admin – Pagina 2 – Progress in Research

Food Waste prevention: the circular economy paradigm

Posted on 14/06/202111/10/2021 by admin

Tag: Circular Economy, Food Waste Hierarchy (FWH), agri-food supply chain
Researchers: Federica Ciccullo, Raffaella Cagliano, Giulia Bartezzaghi, Alessandro Perego
Department: DIG

In the context of the global food supply chain one of the key challenges is preventing or limiting food waste, a phenomenon that has an ecological, economical and social impact.

The Food Waste Hierarchy (FWH) framework offers a more sustainable and holistic approach to the production and the consumption of food at all levels of the supply chain. The FWH works well within the circular economy paradigm, an economic model of production that aims at greater sustainability, limiting the use of resources and minimizing production waste.

A paper by Federica Ciccullo, Raffaella Cagliano, Giulia Bartezzaghi, Alessandro Perego of the Department of Management, Economics and Industrial Engineering (DIG) of Politecnico di Milano has recently published the paper “Implementing the circular economy paradigm in the agri-food supply chain: The role of food waste prevention technologies” on the Journal “Resources, Conservation and Recycling”.

The paper investigates how technology can play a key factor in implementing the principles of the Food Waste Hierarchy. Within the investigation, researchers carried out interviews on the role of technology in the food supply chain, both with technology providers and with companies involved in the production of food. The results identify strategies such as the adoption of various options of technologies as well as a strengthened cooperation at all levels of the supply chain, proving they can reduce food waste (i.e through the use of data science and big data to monitor and forecast the production) and can improve synergies with different level of the supply chain for waste prevention.

Read paper

Faster and sustainable Artificial Intelligence: Politecnico develops a new generation of computing

Posted on 13/06/202111/10/2021 by admin

Tag: resistive memory (ReRAM), resistive switching, computing circuits, memristore
Researcher: Daniele Ielmini
Department: DEIB

Researchers at Politecnico di Milano produced a novel in-memory computing architecture for a new generation of computing accelerators, with the potential to revolutionize the technology of artificial intelligence. Computers produced with this technology will offer greater functionalities and will be able to bypass the memory wall issue of digital computers. Compared with traditional CMOS technology, the new computers will be smaller, with less power consumption and will offer more functionalities, for example the capacity, such as the human brain’s ability to learn and recognize images.

The realized circuit is able to solve a system of linear equations (Ax=b) in a single operation in the timescale of few tens of ns thanks to an innovative method of in-memory computing, where the coefficients of matrix A are stored in a special device called memristor. The memristor is able to store analogue values, thus a memristor matrix can physically map a coefficient matrix A within the circuit, thus strongly accelerating the computation.

The proposed analogue in-memory concept is not only able to solve complex problems with huge saving in time and energy spending but has a lot of future applications, from the Internet of Things (IoT), to neuromorphic processors for artificial intelligence. The research has been carried out under the ERC European project RESCUE (Resistive switch computing beyond CMOS), of which Politecnico di Milano is the coordinating institution under the guidance of Professor Daniele Ielmini. The project was concluded in July 2020. Results have been published on the prestigious journal PNAS of the National Academy of Science of the USA.

Learn more

RESCUE Website

Photo by Alexandre Debiève on Unsplash

From “Black Box” to “Glass Box”: a humancentric Artificial Intelligence

Posted on 12/06/202111/10/2021 by admin

Tag: black-box effect, machine learning, deep learning, decision-making, Explainable AI (XAI)
Researcher: Marco Taisch
Department: DIG

Artificial intelligence will have a predominant importance in the future, making decisions that will have a considerable impact in everyday life.

Project XMANAI, under the Horizon 2020 scheme, started in November 2020 with Politecnico di Milano as one of the main collaborator: the project involves universities and research centers as well as industrial partners, such as Txt E-Solutions, Whirlpool Emea, Cnh Industrial e Deep Blue. XMANAI stands for ‘Explainable Manufacturing Artificial Intelligence’: its aim is to explain how Artificial Intelligence can be of assistance for manufacturing and of service for society while respecting European values and principles.

This is important as the decision-making process by AI is not always visible or understandable: this is also known as the ‘black box effect’, where the machine learning/deep learning algorithms are not explainable once they are computed, which raises fears of biases and mistakes among manufacturers and among the general public. Explainable AI (XAI) is an emerging field that aims at solving this issue by inspecting and attempting to understand the steps and models involved in decision making by Artificial Intelligence.

The project, taking into consideration 4 real-life cases in which Artificial Intelligence has had a positive impact on manufacturing, aims at changing the way AI is adopted by switching to a ‘glass box’ AI model, that keeps humans in the loop of the decision making process and that produces value-based explanations for manufacturers.

Learn more

PoliMappers in Bogotá for humanitarian mapping

Posted on 12/06/202111/10/2021 by admin

An original collaborative and humanitarian mapathonexperience was held with the aim ofmapping informal settlements in Bogotá, in Colombia.

It was all part of the master’s thesis by Maria Alejandra Rojas Bolanos and Silvia Raviscioni, two civil engineering students at Politecnico di Milano who are carrying out their research at IMM DesignLab, under the supervision of Professor Massimo Tadi.

This investigation into the redevelopment of these shanty towns had the ambitious goal of proposing a solution to a worldwide phenomenon that affects many cities globally, namely the proliferation of illegal residential settlements due to rapid urbanisation.

The time and resources required to map areas for study purposes, however, are often disproportionate to the results obtained.

The idea therefore was to set up collaboration with the PoliMappers, a group of volunteer students from the Politecnico, part of the international network YouthMappers as first European local chapter, who aims to form a new generation of mappers, promoting in their activity the culture of free and open-source software. This collaboration proved to be extremely worthwhile.

In this way, after a crucial first phase of data collection in the field with the application of Mapillary by the NGO Techo, the group, with the coordination of Chiara Ponti and Federica Gaspari – respectively president and faculty advisor of PoliMappers – and with the support of the Colombian local chapter YouthMappers Semillero Geolab UdeA, organized an online mapping event in OpenStreetMap environment that involved 70 people from the Politecnico and beyond.

The meeting on 26 March was also part of the innovative “Collaborative and Humanitarian Mapping” course, from the Passion in Action catalogue, which is supported by the MSc in Geoinformatics Engineering and coordinated by Professor Maria Antonia Brovelli. It wasattended by 61 students of the Politecnico di Milano.

The excellent result achieved means this experience is now a pilot project for voluntary mapping that can be replicated in other sectors where the Politecnico is conducting research into territories, such as Dakar, Maputo and Quelimane.

A platform to assist law enforcement agencies in internet forensics

Posted on 10/06/202111/10/2021 by admin

Tag: malware, payments tracking, Internet Forensics
Researcher: Stefano Zanero
Department: DEIB

Crimes are as adaptive as any social behavior, and with technological progress, new threats and issues emerge as well. Offences such as theft and scams are very effective on the internet, and with a relatively low investment perpetrators can steal a great deal of personal information.

RAMSES, a Horizon 2020 project, has had the objective to help Law Enforcement Agencies (LEAs) with digital forensics investigations. Two real-life case studies have been taken into consideration: ransomware and banking Trojans. Researchers used big data technologies to extract, storage, link and interpret information extracted from the internet and to look for patterns of fraudulent behavior.

The project ended in August 2019 and has reached its three main goals: researchers have built guidelines and models shared and made available to LEAs by examining the current landscape of fraudulent activities on the surface and on the deep web as well as have completed a comprehensive examination of best practices around Europe in tackling cyber crime.

Through the use of big data, they were able to search for patterns of fraudulent behaviors and hidden information and were able to build models to track malware payments.

Lastly they have diffused the knowledge and best practices collected in the project at a European level involving all stakeholders and LEAs, by including the experience gathered through the pilot programs that have taken place in the project in three different EU countries (Portugal, Belgium and Spain).

Learn more

Visit Ramses2020 Website

Photo by Markus Spiske on Unsplash

Local Hubs against Food Waste are 2 years old

Posted on 09/06/202111/10/2021 by admin

3,300 families reached and 152,000 meals redistributed, with over 76 tonnes of surplus food collected in 2020 alone: these are the results of the first two years of life of the Milanese Local Hubs against food waste: one in the Isola district inaugurated in January 2019 and one in the Lambrate district opened in October 2020.

On the occasion of the National Day for the prevention of food waste, the monitoring of data carried out by the Politecnico di Milano shows that the “Isola Hub” gathered together 7 brands of large retailers (LIDL Italia, Esselunga, Carrefour, NaturaSi, Erbert, Coop Lombardia, Il Gigante), with 9 retail outlets, and 14 non-profit organizations; while 5 brands (Esselunga, Il Gigante, Bennet, LIDL Italia, Penny Market), with 8 retail outlets, and 11 non-profit organizations are connected to the “Lambrate Hub”.

Even against the difficulties of the current period, the results of the first Hub in Isola and the recently opened Hub in Lambrate have demonstrated the sustainability of a model that is based on structured operational processes and solid cross-sector collaboration.

says Alessandro Perego, Director of the Department of Management, Economics and Industrial Engineering at Politecnico di Milano.

The success of the project is confirmed by the fact that two new local hubs are scheduled to open in the coming months, in the Corvetto and Gallaratese areas.

The Neighbourhood Hubs against food waste project involves many organisations: in addition to the Politecnico di Milano and Assolombarda, partners of the Comune di Milano in the Food Policy project, the project involves Banco Alimentare della Lombardia, Qubi Programme – Fondazione Cariplo, BCC Milano, Avis Milano, NUMBER 1 Logistics Group and Deutsche Bank. The opening of the two new hubs in the coming months will be possible thanks to the support of Fondazione Snam (Corvetto) and Fondazione Milan (Gallaratese).

A revolution in drug discovery: advanced computer-aided drug design

Posted on 08/06/202111/10/2021 by admin

Tag: Supercomputing, VirtualScreening, HPC, health, COVID-19
Researchers: Cristina Silvano, Gianluca Palermo
Department: DEIB – Department of Electronics, Information and Bioengineering

A drug has been found which is able to counter the SARS-CoV-2 virus, responsible for COVID-19. The drug in question is Raxilofene and it has been identified thanks to the European Exscalate4CoV project, supported by the European Horizon 2020 project for research and innovation, with the collaboration of Politecnico di Milano, Dompé Farmaceutici, Cineca and another 15 partners throughout Europe.

Exscalate4CoV uses the fastest pharmaceutical research platform in the world, created with the collaboration of professors Gianluca Palermo and Cristina Silvano from the Department of Electronics, Information and Bioengineering of Politecnico di Milano. From an archive of about 500 billion molecules, the EXSCALATE platform (EXaSCale smArt pLatform Against paThogEns) is able to select the molecules that meet certain compatibility requirements with the SARS-CoV-2 virus. Thanks to the CINECA supercomputers, researchers have analyzed over 10 million pharmaceutical molecules, identifying in Raxilofene the most promising molecule to inhibit the replication of coronavirus inside human cells. In vitro tests have confirmed the results processed by the platform. Raxilofene has been used for years against osteoporosis and is well-tolerated by the human body: this will make it possible to rapidly move forwards to the clinical test phase on patients affected by COVID-19. “One of the most computationally complex phases was the 3D modeling of the virus proteins, which was unknown until just a few months ago” comments Palermo. “Now we have a good model and the Exscalate platform is able to compare it with over 500 billion molecules in just a few weeks, identifying the molecules able to inhibit the virus from replicating”. With the start of the clinical study, the first phase of the project can now be considered over. Since the approval process to test the drug on people has been completed, the IRCSS Lazzaro Spallanzani in Rome and IRCSS Humanitas in Milan research hospitals have been carrying out trials on 450 patients since the end of October. During the second phase of the project, almost 500 billion molecules will be analyzed, many of these have never been used and are not present in nature. While the wait for the results continues, if one of these compounds proves to be interesting, moving forwards to the clinical phase will take time: tests to verify whether a molecule is toxic for humans can take between 5 and 10 years. This is why the project has prioritized the analysis of drugs already being used for other pathologies.

At the time of writing, researchers are carrying out the largest virtual molecule screening experiment in the world. The Politecnico di Milano team is at the forefront of this experiment, which will be developed using the two most powerful supercomputers in Europe: the ENI HPC5 and the CINECA Marconi-100 system. 70 billion molecules evaluated on 15 active sites of 12 SARS-CoV-2 proteins for a total of over one thousand billion evaluations. This number goes well beyond the “just” 2 billion evaluations carried out at the Oak Ridge National Lab in the United States on a single protein for the same reason, using the second most powerful supercomputer in the world, and the billion evaluations made by the same DOMPE-POLIMI-CINECA work group against the Zika virus, which at the time were considered unique experiments. “The EXSCALATE platform has the peculiar characteristic of being designed from the outset for situations like the one we are living through at the moment, where urgent calculations must be deployed at speeds that only supercomputers can achieve. At the moment, we are carrying out an experiment in only a few days which as little time ago as last year, would have taken tens of months” comments Palermo.

The project is coordinated by Dompè Farmaceutici alongside a multidisciplinary team and aims to continue to collaborate with Politecnico di Milano and CINECA during every phase to develop the EXSCALATE platform, thus accelerating the computational process in the search for new drugs and maximizing the efficiency of the new generation of supercomputers. “However, we are currently directly involved with just the computational challenge which we are really excited about thanks to its uniqueness, but no less important will be the next phase when the research carried out will be more than just an end in itself. The data produced by the simulation will be analyzed by Dompé Farmaceutici to identify interesting molecules that may be active on numerous proteins, and will also be made available to the scientific community”. Thanks to the recent investment decided by Italy and Europe, in October it was announced that a new supercomputer called Leonardo will be installed at CINECA next year, which should reach 250 thousand billion calculations per second (petaflop), 10 times more than the current rate. The Politecnico di Milano team is already geared up for this new challenge, also thanks to a new European project called LIGATE (LIgand Generator AT Exsascale), which will see the DOMPE – POLIMI – CINECA team working together for a further 3 years.

A bridge between artificial intelligence and optics

Posted on 07/06/202111/10/2021 by admin

With a study published in the prestigious journal Optica, researchers in the Physics Department at the Politecnico di Milano have built a connection between two fields: artificial intelligence, which has been increasingly studied in recent years, and non-linear optics.

The research, conducted by Carlo Michele Valensise, Giulio Cerullo, and Dario Polli, together with Alessandro Giuseppi from Sapienza Università di Roma, began about a year ago during the first lockdown. It is based on the study of Deep Reinforcement Learning (DRL), that is, the branch of artificial intelligence related to programming agents that can learn to control automated systems. In other words, a DRL agent “learns” thanks to the independent interaction with the system in front of it.

Laboratory experiments then confirmed that the application of DRL to non-linear optics allows for simplification of some processes and, more generally, to speed up experimentation. One possible application, for example, is found in the generation of white light, one of the most common phenomena in this field of research.

What happens within molecules immediately after interaction with light?

Posted on 06/06/202111/10/2021 by admin

Tag: light-matter interaction, attosecond, Molecular electronics
Researcher: Mauro Nisoli
Department: DFIS – Department of Physics

Prof. Mauro Nisoli (Department of Physics, Head of the Attosecond Research Center at Politecnico di Milano), along with Fernando Martín (IMDEA and Universidad Autónoma de Madrid) and Nazario Martín (Universidad Complutense de Madrid), have been awarded an ERC Synergy Grant for the TOMATTO project (the ultimate time scale in organic molecular opto-electronics, the attosecond).

Researchers will explore what happens within individual molecules immediately after interaction with light. This is uncharted territory, since light triggers events that are not easily accessible, happening as they do in extremely short time scales, in the order of attoseconds. The goal here is to study and – possibly – control the light-induced motion of electrons in molecules with an unprecedented temporal resolution; researchers also aim to understand how the interaction with light is influenced by the molecular structure, in order to alter this structure according to a specific design.

This project brings together skills and competences from different research centers and universities. The research, coordinated by a team of experts in laser technologies, is the synthesis of new organic materials and computational methods. The team in Politecnico di Milano will focus on the experimental validation of theoretical work using latest generation instruments. The end goal is to engineer the molecular response to be able to produce materials with improved opto-electronic characteristics.

TOMATTO will be funded by an ERC Synergy Grant under the Horizon 2020 scheme and will receive almost 12 million Euro of funding over 6 years. Of these, 5 million will be allocated to Politecnico di Milano.

Building a European Fintech risk management platform

Posted on 04/06/202111/10/2021 by admin

Tag: Financial Technology, Risk management, Artificial Intelligence, Blockchain
Researcher: Emilio Barucci
Department: DMAT – Department of Mathematics

Financial Technology (Fin Tech) is financial innovation made possible by innovative technology.

Different countries in Europe have different regulatory landscapes: thus, the European Fin Tech sector has the potential of being more competitive through the establishment of a common regulatory field across all Europe.

The FIN-TECH project (A FINancial supervision and TECHnology compliance training programme), funded under EU’s Horizon2020 scheme, involves 24 universities as well as financial institutions and stakeholders from all 28 state members plus Switzerland. Politecnico di Milano will be a partner of FIN-TECH through the contribution of the Department of Mathematics.

The project has the goal of building a common fintech risk management platform. The platform aims at automatize the compliance of Fin-Tech companies (RegTech) as well as at increasing the efficiency of supervisory activities (SupTech). The exchange of information on risk models and management for fintech companies will lay the foundation of the common platform. The research will have three main sources in gathering information: fintech companies and hubs, regulatory institutes, and universities and research centers. Research on risk models will be also carried out through Big Data analytics, AI and Blockchain technologies.

The diffusion of the findings will also be a core activity of the project, aiming at achieving uniformity across Europe: this will be carried out through training and coding session as well as through the establishment of a dedicated website.

Learn more

Cover Photo by Danielle Rice on Unsplash