Webinar #5 – AIDA Webinar Series I “Anomaly detection in large graphs”

On September 30th took place the 5th Webinar “Anomaly detection in large graphs” of the AIDA Webinar Series promoted by the team of the Large Scale Collaborative project AIDA with the support of the CMU Portugal.

The session counted on Christos Faloutsos (Carnegie Mellon University) as main speaker, and also joining the session as speakers Jeremy Lee (Carnegie Mellon University), Mirela Teixeira Cazzolato (Carnegie Mellon University and University of São Paulo), Saranya Vijayakumar. Pedro Fidalgo from the Project company promoter Mobileum, participated as moderator.

Summary Webinar #5: Given a large who-calls-whom graph, how can we find patterns and anomalies? In this presentation we will discuss some patterns that several real graphs seem to obey (small diameter, power-law degree distributions), and how to use them for anomaly detection in real settings, like Mobileum’s call-graph, and other social networks.

This was the last Webinar of the “AIDA Webinar Series I Improving 5G Risk Management” which counted a total of five (5) Webinars held every two months from December 2021 to September 2022, gathering leading experts from academia to industry involved with the project.

To watch the Webinar #5, click below.

New techniques to reduce e-waste introduced under CMU Portugal project WoW

E-waste is one of the fastest growing toxic waste in recent years. Rapid increase in the production of electronics and batteries is draining scarce metals and other mineral resources. Now, researchers from the University of Coimbra (UC) have developed and tested a novel architecture of materials and fabrication techniques that allow us to reverse this reality and apply a new version of 3Rs policy (reduce, reuse and recycle) in the electronics area. That is 3R electronics (resilient, repairable, and recyclable). The results were published in the journal Advanced Materials.

The research, funded under the scope of CMU Portugal project WoW, represents a breakthrough toward overcoming technological pollution. Currently, the production of electronic waste has reached an alarming level of 7 kg/person/year. Only 20% of e-waste is sent for recycling, and only a small percentage of precious metals, mainly gold, are recovered.

Mahmoud Tavakoli, the lead author of the scientific article, explains that soft electronics based on novel polymers will be the best response to the problem of the e-waste. But despite the advances in soft electronics, the 3R electronics is only possible “if we can demonstrate new manufacturing techniques that, on the one hand, are based on resilient, repairable and recyclable materials and, on the other hand, can compete with existing PCB manufacturing techniques in terms of patterning resolution, multi-layer implementation, microchip integration and autonomous manufacturing”.

This research work, which is being carried out at the Institute of Systems and Robotics (ISR) of the Department of Electrical and Computer Engineering (DEEC) of the University of Coimbra (FCTUC), introduces a new architecture for scalable, autonomous, and high-resolution production of 3R electronic devices.

The ISR team has introduced a new architecture for soft materials such as conductive composites and substrates that satisfy 3R goals. They developed autonomous manufacturing techniques, including high-resolution digital patterns and one-step microchip welding, as well as supporting technologies for recycling materials and components.

According to Mahmoud Tavakoli, ISR researcher and professor at FCTUC, another differentiating factor is that the manufacturing process is entirely performed at room temperature, an essential step for green electronics: “everything is done at room temperature, including the deposition, patterning, and microchip soldering. Eliminating the temperature from the sintering process (as is common in printed electronics) and from the soldering process considerably reduces energy consumption, and is a step toward the use of green polymers, that were not possible before due to their heat sensitivity”.

This research presents a paradigm shift toward a more sustainable future and provides the foundation for the next generation of recyclable electronic devices. The team has shown the application of this architecture for wireless biomonitoring patches, and smart textiles that integrate state of the art microchips, for monitoring body temperature, electrocardiogram, respiration frequency, and detection of human motions such as swallowing, or classification of sport activities through wearable sensors.

However, when it comes to industrial level PCBs, such as the ones we see in mobile phones, these developed techniques still require further technological development “to reach the same maturity as the current printed circuit technology. We are rapidly making steps toward industrial-level maturity. We hope in less than 5 years we can start the process for substitution of some the current electronics circuits.,”, concludes Mahmoud Tavakoli.

The paper is available here. 

In the Media: SIC Notícias, Observador, Público, Eco Sapo, Notícias ao MinutoDiário Online (Região Sul), Notícias UC, Sapo Tek

Webinar #4 – AIDA Webinar Series I “Protecting the Security of the AIDA platform and the Privacy of its Data”

The 4th Webinar of the AIDA Webinar Series I Improving 5G Management promoted by the team of the Large Scale Collaborative project AIDA with the support of the CMU Portugal Program took place on June 8 with José Flora, (University of Coimbra) and Cláudia Brito (INESC TEC and University of Minho) and Justine Sherry (Carnegie Mellon University) as moderator.

The session named “Protecting the Security of the AIDA platform and the Privacy of its Data” was focused on how to prevent attacks to AIDA software, both for the security of the platform as for the privacy of the data subject whose data is being exposed and/or used. To achieve that, AIDA will be using state of the art security mechanisms, studied, and evaluated by the researchers of the project team, considering the new risks that rise from the migration to an Edge architecture and the employment of 5G.  The webinar presented and explained these issues within the AIDA platform, but also the mechanisms of intrusion detection and tolerance used, as well as for monitoring and adaptation of the platform. The talk  has also addressed how secure communications were achieved, never forgetting the privacy of the data subject and secure processing.

To watch the Webinar #4, click below.

The “AIDA Webinar Series I Improving 5G Risk Management” will count with a total of five (5) Webinars held every two months from December 2021 to September 2022, gathering leading experts from academia to industry involved with the project.

The next and last Webinar of this Series will take place on September 30, 2022.

For more information about this initiative and about the previous Webinars available at the AIDA Website.


Results from WoW project lead the way for a new generation of electronic devices

A team of researchers at the Universidade of Coimbra have developed a highly promising material for a new generation of electronic devices under the CMU Portugal project WoW. The research work presents a promising material that can be used in flexible displays, flexible solar panels, and even wearable biosensors among others. Led by Mahmoud Tavakoli, the Institute of Systems and Robotics team from Universidade de Coimbra recently published their findings and graciously was featured on the Advanced Materials Technologies journal cover page.

This graphene-coated liquid metal nanocomposite is a novel and promising class of biphasic composite that can be used as a transparent conductor. The authors used an infrared laser source for simultaneous laser sintering, thinning, and ablation of reduced graphene oxide coated eutectic gallium-indium alloy films and demonstrated their application in the fabrication of a high-resolution semitransparent sensor for human breath monitoring.

This is the first report showing a transparent conductor based on liquid metal. According to Mahmoud Tavakoli, “Liquid metals are interesting because they provide stretchability and self-healing, and they are excellent in thermal dissipation. So, this is an important step toward screens that are very resilient, and very resistant.”

The structure of the new material and the manufacturing method presented in this study represents an important step towards a rapid, low-cost, and scalable fabrication of graphene-based electrodes. The next step of the investigation will be, according to Mahmoud Tavakoli, «to explore the use of other types of lasers to improve the conductivity or transparency of the electrodes, as well as to study other applications of this technique such as film electronics, gas sensors, and moisture and energy storage devices.”

Link to Article
Link to Coverpage

In the Media: RTP, Visão, Porto Canal, Notícias de Coimbra, Sapo, Greensavers, Planeta Algarve, Ambiente Magazine


In the Media: CMU Portugal project TAMI supports results for an early detection of Covid-19

Researchers at Institute of Systems and Computer Engineering, Technology and Science (INESC TEC) led a study on the use of Artificial Intelligence (AI) and Deep Learning (DL), in the complementary diagnosis of COVID-19 by Chest radiography (CXR) through deep learning. The work was recently published in the prestigious scientific journal Nature – Scientific Reports under the scope of CMU Portugal TAMI project. 

TAMI proposes to put AI at the service of the health sector, more specifically to support clinical decisions to increase confidence in medical diagnosis. The COVID-19 pandemic has impacted healthcare systems across the world and the speed of transmission made crucial a fast and early diagnosis of the disease. Chest radiography has been one of the main complementary methods for experienced radiologists to diagnose/follow COVID-19 patients, throughout the pandemic. However, the workload of qualified technicians during this period has been compromising the decision process, leading to the use of less experienced clinicians. Automated image analysis through AI techniques and deep learning can play an important role in assessing CXRs, providing a crucial second opinion for radiologists and technicians in the decision process.

Since the pandemic’s beginning, there has been a great effort from the scientific community in these ICT areas to find new approaches to support the medical diagnosis. According to Aurélio Campilho, one of the project PIs, “the goal of this research was exactly to study how Deep Learning can be placed at the service of medical diagnosis”. He adds that “we wanted to evaluate how Deep Learning could help the interpretation/reading of CXRs and support the diagnosis and follow-up of COVID-19 patients. Our study showed that the use of these algorithms in a clinical environment is much more complex than expected”. In close collaboration with ARSN (Regional Health Administration of the North) it was possible to identify the main challenges in applying these Deep Learning tools and develop new techniques that can increase the robustness of these systems.

Deep Learning is a branch of Machine Learning that provides computers with the ability to learn and perform human-like tasks, such as identifying images, recognizing speech, or making prognoses. This study evaluated the performance of a DL system in diagnosing COVID-19 by comparing it to the analysis of radiologists. One of the main conclusions is that distinguishing between COVID-19 and other pathologies on CXRs is a difficult task, even for experienced radiologists. However, it was possible to demonstrate that the performance of DL algorithms in identifying COVID-19 can be significantly improved if they learn directly from radiologists, more clearly identifying the radiological signs of COVID-19 and leading to a better diagnosis.

Although this methodology is still at an early stage, the goal is to apply this research to other pathologies identified by CXR: “Although COVID-19 has been the main focus of our research over the past two years, there are many other pathologies and findings that can be identified on CXRs. Our goal is to develop a system that can identify these automatically. A tool of this sort would be extremely useful to help radiologists, technicians, and less experienced physicians in interpreting CXRs”, concludes Aurélio Campilho.

In a broader scope, the TAMI project that is being led by First Solutions, with INESC TEC, Fraunhofer Portugal, Administração Regional de Saúde do Norte (ARS Norte) and CMU Electrical and Computer Engineering Department will develop tools to support the medical decision, based on artificial intelligence algorithms that will explain to both clinicians and researchers the diagnosis of a specific disease and its causes, focusing on cervical cancer, lung diseases and eye diseases. The project will work on a commercial, scientific, and academic platform that will provide “consumers” access to results and explanations of diagnostic orders, filtered data sets access for investigators or scientists, and a knowledge base for academic purposes.

In the Media: Expresso Online, Público, Observador, SIC Notícias Online, Sapo 24, Sapo Lifestyle, Atlas Saúde, Cidade FM Online, Smooth FM Online, Diário de Notícias da Madeira, HealthNews Online, M80 Online, Notícias ao Minuto, Rádio Comercial Online, S+ Online.

More about the project: https://cmuportugal.org/large-scale-collaborative-research-projects/tami/


Waste production in Lisbon falls sharply during the 1st Covid lockdown due to the abrupt decrease in tourism

A team of researchers from NOVA IMS concluded, in a study carried out under the CMU Portugal Large Scale Project BEE2WasteCrypto, that during the 1st lockdown related to COVID-19, there was a severe drop in the production of waste in Lisbon, for both mixed and recycled waste, essentially due to the fall of tourism.

The restrictions on mobility and economic activities imposed by governments due to COVID-19 and the adoption of remote work affected waste production and recycling patterns and contributed significantly to a change of scenery. Miguel de Castro Neto, Associate Dean at NOVA Information Management School (NOVA IMS) and Principal investigator of the BEE2WasteCrypto project at NOVA Cidade – Urban Analytics Lab, is one of the co-authors of the Paper Impact of COVID-19 lockdown measures on waste production behavior in Lisbon. The recent study focused on waste production in the Lisbon area, considering the approximately 544 thousand inhabitants and 100 km2 of the urban area, between 2017 and the end of 2020.

According to the researcher and the conclusions of the NOVA Cidade – Urban Analytics Lab team, which he leads, “the study showed that COVID-19 led to a decline in the volume of waste collected and that the main cause was the decrease in tourism. On the other hand, we also noticed that in Lisbon the changes were directly related to the type of waste and the spatial distribution of its production within the city. Residential areas with the highest population density were those with a smaller decrease in waste production, while areas with high tourism rates had a greater decline.”

The first state of emergency and consequent lockdown in Portugal declared on March 19, 2020 lasted until May 2, 2020. During that period, the city of Lisbon suspended door-to-door recycling collection until June 1, 2020, and the mixed waste collection was reduced to a maximum of three times per week, which affected 37% of the waste collection circuits, which had a frequency of collection up to 7 times per week.

The restrictions imposed in the context of COVID-19 had an impact not only on the volume of waste produced, but also on its distribution, which brought new challenges for policy-makers and those responsible for urban planning on where to invest efforts while complying with the health recommendations of the Portuguese Directorate-General for Health (DGS). 

According to Miguel Neto “the insights obtained under this study on production and distribution waste can help city officials to develop more targeted and adequate policies for each area, depending on their contextual characteristics in pandemic scenarios or other scenarios that substantially change city dynamics. The goal is to develop tools to analyze data support urban management and planning and integrate into cities’ urban intelligence platforms.”

In the period studied after the end of the confinement, the conclusion is that the production levels of recycled waste increased, but did not return to pre-pandemic levels.

This study was carried out under the BEE2WasteCrypto project developed within the scope of the CMU Portugal Program, in a collaboration between the company Future Compta (project promoter), NOVA Information Management School (NOVA IMS), Instituto Superior Técnico, the company 3drivers and Carnegie Mellon University. The main goal of the project is to develop a differentiating and intuitive IT tool which, based on high resolution data on waste production, allows Regional Waste Management Utilities (RWMUs) to design and manage optimal decentralized solutions for each region, as well as promoting more sustainable waste production and separation behaviors. Using blockchain technology and a cryptocurrency wallet, it will be possible to implement PAYT-type incentive mechanisms to encourage good citizen practices, on which the success of any waste management strategy depends.

Link to the paper on ‘Waste Managent Journal’

News in the Media: Visão; Observador; Diário de Notícias; Sapo.pt; CM Jornal; Saúde Mais 

AIDA Webinar Series: Improving 5G Risk Management

The CMU Portugal Program and the coordination of the Large Scale Collaborative project AIDA will host between December 2021 and September 2022 a series of webinars on the improvement of 5G risk management.

The “AIDA Webinar Series I Improving 5G Risk Management” will count with a total of five (5) Webinars held every two months, gathering leading experts from academia to industry involved in the project. The main goal of this initiative is to launch a discussion that will contribute to highlight different topics and challenges related to this area. 

The five different sessions will consist of an overview talk by an academic or a business expert involved in the AIDA project, followed by a moderated discussion with attendees. 

With this initiative, the organization expects to share relevant knowledge and experiences to a broader audience in order to exemplify how the collaboration between academia and industry can play an important role on the improvement of 5G risk management for the benefit of the telco companies.

Registration to the Webinar #1 is currently open.

For more information visit the AIDA Website.



CAMELOT online Workshop highlighted the results of the first year of project

The CMU Portugal Large Scale Project CAMELOT organized on October 25th its first annual Workshop for an overview and balance of the first half of the project which was launched at the beginning of 2020 and will convene through 2022.

The workshop was held online and counted with representatives from all the institutions involved in the project, including Pedro Bizarro from the project’s leading Company Feedzai, Alcides Fonseca from LASIGE and Faculdade de Ciências da Universidade de Lisboa (FCUL), Bruno Cabral from Universidade de Coimbra (UC), Paolo Romano from Instituto Superior Técnico (IST) and David Garlan from the Computer Science Department at Carnegie Mellon. The Workshop was divided into four (4) sessions, one for each partner Institution starting with Feedzai, who presented work on detecting money laundering and on explaining predictions on time series.

Técnico and CMU followed next with two CMU Portugal Dual Degree Ph.D. students in Software Engineering as speakers. Maria Casimiro started her Ph.D. in 2019 and did an internship at Feedzai during the summer (more about her experience here) and Pedro Mendes who entered the Program in 2021. Both students are being supervised by Paolo Romano (IST) and David Garlan (CMU), researchers of the CAMELOT project, and worked on automatic adaptation and optimization of machine learning systems in the cloud.

In the second session, Alcides Fonseca hosted two presentations from FCUL, one on static verification of Machine Learning pipelines, by MSc student João David, and the second on Genetic Probabilistic Programming by PhD students Guilherme Espada and Paulo Santos, the latter also a PhD Dual Degree student with CMU Portugal.

The final session was chaired by Bruno Cabral, who introduced Qianying Liao, Hugo Matalonga and Francisco Ferreira, from the University of Coimbra, who worked on different approaches for privacy-preserving transfer learning.

The CAMELOT project expects to revolutionize the detection of financial fraud through Machine Learning techniques. The project aims to develop an innovative machine learning platform, which will tackle three key issues that hinder the efficiency and accuracy of modern AI applications such as machine learning models, cloud resources, anonymized data, privacy issues, and integrating information from different, independent, and heterogeneous data platforms.

More about the project here or watch the video below:


CMU Portugal welcomes its Ph.D. students on Pittsburgh Campus

On Thursday, October 7th, the CMU Portugal Program held the 2021 Fall Welcome Back Lunch on campus at Carnegie Mellon University. Dual Degree students attended from five different departments including Computer Science, Language Technologies Institute, Software Engineering, Electrical and Computer Engineering and Engineering and Public Policy.

The CMU Portugal Program currently has 18 students on CMU’s campus this semester, one of the largest numbers ever. From this group, 15 attended the Welcome Back Lunch including many students who are at CMU for the first time. First year students Luis Gomes, Margarida de Almeida, and Pedro Mendes are spending their first academic year studying at CMU. Nuno Sabino, Afonso Tinoco, Manuel Fancisco Reis Carneiro, Pedro Malveiro Valdeira, Afonso Amaral, Patrick Fernandes, and Daniel Ramos are all in their second year of the Program and are now spending their first year at CMU. Neil Mehta and Diogo Mendes Cardoso were able to share even further experiences, it being their third year in the Program; and Jihoon Shin and Artur Balanuta are finishing their Dual Degree Ph.D. Programs at CMU.

At the Welcome Back Lunch, first year through final year students were able to meet and introduce themselves to their colleagues in the Program in an informal setting while enjoying lunch. While getting to know each other, they bonded over the neighborhood of Pittsburgh they are living in and the nuances of the local grocery stores and products in America and Portugal. Other topics of conversation included the courses offered at CMU and in Portugal, the differences between our various Dual Degree Ph.D. Programs, and their experiences settling in at CMU and Pittsburgh. During this networking event, the students also shared their experiences at CMU and their Portuguese Institutions such as Universidade Nova de Lisboa (FCT- UNL), Universidade de Coimbra (FCTUC), Universidade do Porto (FEUP and FCUP) and Instituto Superior Técnico. Many students expressed their appreciation for the gathering and are looking forward to the next on- campus event.