Juliette Mattioli

L’intelligence artificielle (IA) bouleverse tous les secteurs mais surtout le secteur secondaire. En effet, les moyens de productions industriels sont déjà équipées de capteurs qui servent à collecter des informations capitales. Les données vont alors aider à optimiser la production. Les banques, elles-aussi collectent de nombreuses données, comme celles relatives aux cours de bourse, à la santé des entreprises... L’analyse prédictive et prescriptive va permettre de prévoir et de quantifier la… Voir plus

L’intelligence artificielle (IA) bouleverse tous les secteurs mais surtout le secteur secondaire. En effet, les moyens de productions industriels sont déjà équipées de capteurs qui servent à collecter des informations capitales. Les données vont alors aider à optimiser la production. Les banques, elles-aussi collectent de nombreuses données, comme celles relatives aux cours de bourse, à la santé des entreprises... L’analyse prédictive et prescriptive va permettre de prévoir et de quantifier la valeur des actifs et cela afin de prendre les meilleures décisions possibles. Quelle soit statistique, connexionniste ou symbolique, cet article présente comment l’IA contribue à la gestion d’actifs (GDA) tant dans le monde de la finance que celui de l’industrie. Voir moins

L’intelligence artificielle (IA), couplée à la science des données, est devenue incontournable pour apporter une réelle valeur ajoutée dans de nombreux secteurs comme les transports et la mobilité, la santé, l’énergie, l’industrie, la logistique, la finance, le commerce et le marketing, ou encore la défense et la sécurité. Cependant son déploiement dans les systèmes critiques, dont la validation voire la certification, constituent une condition incontournable à leur utilisation, soulève de… Voir plus

L’intelligence artificielle (IA), couplée à la science des données, est devenue incontournable pour apporter une réelle valeur ajoutée dans de nombreux secteurs comme les transports et la mobilité, la santé, l’énergie, l’industrie, la logistique, la finance, le commerce et le marketing, ou encore la défense et la sécurité. Cependant son déploiement dans les systèmes critiques, dont la validation voire la certification, constituent une condition incontournable à leur utilisation, soulève de vrais défis. Ainsi,
qu’ils soient apprenants à partir de données, dirigés par des modèles explicites, ou hybridant les deux approches, les systèmes critiques à base d’IA devront satisfaire, par construction, des principes d’explicabilité, d’auditabilité, de confiance et de responsabilité. Voir moins

Avec la transformation numérique du Groupe Thales, l’intelligence artificielle (IA) qu’elle soit orientée par les modèles (IA symbolique) ou basée sur les données (IA connexioniste) devient un élément clé pour la maintenance prévisionnelle. L’objectif de cet article est de dresser un rapide panorama des différentes technologies d’IA mise en oeuvre dans Thales pour outiller les activités de maintenance prévisionnelle.

Content marketing objectives are to create and distribute valuable, relevant, and consistent content to attract and retain a clearly defined targeted audience. To earn credibility, the brand creates messages that are useful and make a positive difference in the lives of the prospects. As content items, at the most basic level, is information, this paper will present how semantic information fusion operator introduced by [17] becomes a cornerstone of an overall content marketing tool chain… Voir plus

Content marketing objectives are to create and distribute valuable, relevant, and consistent content to attract and retain a clearly defined targeted audience. To earn credibility, the brand creates messages that are useful and make a positive difference in the lives of the prospects. As content items, at the most basic level, is information, this paper will present how semantic information fusion operator introduced by [17] becomes a cornerstone of an overall content marketing tool chain. After introducing Mathematical Morphology framework, this operator which relies on a conceptual graphs, will be sound defined. Some underlying morphological properties such as dilation or idempotence are demonstrated, and we explain how these properties can be used within semantic information fusion. Voir moins

Nowadays, social data is a common research field in Computer Science. It is based on Social Networks (SNs), people and links among them and Social Software enabling to send messages. Social data is easy to gather on the Web as there are plenty of them. As people are also authors in such social platforms, information is not always reliable due to abbreviations, acronyms, misspellings, nicknames, misleading information. Furthermore, people are not aware of the structure of information and few are… Voir plus

Nowadays, social data is a common research field in Computer Science. It is based on Social Networks (SNs), people and links among them and Social Software enabling to send messages. Social data is easy to gather on the Web as there are plenty of them. As people are also authors in such social platforms, information is not always reliable due to abbreviations, acronyms, misspellings, nicknames, misleading information. Furthermore, people are not aware of the structure of information and few are semantically annotating their information. Social Networks Analysis (SNA) is interested in the structure of the network but misspellings or misleading
information are collapsing analysis. We present here algorithms for multi-granular fusion enabling to re-structure social information for use of SNAs and reduce data imperfection. Voir moins

Today, more people than ever are threatened by crisis situations, both from natural origin or caused by malicious acts. These situations lead to both economic and humanitarian tragedies. Reconstruction and recovery operations are increasingly longer-lasting, costly and complex, especially when CBRN decontamination is necessary. Coordinated needs assessment, reconstruction and recovery planning can contribute significantly to mitigate the economic and humanitarian impact of such disasters; yet… Voir plus

Today, more people than ever are threatened by crisis situations, both from natural origin or caused by malicious acts. These situations lead to both economic and humanitarian tragedies. Reconstruction and recovery operations are increasingly longer-lasting, costly and complex, especially when CBRN decontamination is necessary. Coordinated needs assessment, reconstruction and recovery planning can contribute significantly to mitigate the economic and humanitarian impact of such disasters; yet, no advanced software platform is available to support this process as a joint operation in which information is continuously updated and shared between the organisations, progress monitored and accountability facilitated. FP7 DESTRIERO project aims at developing an advanced net-centric information management tool, which structures and presents information to collaborative groups of (international) stakeholder organisations, supports damage and needs assessment and recovery planning. Based on international standards, procedures and methodologies, the tool will offer an integrated framework with innovative functionalities as described in this paper. Voir moins

Motivated by the problem of computing trajectories of a set of aircraft in their final descent, we introduce the K king problem, a dramatic simplification of the initial problem in which time and space are discretized. A constraint-based model relying on several specific global constraints is introduced. Computational experiments are reported and show that small instances of this problem can be solved in reasonable time.

Security of public infrastructures and for large events (cultural, sporting) traditionally relies on monolithic video surveillance systems, where security operators are quickly overloaded with information coming from multiple sources, displayed on multiple monitoring screens. Indeed, in such crowded places, it is quite impossible for operators to detect risk-prone situations in real-time and to react accordingly before such situations degenerate: they can only act after an alarm is triggered;… Voir plus

Security of public infrastructures and for large events (cultural, sporting) traditionally relies on monolithic video surveillance systems, where security operators are quickly overloaded with information coming from multiple sources, displayed on multiple monitoring screens. Indeed, in such crowded places, it is quite impossible for operators to detect risk-prone situations in real-time and to react accordingly before such situations degenerate: they can only act after an alarm is triggered; surveillance is said to be passive. Conversely, the European project SERKET of the seventh ITEA call (EUREKA program), involving twenty-four industrial and academic partners, aims at developing an innovative software approach where dispersed data coming from heterogeneous sensors – cameras, microphones, human beings, as well as badge readers, IR barriers for intrusion detection, etc. – are automatically processed (signal processing), combined (information fusion) and analysed (threat assessment) so as to provide security personnel with the right information at the right time: security then becomes preventive. The objective of this paper is to glance at the innovations of the SERKET security system, and to focus on key layers of intelligent signal processing, advanced information fusion and situational awareness rendering. Keywords: public security, safety of crowded infrastructures, surveillance of large events, open platform-based security system, advanced signal processing, smart sensors, information fusion, threat assessment, global situation awareness. Voir moins

Un regard émerveillé sur des curiosités culturelles, technologiques, poétiques, politiques, ou selon l'humeur un coup de cœur.