Portail HAL des publications du LIRMM
Not a member yet
13279 research outputs found
Sort by
Consensus for a postoperative atlas of sinonasal substructures from a modified Delphi study to guide radiotherapy in sinonasal malignancies
No full textInternational audienceBackground: Sinonasal and skull base tumor surgery-related morbidity has been reduced by the use of endoscopic endonasal skull base surgery (EESBS). Postoperative radiation therapy (poRT) requires precise definition of target volumes. To enhance the accuracy of poRT planning, histological and radiological correlations are necessary to locate the tumor attachment on poRT CT scans. An accurate atlas of structures resected or identified during EESBS could serve for the interdisciplinary postoperative management of patients, personalizing poRT by adequate radiation dose delivery. The objective of this study was to achieve a consensual segmentation atlas on CT scan with surgeons practicing EESBS and radiation oncologists. Methods: The sinonasal structures relevant for poRT of sinonasal malignancies were determined by a two-round Delphi process. A rating group of 25 European experts in sinonasal malignancies was set up. Consensual structures emerged and were used to determine the anatomical limits of the retained structures to draft an atlas with expert based relevant structures. The atlas was then critically reviewed, discussed, and edited by another 2 skull base surgeons and 2 radiation oncologists. Results: After the two rating rounds, 46 structures obtained a strong agreement, 7 an agreement, 5 were rejected and 5 did not reach consensus. The atlas integrating all the selected structures is presented attached. Conclusion: Consensual segmentation atlas on CT scan might allow, through careful poRT planning to limit the morbidity of poRT while maintaining good local control. Prospective studies are necessary to validate this potential precision medicine-based approach
Microservice Identification Using Multi-Objective Genetic Algorithms
No full textInternational audienceMicroservice-based architecture has gained popularity over monolithic architecture during the last few years in both industry and research. This is due to its tremendous advantages (e.g., efficiency, scalability, reliability, etc.). To make use of these advantages, different techniques aiming to migrate monolithic applications to microservices have been proposed. However, these techniques are often based on clustering algorithms that can lead to non-optimal solutions. Also, the identification process often use ad-hoc criteria and tend to overlook several key characteristics of a microservice. Thus, they usually identify microservices that do not match the ones identified by a software architect. To tackle these limitations, we propose in this paper an approach that, on the one hand, takes into account microservice characteristics, and on the other hand, uses well-known metaheuristics in search-based software engineering: the genetic algorithm. The main goal of our approach is to extract microservices from Object-Oriented (OO) monolithic source code by measuring their quality, while considering the semantics of the concept “microservice”. We have experimented with the proposed approach on a collection of Java applications and compared the identified microservices by our approach to those identified by a software architect or domain expert. The conducted experimentation shows the relevance of the identified microservices by our approach
Pushing the Frontiers of Subexponential FPT Time for Feedback Vertex Set
No full textInternational audienceThe paper deals with the Feedback Vertex Set problem parameterized by the solution size. Given a graph G and a parameter k, one has to decide if there is a set S of at most k vertices such that G-S is acyclic. Assuming the Exponential Time Hypothesis, it is known that FVS cannot be solved in time in general graphs. To overcome this, many recent results considered FVS restricted to particular intersection graph classes and provided such algorithms.In this paper we provide generic conditions on a graph class for the existence of an algorithm solving FVS in subexponential FPT time, i.e. time poly, for some {\varepsilon}<1, where n denotes the number of vertices of the instance and k the parameter. On the one hand this result unifies algorithms that have been proposed over the years for several graph classes such as planar graphs, map graphs, unit-disk graphs, pseudo-disk graphs, and string graphs of bounded edge-degree. On the other hand it extends the tractability horizon of FVS to new classes that are not amenable to previously used techniques, in particular intersection graphs of "thin" objects like segment graphs or more generally s-string graphs
Learning to resolve inconsistencies in qualitative constraint networks
No full textInternational audienceIn this paper, we present a reinforcement learning approach for resolving inconsistencies in qualitative constraint networks (QCNs). QCNs are typically used in constraint programming to represent and reason about intuitive spatial or temporal relations like x {is inside of ∨ overlaps} y. Naturally, QCNs are not immune to uncertainty, noise, or imperfect data that may be present in information, and thus, more often than not, they are hampered by inconsistencies. We propose a multi-armed bandit approach that defines a well-suited ordering of constraints for finding a maximal satisfiable subset of them. Specifically, our learning approach interacts with a solver, and after each trial a reward is returned to measure the performance of the selected action (constraint addition). The reward function is based on the reduction of the solution space of a consistent reconstruction of the input QCN. Experimental results with different bandit policies and various rewards that are obtained by our algorithm suggest that we can do better than the state of the art in terms of both effectiveness, viz., lower number of repairs obtained for an inconsistent QCN, and efficiency, viz., faster runtime
Lagrange oscillatory neural networks for constraint satisfaction and optimization
No full textInternational audiencePhysics-inspired computing paradigms are receiving renewed attention to enhance efficiency in compute-intensive tasks such as artificial intelligence and optimization. Similar to Hopfield neural networks, oscillatory neural networks (ONNs) minimize an Ising energy function that embeds the solutions of hard combinatorial optimization problems. Despite their success in solving unconstrained optimization problems, Ising machines still face challenges with constrained problems as they can become trapped in infeasible local minima. In this paper, we introduce a Lagrange ONN (LagONN) designed to escape infeasible states based on the theory of Lagrange multipliers. Unlike existing oscillatory Ising machines, LagONN employs additional Lagrange oscillators to guide the system towards feasible states in an augmented energy landscape, settling only when constraints are met. Taking the maximum satisfiability problem with three literals as a use case (Max-3-SAT), we harness LagONN’s constraint satisfaction mechanism to find optimal solutions for random SATlib instances with up to 200 variables and 860 clauses, which provides a deterministic alternative to simulated annealing for coupled oscillators. We benchmark LagONN with SAT solvers and further discuss the potential of Lagrange oscillators to address other constraints, such as phase copying, which is useful in oscillatory Ising machines with limited connectivity
Overview of GeoLifeCLEF 2025: Plant Species Presence Prediction with Environmental and High-resolution Remote Sensing Data
No full textInternational audienceGeoLifeCLEF 2025 competition, organized as part of the LifeCLEF and FGVC workshops, challenges participants to predict plant species composition at high spatial resolution across Europe using multimodal environmental data. The task builds on a large-scale dataset that combines 5 million Presence-Only (PO) observations and approximately 100,000 standardized Presence-Absence (PA) surveys, paired with Sentinel-2 imagery, Landsat time series, climate rasters, and soil descriptors. This year's edition introduced two major challenges: a geographically shifted test set with plots from previously unseen regions with different species distribution, thereby including many rare species that are under-reported by citizen scientists. These changes increased the modeling difficulty and emphasized the need for generalization under spatial shift and class imbalance. In this paper, we summarize the task design, dataset characteristics, evaluation protocol, participant approaches, and competition results, and discuss implications for scalable species distribution modeling and biodiversity monitoring
MAEVa: A hybrid approach for matching agroecological experiment variables
No full textSource Agritrop Cirad (https://agritrop.cirad.fr/614726/) * Autres projets (id;sigle;titre): 101081973;IntercropValuES;(EU) Developing Intercropping for agrifood Value chains and Ecosystem Services delivery in Europe and Southern countries// 20151501-0000735;GURTDI;(EU) GURTDI//International audienceSource variables or observable properties used to describe agroecological experiments are heterogeneous, nonstandardized, and multilingual, which makes them challenging to understand, explain, and use in cropping system modeling and multicriteria evaluations of agroecological system performance. Data annotation via a controlled vocabulary, known as candidate variables from the agroecological global information system (AEGIS), offers a solution. Text similarity measures play crucial roles in tasks such as word-sense disambiguation, schema matching in databases, and data annotation. Commonly used measures include (1) string-based similarity, (2) corpus-based similarity, (3) knowledge-based similarity, and (4) hybrid-based similarity, which combine two or more of these measures. This work presents a hybrid approach called Matching Agroecological Experiment Variables (MAEVa), which combines well-known techniques (PLMs, multi-head attention, TF–IDF) tailored to the challenges of aligning source and candidate variables in agroecology. MAEVa integrates the following components: (1) Our key innovation, which consists of extending pretrained language models (PLMs) (i.e., BERT, SBERT, SimCSE) with an external multi-head attention layer for matching variable names; (2) An analysis of the relevance and impact of various data collection techniques (snippet extraction, scientific articles) and prompt-based data augmentation on TF–IDF for matching variable descriptions; (3) A linear combination of components (1) and (2); and (4) A voting-based method for selecting the final matching results. Experimental results demonstrate that extending PLMs with an external multi-head attention layer improves the matching of variable names. Furthermore, TF–IDF benefits consistently from the presence of an enriched corpus, regardless of the specific enrichment technique employed
AgriCode: Automated coding for qualitative research and its application to the valorization of agricultural residues
No full textInternational audienceQualitative research, widely employed across various academic fields, explores phenomena using nonnumerical data, with a particular focus on understanding the meanings, experiences, and perspectives of participants. In contrast to other type of research, it seeks to answer how, where, what, when and why individuals behave or respond in certain ways toward specific issues or topics. Qualitative research involves collecting and analyzing textual data, with interviews playing a central role in gathering expert knowledge. An essential part of data analysis is coding, using specially developed code system hierarchy that helps to categorize and organize responses and facilitates the retrieval of insights. Manual data coding is labor-intensive, and to automate this process we developed the AgriCode tool based on machine learning and manually annotated data. To address data scarcity and improve the prediction quality of our offline classifiers, we perform data augmentation using Retrieval-Augmented Generation (RAG), a state-of-the-art method originally designed for online Q&A systems. Our tool automates the coding of interview responses within the Horizon Europe Agriloop project, which focuses on agricultural waste in the food industry. AgriCode predicts a subset of a predefined code system hierarchy, assisting a human coder by accelerating the process and identifying errors in manual coding. Although initially designed for the valorization of agricultural residues, AgriCode's methodology can be adapted for any qualitative research domain characterized by data scarcity and the need of automated textual analysis. To achieve this, responses from the first round of interviews must be manually annotated using dedicated code system hierarchy. They can then be used for fine-tuning the model, while the RAG method can be employed to address the lack of data for certain classes
Restricted Chase Termination: You Want More than Fairness
No full textInternational audienceThe chase is a fundamental algorithm with ubiquitous uses in database theory. Given a database and a set of existential rules (aka tuple-generating dependencies), it iteratively extends the database to ensure that the rules are satisfied in a most general way. This process may not terminate, and a major problem is to decide whether it does. This problem has been studied for a large number of chase variants, which differ by the conditions under which a rule is applied to extend the database. Surprisingly, the complexity of the universal termination of the restricted (aka standard) chase is not fully understood. We close this gap by placing universal restricted chase termination in the analytical hierarchy. This higher hardness is due to the fairness condition, and we propose an alternative condition to reduce the hardness of universal termination
Algorithms to reconstruct past indels: the deletion-only parsimony problem
No full textInternational audienceAncestral sequence reconstruction is an important task in bioinformatics, with applications ranging from protein engineering to the study of genome evolution. When sequences can only undergo substitutions, optimal reconstructions can be efficiently computed using well-known algorithms. However, accounting for indels in ancestral reconstructions is much harder. First, for biologically-relevant problem formulations, no polynomial-time exact algorithms are available. Second, multiple reconstructions are often equally parsimonious or likely, making it crucial to correctly display uncertainty in the results.Here, we consider a parsimony approach where only deletions are allowed, while addressing the aforementioned limitations. First, we describe an exact algorithm to obtain all the optimal solutions. The algorithm runs in polynomial time if only one solution is sought. Second, we show that all possible optimal reconstructions for a fixed node can be represented using a graph computable in polynomial time. While previous studies have proposed graph-based representations of ancestral reconstructions, this result is the first to offer a solid mathematical justification for this approach. Finally we provide arguments for the relevance of the deletion-only case for the general case.</p