International audience

With the continuous increase in the number of satellites orbiting Earth, the efficient and coordinated management of these assets becomes a critical concern. This paper introduces the innovative project Elicitation, a simulator for satellite constellations based on Multi-Agent Systems (MAS), Blockchain, and the Internet of Mobile Things (IoMT). The current scenario highlights growing challenges in the supervision and coordination of satellites, emphasizing the need for automated solutions. Elicitation addresses this complexity by integrating MAS to simulate dynamic interactions between satellites in Earth climate monitoring tasks, taking advantage of blockchain technology to guarantee the security, transparency and integrity of the data generated. One notable aspect that contributes to Elicitation’s appeal is its ability to take advantage of authentic satellite positioning data and real information relating to natural events. Consequently, the system operates autonomously to identify the ideal satellite capable of capturing data related to natural events at any given time. The average decision time per agent was 0.19 seconds for a collective set of 11 agents, corresponding to 11 satellites in a 120-day dataset with 43 target events.

International audience

The development of Internet of Things (IoT) creates large amount of data usable by decision making systems in various domains. In particular, in the field of health monitoring, it enables to follow the medical state of a patient at home in real-time. A challenge is to interpret these data with a high-level representation model in order to have a better understanding of the medical state of a patient. We propose in this article to use Stream Reasoning associated to an ontological representation of the medical context of a patient to understand her situation. This permits to combine in real time static knowledge stored in an ontology and dynamic information provided by smart sensors. To facilitate this process, we introduce constraints and situations concepts to ease the translation of expert knowledge into logical queries. We provide in this paper an experimental analysis of real body temperature data to illustrate how situations may be detected.

We formalize a particular class of problems called \textit{survival multiarmed bandits} (S-MAB), which constitutes a modified version of \textit{budgeted multiarmed bandits} (B-MAB) where a true \textit{risk of ruin} must be considered, bringing it closer to \textit{risk-averse multiarmed bandits} (RA-MAB). In a S-MAB, pulling an arm can result in both positive and negative rewards. The agent has an initial budget that evolves in time with the received rewards. The goal is finding a good \textit{exploration-exploitation-safety} trade-off, maximizing rewards while minimizing the probability of getting ruined (i.e. hitting a negative budget). Such simple and until now neglected modification in the MAB statement changes the way to approach the problem, asking for adapted algorithms and specific analytical tools, and also make it more likely related to some important real-world applications. We are interested in the following open problems which stem from such new MAB definition: (a) how can the regret be meaningfully defined in formal terms for a S-MAB given its multiobjective optimization nature? (b) can a S-MAB be reduced to a RA-MAB or a B-MAB, transferring their theoretical guarantees? (c) what kind of method or strategy must an agent follow to optimally solve a S-MAB?

Nowadays, Online Social Networks (OSN) are commonly used by groups of users to communicate. Members of a family, colleagues, fans of a brand, political groups... There is an increasing demand for a precise identification of these groups, coming from brand monitoring, business intelligence and e-reputation management. However, a gap can be observed between the communities detected by many data analytics algorithms on OSN, and effective groups existing in real life: the detected communities often lack of meaning and internal semantic cohesion. Most of existing literature on OSN either focuses on the community detection problem in graphs without considering the topic of the messages exchanged, or concentrates exclusively on the messages without taking into account the social links. In this article, we support the hypothesis that communities extracted on OSN should be topically coherent. We therefore propose a model to represent the groups of interaction on Twitter, the reference on micro-blogging OSN, and two metrics to evaluate the topical cohesion of the detected communities. As an evaluation, we measure the topical cohesion of the groups of users detected by a baseline community detection algorithm.

Our goal is to design software agents able to collaborate with a user on a document retrieval task. To this end, we studied a corpus of human-human collaborative document retrieval task involving a user and an expert. Starting with a scenario built from the analysis of this corpus, we adapt it for a human-machine collaborative task. We propose a model based on social commitments to link the task itself (collaborative document retrieval) and the interaction with the user that our assistant agent has to manage. Then, we specify some steps of the scenario with our model. The notion of triggers in our model implements the deliberative process of the assistant agent.

Nowadays, Online Social Networks (OSN) are commonly used by groups of users to communicate. Members of a family, colleagues, fans of a brand, political groups: the demand for a precise identification of these groups is increasing from brand monitoring, business intelligence and e-reputation management.

In the automated many-to-many negotiation model for leasing resource contract under Cloud computing environment, the main concern will be over finding a good approximation approach to this type of negotiation problem, since an optimal solution to that problem would be intractable due to the inherent complexity of the leasing resource negotiation along with the Cloud’s specifications. In order to get that good approximation, decentralized negotiation, leveled commitment contracts as well as lightweight agent strategies had been proposed, resulting to a fast and well-approximate negotiation decisions. To this end, we had conceived a “composite-greedy” algorithm for the seller’s strategy to address a variant of WDP which is the seller’s main problem under such settings. The composite greedy seller strategy will be a two-step strategy: the first one applies a classification according to the offers’ revenue and the second one according to the offers’ densities, and thereafter the seller will pick the one that maximizes the most his expected utility. Experimental results show the effectiveness of our approach compared to some related ones over different performance measures.

Virtual communities are complex systems interweaving technical and human aspects.We propose here to identify usual functions provided by virtual communities and define a typology based on the common objects or goals shared by their users.The papers included in this special issue show some examples of research works lead in some of these categories of communities.

Nowadays, social media sites are growing day after day and they are gathering the most important number of visitors on the internet. But among these visitors there is also a big number of manipulators that try to benefit from the others for many reasons, which leads to increase the need to detect t he fake accounts that try to manipulate over the online social media (OSN). A malicious account on OSNs can be created for different objectives such as social spam, identity theft, spear phishing and sybil attacks. In this article, we study and analyze the multiple fake accounts created by one user in order to manipulate and bypass the OSN regulation. We present a new methodology to detect the multiple identity fake accounts and validate it on a set of 10000 accounts extracted from English Wikipedia (EnWiki). In this methodology, we propose a set of features that differentiate between fake and legitimate accounts and grows on previous literature, then we train and test them using machine learning algorithms. The results compare several machine learning algorithms to show that our new features and training data enable to detect 99% of fake accounts, improving previous results from the literature.

Web Intelligence deals with intelligent methods and information & communication technologies that are integrated to enhance different web-based applications. Communities are popular, particularly on the World Wide Web, as a means for like-minded

Contextual Integrity has been proposed to define privacy in an unusual way. Most approaches take into account a sensitivity level or a “privacy circle”: the information is said to be either private or public and to be constrained to a given group of

International audience