Archive for category: Digital

On January 30 and 31, 2018 in Nantes, the aLIFE symposium focused on the software industry’s contribution to the industry of the future. It was being organized by IMT Atlantique, and aimed to bring together manufacturers and researchers in order to target shared problems, and respond to national and European calls for projects in the future: cloud manufacturing, data protection, smart factories, etc. Hélène Coullon, Guillaume Massonnet and Hugo Bruneliere, researchers at IMT Atlantique and co-organizers of the symposium, answered our questions about this event and the issues surrounding the industry of the future.

What were the objectives of the aLIFE symposium?

Hélène Coullon – The objective of this symposium were to hold a meeting bringing together researchers from IMT Atlantique, other academic players such as the Technical University of Munich or Polytechnique Montreal, and manufacturers like Dassault Systems and Airbus, to focus on the theme of the industry of the future, and more specifically on the contribution of the software industry to the industry of the future.

Guillaume Massonnet – We were also seeking to adopt a coherent and constructive approach to connecting the research we are conducting with the needs of industry, and to determine which challenges we should respond to today. Finally, we wanted to form a consortium of stakeholders from the industrial and academic worlds to respond to European and national calls for projects.

What themes have been addressed?

HC – The main themes included smart factories, cloud manufacturing, which is related to cloud computing, the modeling of processes, resources and data (physical and software), and the related optimization issues.

Hugo Bruneliere – On the one hand, we are inspired by software approaches that can be applied to the context of industrial systems, which include a significant physical aspect, and on the other hand, there is the question of how to position and use the software within these new industrial processes. These two aspects are complementary, but they can be addressed independently. This is a relatively new area. A great deal of research has been carried out on the topic, and initiatives are beginning to emerge, but there is still much work to do.

What is cloud manufacturing?

HC – Cloud computing allows IT resources to be rented “on demand”, for example: processors, data storage, software resources, etc. Cloud manufacturing is the application of cloud computing concepts aimed at transferring IT resources to industrial resources. In other words, cloud manufacturing makes it possible to move towards “on-demand” production.

For example, we can imagine a user making a production request using an online platform. Via the cloud, this platform would distribute the tasks to be performed using different means of production, located in different geographical places.

What can cloud manufacturing offer manufacturers?

HB – It allows them to render their production units more profitable. Large companies have machines they have invested in, and they want to operate them as much as possible to make them profitable. If they do not use them continuously, they can make the unused production capabilities available to startups that do not have the means to invest in these machines. This allows large companies to have a better return on investment and prevents smaller companies from having to invest in expensive equipment.

We can also imagine a new way of producing for individuals, no longer by mass, but on demand, with the possibility of greater product customization.

How can this software contribute to data security?

HC -Industrial data is sensitive by definition. Of course, in the context of the industry of the future, with distributed production, the data will travel through external networks and be stored on remote servers. They will therefore potentially be exposed to attacks. We must secure the entire path taken by the data by using cryptography, for example, among many other techniques.

What are smart factories?

GM – A smart factory is an industry in which the various means of production are automated, intelligent, and able to communicate with each other. This raises issues related to the size of the data flow: issues of big data. We must therefore take this information into account to integrate it into the production decisions and their optimization.

The new modes of production break with traditional practices, in which production chains were dedicated to specific, mass-produced products. Today, new machines have become reconfigurable, and the same production lines are used for several types of products. Therefore, there is a move towards an industry that increasingly seeks to customize its production.

And these changes will take place through the development of specific software architectures?

HB – Through the aLIFE symposium, we wish to show that the contribution of software is necessary in responding to the problems facing the industry of the future. We have significant experience in software in our laboratory, and we intend to build on this expertise to show that we can provide the industry with solutions.

Everyone who wears glasses knows: finding the best pair for your face can be a daunting task… The VESPA project, led by researchers at IMT Lille Douai and hosted by the Teralab platform, is working with Cape Trylive to develop machine learning algorithms that can determine users’ facial characteristics during virtual online fittings and recommend products based on their morphology.

Do you have a round face? Then the best glasses for you would be angular and narrow designs. Do you have a square face? Then try butterfly-shaped glasses! Based on your face shape, certain types of frames will look better on you than others. For a few years now, plug-ins on opticians’ websites have allowed users to try on glasses virtually. However, they do not offer features to help users find the best frames for their face.

The VESPA project, led by Jacques Boonaert and Stéphane Lecoeuche at the IMT Lille Douai Computer and Control Sciences Research Unit, in collaboration with Pascal Mobuchon of Acep Trylive, a virtual fitting plug-in supplier, aims to develop a machine learning algorithm capable of identifying users’ face shapes and recommending glasses based on their morphological characteristics. “Acep Trylive has developed technology for establishing the key points on users’ faces while they are filmed via webcam during virtual fittings,” Stéphane Lecoeuche explains. “The goal of the VESPA project is to develop algorithms capable of analyzing the position of key elements on faces to determine the user’s morphology.” All the data used in the context of this project are anonymized and hosted on the secure, neutral and sovereign Teralab platform. TeraLab also provides researchers with tools for processing these data sets.

Read more on I’MTech: TeraLab, a big data platform with a European vision

Algorithms that can identify facial morphology

The algorithms developed by the researchers follow a supervised learning logic. “This means that we submit a set of images labeled by human experts to the algorithms, which determine if the person’s face is round, square, oval…” Jacques Boonaert explains.

In addition, the key points that Acep Trylive’s software automatically establishes on the user’s face provide the algorithm with a set of descriptors. For example, a descriptor could be a measurement of the key points on the face: this could be the height of the forehead, the shape of the chin, the width of the face or the jaw, etc. Based on the data labelled by human experts, the algorithm will determine which descriptors are most relevant in recognizing the user’s morphology. “We have tested sub-sets of descriptors. In all, there are over 20,” says Stéphane Lecoeuche. “The algorithms then ascertain the influence of the descriptors on their own to define the best morphological characterization.”

There are three of these morphological classification algorithms. One focuses on the shape of the jaw, the second on the face shape, and the third on the width of the forehead. Digital descriptors of the user’s hair, eye and skin color are also used to propose the most suitable colors for the frames. All of this data is then merged to create recommendations for glasses adapted to the user based on these characteristics.

The Acep Trylive software highlights the key points on users’ faces (in blue)

Recommending products based on users’ morphology

Based on the monitoring of behavior and consumers’ history, the researchers were able to determine which glasses each internet user preferred: “Someone tries on a first pair of glasses, then a second, comes back to the first, tries a third pair, then again comes back to the first… In observing this sequence, we can determine which product the person prefers!” Jacques Boonaert explains.

The learning algorithm takes this fitting history into account and statistically consolidates the glasses the user preferred by morphology type. “Thanks to the data from thousands or even hundreds of thousands of fitting sessions, the algorithm makes the connection between the face shape and the products that were tried on,” says Stéphane Lecoeuche.  Therefore, for each new user who tries the application, the morphological analysis algorithms will determine their face shape and, depending on the choices of users with a similar morphology, and the recommendation engine will propose a set of products most likely to please them.

Seeking a partner company for further development

“We also had to work on the product’s geometric classification. The problem is that we have not been able to access the data from opticians’ catalogs, which classify glasses by shape, style, color…” Stéphane Lecoeuche explains. The researchers had planned to work on the association between the customer’s morphological characteristics and the products’ geometrical characteristics. While the algorithmic analysis of the facial morphology provided good results, the lack of data on the frames has limited their objectives.

“The other difficulty is that we do not have access to users’ final purchase decisions,” Jacques Boonaert adds. “We are aware that this is sensitive data for businesses. This is why we would like to create a strong partnership with an optician in order to further develop this project.” The researchers wish to implement a second phase of experimentation with a partner company, in which the algorithm could integrate the users’ buying decision and the products’ geometric classification. In the meantime, while waiting to find a company that would like to integrate the project consortium, the research team is continuing its work in machine learning geared towards industry and trade.

Starting with Algorithm and ending with Virus, this list features terms like Phishing and Firewall… As the symposium entitled “Are we entering a new era of cybersecurity?” is getting underway at IMT, here are 24 words to help you understand the concepts, technologies and systems used to protect people, materials and organizations from cyberattacks. This glossary was compiled with the help of Hervé Debar, a researcher at Télécom SudParis, an expert in cybersecurity and co-organizer of the symposium.

Algorithm – A sequence of instructions intended to produce a result (output data) by means of a calculation applied to input data.

Critical infrastructures – Infrastructures for which a cyberattack could have very serious consequences for the services provided, even to the point of putting lives at risk.

Cryptography – The science of secrets. Cryptography proposes algorithms that can make data unreadable for those who do not have the secret. It also makes it possible to sign digital documents.

Cyberattack – A sequence of actions that lead to the violation of the security policy. This violation often takes the form of a computer system or network malfunction (inability to connect, a service that is no longer available, or data being encrypted using ransomware). A cyberattack can also be invisible, but lead to serious consequences, such as the theft of confidential information.

Cyber defense – A country’s means of attacking and defending its computer systems and networks.

Cyber range – A training platform for cyberattacks and defense.

Denial of Service Attack (see Distributed Denial of Service Attack)

Distributed Denial of Service Attack (DDoS Attack) – An attack aimed at overloading a service provider’s resources (often related to the network), making it inaccessible.

Electromagnetic injection – An electromagnetic signal sent to disrupt the operation of an electronic component (processor, memory, chip card…).

Firewall – A network component that filters incoming and outgoing traffic on a website.

Flaw – A (software) flaw is a programming error made by the programmer that allows a hacker to run a program for a different use than what was intended. The most prevalent example is SQL injection, in which hackers use a web site’s interface to control databases they could not normally access.

Google Project Zero – A Google project aimed at finding new vulnerabilities in software.

Hacking – Computer data theft.

Intrusion – Unauthorized connection to a system.

Krack (Key Reinstallation Attacks) – Attacks against the WPA2 protocol that allow an attacker to force the reuse of an encryption key. This allows the attacker to collect a large number of packets, and therefore decrypt the network traffic more easily, without knowing the key.

Malicious software (see Malware)

Malware – A program used for a purpose that is inconsistent with the user’s expectations and violates the security policy. Malware often uses vulnerabilities to enter a system.

National Vulnerability Database – A project of the National Institute of Standards and Technology (NIST) that identifies and analyzes software flaws.

Phishing – A social engineering technique, in which an attacker convinces a victim to act without understanding the consequences. The technique often relies on emails with fraudulent content (e.g. CEO fraud scams).

Ransomware – Malicious software (malware) aimed at extorting money from a victim, often by encrypting the data on their computer’s hard disk and demanding payment in exchange for the decryption key (often these keys are useless, and purchasing them is therefore useless).

Resilience (by design) or cyber-resilience – A system’s ability to function in the event of an attack, that is, provide a service to its users in any condition, albeit at a reduced level.

Security Information and Event Management – A platform for uploading and processing alerts that allows operators to monitor their systems’ security and react in the event of an attack.

Trojan Horse – A backdoor installed on a system without the users’ and administrators’ knowledge, which allows a hacker to regularly and easily connect to the system without being seen.

Virus – Malicious software capable of entering a system and spreading to infect other systems.

Mohamed Daoudi, a researcher at IMT Lille Douai, is interested in the recognition of facial expressions in videos. His work is based on geometrical analysis of the face and machine learning algorithms. They may pave the way for applications in the field of medicine.

Anger, sadness, happiness, surprise, fear, disgust. Six emotions which are represented in humans by universal facial expressions, regardless of our culture. This was proven in Paul Ekman’s work, published in the 60s and 70s. Fifty years on, scientists are using these results to automate the recognition of facial expressions in videos, using algorithms for analyzing shapes. This is what Mohamed Daoudi, a researcher at IMT Lille Douai, is doing, using computer vision.

We are developing digital tools which allow us to place characteristic points on the image of a face: in the corners of the lips, around the eyes, the nose, etc.” Mohamed Daoudi explains. This operation is carried out automatically, for each image of a video. Once this step is finished, the researcher has a dynamic model of the face in the form of points which change over time. The movements of these points, as well as their relative positions, give indications on the facial expressions. As each expression is characteristic, the way in which these points move over time corresponds to an expression.

The models created using points on the face are then processed by machine learning tools. “We train our algorithms on databases which allow them to learn the dynamics of the characteristic points of happiness or fear” Mohamed Daoudi explains. By comparing new measurements of faces with this database, the algorithm can classify a new video analysis of an expression into one of six categories.

This type of work is of interest to several industrial sectors. For instance, for observing customer satisfaction when purchasing a product. The FUI Magnum project has taken an interest in the project. By observing a customer’s face, we could detect whether or not his experience was an enjoyable one. In this case, it is not necessarily about recognizing a precise expression, but more about describing his state as either positive or negative, and to what extent. “Sometimes this is largely sufficient, we do not need to determine whether the person is sad or happy in this type of situation” highlights Mohamed Daoudi.

The IMT Lille Douai researcher highlights the advantages of such a technology in the medical field, for example: “in psychiatry, practitioners look at expressions to get an indication of the psychological state of a patient, particularly for depression.” By using a camera and a computer or smartphone to help analyze these facial expressions, the psychiatrist can make an objective evaluation of the medication administered to the patient. A rigorous study of the changes in their face may help to detect pain in some patients who have difficulty expressing it. This is the goal of work by PhD student Taleb Alashkar, whose thesis is funded by IMT’s Futur & Ruptures (future and disruptive innovation) program and supervised by Mohamed Daoudi and Boulbaba Ben Amor. “We have created an algorithm that can detect pain using 3D facial sequences” explains Mohamed Daoudi.

The researcher is careful not to present his research as emotional analysis. “We are working with recognition of facial expressions. Emotions are a step above this” he states. Although an expression relating to joy can be detected, we cannot conclude that the person is happy. For this to be possible, the algorithms would need to be able to say with certainty that the expression is not faked. Mohamed Daoudi explains that this remains a work in progress. The goal is indeed to introduce emotion into our machines, which will become increasingly intelligent.

[box type=”info” align=”” class=”” width=””]

From 3D to 2D

To improve facial recognition in 2D videos, researchers incorporate algorithms used in 3D for detecting shape and movement. Therefore, to study faces in 2D videos more easily, Mohamed Daoudi is capitalizing on the results of the ANR project Face Analyser, conducted with Centrale Lyon and university figures in China. Sometimes the changes are so small they are difficult to classify. This therefore requires creating digital tools making it possible to amplify them. With colleagues at the University of Beihang, Mohamed Daoudi’s team has managed to amplify the subtle geometrical deformations of the face to be able to classify them better.[/box]