la operatividad 24/7 del sistema desarrollado mediante la realización de campañas de medida en un terreno con contaminación heterogénea por encima del nivel natural.

Desarrollo:

En el desarrollo del proyecto en el que se enmarca el TFM se dispone de la instrumentación necesaria para la adquisición de datos radiólogos y de las imágenes del terreno. En concreto se dispone de un equipo de espectrometría gamma de NaI de 50 mm x 50 mm, un dron DJI Matrice 350RTK y una cámara Zenmuse L2 que permite tanto realizar una nube de puntos mediante el uso de un LiDAR 3D o la realización de fotos de alta calidad.

El software disponible permite descargar los datos y realizar una reconstrucción del terreno en 3D, tanto mediante el LiDAR 3D como mediante la fotogrametría.

Los objetivos concretos serian:

·       Procesar los ficheros del LiDAR 3D y fotogrametría para disponer de un mallado del terreno que permita llevar a cabo los cálculos radiológicos

·       Incorporar los datos radiológicos en el sistema de coordenadas del terreno para obtener las funciones respuesta del detector para cada celda del mallado del terreno.

·       Analizar diversos métodos de cálculo matemático para obtener el mejor mapa de radiactividad del escenario.

·       Implementar el método de cálculo en  un programa que permita optimizar la definición de las celdas del mallado.

Dentro de los citados objetivos, se pactara con el alumno/a qué objectivo concreto se priorizará y formará parte de su TFM. No se espera que el alumno desarrolle todos los puntos, sino más bien que pueda entender el contexto en el que se enmarcará su trabajo.

This approach is essential for studying advanced network solutions, including scenarios where machine learning and AI techniques are applied for radio resource management, optimization of data rates, and network reliability.

This Final Degree Thesis will be co-supervised by UPC Co-advisor: Cristhian J. Rodrigues Dos Santos (now in Mobility at NII-Tokyo)

A financing for the student is available depending on the level of the student, to be agreed with the company, NOKIA, collaborating on the project.

To develop a virtual 5G core and RAN architecture that accurately replicates the structure and operational conditions of a real research network, providing a flexible and robust platform for network experimentation, optimization tests, and evaluation of emerging 5G/6G technologies in a safe, non-disruptive environment.

Thematic Areas that you will learn:
- 5G and Beyond Network Architecture

-Digital Twins in Telecommunications

- Virtualized Core and RAN Deployment

- Radio Resource Management (RRM)

- Artificial Intelligence and Machine Learning in Telecommunications

- Network Simulation and Emulation for Research and Development

This project offers the candidate a unique opportunity to apply artificial intelligence techniques to real-world challenges in lung cancer research and treatment. As part of this thesis, the candidate will work with datasets, including patient records, genetic data, molecular alterations, treatment outcomes, and exposome data. These datasets will serve as the foundation for developing AI models that address critical challenges in lung cancer treatment, such as predicting patient outcomes and identifying optimal treatment strategies.

The candidate will focus on the following core tasks:

Data Exploration and Preprocessing: The candidate will gain experience in handling complex medical datasets by cleaning, preparing, and structuring the data to ensure it is suitable for advanced AI analysis.

Building AI Models: Using machine learning and deep learning techniques, the candidate will develop models aimed at predicting lung cancer progression, evaluating treatment efficacy, and understanding the impact of various environmental and genetic factors.

Interpretability and Explainability: A significant emphasis will be placed on making AI models interpretable and transparent. The candidate will explore techniques to ensure that the models produced are not just accurate but also explainable, providing healthcare professionals with clear insights into the model's predictions and decisions.

Exploring Interaction Networks: The candidate will analyze interaction networks, studying relationships between patient genetics, environmental factors, and treatment responses to identify key drivers of lung cancer outcomes.

Throughout the project, the candidate will not only gain hands-on experience with cutting-edge AI tools and methodologies but also develop a deeper understanding of AI's role in healthcare. This project provides an impactful opportunity to contribute to a field where AI innovation can directly improve patient outcomes.

In the proposed project, we are interested in the mobile setting, and propose the use of depth information, on top of the usual RGB (Red, Green, Blue) pixel data acquired by mobile device cameras, to track and quantify visual attention. Depth information can either be estimated with post computer visual processing or acquired directly with high precision, using advanced LiDAR sensors that newer smartphone models are currently equipped with. Furthermore, we propose the use of "lightweight" Deep Learning (DL) techniques to achieve an accurate and robust gaze point estimation without the need of extensive calibration. Unlike prior art, we will consider the use of historical information to inform future predictions and will examine how such models can be tailored to each user by injecting personalized data. In addition, we propose a more lightweight Neural Network (NN) architecture, suitable for the processing power of mobile devices, that also leverages the use of video or photo frames with depth sensory data.

The candidate will:

• Develop an app for iPhone (in Swift) for collecting gaze information and image data (using the device's frontal camera and LiDAR sensors), while completing a simple task of tracking a red dot in a matrix.
  
• Incorporate in the app the functionality offered by SensingKit,  an open-source mobile sensing framework compatible with iOS specialised in capturing motion, orientation, location and proximity (using iBeacon¿ or Eddystone¿) data and transmitting them on a server over any Internet connection. [https://github.com/SensingKit/SensingKit-iOS]
• Carry out a crowdsourcing study and collect data from a number of participants.
• Train lightweight DL models to predict accurately gaze point estimation, using the collected data, and compare against prior baselines/experiments (these should be replicated).
• Carry out ablation studies, personalisation techniques, error analyses, etc.
• Contribute to authoring a scientific article

Eye movement features are considered to be direct signals reflecting human attention distribution with a low cost to obtain, inspiring researchers to augment language models with eye-tracking (ET) data. In this project, we want to investigate how to operationalise eye tracking (ET) features, such as first fixation duration (FFD) and total reading time (TRT), as the cognitive signals to augment LAI models' attention mechanism (e.g., Transformer attention) during training. We want to demonstrate experimentally that augmenting a model with ET data carries linguistic features complementing the information captured by the model and demonstrate that it improves the models' performance. To this end, we will have to collect data from participants and test how different Transformer models benefit from different types of ET attention masks.

The candidate will:

• Carry out controlled studies and collect data from a number of participants.
• Try different approaches to incorporating gaze features in the training process of DL/LLM models and compare against baselines/experiments (these should be replicated).
• Carry out ablation studies, personalisation techniques, error analyses, etc.
• Contribute to authoring a scientific article

Recent advancements in nanotechnology have enabled the development of means for sensing and wireless communications with unprecedented miniaturization and capabilities, to the point that they can be introduced into the gastrointestinal tract inside a pill or into the bloodstream in the form of passively flowing nanomachines. 

This opens the door to the idea of intra-body communication networks, this is, a swarm of nanosensors inside the human body that use communications to coordinate their actions to sense and localize specific events (lack of oxygen, biomarkers, etc). This can lead to the development of applications such as continuous monitoring of diabetes, detection and localization of cancer micro-tumors, or early detection of blood clots. These possibilities are currently investigated by our team at the N3Cat (www.n3cat.upc.edu).

In this context, we are looking for excellent and self-motivated individuals who are eager to work on developing AI schemes (based on graph neural networks or multi-agent RL) for the detection and localization of events inside of the human body. Data will be gathered with an in-house simulator that integrates mobility models (BloodVoyagerS) and communication models (TeraSim).

Seeing that not all neural networks fit to all problems, and that relational data is present in a wide variety of aspects of our daily life, the main focus of this thesis in N3Cat (www.n3cat.upc.edu) and BNN-UPC (www.bnn.upc.edu) is to explore the possibilities of the Graph Neural Networks (GNNs), whose aim is to learn and model graph-structured relational data. We are looking for students willing to study the uses, architectures, and algorithms of GNNs. To this end, the candidate will work on ONE of the following areas:

• Uses: Applying GNNs in emerging application areas, including but not limited to (1) electroencephalogram (EEG) analysis for Alzheimer's disease detection, epilepsy classification, motor imagery; (2) acceleration of the compilation of quantum computing algorithms
• Architectures: Investigating ways to accelerate the processing of GNNs in multiple computing platforms (CPU, GPU, accelerators).
• Algorithms: Developing meta-learning data-driven models to estimate the accuracy of a GNN for a given graph, without training, through synthetic graph generation and correlation analysis.

Quantum computers promise exponential improvements over conventional ones due to the extraordinary properties of qubits. However, a quantum computer faces many challenges relative to the movement of qubits which is completely different from the movement of classical data. This thesis delves into these challenges and proposes solutions to create scalable quantum computing systems and the algorithms that run within them, following the current European projects at N3Cat (www.n3cat.upc.edu) on scalable quantum computing.

The interested candidate will work in a group of several PhD students and in collaboration with Universitat Politècnica de València, working in ONE of the following areas:

• Study the use of AI to model quantum computers or to assist in the development of architectural methods (qubit mapping, qubit partitioning, qubit routing).
• Study the potential scaling and adaptation of the existing quantum computing architectures to specific quantum machine learning algorithms (QAOA, VQE, others).

LABINQUIRY project aims to develop a didactic infrastructure to help secondary school and university teachers to implement inquiry-based learning processes called study and research paths (SRPs). The starting point of an SRP is an open question that students address in small groups with the help of the teacher, they have to search for data, information, new tools and knowledge, etc, study them and jointly elaborate a single answer of the whole class.

One difficulty posed by the SRPs in terms of management is the teacher's treatment of the weekly reports produced by the student groups with the partial results of the work done during the week. The teacher responsible for the SRP has to "process" these reports in limited time in order to prepare the next class session. In this processing, the teacher has to read the reports - about 10-12 per class -, compile the most important information and group them according to the type of questions raised by each team, the data collected, the interim results provided, and the sources of information used.

The research group responsible for the LABINQUIRY project is interested in achieving an automatic processing of the content of student reports. The aim of the TFM would be, from a set of 10-12 reports, to collect and organise the information contained in the reports to help the teacher organise the next task. Both the questions posed by the teacher in the SRP and the students' reports are natural language texts. The collection and organisation of the information can be done at different levels and from different points of view (some of which are already fixed but some of which are not), giving flexibility to the work to be done during the TFM. In principle, the techniques to be used would fall into the following areas: unsupervised learning (clustering) and natural language processing (word embeddings).

The expected timing is January-June 2024.

To carry out this project it is advisable to have a good mastery of Spanish and/or Catalan and the techniques mentioned above.