Blog

The goal is to create AI models to assist in the analysis of thoracic radiographies in patients in a context of emergency.

A consortium integrating Hospital da Luz Learning Health, Instituto Superior Técnico (IST) and INESC-ID has an innovative project in progress, with the purpose of developing a solution composed of artificial intelligence (AI) models for the analysis of thoracic radiographies undertaken by patients in hospital emergency units, estimating the probability of presenting the characteristics of covid-19 infection. In case of high probability, the models enable to estimate the degree of severity of the disease.

The early identification and characterization of patients with covid-19 in emergency units is crucial to provide the best health care, the thoracic radiography being a complementary global means of diagnosis, which is fast and easy to perform. The creation of these AI models, applied to the analysis of thoracic radiographies in patients in emergency units, assists, in combination with further clinical data, the medical professionals in the detection of suspected cases of covid-19.

The aim is to respond to the following needs:

1. Optimize the work of radiologists, identifying and prioritizing in work schedule those radiographies suspected of covid-19;
2. Assist physicians of other specialties in the context of emergency, when radiologists are not available, with a tool for the analysis of thoracic radiographies;
3. Simplify the decision making for health professionals in the definition of the clinical protocol.

This project is being developed by a multidisciplinary team of radiologists, physicians from the emergency services of Hospital da Luz Lisboa and Hospital Beatriz Ângelo, specialists in ergonomics and human factors, researchers in the areas of machine learning and artificial intelligence, specialists in information systems and managers. The project is financed under the program Portugal 2020 and results will be presented during the first semester of 2021.

Our researcher Arlindo Oliveira was recently appointed CESAER’s envoy on the European Research Area (ERA) and the European Education Area (EEA).

The appointment ensures CESAER association ongoing and strong commitment to the shaping of the ERA and the EEA, through positions ‘Towards a truly reinforced European Research Area’ and ‘Towards a dynamic European Education Area driven by excellence’, which provide concrete recommendations in response to the European Commission’s communications on the topics earlier this year.

Know more here.

Team advised by INESC-ID Researcher Rui Henriques has participated in the 2020 edition of the EDP University Challenge and conquered a place in the top 3.
Daniel Marques de Castro, Miguel Trinca and João Aparício da Costa presented the work “Vehicle Smart Grid based on a Multi-Agent System”.
This project aims to “manage the cost of changing charging stations, minimize the number of unused charging stations minimize waiting time of vehicles to charge”.

Researchers Diogo Barradas, Nuno Santos, and Luís Rodrigues were distinguished with the ANRW ISOC.PT 2020 Prize: Best Research Paper and Internet Impact Acknowledge Mention, with paper “On the unobservability of multimedia-based covert channels for Internet censorship circumvention”.

Using multimedia covert channels for Internet censorship circumvention

It is widely known that totalitarian states apply censorship techniques to prevent the free access to information online. In this work, we tackle the development of tools that allow for circumventing censorship by leveraging covert channels established over non-blocked multimedia applications, such as Skype. We also assess the ability of censors to detect covert channels when resorting to detection techniques based in machine learning. We explored the limitations of such techniques to develop new encoding mechanisms to create covert channels that are able to avoid detection. Our results make an important contribution towards the ability to bypass censorship, delivering a set of tools that allow citizens located in countries ruled by repressive regimes to freely access information in the Internet.

João Amado, Miguel Correia and Fernando M. V. Ramos were awarded with ANRW ISOC.PT 2020 Prize Relevant Research Mention, with the work “Intrusion Detection with Programmable Switches”.

This work aims to improve intrusion detection in computer networks by leveraging the novel monitoring capabilities of modern programmable switches. To defend against the growing sophistication of network attacks, our solution explores machine learning techniques that analyze network traffic data for timely identification and response to new attacks.

Congratulations!

Join us!

All the information is available at European Researchers’ Night website.

Find the full programme here.

INESC-ID’s researchers João Vieira, Rui P. Duarte, and Horácio Neto, were awarded the IEEE Access Best Multimedia Award 2019 part 2. 

The video recently distinguished in this award is associated with the article “kNN-STUFF: kNN STreaming Unit for Fpgas”. 

K-Nearest Neighbors (KNN) is an algorithm used to classify datasets and runs normally on a computer. However, as datasets grow, the processing time increases and it becomes necessary to accelerate the algorithm execution. This research presents a HW/SW architecture to accelerate the processing of a classifier using a KNN algorithm in FPGA.

Watch the winning video here.

The IFIP International Internet of Things (IoT) Conference is an annual event of IFIP entirely dedicated to IoT research, innovations, and applications.

The 3rd IFIP IoT will take place virtually on November 5^th and 6^th, 2020.

The conference brings together researchers from 6 countries to present 8 talks, which reflect the state-of-the-art of IoT in its different domains.

Augusto Casaca, researcher at INESC-ID, is a member of Steering Committee for IFIP International Internet of Things and will be presenting the talk “A Perspective on IoT Edge Computing and On Its Challenges “, on the 1st day of the event.

Programme |Registration

The National Science Summit’20 will take place from November 3rd to 4th, 2020, at the Lisbon Congress Centre.

Rodrigo Rodrigues, INESC-ID’s researcher, will moderate the session: “CMU Portugal – defining new frontiers in Technology within the health sector”, on November 4 at 2 p.m.

Several INESC-ID’s PhD students are also presenting their scientific posters at this event.

The National Science Summit is promoted by Fundação para a Ciência e a Tecnologia in collaboration with the Ciência Viva – National Agency for Scientific and Technological Culture, and the Parliamentary Commission of Education and Science.

Registration is free and required.

More information here.