The work plan focuses on the development of models based on time series for the prediction of marine biotoxins in bivalves, based on multivariate series of data from different sources, namely historical data from in-situ chemical and biological monitoring and weather data. It will involve clustering techniques and survival analysis for forecasting.

The selected candidate will be a member of the research project PassCert, which aims at building an open-source, proof-of-concept password manager that through the use of formal verification, is guaranteed to satisfy properties on data storage and password generation. PassCert is a research collaboration between researchers from INESC-ID Lisboa (PT), INESC TEC (PT), and Carnegie Mellon University (US).
The selected candidate will:
1) Contribute to the collection of functional and security requirements for the proof-of-concept password manager and to the identification of properties that will be formally verified.
2) Formally verify properties relevant to password managers (e.g. properties on generation of secure passwords and properties related to data location).
3) Contribute to the development of the proof-of-concept verified password manager.
4) Actively participate in and contribute to PassCert's activities and regular meetings.

BI|2020/107 
Stateful Functions is an open source framework that provides a powerful abstraction for event-driven architectures, reducing the complexity of building and orchestrating distributed stateful applications at scale, by bringing together benefits of stream processing and Function-as-a-Service (FaaS).  This work explores leveraging Stateful Functions in Flink in order to design and develop an extension to this Big-data platform to achieves increased scalability and performance, with adaptable resource management driven by service-level objectives regarding performance (latency, throughput), result accuracy, and resource management.
BI|2020/108  
Graphs processing systems provide a powerful abstraction for sophisticated Big-Data applications. This work addresses graph storage (e.g., DGraph, Neo4j, JanusGraph, Nebula Graph) and processing (e.g., GraphX on Spark and Gelly on Flink) and their space- and time-efficiency, exploring how these metrics can be improved, e.g., by employing summarized data representations to reduce storage occupation, while allowing dynamism (i.e., update-able data), while still enabling implementing popular graph algorithms and workloads.

Development of multi-objective local searches and machine learning algorithms for the optimization of public transportation networks using smartcard validations. The grant holder will primarily develop contributions in the context of Tasks 6, 7 and 8 of the ILU project.

To research and experiment with novel security technologies, namely AMD's SEV-SNP, to strengthen the security and privacy aspects of the project.

To design and implement a solution to the issue of persistent storage on a cloud provider, from the standpoint of a client who is located on a different trust domain.

To design and implement an extension to the FaaS model so that it retains the interesting new properties of serverless computing, while extending it with the ability for functions to generate arbitrary side effects such as accessing persistent storage or communicating with other services.

LAW-NLP aims to explore the use of natural language processing to help users understand and identify relevant Portuguese consumer laws that apply to their situation. To that end, the applicant will explore the use semantic reasoning techniques based on a formal (or semi-formal) representation that will be automatically extracted from the Portuguese Consumer Law.

This grant will involve the development of a diarization system, using state-of-the-art methods that can be adapted to the constraints imposed by privacy-preserving techniques. 
This system will consist of different modules:
- a pre-processing/feature extraction stage;
- a Voice Activity Detection module;
- a Speaker Modelling module, using x-vector embeddings obtained from a neural network trained for Speaker Verification;
- a final clustering stage.
This grant will also include procuring and preparing data for the training and development of the system’s modules, as well as for their evaluation.

Develop cognitive models for artificial personas to be used in automated UX testing of interactive systems. These personas should define different cognitive capabilities and different strategies for the interaction with an environment under test. The personas will be implemented as AI agents combining cognitive affective features to drive the decisions. The output of the testing will be the internal state of the agents and the interaction traces with the system. Those can be checked and compared to the design goals of the environment under test.

ICare4U is a project that proposes the development of a decision support system based on intelligent modelling and patient sub-group analysis, to provide personalized therapy for critically ill patients.
It is hypothesized that the 'Collective Experience' from large clinical databases, where clinical decisions are linked with patient outcomes, can be used to identify specific patient sub-groups and build personalized therapy models towards a new era of personalized medicine, allowing the improvement of patient outcomes in the ICU. The validity of the proposed systems will be tested using two case studies where generalized severity scoring systems have consistently performed poorly: patients admitted to the ICU who then develop acute kidney injury, where two-thirds of these patients require renal support therapy; and severe sepsis a typical heterogeneous disease among critically ill patients, in which the immune response is highly dynamic
and variable, and likely to need complex therapies to improve patient outcomes.
One of the tasks of the project involves using existing text-based information, such as medical reports and physicians and nurses’ notes, to improve the decision-making process. The work to be developed by the researcher will be in the context of this task, and consists of implementing and integrating a technique called “Fuzzy Fingerprints” in the decision support system, and to enhance and integrate Fuzzy Fingerprints with Deep Learning.
Digital fingerprints aim to extract information about a user that he/she has not provided knowingly, and represent such information in a compact and efficient form. Fuzzy fingerprints based on the order of top-k events have been successfully applied in many areas, including text mining, and will be used in this project to help identifying critically ill patients (by creating patient sub-group fingerprints). The technique presents a simple but extremely effective and robust way to evaluate and compare the relevant features of event patterns, which in the present case would be the text contained in the physicians/nurses notes. Important phrases and/or keywords will be used as events and event patterns. A text based fingerprint will be created for each admitted patient. A sliding window top-k algorithm will be adapted to create an evolving patient fingerprint algorithm to cope with patients’ evolving condition. Patients will be attributed to patient sub-groups based on fuzzy fingerprint similarity.
The MIMIC II database will be used for this project. All text data will have to be “cleaned up” on a pre-processing phase since textual medical databases have several particularities that prevent its immediate and effective use.

BI|2021/114
The objective of this project is to research MDRE (Model-driven Requirements Engineering) techniques and tools with a particular focus on the design and development of complex Web Apps, based on textual platform-independent specifications. The evaluation of this project would be in the development of the RiverCure Portal, a collaborative web application that would allow to manage resources like Water Rivers and Watersheds and related environmental objects and events.
 -----------
BI|2021/115
The objective of this project is to research MDRE (Model-driven Requirements Engineering) techniques and tools with a particular focus on the design and development of Web and GIS (Geographic Information Systems) Apps. The evaluation of this project would be in the development of the RiverCure Portal, a collaborative web application that would allow to manage resources like Water Rivers and Watersheds and related environmental objects and events.

The objective of this project is to research MDRE (Model-driven Requirements Engineering) techniques and tools with a particular focus on the design and development of complex Web and GIS-based (Geographic Information Systems) Apps, based on platform-independent textual specifications. The evaluation of this project would be in the development of the RiverCure Portal, a collaborative web application that would allow to manage resources like Water Rivers and Watersheds and related environmental objects and dynamic events like flood simulations.

1.	Extend Khepri with additional modules (e.g., evacuation simulation, visualization in virtual reality) that support the existing analysis.
2.	Explore the use of Khepri to solve problems in the architecture domain.

1.	Experiment with the generation of analytical models (e.g., for measuring lighting, energy, and acoustic performance) in different case studies.
2.	Explore and test the automatic analysis of architectural problems.
3.	Experiment with optimization algorithms for architectural design problems.

This research work aims to develop a real-time embedded system within the scope of project SARRROCA. The research work will involve designing novel hardware architectures, and study and implement optimization techniques. Expected outputs of this work are the implementation of prototypes for real-time fault-tolerant architectures.

The grant holder will:
1) Learn the internals of programming smart network equipment and catalog the requirements, constraints, and limitations of each platform.
2) Help build the first SyNAPSE research prototype synthesis engine.
3) Develop optimizations for the synthesis engine to offload functionality to the smart devices.

The objective of the project is to investigate, design, implement, evaluate, and report new security & dependability mechanisms for BaaS clouds.

The candidates should have an MSc in Computer Science, Electrical and Computer Engineering, or equivalent scientific areas. Excellent academic and practical background in programming, machine learning, and natural language processing. The candidate should have good knowledge of written and spoken English, be self-motivated and show initiative in solving problems. Strong preference is given to candidates with sound knowledge of Python and Pytorch.
Required language skills: proficiency in English.