This challenge arose directly from conversations prior to the opening of the competition, between a group of Iscte teachers (under the aegis of the IA>AP Competence Center, https://iaap.iscte-iul.pt) and members of the PlanApp board. Among the tasks that were considered interesting for exploring and testing possibilities, the following stood out (in the area of AI / Data Science): 1. Analysis of topics from the outputs of the “Building Bridges” workshops 2. Extraction, processing and analysis of inequality monitoring indicators 3. Extraction of fields in public policy planning documents 4. Analysis of demographic indicators Task 1 aims to test the possibilities of semi-automatic processing of conference output in order to reduce processing time and/or flag up particularly relevant parts for the PlanApp of the documents resulting from the “Science and Public Policy Workshops: How to build bridges?”. In these workshops, participants are invited to write short texts with proposals, difficulties and challenges related to the interaction between academia and public policy, but the manual processing of this amount of text is demanding in terms of reading time for the organizers, and a semi-automatic processing is beneficial, which can not only highlight the most addressed topics, but also point out the most relevant parts (or those that address more original topics). The aim of Task 2 is to help with the implementation of the Inequalities Report, where PlanAPP has developed quantitative (description and simulation) and qualitative analyses of various dimensions of inequality. One of the main difficulties in this process is the continuous need to merge information from different sources. The aim of this task is to map the various sources and organize the process of merging and cleaning data, which will allow for a more stable analysis of these indicators. Task 3 is a task of structuring semi-structured documents. Public policy planning documents are usually semi-structu...

Nowadays, digital health devices play an active role in our healthcare and even let us cooperate with our physicians to improve our health, preventing health deterioration and real-time response to decrease health costs and increase general health quality for individuals. Patients can have greater access to specialized care if equipped with sensing devices that effectively monitor health status and acknowledge alterations or abnormal events. More and more people are effectively using digital health devices, many of which are classified as medical devices (according to the European Union Regulation (EU) 2017/745 and Regulation (EU) 2017/746), equipped with or sending data to AI systems. Shortly, most clinicians, including speciality doctors, paramedics, and nursing staff, will be using some AI technology. These digitally empowered healthcare solutions provide accelerated case detection, constant surveillance, access, and advanced decision-making while improving the quality of services and personalizing health.However, for digital health technology to be effective, reusable, and universal, not only are there insufficient standards yet that allow for the validation of many of these services but also the digital connection with the medical aid and AI processing of health-related data is lacking standardization. While digital health can be underpinned via common standards (like HL7 FHIR) to facilitate communication between devices and systems, we also need standards allowing for the establishment of uniform, transparent, and trustworthy AI processes to be performed on health data, ensuring the compliance of those processes with the existent regulatory framework, well-established Data Privacy safeguards and AI Act compliance. Personal health devices can positively change individual patient outcomes and help make progress in reducing health disparity. However, the data you collect from the devices needs to work with other devices, apps, and platform to communicate with pla...

AI4PA Portugal's strategic objectives and action plan are clearly aligned with the main focus areas of the Digital Transition Action Plan:    Pillar I - Empowerment and digital inclusion of people    Pillar II - Digital transformation of the business fabric    Pillar III - Digitalisation of the State    The Centre's activity will pursue six strategic objectives, aligned with the Digital Transition Action Plan, namely: optimising public policies in the various areas of governance based on Artificial Intelligence and the promotion of innovative digital technological solutions; improving the interaction of public services with citizens and businesses; assessing the social impacts and ethical implications of technologies, including Artificial Intelligence; increasing the digital skills of public entities and the small and medium-sized enterprises (SMEs) that provide them with services; disseminating good practices and reusable solutions of national and international origin; and improving governance for the digital transition at the various levels of state intervention.    AI4PA Portugal aligns its intervention with the model established in the European network of Digital Innovation Hubs, targeting the priority services of the Digital Innovation Hubs described in the Digital Transition Action Plan,    1- Experimentation and testing of digital technologies in the phase prior to the investment decision; 2- Qualification and training in digital skills; 3- Support in finding funding for investment in digital technologies; 4- Acting as a facilitator bringing together different actors.  

This study contributes to the knowledge of the reality, the risk assessment and the definition of fraud prevention strategies associated with the use of European funds in Portugal.  The main objectives of this study are: * To collect information, process, systematise and analyse data on European funds in Portugal, particularly regarding situations of irregularities in their use; * To identify opportunities for improvement in the process of data collection, in the management of information systems, and in the sharing of information between the various organisations involved;  * To increase transparency in the use of funds in Portugal.  Entities involved: Iscte, NovaSBE, ADC, IFAP, PGR Project starting date: 1 April 2022 Duration: 12 months

The object of study is the timely prediction of the possibility of non-compliance in terms of timings or financial targets. This research will test the potential of a system capable of generating an alerts for the possibility of non-compliance based on known data at the time of application or at key moments in the project's monitoring. This alert should be substantiated according to the studied variables that are directly involved in this result, in order to support a properly informed decision.   

The ECI4.0 project aims to develop and validate a prototype of multimodal platform for intelligent analysis of costumer behvior in comercial spaces using computer-vision, sensor fusion, and machinel learning techniques to enable an advancement in terms of the ambient intelligence for specialized retail spaces.

The project aims to improve incentive management, using machine learning approaches to identify operational and strategic risk levels in the analysis and verification phases of project payment requests.

Mobile security faces serious challenges, with alarming threat levels of malicious applications (malware). Malware applications attempt to capture user’s private data for illicit purposes, namely financial data, of personal context (such as location), business / corporate or other kinds of valuable information.  To address this problem the AppSentinel project proposes that App Stores should incorporate proactive and intelligent anti-malware mechanisms themselves, given its privileged position between developers and end-users. In this sense, we propose to research and develop an intelligent anti-malware system for Android App Stores, capable of performing static and dynamic analysis of malicious applications from several sources and understand their behavior patterns, which will then be used in testing new applications submitted to these stores. Moreover, these new applications will also be tested regarding good practices in secure mobile software development, which will lead to educational feedbacks to developers. Finally, a supervised machine learning system will be investigated and developed for efficient detection of new malicious applications based on users’ feedback. With these technological innovations we intend to reduce the incidence of malware on mobile devices, increase the efficiency in the analysis of virus reported by users and accelerate the reaction to new threats, and contribute to the adoption of secure mobile software development practices by developers.

IT tasks:a) Support in the definition of the technologies to apply in the Decision Support System to implement in the project;b) Support, the implementation, with technical revisions;c) Coordination of the MsC. thesis associated to the project;d) Coordination of the scientific dissemination activities.