Doctoral thesis: « Deep Learning for Internet of Things (IoT) Network Security »
Publié le March 11 2021
Doctoral School: Sciences et Technologies de l’Information et de la Communication and the Research Unit SAMOVAR (UMR 5157) – Services répartis, Architectures, Modélisation, Validation, Administration des Réseaux are presenting the “examination of a thesis” by Mr Mustafizur Rahman SHAHID, who is expected to defend his research to obtain his PhD at l’Institut Polytechnique de Paris, prepared at Telecom SudParis in : Computer science
« Deep Learning for Internet of Things (IoT) Network Security »
MONDAY, MARCH 22, 2021 at 10:00 a.m. (Defense in visio – Covid-19).
Jury members:
M. Hervé DEBAR, Professor, Telecom SudParis – Institut Polytechnique de Paris, FRANCE – Supervisor
M. Gregory BLANC, Associate professor, Telecom SudParis – Institut Polytechnique de Paris, FRANCE – Co-supervisor
M. Sébastien TIXEUIL, Professor, Sorbonne Université, FRANCE – Reviewer
M. Eric TOTEL, Professor, IMT Atlantique, FRANCE – Reviewer
M. Youki KADOBAYASHI, Professor, Nara Institute of Science and Technology, JAPAN – Examiner
M. Thomas CLAUSEN, Professor, École Polytechnique, FRANCE – Examiner
Mme Cristel PELSSER, Professor, Université de Strasbourg, FRANCE – Examiner
M. Urko ZURUTUZA, Associate professor, Mondragon University, SPAIN – Examinateur
Abstract :
The growing Internet of Things (IoT) introduces new security challenges for network activity monitoring. Most IoT devices are vulnerable because of a lack of security awareness from device manufacturers and end users. As a consequence, they have become prime targets for malware developers who want to turn them into bots.
Contrary to general-purpose devices, an IoT device is designed to perform very specific tasks. Hence, its networking behavior is very stable and predictable making it well suited for data analysis techniques. Therefore, the first part of this thesis focuses on leveraging recent advances in the field of deep learning to develop network monitoring tools for the IoT.
Two types of network monitoring tools are explored: IoT device type recognition systems and IoT network Intrusion Detection Systems (NIDS). For IoT device type recognition, supervised machine learning algorithms are trained to perform network traffic classification and determine what IoT device the traffic belongs to. The IoT NIDS consists of a set of autoencoders, each trained for a different IoT device type. The autoencoders learn the legitimate networking behavior profile and detect any deviation from it. Experiments using network traffic data produced by a smart home show that the proposed models achieve high performance.
Despite yielding promising results, training and testing machine learning based network monitoring systems requires tremendous amount of IoT network traffic data. But, very few IoT network traffic datasets are publicly available. Physically operating thousands of real IoT devices can be very costly and can rise privacy concerns. In the second part of this thesis, we propose to leverage Generative Adversarial Networks (GAN) to generate bidirectional flows that look like they were produced by a real IoT device. A bidirectional flow consists of the sequence of the sizes of individual packets along with a duration.
Hence, in addition to generating packet-level features which are the sizes of individual packets, our developed generator implicitly learns to comply with flow-level characteristics, such as the total number of packets and bytes in a bidirectional flow or the total duration of the flow. Experimental results using data produced by a smart speaker show that our method allows us to generate high quality and realistic looking synthetic bidirectional flows.
QS 2021: Télécom SudParis continues to climb the rankings
Publié le March 5 2021
The QS World University Rankings by subject focus on engineering and technology. They are among the three most reputable rankings in the world, with THE and Shanghai, and cover 51 subjects across 5 major areas.
Télécom SudParis confirms its progression as a leading engineering school at national level, now ranking 15th in Engineering Technology: Computer Science & Information Systems. Internationally, Télécom SudParis has gained 50 places and is now ranked in the 351-400 group in Engineering Technology: Computer Science & Information Systems, with a score of 55,9.
QS World University is a multi-criterion ranking based on reputation among employers and global scientists in the field, as well as the impact of published scientific work.
Our high score for employability is based on votes from over 50,000 employers worldwide between 2016 and 2020. This is reflected in the results of the CGE’s annual 1st job survey, where Télécom SudParis performs well every year.
We should also commend the scores obtained by our teacher-researchers for the quality and reputation of their scientific work, with 67.2 and 66.3 out of 100, respectively. This underlines the high quality of Télécom SudParis faculty and their training and research.
Founded in 1990, London-based Quacquarelli Symonds has been producing global rankings of higher education institutions since 2004. This year, nearly 14 million articles were analysed to produce its ranking of 1,453 institutions.
Télécom SudParis and elm.leblanc: the keys to a successful partnership
Publié le March 2 2021
The theme of the industry of the future, and in particular the application of augmented reality, has been a Télécom SudParis research focus since 2016. Manufacturers such as elm.leblanc (Bosch Group), meanwhile, have been following a similar line of thought and have identified augmented reality as a driver of performance. Télécom SudParis and elm.leblanc therefore entered a partnership in 2017. A few years later, and the results are there. The expertise of academic researchers combined with that of industrial stakeholders has helped move innovation forward. This is a public research and industry partnership, supported by the Carnot label, one of the schemes in the State’s Future Investments program.
The demonstrator: a first step
“In order to take up this great challenge at Télécom SudParis, we started by identifying researchers whose work was close to this field and encouraging them to move towards the field of the industry of the future”, recalls Olivier Martinot, Director of Innovation and Corporate Relations.
At the end of 2017, Télécom SudParis allocated part of its Carnot funding to setting up the first augmented reality demonstrator for training and maintenance in industry. The demonstrator was developed through the Télécom Sud Paris MyMultimediaWorld platform headed by Marius Preda, a lecturer-researcher in the ARTEMIS Department which specializes in image processing technologies.
This demonstrator is an essential step towards starting meaningful discussions with manufacturers. By showing the precision of the match between virtual images and real environment, one of the major issues of virtual reality, the demonstrator showed all the potential of augmented reality when applied to industry. A research project was therefore set in motion in partnership between Institut Mines-Télécom and elm.leblanc.
Showing the precision of the match between virtual images and real environment
The aim was to study the conditions for the success of this transformation, drawing on the academic skills of the laboratories of Télécom SudParis and IMT Atlantique and their ability to collaborate with industry.
At the end of 2017, Télécom SudParis also gave its support to a start-up, Spectral TMS, housed in its incubator. Marius Preda helped with the production of the first prototypes. The start-up is now working with industrial partners such as Safran, an example that shows that Télécom SudParis is capable of working with both start-ups and large industrial companies
The challenge of elm.leblanc: an uncertain environment
As a leader in the heating industry, elm.leblanc must constantly adapt to a complex and uncertain environment by increasing the flexibility of its production. This aim can be met by making production line operators more versatile and by turning them into key players in the transformation of the industry. This means learning their work more effectively from their workstation.
“For example, our sales are immediately impacted by regulatory changes, such as the ban on fuel,” explains Emmanuel Bricard, IT Director at elm.leblanc.
“Similarly, responding to the market means gradually moving towards “customized” production, with small production runs or even one-off items. In addition, we must adapt to the seasonality of sales and resulting changes in the workload. We do this by hiring staff on short-term contracts during the heating season, but this requires new staff to be trained in our assembly processes in a very short space of time. The challenge is to limit the risks of disorganization that could result from our experts being taken up by supervising the training.”
AR makes it possible to train personnel in assembly processes, often in a short period of time.
The contribution of technology
“Our products are increasingly digital to improve the daily lives of our customers by offering them more practical applications”, says Emmanuel Bricard. “We also believe that technology provides some answers to the industrial challenges we are facing”.
Bosch and elm.leblanc are thus committed to the industry of the future and their aim is to develop “agile” industries capable of adapting their production to demand. This could help maintain the presence of industrial sites in countries such as France. This approach involves planning investments and developing staff skills to make them more versatile. To do so, it is essential that the training should become more efficient and reduce its impact on production.
Component assembly station with supermarket for provision of parts
The challenges of training
The aim of the Iron Men Project is to train operators more quickly and efficiently, directly at their workstations. Mixed reality became widely available on the market with Hololens headsets in 2016, and elm.leblanc identified this as a possible training method.
By equipping operators with augmented reality headsets, it could be possible to send them instructions in real time in the form of holographic projections. This would allow them to carry out their work and interact with their colleagues while getting the feedback on their work they would normally get from a supervisor. This tool should help develop the versatility of staff, which is a key factor for competitiveness in industry.
Operators are fitted with augmented reality headsets.
A structuring framework
The framework agreement between the management of IMT and elm.leblanc led to a research partnership in Industry 4.0. and more particularly in augmented reality (AR).
At Télécom SudParis, the team led by Marius Preda had the skills to apply research methods to the study of these problems.
The Iron Men Project was thus born with a consortium comprising IMT, elm.leblanc and companies specializing in AR. As a winner of the Digital Challenges call for projects funded by the State as part of the Carnot Future Investments program, in the “Augmented Reality/Mixed Reality” category, Iron men started in 2018 for a planned period of 3 years.
It is a large-scale and long-term strategic business partnership (PSE). To date, it is the most ambitious industrial partnership for Carnot and involves several Cifre theses by PhD students hired by elm.leblanc and supervised academically by scientists from partner laboratories.
“The PhD students divide their time equally between the factory and the laboratory. When they are in the factory, they are close to the production line. In the laboratory, we analyze what they have discovered in the factory, we review the actions of the operator,” explains Marius Preda. “Partnerships are the best way to work together”.
A complementary fit between research and industry
For elm.leblanc, the roll-out of AR first required an overview of this new area for which it did not have in-house skills. Since the creation of its innovation unit seven years ago, elm.leblanc has been calling upon PhD students to work on various topics, such as hybrid boilers or the Internet of Things.
“Despite the cultural differences that exist between the worlds of public research and industry, we are convinced that their complementary fit can enable us to move very quickly on new topics,” says Emmanuel Bricard.
Designed in preparation for the roll-out of mixed reality at elm.leblanc, the Iron Men Project is unprecedented in its scope, with three theses being carried out in the laboratories of Télécom SudParis on aspects surrounding augmented reality applied to the industry and two at IMT Atlantique on connected lenses. A sixth thesis is even being envisaged to redesign the production line, once Iron Men has delivered its results.
“Ourcontacts combine academic skills with an experience of industrial realities, which is very valuable,” says Emmanuel Bricard.
Skills research
The aim is therefore to create methods and tools which facilitate and accelerate learning of the work on assembly processes, without the intervention of an expert.
“Surprisingly, I discovered through elm.leblanc, that Industry 4.0 is not only based on increased robotics, but on the contrary, that human workers remain our main priority,” says Marius Preda.
“As there is a need to produce many models of boilers in small production runs, operators are considered as the best fit to make the production process more agile, provided they are well trained.”
The challenge is really to design effective “AR experiences” upstream, in a context of real-time operator guidance. The key is presenting the right information at the right time, in the right place and in the right way depending on the operator’s skills. In other words, transforming information and contextualizing it by adapting it to each operator.
Presenting the right information at the right time, in the right place and in the right way according to the operator’s skills
“One of the theses will look at how to evaluate the different modalities used in AR to interact with theenvironment: voice, gestures, etc.” sums up Thierry Duval, professor and expert in interactions and 3D mixed reality at IMT Atlantique. “Another question is how well AR headsets will be accepted: how long can they be worn during the day? What are the effects on the human visual system and eye movement between the real and the virtual?”.
The Cifre theses are working on real case scenarios and have a precise aim.
“In our, case,” says Thierry Duval, “elm.leblanc wants to have a tool that can be used on a production line within four or five years.”
As assembly lines are constantly being reconfigured, it is also necessary to have the tools to facilitate the modelling of the workstation in order to maintain the coherence between the real and virtual worlds. This is why the topics covered by the theses include evaluating methods of viewing 3D images in different assembly scenarios, studying the simplification of data to allow their visualization in real time, the development of 3D semantic models aimed at improving the understanding of the environment from the images captured by AR headsets.
Putting it all to use
The various modules associated with the features described above (movement and environmental recognition, workstation modelling, modelling of work instructions in mixed reality) will be integrated into tools that meet the business needs of elm.leblanc and will be used at its Drancy and Saint Thegonnec factories.
Thanks to a design based on the existing standards, Iron Men’s results can be transferred to other production lines. This transfer is an integral part of the IMT’s mission and the culture of Télécom SudParis, and “also stimulates academic work by providing concrete problems to solve” according to Marius Preda.
“Applying the work to an industrial environment has significant benefits for scientific publications.”
The synergy at the heart of the Iron Men project reflects its ambition to contribute to the development of the industry of the future.
Recognizing faces, objects, patterns, music, architecture, or even camera movements: thanks to progress in artificial intelligence, every plan or sequence in a video can now be characterized. In the IA TV joint laboratory created last October between France Télévisions and Télécom SudParis, researchers are currently developing an algorithm capable of analyzing the range of fiction programs offered by the national broadcaster.
As the number of online video-on-demand platforms has increased, recommendation algorithms have been developed to go with them, and are now capable of identifying (amongst other things) viewers’ preferences in terms of genre, actors or themes, boosting the chances of picking the right program. Artificial intelligence now goes one step further by identifying the plot’s location, the type of shots and actions, or the sequence of scenes.
The teams of France Télévisions and Télécom SudParis have been working towards this goal since October 2019, when the IA TV joint laboratory was created. Their work focuses on automating the analysis of the video contents of fiction programs.
“Today, our recommendation settings are very basic. If a viewer liked a type of content, program, film or documentary, we do not know much about the reasons why they liked it, nor about the characteristics of the actual content. There are so many different dimensions which might have appealed to them – the period, cast or plot,” points out Matthieu Parmentier, Head of the Data & AI Department at France Télévisions.
AI applied to fiction contents
The aim of the partnership is to explore these dimensions. Using deep learning, a neural network technique, researchers are applying algorithms to a massive quantity of videos. The different successive layers of neurons can extract and analyze increasingly complex features of visual scenes: the first layer extracts the image’s pixels, while the last attaches labels to them.
“Thanks to this technology, we are now able to sort contents into categories, which means that we can classify each sequence, each scene in order to identify, for example, whether it was shot outside or inside, recognize the characters/actors involved, identify objects or locations of interest and the relationships between them, or even extract emotional or aesthetic features. Our goal is to make the machine capable of progressing automatically towards interpreting scenes in a way that is semantically close to that of humans”, says Titus Zaharia, a researcher at Télécom SudParis and specialist in AI applied to multimedia content.
Researchers have already obtained convincing results. Is this scene set in a car? In a park? Inside a bus? The tool can suggest the most relevant categories by order of probability. The algorithm can also determine the types of shots in the sequences analyzed: wide, general or close-up shots. “This did not exist until now on the market,” says Matthieu Parmentier enthusiastically. “And as well as detecting changes from one scene to another, the algorithm can also identify changes of shot within the same scene.”
According to France Télévisions, there are many possible applications. Firstly, the automatic extraction of the key frames, meaning the most representative image to illustrate the content of a fiction, for each sequence and according to aesthetic criteria. Then there is the identification of the “ideal” moments in a program to insert ad breaks. “Currently, we are working on fixed video shots, but one of our next aims is to be able to characterize moving shots such as zooms, traveling or panoramic shots. This could be very interesting for us, as it could help to edit or reuse contents”, adds Matthieu Parmentier.
Multimodal AI solutions
In order to adapt to the new digital habits of viewers, the teams of France Télévisions and Télécom SudParis have been working together for over five years. They have contributed to the creation of artificial intelligence solutions and tools applied to digital images, but also to other forms of content, texts and sounds.
In 2014, the two entities launched a collaborative project, Média4Dplayer, a prototype of a media player designed for all four types of screens (TV, PC, tablet and smartphone). This would be accessible to all, and especially to elderly people or people with disabilities. A few months later, they were looking into the automatic generation of subtitles. The are several advantages to this: equal access to content and the possibility to view a video without sound.
“In the case of television news, for example, subtitles are generated live by professionals typing, but as we have all seen, this can sometimes lead to errors or to delays between what is heard and what appears on screen,” explains Titus Zaharia. The solution developed by the two teams allows automatic synchronization for the Replay content offered by France TV. The teams were able to file a joint patent after two and a half years of development.
“In time, we are hoping to be able to offer perfectly synchronized subtitles just a few seconds after the broadcast of any type of live television program,” continues Matthieu Parmentier.
“France Télévisions still has issues to be addressed by scientific research and especially artificial intelligence. What we are interested in is developing tools which can be used and put on the market rapidly, but also tools that will be sufficiently general in their methodology to find other fields of application in the future,” concludes Titus Zaharia.
François Dellacherie, New Director of Telecom SudParis
Publié le November 20 2020
PRESS RELEASE – 20 November 2020
François Dellacherie has been appointed Director of Telecom SudParis by Bruno Lemaire, Minister for the Economy, Finance and Recovery (the ministry with supervisory authority over Institut Mines-Télécom), Agnès Pannier-Runacher, Secretary of State to the Minister for the Economy, Finance and Recovery and Cédric O, Secretary of State to the Minister for the Economy, Finance and Recovery and to the Minister for Territorial Cohesion and Relations with Local Government through a decree dated 19 November 2020. He will take over as head of the engineering graduate school on 1 December 2020. He will be succeeding Christophe Digne, who has joined the French National Frequency Agency (ANFR).
Up to now, he has been serving as Deputy Director of Technology for the French Ministry for the Armed Forces, where he managed centers of excellence in big data, cybersecurity, software development, telecommunications and artificial intelligence. François Dellacherie was responsible in particular for developing the innovation policy, recruiting young talent, collaborations with innovative companies in the digital sector and researchers from the academic world, and international cooperation in his field.
As the Director of Telecom SudParis, François Dellacherie’s responsibilities will include continuing the school’s development based on its fields of excellence (cybersecurity, data science and artificial intelligence, networks and Internet of Things, multimedia), developing and implementing the overall strategy of Institut Mines-Telecom (IMT), of which the school is a member, and helping build Institut Polytechnique de Paris (IP Paris).
François Dellacherie is a graduate of École Polytechnique. In 1991, he joined the Corps of Telecommunications Engineers. He continued his engineering training at Télécom Paris with a Diploma of Advanced Studies (DEA) in Applied Mathematics for Image Processing, before joining the French Ministry for Defense. From 1996 to 2014, he held management positions in a number of fields: as head of the R&D Office (information system security), then as department head (information system security and cryptology), where he managed all of the R&D activities in the fields of electronics and computer science, industry relations and international partnerships. In 2006 he led the department responsible for telecommunications, image processing and digital mobility laboratories. Since 2014, as Deputy Director he has actively contributed to the development and operational implementation of the Ministry’s digital strategy for defense and national security activities.
Upon being appointed Director, François Dellacherie declared, “I am particular proud to take over as Director of Telecom SudParis! I’ve long been aware of the school’s many strengths, and I look forward to working with the existing teams to continue its development – and to strengthen its role as an academic and economic player in the various digital ecosystems in France and internationally.”
Hervé Debar, Director of Research and Doctoral Programs at Telecom SudParis, is serving as interim director of the school until François Dellacherie’s arrival.
PROCCI Week, Behavioral and Communication Profiles
Publié le November 3 2020
“PROCCI” Week, the French acronym for “Behavioral and Communication Profiles” is organized each year on our Evry and Palaiseau sites. This educational program for third-year engineering students includes several workshops and training sessions. They all have a common goal: getting to know each other better to work together more effectively.
It’s no secret that tensions can arise in working groups, schools and companies. To address these situations more effectively, PROCCI week helps students to understand the experience of working in a group and personality differences.
Several activities led by specialists in behavioral psychology will facilitate this learning. The goal is to provide future engineers with tools for managing human relations.
This year, PROCCI will provide training to 165 student engineers in their final year on a paradigm widely supported by conventional wisdom: Interacting with others as we would want them to interact with us.
A cross-disciplinary event using innovative methods
PROCCI, coordinated by psychotherapist Alexandra Beucler and Télécom SudParis research professor Michel Simatic, will help students better understand the behavior of individuals with complex and even “difficult” personalities.
A variety of innovative educational methods will be used. Students will also practice speaking in public using the VocaCoach application. This solution offers the public with tools for improving oral communication. PROCCI week will also include role playing games and workshops to allow students to use the knowledge they gain during the training.
Conferences and panels
This educational week usually offers students the opportunity to attend several conferences and panels. This year, for example:
Conference ” Better knowing ourselves to manage in a company ” with Isabelle Vandenbussche Masclet, Consulting firm and author of the book ” L’empathie pour manager demain / Du management au leadership ” (Editions Dunod).
Round table with some representatives of our partners companies:
– Badr Bouganga, IT Strategy Manager at Accenture,
– Sébastien Charreire, Head of Technology Advantage at Sia Partners,
– Virginie Chevallard, Director of HR Operations at Devoteam,
– Christophe Maillet, Vice President in charge of value propositions and projects for Human Resources Departments at CGI,
– Stephen PERIN, Technical Director in the “Application Services” department,
– Guillaume Roul, Manager | Prince2 Practitioner ITILv3 at setec is
Ten partners will participate in this year’s edition.
Conferences and panels
This educational week usually offers students the opportunity to attend several conferences and panels. This year, for example:
Conference ” Better knowing ourselves to manage in a company ” by Isabelle Vandenbussche Masclet , Consulting firm and author of the book ” L’empathie pour manager demain / Du management au leadership ” (Editions Dunod).
Round table with some representatives of our partners companies:
– Badr Bouganga, IT Strategy Manager at Accenture,
– Sébastien Charreire, Head of Technology Advantage at Sia Partners,
– Virginie Chevallard, Director of HR Operations at Devoteam,
– Christophe Maillet, Vice President in charge of value propositions and projects for Human Resources Departments at CGI,
– Stephen PERIN, Technical Director in the “Application Services” department,
– Guillaume Roul, Manager | Prince2 Practitioner ITILv3 at setec is
Translated with www.DeepL.com/Translator (free version)
Télécom SudParis extends its deepest sympathy to Samuel Paty’s family, friends, colleagues and students, sharing the emotion that gripped our country after his assassination.
Télécom SudParis is also in solidarity with the entire teaching staff, whose mission of awakening to knowledge, training critical thinking skills and freedom to think for oneself remains irreplaceable.
Doctoral thesis: « Machine Learning based localization in 5G »
Publié le October 15 2020
Doctoral School: Sciences et Technologies de l’Information et de la Communication and the Research Unit SAMOVAR (UMR 5157) – Services répartis, Architectures, Modélisation, Validation, Administration des Réseaux are presenting the “examination of a thesis” by Mr Abdallah SOBEHY who is expected to defend his research to obtain his PhD at l’Institut Polytechnique de Paris, prepared at Telecom SudParis in : Computer science
« Machine Learning based localization in 5G »
FRIDAY NOVEMBER 6, 2020 at 2:00 pm (Telecom SudParis – Room C06
9 rue Charles Fourier, 91000 Evry-Courcouronnes).
Jury members:
M. Eric RENAULT, Professor, ESIEE Paris, FRANCE – Supervisor
M. Paul MUHLETHALER, EVA Team Leader, Inria, FRANCE – Co-supervisor
M. Nadjib AIT SAADI, Full professor, Université de Versailles Saint-Quentin-en-Yvelines, FRANCE – Examinateur
M. Sidi-Mohammed SENOUCI, Professor, Université de Bourgogne, FRANCE – Rapporteur
Mme Hamida SEBA, Associate Professor, Université Claude Bernard Lyon 1, FRANCE – Rapporteur
M. Stephane MAAG, Professor, Telecom SudParis, FRANCE – Examiner
Mme Oyunchimeg SHAGDAR, Research Team Leader, VEDECOM, FRANCE – Examiner
M. Urko ZURUTUZA, Associate Professor, Mondragon University, SPAIN – Examiner
Abstract:
Localization is the process of determining the position of an entity in a local or global coordinate system. The applications of localization are widely spread across different contexts. For instance, in events, tracking the participants can save lives during crises. In health-care, elderly people can be tracked to respond to their needs in critical situations like falling. In warehouses, robots transferring products from one place to another require accurate knowledge of products’ positions as well as other robots.
In industrial context of the factory of the future, localization is invaluable to achieve automated processes that are flexible enough to be reconfigured for various purposes. Localization is considered a topic of high interest both in the academia and industry especially with the advent of 5G. The requirements of 5G pave the way for revolutionizing localization capabilities; Enhanced Mobile Broadband (eMBB) that is expected to reach 10 Gbits/s, Ultra-Reliable Low-Latency Communication (URLLC) which is less than 1 ms and massive Machine-Type Communication (mMTC) allowing to connect around 1 million devices per km.
In this work, we focus on two main types of localization; range-based localization and fingerprinting based localization. In range-based localization, a network of devices with a maximum communication range estimate inter-distance values to their first-hop neighbors. These distances along with knowledge of positions of few anchor nodes are used to localize other nodes in the network using a triangulation based solution.
The proposed method is capable of localizing ≈ 90% of nodes in a network with an average degree of ≈ 10. In the second contribution, wireless channel responses, aka. Channel State Information (CSI) is used to estimate the position of a transmitter communicating with a MIMO antenna. In this work, we apply classical learning techniques (K-nearest neighbors) and deep learning techniques (Multi-Layer Perceptron Neural Network and Convolutional Neural Networks) to localize a transmitter in indoor and outdoor contexts.
Our work achieved the first place in the indoor positioning competition prepared by IEEE’s Communication Theory Workshop among 8 teams from highly reputable universities worldwide by achieving a Mean Square Error of 2.3 cm.
Fundraising dinner for IMT students with Jean Todt
Publié le September 21 2020
The 9th edition of the Mines-Télécom Foundation annual fundraising dinner will take place on Tuesday October 6, 2020. Due to the health situation, this will take place online. Jean Todt, President of the FIA and Special Envoy for “Road Prevention and Safety” to the Secretary General of the United Nations, will be the guest of honor of this digital edition.
The focus of this evening will be conviviality and solidarity. Private virtual lounges and live interactivity will allow graduates to interact with each other and to ask Jean Todt some questions.
The funds raised will be used to support students attending the 8 ITM schools (IMT Atlantique, IMT Lille Douai, IMT Mines Albi, IMT Mines Alès, Mines Saint-Etienne, Télécom Paris, Télécom SudParis and Institut Mines-Télécom Business School) via scholarships and initiatives promoting social diversity, such as mentoring.
Télécom SudParis ranked 18th in the Times Higher Education’s World University Ranking of French institutions
Publié le September 21 2020
This Wednesday September 2, 2020, the English newspaper Times Higher Education published its university world ranking.
The Times Higher Education ranking is based on 13 performance indicators, encompassing five areas: teaching (learning environment), research (volume, revenue and reputation), citations (research influence), internationalperspectives (staff, students and research) and industry revenue (knowledge transfer). They sifted through data from a very large number of universities and grandes écoles and in the end, 1,527 institutions with significant scientific output were ranked this year.
For the first time, Télécom SudParis appears in this leading league table, and in a good position! Ranked within the 501-600 group, the school is tied in 18th place out of 41 French schools in the ranking. This league table thus illustrates the quality of Télécom SudParis’ teaching and research and reinforces its international reputation.
See all rankings and certifications
This site is registered on wpml.org as a development site. Switch to a production site key to remove this banner.
Researchers have already obtained convincing results. Is this scene set in a car? In a park? Inside a bus? The tool can suggest the most relevant categories by order of probability. The algorithm can also determine the types of shots in the sequences analyzed: wide, general or close-up shots. “This did not exist until now on the market,” says Matthieu Parmentier enthusiastically. “And as well as detecting changes from one scene to another, the algorithm can also identify changes of shot within the same scene.”
