Ofertes de projectes

The future of communication is taking us beyond traditional terrestrial networks. In the next decade, 6G networks will connect more than just smartphones-they will support flying cars and underwater robots using such high-tech enablers as lasers, satellites, drones, and high-altitude platforms (HAPs, flying at 20-40 km). To make this vision a reality, we need to tackle challenges like ensuring seamless connectivity for high-speed aerial vehicles, enabling underwater data transmission, and predicting large-scale network performance in urban environments. By working on these problems, you will be at the forefront of working on groundbreaking challenges in the rapidly evolving field of 6G and Non-Terrestrial Networks.  

The student will work on one of the following research objectives (or on a sensible combination of them):

- Performance modeling and optimization of communication links with satellites (such as starlink) and high-altitude platforms

- Development of advanced AI-driven beamsteering solutions to improve data transmission in underwater laser communication

- Design of an underwater-to-satellite (or HAP) communication system

- 6G-enabled 3D weather sensing and climate monitoring

- Usage of open big real-world data (e.g., OpenStreetMaps) to predict network coverage and performance in large urban areas, helping to optimize infrastructure deployment

- Design of 6G handover strategies for reliable connections with highly mobile (up to 300 kmh) flying cars/taxis

A common trait of current computing systems is that their internal data communication has become a fundamental bottleneck. Traditional interconnects are insufficient and threatening to halt progress unless fast and versatile communication alternatives are developed.

In the NaNoNetworking Center in Catalunya (N3Cat, www.n3cat.upc.edu), we are investigating the use of ultra-short range wireless communications an alternative to current interconnects. In our EU project EWiC, we aim to emulate chip-to-chip wireless communications within a computer. For that, we will emulate the behavior of a multi-chip CPU with FPGAs, and connect them wirelessly using Software-Defined Radios (SDR). 

N3Cat is looking for students wanting to acquire hands-on experience in the programming and interconnection of FPGAs, and to participate in a cutting-edge project to interconnect these FPGAs wirelessly. In more detail, the objectives of the thesis are:

- To help establishing the emulator and be able to simulate its behavior.
- To work in the implementation of adequate communication protocols for the integration of wireless interconnects in the emulated multi-FPGA system.
- To assess the performance of the system via measurement campaigns.

This Bachelor Thesis will take place at the Departament d'Arquitectura de Computadors (DAC) in collaboration with the STAR group at the Barcelona Supercomputing Center (BSC).

The System Tools and Advanced Runtimes (STAR) group at BSC focuses on research crossing multiple software layers, from OS, runtimes, and low-level APIs, to programming models, tools, and applications. We run traditional HPC, AI, and Data Analytics applications on massively parallel HPC and Cloud platforms.

Machine learning (ML) has experienced a sustainable growth during the last decade and more lately with the emergence of LLMs driven almost exclusively by industry corporations. The size of such models is currently one of the major limitations to deploy them on resource-constrained environments. CPU manufacturers have begun introducing new hardware extensions such as VNNI and AMX in order to accelerate computations during ML training and inference.

The student will be tasked to implement OpenMP and OmpSs-2 parallel programming models on an already existing pretraining code and measure the gains in performance as well as the potential issues or bottlenecks.  Next, he or she will optimize some of the most time-consuming kernels by relying upon optimised third-party libraries.

The student will have the support from researchers within the STAR group, which will provide them guidance throughout the duration of the thesis.  LLMs will be evaluated using the computational resources of our group.

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 develop ideas that will have a positive societal or socio-economic impact. In particular, the students will work on ONE of the following areas:

• Developing means of zero-power communications between nanosensors inside the human body.
• Designing protocols for communications from nanomachines inside the human body and implants or antennas in the skin surface.
• Studying mobility inside the gastrointestinal tract and human bloodstream towards creating mobility models for accurate simulation of intra-body communications.
• Dimensioning the system (inferring the required nanomachine density) to achieve a particular sensing goal/application.
• Developing AI schemes for the localization of events inside of the human body.

State-of-the-art models such as LLMs are too large to fit in a single compute node (GPU, NPU, CPU), both for training and inference on a device (e.g., phone, laptop, tablet) or in larger-scale data centers. There is a need to develop optimization techniques to split and place these models onto a distributed set of compute nodes so that the overall system performance is maximized. The research will be focused on optimizing the placement of AI models onto distributed systems considering training time, energy consumption, and computational resources. 

In this thesis, the student will model and simulate distributed AI workloads using both mathematical frameworks and simulators. This encompasses the modeling of network, compute, and memory components within a distributed architecture. Developing new modules to enhance the modeling process. Evaluating and optimizing various parallelization techniques to improve overall system performance.

The Universitat Politècnica de Catalunya · BarcelonaTech offers Master thesis fellowships in the field of LLM training. The research will be supported by Qualcomm and will be carried out in an environment with a strong interaction with leading experts in the field, with opportunities for doing internships in the company.

More information here: https://www.cs.upc.edu/~jordicf/priv/eda/llm_qc.html

Traffic analysis is crucial for urban operations and planning, while the availability of dense urban traffic data beyond loop detectors is still scarce. A large-scale floating vehicle dataset of per-street segment traffic information, Metropolitan Segment Traffic Speeds from Massive Floating Car Data in 10 Cities (MeTS-10) is available for 10 global cities with a 15-minute resolution for collection periods ranging between 108 and 361 days in 2019¿2021 and covering more than 1500 square kilometers per metropolitan area. MeTS-10 enables novel, city-wide analysis of mobility and traffic patterns for ten major world cities, overcoming current limitations of spatially sparse vehicle detector data.  MeTS-10 features traffic speed information at all street levels from main arterials to local streets for Antwerp, Bangkok, Barcelona, Berlin, Chicago, Istanbul, London, Madrid, Melbourne, and Moscow. The dataset leverages the industrial-scale floating vehicle Traffic4cast data with speeds and vehicle counts provided in a privacy-preserving spatio-temporal aggregation. Data has to be map-matched to the OpenStreetMap (OSM) road graph. City datasets can be compared with other publicly available stationary vehicle detector data (for Berlin, London, and Madrid) and the Uber traffic speed dataset (for Barcelona, Berlin, and London). A comparison of the differences across some of the datasets in spatio-temporal coverage and variations in the reported traffic will be addressed in this project. The large spatial and temporal coverage offers an opportunity for joining the MeTS-10 with other datasets, such as traffic surveys in traffic planning studies or vehicle detector data in traffic control settings. A pipeline is already available to derive the dataset from the Traffic4cast data published by HERE. HERE is a technologal company providing a platform for the visualization and analysis of location data. To ensure data privacy, the Traffic4cast dataset was published as rasterized and aggregated cell-based data, nevertheless providing a high spatial and temporal resolution.

This project investigates how adversarial inputs alter the internal activation dynamics of neural networks by modeling activation flows as graphs. By computing and analyzing graph-theoretic metrics-such as path entropy, node centrality, and flow divergence-the study aims to quantify disruptions in information propagation and identify structural vulnerabilities in the model. The approach focuses on adversarial robustness, network science, and interpretability, with the goal of diagnosing and understanding neural networks' behavior under adversarial attacks.

This Bachelor Thesis will take place at the Departament d'Arquitectura de Computadors (DAC) in collaboration with the STAR group at the Barcelona Supercomputing Center (BSC).

The System Tools and Advanced Runtimes (STAR) group at BSC focuses on research crossing multiple software layers, from OS, runtimes, and low-level APIs, to programming models, tools, and applications. We run traditional HPC, AI, and Data Analytics applications on massively parallel HPC and Cloud platforms.

High-performance computing (HPC) is a hot research topic that drives the interest of many researchers, institutions, and countries all around the world.  The high-performance Linpack, also known as HPL, is the quintessential bencharmk for measuring the performance of supercomputers and it is used to rank them in the famous top500.org website.  Tradditionally, this application has been run on distributed and homogeneous systems equipped with CPUs using highly optimised BLAS libraries and MPI.  With the popularisation of accelerators like GPUs to speedup computations, there has been a plethora of new HPL implementations to exploit distributed and heterogeneous systems.

The student will be asked to implement OpenMP and OmpSs-2 parallel programming models on an heterogeneous version of the HPL benchmark for heterogeneous systems.  First, he or she will perform a porting from AMD GPUs to NVIDIA GPUs by replacing the corresponding calls to specialised BLAS libraries as well as in-house low-level kernels.  Second, the student will enable task-based, shared-memory parallelism to CPU kernels, studying different types of optimisations to effectively overlap computations and communications on both CPUs and GPUs.  Third, the student will perform and exhaustive and quantitative analysis of the various factors affecting the performance of fork-join and task-based implementations.

The student will have the support from researchers within the STAR group, which will provide them guidance throughout the duration of the thesis.  The HPL application will be evaluated using the computational resources of our group.

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.

Vision Transformers (ViT) have become the state-of-the-art technique underlying many computer vision tasks. The ability to deploy them on edge devices spreads the computing load and also enables applications that require real-time performance, enhanced privacy, or offline operation. However, the computational complexity and memory demands of ViTs often make them impractical for edge applications.

Computing systems are ubiquitous in our daily life and have transformed the way we learn, work, or communicate with each other, to the point that progress is intimately tied to the improvements brought by new generations of the processors that lie at the heart of these systems. 

A common trait of current computing systems is that their internal data communication has become a fundamental bottleneck. Traditional interconnects are insufficient and threatening to halt progress unless fast and versatile communication alternatives are developed.

In the NaNoNetworking Center in Catalunya (N3Cat, www.n3cat.upc.edu), we envisage a revolution in computer architecture enabled by the use of wireless communications (and other unconventional interconnect technologies) inside computer chips, both classical and quantum. Of course, this vision comes with its own set of challenges since we need to figure out the best way to architect these systems with the new capabilities of the interconnects. In this direction, the candidate will work on one of the following areas:

• Analysis of the communications workload in nowadays computer chips and development of network-on-chip architectures to serve such traffic optimally.
• Development of chiplet-based architectures in the classical domain in cache-coherent based systems, delving into the cache coherence protocol and the interface with the wireless interconnect.
• Development of a supercomputer-in-a-package, a chiplet-based architecture based on message passing, delving into how to speed up the MPI primitives with wireless communications.
• Study of scalable quantum computing systems enabled by wireless classical communication across the chips of the quantum computer and inside a cryogenic refrigerator.

This Master Thesis will take place at the Departament d'Arquitectura de Computadors (DAC) in collaboration with the STAR group at the Barcelona Supercomputing Center (BSC).

The System Tools and Advanced Runtimes (STAR) group at BSC focuses on research crossing multiple software layers, from OS, runtimes, and low-level APIs, to programming models, tools, and applications. We run traditional HPC, AI, and Data Analytics applications on massively parallel HPC and Cloud platforms.

Machine learning (ML) has experienced a sustainable growth during the last decade and more lately with the emergence of LLMs driven almost exclusively by industry corporations. The size of such models is currently one of the major limitations to deploy them on resource-constrained environments. CPU manufacturers have begun introducing new hardware extensions such as VNNI and AMX in order to accelerate mixed-precision calculations during ML training and inference of low-bit precision LLMs.

The student will be tasked to quantise an already existing pretraining code and measure the gains in performance as well as the potential issues like accuracy losses. Next, he or she will optimize some of the most time-consuming kernels by relying upon optimised third-party libraries. Two variants of shared-memory parallelism will be explored to benchmark the model and identify potential bottlenecks. Finally, several model sizes be analysed and compared.

The student will have the support from researchers within the STAR group, which will provide them guidance throughout the duration of the thesis.  LLMs will be evaluated using the computational resources of our group.

There is now an opportunity to create your own DPP prototype and get experience in the field.

The project proposes to develop a DPP prototype for second hand recycled materials.

The frontend of a DPP system may seem a classic Web application. But to provide trusted data, to enable different actors to write to the DPP system, there are several more services running in the background, like a distributed ledger (blockchain) to store proofs of the stored information, and the use of decentralized identifiers (DID) and verifiable credentials (VC).  

For this project, it will be necessary lo look at DID and VC, which are recent W3C standards  https://www.w3.org/TR/did-core/ and https://www.w3.org/TR/vc-data-model-2.0/.

Quick reads to get an idea of the DPP:

https://medium.com/spherity/a-decentralized-digital-product-passport-for-textiles-eea7ea161d79

https://medium.com/spherity/the-worlds-first-decentralized-verifiable-battery-passport-a0f42c1bcb5e

In our group we have some Python code for DID and VC generation from our collaboration partner Pangea which can be a starting point to be used in this project:

https://github.com/eReuse/IdHub

https://github.com/eReuse/pyvckit

https://github.com/eReuse/devicehub-django

https://gitlab.com/dsg-upc/ereuse-dpp (too complex maybe)

Advanced Persistent Threats (APTs) are becoming one of the most significant cybersecurity challenges nowadays. These attacks are characterized by being developed in a stealthy manner and over long periods of time (e.g., months or years), causing financial losses, data breaches, and operational disruptions. Famous examples of APTs are the SolarWinds cyber-attack and NotPetya, affecting multiple government agencies and global enterprises like Maersk. To defend from such threats, methods based on audit logs have been widely developed to detect suspicious behaviors in the system. Specifically, cybersecurity experts switched their attention to data provenance to develop tools and methods to combat APTs. Data provenance consists of parsing system logs and building provenance graphs that describe the entire system execution.

The objective of this thesis is to develop novel ML-based techniques for detecting APTs. During this project, the student will work with industry experts from Telefónica towards the design and implementation of a new set of tools for anomaly detection in audit logs. The student will gain hands-on experience in working with real-world datasets and will acquire technical skills to develop state-of-the-art anomaly detection techniques. In addition, the student will gain experience in graph-based ML, sequence modeling, and advanced embedding techniques.

Objectives:

· Design and develop novel pipelines for processing system log information.
· Research, apply and develop state-of-the-art methods in anomaly detection and cyber threat intelligence.
· Develop techniques for provenance-based intrusion detection systems to trace attack patterns.
· Contribute to research publications and technical documentation to communicate the results to international venues or conferences.

The Ride-Sharing Problem (RSP) seeks to efficiently match travelers with similar itineraries and schedules on short notice, yielding substantial social and environmental benefits by reducing the number of cars used for personal travel and optimizing the use of available seat capacity in urban areas.

The static version of RSP is inadequate for real-world applications, as it does not account for the inevitable delays caused by traffic, cancellations, or new services. Therefore, a dynamic version is necessary to accommodate these circumstances.

This TFM proposes the development of a Hybrid Metaheuristic to address the Dynamic RSP, combining Metaheuristic optimization with Agent-based simulation. This optimization method must include the following features:

• Adaptation to traffic conditions.
• Integration of new services en route.
• Management of route cancellations.

Background

Bipolar Disorder (BD) is a psychiatric condition in which people experience significant shifts in mood, energy, and thought processes during manic and depressive episodes (Nierenberg et al., 2023). Manic episodes involve heightened energy, rapid speech, and grandiose thoughts, while depressive episodes are marked by low energy, slow speech, and feelings of hopelessness.

Language, expressed through speech, provides a privileged window into the mind and is thus a cornerstone of psychiatric evaluation. During these evaluations, clinicians routinely assess speech features such as (A) acoustic properties, (B) formal aspects, (C) language content, and (D) emotionality, albeit subjectively.

1. Acoustic features (Table 1) (e.g., pitch and volume) reflect mood states (Low, Bentley and Ghosh, 2020). Manic episodes might be characterized by increased pitch and loudness, while depressive episodes may present with reduced pitch variation and monotonous speech.
2. Formal aspects (Table 2) (e.g., flow, fluency, rhythm, quantity, and latency) can delineate distinct patterns associated with different phases (euthymia, mania, depression) of BD (Weiner et al., 2019). Overly rapid speech may indicate manic thought patterns, whereas slowed, halting speech can suggest depressive cognition.
3. Language content features (Table 3) (e.g., coherence and cognition) reflects thought organization (Iter, Yoon and Jurafsky, 2018). Manic episodes may involve tangential or circumstantial speech, while depressive episodes often include pervasive negative thoughts.
4. Emotionality features (Table 4) (e.g., emotional valence and content) helps differentiate manic and depressive phases (Khorram et al., 2018). Manic speech often conveys exaggerated positive emotions, whereas depressive speech typically reflects sadness and despair.

Modern technology enables high-fidelity speech recording and automated analysis of these features (DeSouza et al., 2021), showing potential in diagnosing and monitoring BD (Guidi et al., 2015; Faurholt-Jepsen et al., 2016).

In previous work, we applied machine learning to detect depression by integrating acoustic, linguistic, and emotional features from the DAIC-WOZ dataset. Six models-including Decision Tree, SVM, and XGBoost-were tested with various balancing (e.g., SMOTE) and feature selection methods. The best-performing model, a decision tree with SMOTE, achieved 0.78 accuracy and F1-score using just eight multimodal features. This demonstrated that simple, interpretable models, when supported by careful preprocessing, can effectively identify mood-related speech patterns.  These findings provide a methodological foundation for extending such speech-based predictive approaches to other mood disorders, such as bipolar disorder, where affective and cognitive states are likewise encoded in speech (Aljaz et al., in preparation).

We hypothesize that (i) speech features will correlate with the severity of manic and depressive symptoms, (ii) they will effectively differentiate between manic, depressive, and euthymic phases in BD, as well as between mania/depression and response/remission, (iii) only specific speech features and speech tasks will be relevant for each of these analyses.

Aims

1. To correlate speech features with manic-depressive symptoms severity in BD
2. To use speech features to develop predictive models for diagnostic (i.e., manic, depressive, and euthymic phases in BD), and treatment outcomes (i.e., acute phases of mania/depression vs response/remission)
3. To determine which specific speech features and speech tasks are most relevant for each of the previous analyses.

Methods

A naturalistic, observational study was conducted including 85 participants with BD (25 manic, 25 depressed, 35 euthymic). Patients with BD experiencing manic and depressive episodes underwent longitudinal audio recording during acute phases and after response/remission using a dual-microphone setup. Patients during euthymia (mood stability) were recorded once. Interviews included clinical evaluation, cognitive tasks, standard text reading, and emotional and non-emotional storytelling. Audio recordings were automatically diarized and transcribed.

Plan

1. To extract speech features from the audio recordings, including (A) acoustic properties, (B) language content, (C) formal aspects, and (D) emotionality.
2. Statistical analyses:

1. To correlate speech features with clinical scales, 
2. To use lasso logistic regression to develop predictive models for diagnostic and treatment outcomes using speech features, and 
3. To use variable relevance methods to identify the most pertinent speech features for these analyses, and assessing the magnitude of correlation and prediction accuracies across different speech tasks.

Impact: Automated speech analysis in BD might provide objective, quantitative markers for psychopathological (manic/depressive) alterations. This technology could potentially identify subtle alterations imperceptible to clinicians, signaling early signs of acute relapse and allowing for early intervention. Implementing this technology could improve diagnosis, monitoring, and prediction of treatment response.

References

DeSouza, D.D. et al. (2021) 'Natural Language Processing as an Emerging Tool to Detect Late-Life Depression', Frontiers in Psychiatry. Frontiers Media S.A. Available at: https://doi.org/10.3389/fpsyt.2021.719125.

Faurholt-Jepsen, M. et al. (2016) 'Voice analysis as an objective state marker in bipolar disorder', Translational psychiatry, 6, p. e856. Available at: https://doi.org/10.1038/tp.2016.123.

Guidi, A. et al. (2015) 'Voice quality in patients suffering from bipolar disease', in Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS. Institute of Electrical and Electronics Engineers Inc., pp. 6106¿6109. Available at: https://doi.org/10.1109/EMBC.2015.7319785.

Iter, D., Yoon, J. and Jurafsky, D. (2018) 'Automatic Detection of Incoherent Speech for Diagnosing Schizophrenia', in. Association for Computational Linguistics (ACL), pp. 136¿146. Available at: https://doi.org/10.18653/v1/w18-0615.

Khorram, S. et al. (2018) 'The PRIORI Emotion Dataset: Linking Mood to Emotion Detected In-the-Wild'. Available at: http://arxiv.org/abs/1806.10658.

Low, D.M., Bentley, K.H. and Ghosh, S.S. (2020) 'Automated assessment of psychiatric disorders using speech: A systematic review', Laryngoscope Investigative Otolaryngology, 5(1), pp. 96¿116. Available at: https://doi.org/10.1002/lio2.354.

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 computers enabled by quantum communications, 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:

• Designing classical (bit) and quantum (qubit) communication protocols and network architectures for communications inside a quantum computer.
• Assisting in the modeling of quantum short-range communications within our simulation framework, which is based on NetSquid.
• Developing qubit mapping, partitioning, and routing for scalable quantum computers.
• Study the use of AI to model quantum computers or develop qubit mapping and routing schemes.
• Study the potential scaling and adaptation of the existing quantum computing architectures to specific quantum machine learning algorithms (QAOA, VQE, others)

To evaluate the impact of the AI assistant, we will conduct a user study that examines both its effectiveness in supporting participants and its overall usability within the VR simulation.

Wrong working habits and postures are the source of many long-term lesions such as Carpal Tunnel Syndrome (CTS) or Forward Head Posture (FHP). These lesions may lead to many kinds of physical problems. 

The goal of the project is to create a lightweight system that tracks postures in realtime and reacts to bad postures by interactive guidance. 

If you are interested in the project, feel free to send me an email to get more details. But in any case, please, check the information for prospective students in my webpage.

Virtual reality is becoming a tool for helping patients with several illnesses (strokes, frozen shoulder...) to engage in the rehabilitation exercises.

The purpose of this project is the creation of a serious game that helps patients to engage in rehabilitation exercises for the frozen shoulder.

If you are interested, do not hesitate to ask for more information. But please, before doing so, check my "Prospective students" tab on my webpage.

Virtual reality is becoming a tool for helping patients with several illnesses (strokes, frozen shoulder...) to engage in the rehabilitation exercises.

The purpose of this project is extending a serious game for physiotherapy rehabilitation.

If you are interested, do not hesitate to ask for more information. But please, before doing so, check my "Prospective students" tab on my webpage.

Pointing in 3D VR environments is complex because the user gets exhausted, and suffers the gorilla arm syndrome. The idea of the project is to develop new pointing techniques that reduce or avoid fatigue. To ensure the system works, a user study will need to be performed and the data analyzed.

If you are interested in the project, feel free to send me an email to get more details. But in any case, please, check the information for prospective students in my webpage.