This paper proposes a smart solution for on-street parking based on reinforcement learning. As part of a collaborative parking system, we show the ability of reinforcement learning (RL) techniques to find optimal strategies for guiding drivers toward available spots, especially in areas where free parking is scarce. We implement a proof of concept by first training an agent using a Q-learning method in a reduced-dimensional virtual environment to validate the feasibility of our approach. To simulate realistic urban dynamics, we design a multi-agent system comprising a city sub-model based on the Manhattan grid, partitioned in several areas, and a mobility model that reflects typical traffic flows and parking behaviors. The agent-based simulations are conducted using the NetLogo platform. From the resulting synthetic data, which capture the collaborative interactions between agents in search of parking, we build a dataset to train a deep reinforcement learning (DRL) model. Our experiments demonstrate the potential of offline DRL methods to learn efficient policies from simulated collaborative parking scenarios, contributing to the development of intelligent, data-driven urban mobility solutions.

In recent years, significant strides have been made in the field of subgroup discovery by proposing methods that extract subgroups faster and with high utility levels. However, while the most effective works extract subgroups with more complex descriptions that improve utility by maximizing the quality criterion, the question of the usability of the extracted patterns is central for their understanding and application in the field. In this paper, we focus on the SD-CEDI approach, known for identifying the most relevant subgroups, but which the description is based on discontinuous attribute intervals. In this work we propose, and study, various strategies designed to add usability to the extracted patterns and we thus highlight the dilemma between Utility and Usability, that can be seen as a balance to be struck between adding value and degrading quality.

In this paper, we present an original evolutionary approach for Mycobacterium tuberculosis lineages classification. We use a protein frequency analysis in order to transform the genomic source data into more usable forms. First we consider the number of occurrences of each protein in each tuberculosis genome, then we only consider the presence or absence of proteins in a genome and generate binary sequences. Depending on their frequency of apparition, some proteins are discarded in order to reduce the number of predictive attributes. Classifiers composed of multiple binary masks are evolved through a dedicated evolutionary algorithm in order to reach optimal classification performances. We show that the performances obtained by such classifiers on binary presence sequences are quite good in comparison to the performances of classical machine learning techniques such as decision trees on protein occurrence data. All models investigated in this work are easily interpretable as it is important to get some insight about which proteins are important for prediction.

In this work, we focus on the tracking of cluster of links, called conceptual links, in dynamic networks. We seek to understand how conceptual links appear and evolve during the network development. For this purpose, we propose a set of measures to capture some behaviors characterizing the evolution of these clusters. Our approach is used to understand the evolution of the conceptual links extracted on two real world networks: a scientific co-author network and a mobile communication network. The results obtained highlight significant trends in the evolution of the conceptual links in these two networks.

In this work, we study the relevance of using virtual reality (VR) to carry on distance education that promotes learner engagement. Indeed, we have conducted a study with master's students for which we offered courses within the metaverse. Our objective was to evaluate the utility of VR as a distance learning framework and to identify its impact on the cognitive, behavioural and emotional engagement of learners. The results obtained have highlighted the contribution of VR and its utility in the context of post-pandemic distance education context.

Data obtained from new sequencing technologies are evolving rapidly, leading to the development of specific bioinformatic tools, pipelines and softwares. Several algorithms and tools are today available allowing a better identification and description of Mycobacterium tuberculosis complex (MTBC) isolates worldwide. Our approach consists in applying existing methods to analyze DNA sequencing data (from FASTA or FASTQ files), and tentatively extract meaningful information that would facilitate identification as well as a better understanding and management of MTBC isolates (taking into account whole genome sequencing and classical genotyping data). The aim of this study is to propose a pipeline analysis allowing to potentially simplify MTBC data analysis by providing different ways to interpret genomic or genotyping information based on existing tools. Furthermore, we propose a “reconciledTB” list making a link with results directly obtained from whole genome sequencing (WGS) data and results obtained from classical genotyping analysis (data inferred from SpoTyping and MIRUReader). Data visualization graphics and trees generated provide additional elements to better understand and confer associations among information overlap analyses. Additionally, comparison between data entered in an international genotyping database (SITVITEXTEND) and ensuing data obtained from the pipeline not only provide meaningful information, but further suggest that simpiTB could also be suitable for new data integration in specific TB genotyping databases.

AbstractSummarySequencing and other biological data are now more frequently available and at a lower price. Mutual tools and strategies are needed to analyze the huge amount of heterogeneous data generated by several research teams and devices. Bioinformatics represents a growing field in the scientific community globally. This multidisciplinary field provides a great amount of tools and methods that can be used to conduct scientific studies in a more strategic way. Coordinated actions and collaborations are needed to find more innovative and accurate methods for a better understanding of real-life data. A wide variety of organizations are contributing to KaruBioNet in Guadeloupe (French West Indies), a Caribbean archipelago. The purpose of this group is to foster collaboration and mutual aid among people from different disciplines using a ‘one health’ approach, for a better comprehension and surveillance of humans, plants or animals’ health and diseases. The KaruBioNet network particularly aims to help researchers in their studies related to ‘omics’ data, but also more general aspects concerning biological data analysis. This transdisciplinary network is a platform for discussion, sharing, training and support between scientists interested in bioinformatics and related fields. Starting from a little archipelago in the Caribbean, we envision to facilitate exchange between other Caribbean partners in the future, knowing that the Caribbean is a region with non-negligible biodiversity which should be preserved and protected. Joining forces with other Caribbean countries or territories would strengthen scientific collaborative impact in the region. Information related to this network can be found at: http://www.pasteur-guadeloupe.fr/karubionet.html. Furthermore, a dedicated ‘Galaxy KaruBioNet’ platform is available at: http://calamar.univ-ag.fr/c3i/galaxy_karubionet.html.Availability and implementation Information about KaruBioNet is availabe at: http://www.pasteur-guadeloupe.fr/karubionet.htmlContactdcouvin@pasteur-guadeloupe.frSupplementary informationSupplementary data are available at Bioinformatics Advances online.

The search for on-street parking spot has become a major problem for both users and municipalities. This is partly due to the increase in the flow of vehicles and the concomitant scarcity of available spaces. This paper studies this problem from the economic point of view where supply and demand of goods concern parking spaces and each driver is alternatively producer and consumer. The proposed model deals with situations where supply of parking spaces is not sufficient to meet demand. As in this circumstance the time to find a parking space increases by itself, the decrease in demand is a natural process. In contrast, the reduction in on-street parking time - and thus the increase in supply - is the result of deliberate action by decision-makers who may, for example, monetise parking time. An agent-based approach makes it possible to model and simulate this dual process and to design strategies for decision-makers to balance well supply and demand.

The subgroup discovery problem aims to identify a subset of objects which exhibit interesting characteristics according to a quality measure defined on a target attribute. In this paper, we propose a new optimized approach, called SD-CEDI, which originality consists of extracting subgroups defined on discontinued attribute intervals. The intuition behind this approach is that disjoint intervals allow refining the definition of subgroups and therefore the quality of the subgroups identified. For this purpose, the approach we propose models the search space through a hypercube and aims to slice this hypercube to highlight subgroups. Unlike recent methods that also exploit the concept of hypercubes, the originality of our approach relies on the way it performs the slicing in order to bring out discontinuous attribute intervals. The good performances of the approach are demonstrated by comparing, qualitatively and quantitatively, the results with the main algorithms that are the references in the domain.

In this paper, we focus on the problem of the search for subgroups in numerical data. This approach aims to identify the subsets of objects, called subgroups, which exhibit interesting characteristics compared to the average, according to a quality measure calculated on a target variable. In this article, we present DISGROU, a new approach that identifies subgroups whose attribute intervals may be discontinuous. Unlike the main algorithms in the field, the originality of our proposal lies in the way it breaks down the intervals of the attributes during the subgroup research phase. The basic assumption of our approach is that the range of attributes defining the groups can be disjoint to improve the quality of the identified subgroups. Indeed the traditional methods in the field perform the subgroup search process only over continuous intervals, which results in the identification of subgroups defined over wider intervals thus containing some irrelevant objects that degrade the quality function. In this way, another advantage of our approach is that it does not require a prior discretization of the attributes, since it works directly on the numerical attributes. The efficiency of our proposal is first demonstrated by comparing the results with two algorithms that are references in the field and then by applying to a case study.

The subgroup discovery problem aims to identify, from data, a subset of objects which exhibit interesting characteristics according to a quality measure defined on a target attribute. Main approaches in this area make the implicit assumption that optimal subgroups emerge from continuous intervals. In this paper, we propose a new approach, called DISDi, for extracting subgroups in numerical data whose originality consists of searching for subgroups on discontinuous attribute intervals. The intuition behind this approach is that disjoint intervals allow refining the definition of subgroups and therefore the quality of the subgroups identified. Thus unlike the main algorithms in the field, the novelty of our proposal lies in the way it breaks down the intervals of the attributes during the subgroup research process. The algorithm also limits the exploration of the search space by exploiting the closure property and combining some branches. The efficiency of the proposal is demonstrated by comparing the results with two algorithms that are references in the field of several benchmark datasets.

Climate services were initially established with the aim to make the vast amount of climate data, projections and other climate science output publicly available to support the development of responses to society's vulnerability to climate change. In Europe embraced the concept was not only embraced to provide access to scientific knowledge and reduce vulnerability, but also as an opportunity to promote innovation, business opportunities and employment, highlighting the importance of involving users in developing climate services. However, not only differences in knowledge and skills, but also in framing of climate risks and information needs, pose a serious gap between suppliers and users of climate information, sometimes called the "valley of death". Focusing on urban and rural development at the regional and local level as key areas of application for climate services, the paper characterizes this valley of death and suggests options to bridge the gap. We suggest that reframing of the concept of climate services can help expand their applications and effectiveness, taking local non-climate challenges, opportunities and narratives into account. We provide examples from the European ERA4CS project INNOVA. The current focus of climate service development is very much on digital forms of climate change information. While this may provide a useful "back office" function, active brokerage and mediated transfer of knowledge between public and private actors, face-to-face collaboration between providers and clients ("front office"), and integration of social, economic and non-climate environmental challenges with climate risks can help bridging the "valley of death".

Many of us have experienced this when driving in the city, we had to “turn for hours” to find a parking space. To attenuate this drawback, this paper proposes a collaborative parking search strategy based on the reality of a drivers network in which, depending on his/her role at a given time, each one can help the others to find public on-street parking spots. To highlight a situation of parking spot scarcity, we assume the extreme case where there is no free space and the only solution to park is to swap with a parked car that leaves its location. Under this assumption, agent-based modelling and simulations allow to compare the ReadyPark solution with the classical approach that consists, by luck, in taking the place of a nearby car that is leaving its spot.

This article falls within the related areas of climate services and geographic information. We present the architecture and features of the Data and Knowledge Platform (DKP), innovative geographic software that was designed as support for climate-service elaboration in the context of change on given geographic areas. It is intended for a community of stakeholders who need visual and geographic tools to design services improving the resilience of society regarding specific local issues. The platform provides different functions for seeking all available geographic information. Anticipating large volumes of data that are to be stored, we opted for a NoSQL database rather than a textual repository. In this paper, we present the different features of the platform and its ability to support visual climate service co-design, and we illustrate our statement with an example.