International audience

Translating unstructured text into logical format is a key challenge for building ontologies automatically and addressing deductive inference. Most of the approaches have tackled the identification of concepts and relations in text, but few of them have addressed the most complex axioms like class expression subsumption. This work proposes DeLIR, a neuro-symbolic approach to identify complex logical patterns in text by combining a grammatical translation of dependency parsing trees and a fine-tuned Large language Model (LLM). DeLIR combines the strength of the parsing accuracy provided by a grammatical approach and pattern flexibility provided by a finetuned LLM. We evaluated our approach on FOLIO dataset for both translation capacity and inference capability. Our grammatical approach has a perfect parsing accuracy and combining the grammatical approach with LLMs improves the LLMS translation capacity: tinyLlama, T5-small-text2logic, Llama-7B and Mistral-7B. We also evaluate the inference capacity of the different LLMs. Mistral-7B, while being smaller than the state-of-the-art approach using GPT-4, presents similar results to predict the correct inference labels.

CONTEXT: Computational modeling involves the use of computer simulations and models to study and understand real-world phenomena. Its application is particularly relevant in the study of potential interactions between biological elements. It is a promising approach to understand complex biological processes and predict their behavior under various conditions. METHODOLOGY: This paper is a review of the recent literature on computational modeling of biological systems. Our study focuses on the field of oncology and the use of artificial intelligence (AI) and, in particular, agent-based modeling (ABM), between 2010 and May 2023. RESULTS: Most of the articles studied focus on improving the diagnosis and understanding the behaviors of biological entities, with metaheuristic algorithms being the models most used. Several challenges are highlighted regarding increasing and structuring knowledge about biological systems, developing holistic models that capture multiple scales and levels of organization, reproducing emergent behaviors of biological systems, validating models with experimental data, improving computational performance of models and algorithms, and ensuring privacy and personal data protection are discussed.

Building formal ontologies remains a complex process for companies. In the literature, this process is based on the technical knowledge and expertise of domain experts, without further details on the used methodologies. Possible problems of disagreements between experts, expression of implicit knowledge related to high level know-how rarely verbalized, qualification of results by use cases, or simply adhesion of the group of experts, remain currently unsolved. This paper proposes a methodological approach based on knowledge elicitation for the conception of formal, consensual, and shared ontologies. The proposed approach is experimentally tested on industrial collaboration projects in the field of manufacturing (associating knowledge sources from multinational companies) and in the field of viticulture (associating explicit knowledge and implicit knowledge acquired through observation).

The problem of association rules mining has given rise to a rich literature, especially in classic binary bidimensional data. In particular, the representation of the set of rules without loss of information is well understood. This is not the case in multidimensional binary data. This paper shows that the knowledge of n-1 components of every closed n-sets of a multidimensional Boolean tensor, as well as the cardinality of the remaining dimension, is enough to allow for the derivation of the confidence of every multidimensional association rule. This generalises well-known results in the bidimensional case. This paper provides experimental comparisons between the numbers of closed n-sets and frequent associations.

International audience

Undoubtedly, the steady increase in the number of elderly people is not to be underestimated. These demographic changes call attention to new challenges regarding adequate aging-in-place strategies. Since the majority of the senior population spend up to 90% of their time indoors, appropriate and comfortable housing represents an important foundation for such strategies. In this respect, different types of data gathered from sensors, connected devices, and Internet of Things (IoT) technologies come to play an important role to support services for the elderly population in indoor environments. One of the aspects of concern is thermal comfort. In this paper, we introduce a new deep learning-based model framework named STCMS, that uses both Long-Short Term Memory (LSTM) and Deep Neural Networks (DNN) architectures, dedicated to predicting thermal comfort for elderly people. Experiments based on the publicly available dataset, show that our proposed models outperform the pioneering approaches of the literature on the agreed assessment metrics, particularly with an accuracy that varies between 80.29% to 88.16% using only internal and external temperatures data. The proposed approach can be used as a smart thermostat solution integrated into smart home ecosystems dedicated to elderly people. Thus, it would contribute simultaneously to improve their well-being and to reduce energy consumption and health costs.

Achieving thermal comfort for occupants in buildings has been the main focus of several studies in recent years. The challenging issue of the building envelope is to save energy and achieve a high comfortable environment simultaneously. To calculate the thermal comfort level in a living space, environmental factors such as indoor air temperature, mean radiant temperature, air velocity, and humidity are needed. The latter parameters are aggregated through the well known PMV index. In this paper, we introduce a wireless sensor network (WSN)-based comfort measurement approach, called OnCom, using a dedicated ontology and the emotional state analysis of the occupant to reach the "adequate" indoor thermal comfort. The main thrust of OnCom stands on the smooth connection of human emotions with the thermal sensations. Carried out experiments showed that emotions, unveiled from tweets, have been efficiently used to mitigate user thermal discomfort.

Given the France's rich wine heritage as well as its pioneering position as the world's second wine producer, the production of high quality wines plays a role of primary importance. The recent development of IOT and efficient big data processing has been shown to provide purposeful issue to permanent monitoring during the entire wine making process. Standing within this trend, we introduce in this paper an intelligent system for vineyards monitoring in the Burgundy region. The main trust of the proposed system relies on the use of the Swrl rules in WineCloud ontology. The design of the ontology is mainly based on information gathered from interviews with wine growers. In addition, sensor data is also collected and used to feed the ontology after being processed. The system is used in the aim to have better grape quality with an improved vineyard management. To do so, association rules are extracted from the collected data aiming to provide useful knowledge to forecast vine diseases.

Recently, the civilian applications of Unmanned Aerial Vehicles (UAVs) are gaining more interest in several domains. Due to operational costs, safety concerns, and legal regulations, Agent-Based Simulation (ABS) is commonly used to design models and conduct tests. This has resulted in numerous research works addressing ABS in civilian UAV applications. This paper aims to provide a comprehensive overview of the ABS contribution in civilian UAV applications by conducting a Systematic Literature Review (SLR) on the relevant research in the previous ten years. Following the SLR methodology, this objective is broken down into several research questions aiming to (i) understand the evolution of ABS use in civilian UAV applications and identify the related hot research topics, (ii) identify the underlying artificial intelligence systems used in the literature, (iii) understand how and when ABS is integrated in broader and more complex internet of things & ubiquitous computing environments, and (iv) identity the communication technologies, tools, and evaluation techniques used to design, implement, and test the proposed ABS models. From the SLR results, key research directions are highlighted including problems related to autonomy, explainability, security, flight duration, integration within smart cities, regulations, and validation & verification of the UAV behavior.

The identification of objects in 3D point cloud data has always presented a real challenge. Such a process highly depends on human interpretation of the scene and its objects. Actual approaches are numerical based; in best cases, static models are used as a template for the detection process. By the presented work, we aim at extending the detection process by bringing the human expert knowledge about the scene, the objects, their characteristics and their relations onto the processing chain. To do, we present in this paper a knowledgedriven method for the detection of object and its qualification using OWL ontology. The knowledge contained by the ontology defines the constraints about the objects. Logic programs are used as rules to define constrains between objects. The processing of the scene is an iterative annotation process that combines 3D algorithms, geometric analysis, spatial analysis and especially specialist’s knowledge. The created platform takes a set of 3D point clouds as input and produces as output a populated ontology corresponding to an indexed scene. The context of the study is the detection of railway objects materialized within the Germany Railway scene. Thus, the resulting enriched and populated ontology contains the annotations of objects in the point clouds, and can be used further on to feed a GIS system or an IFC file for architecture purposes.

This work aims at bound geometrical detection of 3D objects from a point cloud using semantic descriptors to improve reusability of architectural building reconstruction and aid automatic reasoning in building information modeling (BIM). Based on exploring cognitive origins of spatial semantics representations, semantics conceptualization and classification is proposed for management of architectural objects. The knowledge classification is formalized with transformations among closed world assumption (CWA) and open world assumption (OWA). Initial case study of a building prototype complying with the IFC standard reveals the organization of empirical knowledge rules and semantics scopes both in a bottom up manner of geometry→topology→semantics, and vice versa.

This paper presents an ongoing research which aims at combining geometrical analysis of point clouds and semantic rules to detect 3D building objects. Firstly by applying a previous semantic formalization investigation, we propose a classification of related knowledge as definition, partial knowledge and ambiguous knowledge to facilitate the understanding and design. Secondly an empirical implementation is conducted on a simplified building prototype complying with the IFC standard. The generation of empirical knowledge rules is revealed and semantic scopes are addressed both in the bottom up manner along the line of geometry → topology → semantic, and a vice versa top down manner. Concrete implementation is on the platform of protégé with Semantic Web Rule Language (SWRL).

The "Industrial Foundation Classes" (IFC) are an ISO norm to define all components of a building in a civil engineering project. IFC files are textual files whose size can reach 100 megabytes. Several IFC files can coexist on the same civil engineering project. Due to their size, their handling and sharing is a complex task. In this paper, we present an approach to automatically identify business objects in the IFC files and simplify their visualization and manipulation on the Internet. We construct an IFC Viewer which transforms the IFC file into a XML IFC tree manipulated through the 3D visualization of the building. The IFC Viewer composed a web-based platform called ACTIVe3D BUILD SERVER. This platform lets geographically dispersed project participants-from architects to electricians-directly use and exchange project documents in a centralized virtual environment during the life cycle of a civil engineering project.

This paper presents a Web-based data integration methodology and tool framework, called X-TIME, for the development of business-to-business (B2B) design environments and applications. X-TIME provides a data model translator toolkit based on an extensible metamodel and XML. It allows the creation of adaptable semantics oriented metamodels to facilitate the design of wrappers or reconciliators (mediators) by taking into account several characteristics of interoperable information systems such as extensibility and composability. X-TIME defines a set of meta-types for representing meta-level semantic descriptors of data models found in the Web. The meta-types are organized in a generalization hierarchy to capture semantic similarities among modeling concepts of interoperable systems. We show how to use the X-TIME methodology to build cooperative environments for B2B platforms involving the integration of Web data and services.

The paper presents a methodology based on data model translation for the management of interoperable information systems. The key feature of this solution are: 1) a set of abstract metatypes that capture the characteristics of various modeling concepts; and 2) the organization of the metatypes in a generalization hierarchy to allow unification and correlation of data models. Description logic formalism is used to provide formal specification of the metatypes and a tool called "Strategic Hierarchy Builder" is defined to build the metatype hierarchy semi-automatically. The Strategic Hierarchy Builder organizes the hierarchy and implements an extensible metamodel in which new metatypes are created by specialization of existing metatypes.