Academic literature on the topic 'Interaction humain et machine'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Interaction humain et machine.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Journal articles on the topic "Interaction humain et machine"
1
Guay, Hervé. "Le solo-machine : incursion dans le travail scénique de Carole Nadeau." L’Annuaire théâtral, no. 58 (December 13, 2016): 115–33. http://dx.doi.org/10.7202/1038323ar.
Full textAbstract:
Cet article aborde le rôle de la machine au sein du solo théâtral à l’aide de deux spectacles de Carole Nadeau créés à dix ans d’intervalle : MeMyLee Miller (2000) et Le mobile (2010). L’auteur s’attache à ce qui distingue ce type de solo d’un « monologue » axé sur la parole et sur la « pure » présence de l’acteur dans la mise en place de ce régime scénique. L’article étudie le dialogisme humain-machine dans ses particularités performatives en portant attention à la manière dont le jeu de l’acteur et l’espace scénique sont transformés par les technologies retenues. Il est ainsi question d’observer comment cette interaction humain-machine influe sur la réception de ces solos, autrement dit « ce que la machine fait au solo », pour paraphraser le titre d’un essai célèbre de Nathalie Heinich.
2
HADAD, Fatiha, Marie-Claude SAN JUAN, and Mehdi HAMDI. "Intelligence artificielle : Enjeux et risques pour la traduction." ALTRALANG Journal 6, no. 1 (June 30, 2024): 197–207. http://dx.doi.org/10.52919/altralang.v6i1.416.
Full textAbstract:
ABSTRACT: Artificial Intelligence (AI) has rapidly expanded across various fields, impacting society by transforming linguistic and cultural habits in translation and breaking down language barriers. While offering opportunities like instant translations and recognition software, caution is necessary due to AI's limitations, particularly in automatic translation. The evolving interaction between humans and machines creates new frontiers in global connectivity, prompting questions about their roles in translation for the humanities and social sciences. Our analysis explores the current state of AI, its possibilities, and tools, focusing on its role in literary and academic translation. We also delve into the limits and risks of AI, underscoring the vital role of the human translator. The central question revolves around whether AI, especially in automatic translation, can reliably serve the humanities. Our hypothesis asserts that the human translator is crucial, using knowledge and experience to provide authentic translations, with the machine acting as a legitimate complement, tempered by the cultural insight of the human translator. RÉSUMÉ : L'intelligence artificielle (IA) s'est rapidement développée dans divers domaines, impactant la société en transformant les habitudes linguistiques et culturelles en matière de traduction et en éliminant les barrières linguistiques. Les possibilités qu’offre cette intelligence pour la traduction sont énormes. Toutefois, il est important de faire attention, car il s’agit enfin de machines programmées à cet effet. Le recours de plus en plus accru à ces machines de traduction qui évoluent rapidement suscite des interrogations des spécialistes de la traduction quant à la fiabilité et l’important domaine recouvert par ces dernières. D’autres questions émanent également sur leur conséquence et la place à occuper face au traducteur humain. C’est pourquoi notre analyse explore l’état actuel de l’IA, ses possibilités, ses outils et son rôle dans la traduction littéraire et académique. Il sera question, conjointement à cela, de voir les limites et les risques de l’IA, en soulignant le rôle vital du traducteur humain. En somme, la question centrale est de savoir si l’IA, en particulier dans la traduction automatique, peut servir de manière fiable les sciences humaines. Notre hypothèse affirme que l’intervention du traducteur humain dans cette équation est primordiale. Ses connaissances et son expérience seraient essentielles pour fournir des traductions authentiques.
3
Addessi, Anna Rita, and François Pachet. "Experiments with a musical machine: musical style replication in 3 to 5 year old children." British Journal of Music Education 22, no. 1 (March 2005): 21–46. http://dx.doi.org/10.1017/s0265051704005972.
Full textAbstract:
The relationship between new technology and learning is gaining increasing relevance in the field of music education (Webster, 2002; Folkestad et al., 1998). However, only a few studies have considered the nature of the interaction between children and musical machines. This article describes an observation study of children aged 3–5 years confronting a particular interactive musical system, the Continuator, which is able to produce music in the same style as a human playing the keyboard (Pachet, 2003). The analysis of two case studies suggests that the Continuator is able to develop interesting child/machine interactions and creative musical processes in young children. It was possible to observe a ‘life cycle’ of interaction, as well as micro-processes similar to those observed in child/adult interactions (Stern, 1985; Imberty, 2002). The ability of the system to attract and hold the attention of children has been interpreted through Csikszentmihalyi's (1990) ‘flow theory’.
4
Laverdière, Roxanne, Lye-Ann Robichaud, Annie Toulouse-Fournier, Audrey Marcoux, and Philip Jackson. "Influence du genre sur la perception de l'empathie à l'aide d'avatars." Psycause : revue scientifique étudiante de l'École de psychologie de l'Université Laval 10, no. 2 (November 20, 2020): 13–15. http://dx.doi.org/10.51656/psycause.v10i2.40770.
Full textAbstract:
L’empathie, soit la capacité de comprendre et partager les émotions d’autrui, peut s’exprimer par le langage non verbal, notamment par l’entremise d’avatars dans les plateformes virtuelles en clinique et en recherche. Cependant, l’influence du genre dans l’interaction humain-avatar demeure encore inconnue. Cette étude en ligne vise à évaluer si la perception de l’empathie varie en fonction du genre du participant (homme/femme) et de la représentation de l’avatar (masculin/féminin), indépendamment des comportements non verbaux affichés par les avatars (Contact visuel; Expression faciale congruente; Inclinaison du tronc). Cent vingt adultes de la population générale âgés entre 18 et 60 ans ont été recrutés (76 s’identifiant comme une femme). Ils ont visionné des vidéos d’avatars (deux masculins et deux féminins) affichant différents comportements non verbaux, puis ont évalué l’empathie qu’ils percevaient. Les résultats de l’ANOVA factorielle mixte montrent que les participants perçoivent significativement plus d’empathie lorsqu’exprimée par des avatars féminins, ce qui est congruent avec les stéréotypes liés aux genres. Les résultats montrent également que le genre du participant n’influence pas le niveau l’empathie perçue. Les données obtenues montrent l’importance d’une représentation d’avatar féminin et permettront d’améliorer les plateformes virtuelles existantes, en plus d’améliorer les connaissances sur les interactions empathiques humain-machine.
5
Patterson, Robert Earl. "Intuitive Cognition and Models of Human–Automation Interaction." Human Factors: The Journal of the Human Factors and Ergonomics Society 59, no. 1 (February 2017): 101–15. http://dx.doi.org/10.1177/0018720816659796.
Full textAbstract:
Objective: The aim of this study was to provide an analysis of the implications of the dominance of intuitive cognition in human reasoning and decision making for conceptualizing models and taxonomies of human–automation interaction, focusing on the Parasuraman et al. model and taxonomy. Background: Knowledge about how humans reason and make decisions, which has been shown to be largely intuitive, has implications for the design of future human–machine systems. Method: One hundred twenty articles and books cited in other works as well as those obtained from an Internet search were reviewed. Works were deemed eligible if they were published within the past 50 years and common to a given literature. Results: Analysis shows that intuitive cognition dominates human reasoning and decision making in all situations examined. The implications of the dominance of intuitive cognition for the Parasuraman et al. model and taxonomy are discussed. A taxonomy of human–automation interaction that incorporates intuitive cognition is suggested. Application: Understanding the ways in which human reasoning and decision making is intuitive can provide insight for future models and taxonomies of human–automation interaction.
6
Shibata, Shigeki Suganoand Takanori. "Special Issue on Toward Establishment of Entertainment and Amusement Machine Technology." Journal of Robotics and Mechatronics 14, no. 1 (February 20, 2002): 1–2. http://dx.doi.org/10.20965/jrm.2002.p0001.
Full textAbstract:
Advances in society have enriched lifestyles, making them more comfortable and increasing spare time. People spend more time and money on entertainment 'and amusement, purchasing more than basic necessities and spending time at recreational facilities. Devices used in entertainment and amusement frequently interact with people, making it important to design them emphasizing subjective evaluations by people who interact with them rather than objective evaluations such as speed and accuracy. This makes technologies on entertainment and amusement interdisciplinary, going beyond the scope of conventional engineering with consideration of human sensitivities. Sugeno describes this interdisciplinary technology and discusses its possibilities in ""Engineering and Amusement."" This special edition presents information on Japanese mechatronics technologies for entertainment and amusement to overseas people. Included are papers on scholarly- and technologically-de novo research and developments and technologies already put into practical use as commercially available products. Devices for entertainment and amusement must interact with people in different ways, and as such, they take a wide variety of shapes and have a broad array of controllers to suitably accommodate different human needs. It is therefore of critical importance to give special consideration to human sensitivity, which makes this area of engineering difficult to standardize and generalize. It is, however, becoming increasingly important in different fields of engineering to take interaction between machinery and people into consideration. This special edition provides perspectives and technologies that hold clues for the field of entertainment and amusement and also for many other areas of research and development. Kuroki et al. discuss the structure and the control architecture of SDR-X, a humanoid robot developed for entertainment, and detail the dancing performance of this robot in ""A Small Biped Entertainment Robot."" Shibata et al. statistically analyze the findings of subjective evaluation of the Mental Commit Robot Paro, a robot shaped like a baby seal developed to provide positive psychological effects such as pleasure and comfort to people through interaction, and considers the results in ""Subjective Evaluation of Seal Robot Paro."" Mitsui et al. tell about the results of physiological experiments and subjective evaluations of psychophysiological effects of interactions with a seal-shaped Mental Commit Robot on people in ""Psycho-physiological Effects by Interaction with Mental Commit Robot."" Nakata et al., in ""Analysis of Impression of Robot Bodily Expression,"" suggest a method for setting up physical characteristics of movements based on the theory of Laban in Choreologia as a way of quantitatively evaluating impressions of movement of a robot a person gets during interaction, and discuss the method's effectiveness. Tanaka et al., in ""Principle of Stable Running of A Unicycle Robot,"" describe the research and development of a unicycle robot modeled after the movement of a person riding a unicycle. They analyzed the mechanism of complex and skillful movements to have the robot make comical human-like movements. These findings could be applied to controlling robots in general. Kobayashi et al., in ""A New Concept of the Robotic Technology Applicable to Human Physical Support,"" describe a muscle suit to support human muscles with the help of air tube actuators. Because this suit enables people to move about naturally, its technology is applicable as component technology for new types of entertainment. Yamamoto et al., in ""Conversation with a Communication Robot Named Wonder - for the Mental Support of the Elderly Living Alone,"" discuss results of a validation experiment for a robot developed with several objectives, including the 'reduction of the psychological burden on elderly people who live alone and applications as a pet and/or a speech partner and as an interface for outside communication through CATV to make their daily life safer. Fuj ita, in ""Personal Robot PaPeRo,"" tells about the objective of the development, design, function, and structure of the autonomous robot PaPeRo developed for communication with people in private households and reports the results of an experiment in which 12 families lived together with the robot for about 2 months. Miyake et al., in ""Interactive Simulation Ride System,"" present a simulation system with a high degree of virtual sense capability being achieved by a 3-6 mensional audiovisual perception data display using virtual reality technology and a ride system with 4 degrees of freedom. This system is already being used in amusement facilities and museums. Haga, in ""WonderBorg and BN-l,"" describes the concept of development, system structure, and control of an insect-shaped robot ""WonderBorg"" and a cat-like robot BN-I developed with the objective of offering interactive entertainment to people through assembling and programming robot. Nagasu, in ""Dream Force O1,"" tells about the concept of development and the structure of Dream Force 01, a bipedal locomotion robot that can be operated by the user for pleasure with the help of a robot controller. Omshi, in ""POO-CHI,"" discusses the design and the function of a dog-shaped robot toy POO-CHI that has become a hot seller all over the world. We thanks Japan Toy Culture Foundation on supports for preparation of developments reports.
7
Razavi-Mohseni, Milad, Dustin Shigaki, and Michael A. Beer. "Machine Learning Sequence Modeling Identifies Gene Regulatory Responses to Bone Marrow Stromal Interactions in Multiple Myeloma." Blood 142, Supplement 1 (November 28, 2023): 4144. http://dx.doi.org/10.1182/blood-2023-186981.
Full textAbstract:
Introduction Multiple myeloma (MM) is a hematological malignancy of plasma cells which affects different organs including the bone marrow. The interaction between MM and the bone marrow stromal cells (BMSC) has been shown to affect the disease progression and response to treatment (Kumar et al. Multiple myeloma. Nat. Rev. Dis. Primers, 2017). An in vitro system to isolate the signaling mechanisms between BMSC and MM cells has been developed by (Dziadowicz et al., Cancers, 2022), who co-cultured MM cell lines in transwell media (TSW) exposed to BMSC secreted factors and compared their ATAC-seq profiles to MM cell lines (MONO) in isolation without the exposure to BMSC. While some of the gene expression changes induced by the BMSC-MM crosstalk were reported in (Dziadowicz et al., Cancers, 2022), here we model the entire chromatin accessibility profiles with a DNA-sequence based machine learning model to detect the altered Transcription Factor (TF) and enhancer activity responsible for driving the gene expression changes. We used sequence-based machine learning models (Beer et al., 2020, Annu. Rev. Genom. Hum. Genet.) and applied a systematic approach to model the chromatin accessibility changes induced by the interaction of BMSC and MM cells (MM-TSW) vs. MM cell lines cultured in isolation (MM-MONO). Methods We trained gapped-kmer SVM (gkm-SVM) machine learning models on MM1S and RPMI8226 MM cell line ATAC-seq data generated by Dziadowicz et al. as well as 1270 DNase-seq chromatin accessibility profiles of various human primary tissues and cell lines (including MM1S and RPMI8226) from the ENCODE consortium. We trained gkm-SVM on the top 2000 differentially-accessible distal ATAC peaks (>2000bp from transcription start site, e.g. enhancers) to find the differential TF activity between MM-TSW and MM-MONO (Figure 1) and found the TF binding site motifs explaining the gkmSVM output kmer weight distribution (Figure 2). We also identified the set of differentially-expressed TFs and performed gene set enrichment using MSigDB. Results We found that RUNX and Ebox-binding (5‘-CACCTG-3‘) TF family members are the most active TFs in MM1S-MONO and RPMI8226-MONO enhancers (gkmSVM AUROCs~0.92). The contribution of the Ebox TFs to distal chromatin accessibility in the MM cell lines is greater than in any other ENCODE sample (n=1270). Principal Component Analysis (PCA) on distal ATAC peaks compared to promoters showed that the MM transcriptional response to BMSC is more clearly explained by the differences in enhancer activity rather than promoters. This response is driven by dysregulated activity of a set of enhancer regions in MM-TSW compared to MM-MONO (Figure 1) and our machine learning method can identify these regulatory changes (AUROC~0.90). In addition to the altered AP1 and JAK/STAT activity reported by Dziadowicz et al., we discovered that RUNX and Ebox-binding transcriptional activity are downregulated in MM cells following the interaction with BMSC (Figure 2). Although our RNA-seq analysis found differential expression of some Ebox-binding TFs such as TCF3 and ZEB1 and RUNX members, the identification of the exact TF member(s) driving these RUNX and Ebox/E2A downregulation in MM-TSW is still challenging. Furthermore, PCA analysis of the gene expression profiles of MM1S and RPMI8226 cells showed that the targets of Bone Morphogenetic Protein 2 (BMP2) are upregulated in MM-TSW (FDR < 10 -28). Conclusion While some of the gene expression changes induced by the BMSC-MM interaction were reported in (Dziadowicz et al., Cancers, 2022), our modeling of the entire chromatin landscape discovered the previously unreported downregulation of RUNX and Ebox/E2A TFs in MM as the dominant response of MM interacting with BMSCs, accompanied by an upregulation of AP1 and JAK/STAT. RUNX and E2A-binding families of TFs include RUNX1/2/3, ZEB1/2, SNAI1/2 and TCF3, some of which we previously found to be strongly involved in epithelial to mesenchymal transition in gastric cancer and its invasiveness (Razavi-Mohseni et al., submitted, 2023). Bone marrow microenvironment interactions with MM are known to affect the disease progression and treatment, therefore, identifying the set of TFs driving the MM response to stroma may provide better understanding of the disease and better therapeutic opportunities.
8
Aribowo, Agus Sasmito, Halizah Basiron, Noor Fazilla Abd Yusof, and Siti Khomsah. "Cross-domain sentiment analysis model on Indonesian YouTube comment." International Journal of Advances in Intelligent Informatics 7, no. 1 (March 31, 2021): 12. http://dx.doi.org/10.26555/ijain.v7i1.554.
Full textAbstract:
A cross-domain sentiment analysis (CDSA) study in the Indonesian language and tree-based ensemble machine learning is quite interesting. CDSA is useful to support the labeling process of cross-domain sentiment and reduce any dependence on the experts; however, the mechanism in the opinion unstructured by stop word, language expressions, and Indonesian slang words is unidentified yet. This study aimed to obtain the best model of CDSA for the opinion in Indonesia language that commonly is full of stop words and slang words in the Indonesian dialect. This study was purposely to observe the benefits of the stop words cleaning and slang words conversion in CDSA in the Indonesian language form. It was also to find out which machine learning method is suitable for this model. This study started by crawling five datasets of the comments on YouTube from 5 different domains. The dataset was copied into two groups: the dataset group without any process of stop word cleaning and slang word conversion and the dataset group to stop word cleaning and slang word conversion. CDSA model was built for each dataset group and then tested using two types of tree-based ensemble machine learning, i.e., Random Forest (RF) and Extra Tree (ET) classifier, and tested using three types of non-ensemble machine learning, including Naïve Bayes (NB), SVM, and Decision Tree (DT) as the comparison. Then, It can be suggested that the accuracy of CDSA in Indonesia Language increased if it still removed the stop words and converted the slang words. The best classifier model was built using tree-based ensemble machine learning, particularly ET, as in this study, the ET model could achieve the highest accuracy by 91.19%. This model is expected to be the CDSA technique alternative in the Indonesian language.
9
Spiekermann, Kevin A., Thijs Stuyver, Lagnajit Pattanaik, and William H. Green. "Comment on ‘Physics-based representations for machine learning properties of chemical reactions’." Machine Learning: Science and Technology 4, no. 4 (October 6, 2023): 048001. http://dx.doi.org/10.1088/2632-2153/acee42.
Full textAbstract:
Abstract In a recent article in this journal, van Gerwen et al (2022 Mach. Learn.: Sci. Technol. 3 045005) presented a kernel ridge regression model to predict reaction barrier heights. Here, we comment on the utility of that model and present references and results that contradict several statements made in that article. Our primary interest is to offer a broader perspective by presenting three aspects that are essential for researchers to consider when creating models for chemical kinetics: (1) are the model’s prediction targets and associated errors sufficient for practical applications? (2) Does the model prioritize user-friendly inputs so it is practical for others to integrate into prediction workflows? (3) Does the analysis report performance on both interpolative and more challenging extrapolative data splits so users have a realistic idea of the likely errors in the model’s predictions?
10
Cherif, Emna, and Jean-François Lemoine. "Les conseillers virtuels anthropomorphes et les réactions des internautes : une expérimentation portant sur la voix du conseiller." Recherche et Applications en Marketing (French Edition) 34, no. 1 (June 29, 2018): 29–49. http://dx.doi.org/10.1177/0767370118775963.
Full textAbstract:
Les conseillers virtuels se sont fortement démocratisés sur les sites marchands. Compte tenu des bénéfices qu’ils offrent aux entreprises pour améliorer la navigation et l’interaction avec le consommateur, chercheurs et praticiens s’accordent sur l’intérêt de les doter de caractéristiques anthropomorphiques. Cette recherche s’intéresse particulièrement à l’effet de la voix du conseiller virtuel. Bien qu’il existe quelques recherches en interaction homme-machine sur la question, il n’existe pas de travaux traitant le sujet d’un point de vue marketing et comparant l’effet d’une voix humaine vs une voix de synthèse. Les résultats montrent que les consommateurs qui ont interagi avec un conseiller virtuel doté d’une voix humaine éprouvent un sentiment de présence sociale plus fort que ceux interagissant avec un conseiller doté d’une voix de synthèse. La voix humaine permet également de susciter plus de confiance envers le conseiller virtuel et de générer de meilleures intentions comportementales.
Dissertations / Theses on the topic "Interaction humain et machine"
1
Buseyne, Julien. "Jeu vidéo et traduction, étude d’une relation humain-machine." Thesis, Université Paris-Saclay (ComUE), 2018. http://www.theses.fr/2018SACLE001/document.
Full textAbstract:
Depuis son acte de naissance au début des années 1970, l’industrie du jeu vidéo s’est hissée au premier rang des industries du loisir. La traduction des œuvres joua un rôle prépondérant dans la conquête de nouveaux marchés, qui a permis à certains fabricants, producteurs et éditeurs d’acquérir une dimension internationale. Les jeux vidéo sont des objets techniques interactifs dont la fabrication repose à la fois sur la programmation d’un logiciel capable de produire une structure jouable, et sur des procédés artistiques capables de produire une représentation actionnable. Ils constituent un contexte opératoire dont les propriétés posent un écheveau de problèmes que les agents chargés d’effectuer leurs traductions doivent résoudre. L’objectif de cette thèse est de produire une étude compréhensive du rapport entre jeu vidéo et traduction, approché sous l’angle de la relation entre humain et machine. Malheureusement, les pratiques de l’industrie en matière de protection de la propriété intellectuelle, la complexité des objets techniques concernés et la taille des œuvres opposent une résistance sensible à leur analyse. Elle propose d’y remédier par une analyse de la traduction comme opération technique effectuée sur une famille d’objets, le jeu vidéo, dans l’environnement que constitue le système technique numérique. Elle est parachevée par des études de cas. Sa conclusion ouvre des pistes en matière de recherche et développement, en partenariat avec les acteurs de ce secteurSince it came into being in the beginning of the 970 decade, the video games industry made its way to the top of the entertainment industry. The translation of the product it delivered played an important part in this evolution, allowing some platform holders, developers and publishers to become worldwide actors. Video games are interactive technical artifacts. Their fabrication relies on both the coding of a software acting as a playable structure, and on artistic assets used to build its representation. Translators operating in such a context are confronted with a mesh of challenges that they need to overcome in order to successfully complete their task. This PhD thesis is a comprehensive study of the interaction between video games and translation, considered as a human-machine relationship. Unfortunately, the rules enforced by the industry regarding the protection of intellectual property, the complexity of the technical artifacts involved and the size of the productions are an impediment to any analysis. In order to remedy this situation, this study endeavors to analyze translation as a technical operation, performed on a type of artifacts, video games, while considering the digital technical system as an environment. Case studies complete this work. Its conclusion gives several leads for research and development, to be investigated in partnership with actors in the localization or video games industry
2
Coutrix, Céline. "Interfaces de réalité mixte : conception et prototypage." Grenoble 1, 2009. http://www.theses.fr/2009GRE10064.
Full textAbstract:
Depuis plusieurs décennies, la recherche en Interaction Homme-Machine travaille sur les systèmes qui mélangent le monde physique avec le monde numérique. Les interfaces de réalité mixte visent à faire disparaître la frontière entre ces deux mondes. Face au manque de capitalisation et d'aide lors de la conception de ces systèmes, nos travaux ont pour objectif de définir un modèle d'interaction avec les systèmes de réalité mixte unificateur capitalisant les approches du domaine existantes. Ce modèle, appelé Modèle d'Interaction Mixte, permet au concepteur de décrire, caractériser et explorer les techniques d'interaction. Pour cela, nous considérons les objets mixtes, à la fois physique et numérique, qui prennent part à l'interaction avec l'utilisateur. Pour opérationaliser ce modèle d'interaction pendant la conception et permettre la réalisation d'ébauches interactives simultanément, nous avons développé un outil de prototypage. Cet outil reprend les concepts du Modèle d'Interaction Mixte. Nous avons validé ces travaux en considérant deux formes de validations : conceptuelles et expérimentales. Nous avons considéré des cadres de validation existants et nous avons conçu plusieurs systèmes en collaboration avec des acteurs de la conceptionResearch in Human-Computer Interaction explores Mixed Reality Systems for several decades. Mixed interfaces seek to smoothly merge the physical and digital (data processing) environments. Facing a lack of capitalization and help when designing such systems, our work aims at defining a unifying model of interaction with mixed reality systems, capitalizing existing approaches in this domain. This model, called Mixed Interaction Model, allows a designer to describe, characterize and explore interaction techniques. In order to do so, we focuse on physical-digital objects taking part in the interaction with the user. In order to operationalize this interaction model during design and allow designers to realize interactive sketches simultaneously, we developped a prototyping tool. This tool capitalizes the concepts of the Mixed Interaction Model. We conducted conceptual and experimental evaluations, by considering existing validation frameworks and we designed several systems in collaboration with design actors
3
Horchani, Meriam. "Vers une communication humain-machine naturelle : stratégies de dialogue et de présentation multimodales." Phd thesis, Grenoble 1, 2007. http://www.theses.fr/2007GRE10290.
Full textAbstract:
Cette thèse a pour thème la communication humain-machine multimodale pour des systèmes d'information grand-public. Dans ce contexte, la communication naturelle repose sur l'accessibilité sensoriactionnelle, cognitive et rhétorique aux informations et aux moyens d'action. Pour cela, nous identifons le rôle clef que jouent les stratégies de dialogue et de présentation : 1) La stratégie de dialogue pour des systèmes coopératifs définit la tâche dialogique qui oriente la suite du dialogue et conditionne, voire contraint, le choix du contenu, comme la relaxation, la présentation ou la restriction. 2) La stratégie de présentation définit une configuration multimodale des unités informationnelles à rendre perceptibles par l'utilisateur. Nous prônons le choix concerté de la stratégie de dialogue avec celle de présentation et nous proposons un composant logiciel dédié au choix conjoint des stratégies de dialogue et de présentation au sein de l'architecture logicielle de référence Arch. Ce nouveau composant, intermédiaire entre le contrôleur de dialogue et les composants de présentation concrète, prend en compte les contraintes de présentation, qu'elle soient définies par l'utilisateur ou issues du contexte d'utilisation et/ou d'études ergonomiques et cognitives, pour déterminer la réaction multimodale du système interactif. Outre la réalisation logicielle du composant au sein de deux systèmes, nous proposons un outil de conception destiné à des non-informaticiens qui permet la conception incrémentale et la génération d'un composant de choix pour un système donné grâce à une interface graphique. L'outil est associé à une plate-forme de simulation pour des expérimentations magicien d'OzThis thesis focuses on multimodal human-computer communication for public service systems. In this context, the naturalness of the communication relies on sensory-motor, cognitive and rhetorical accessibility of the interactive system by the user. Towards this goal of natural communication, we identify the key role of dialogic and presentation strategies : 1) A dialogic strategy of a cooperative information system defines the behavior of the system and the content to convey : Examples include relaxation, statement and restriction. 2) A presentation strategy defines a multimodal presentation specification, specifying the allocated modalities and how these modalities are combined. Highlighting the intertwined relation of content and presentation, we identify a new software component, namely the dialogic strategy component, as a mediator between the dialogue controller and the concrete presentation components within the reference Arch software architecture. The content selection and the presentation allocation managed by the dialogic strategy component are based on various constraints including the inherent characteristics of modalities, the availability of modalities as well as explicit choices or preferences of the user. In addition to the software development of this new component in two systems, we developed a design tool, which allows ergonomists and non-programmers to define and configure the dialogic strategies and to generate the dialogic strategy component of a particular system, as part of an iterative user-centered design process. Moreover this tool is integrated with a simulation framework for wizard of Oz experiments
4
Horchani, Meriam. "Vers une communication humain-machine naturelle : stratégies de dialogue et de présentation multimodales." Phd thesis, Université Joseph Fourier (Grenoble), 2007. http://tel.archives-ouvertes.fr/tel-00258072.
Full textAbstract:
Cette thèse a pour thème la communication humain-machine multimodale pour des systèmes d'information grand-public. Dans ce contexte, la communication naturelle repose sur l'accessibilité sensoriactionnelle, cognitive et rhétorique aux informations et aux moyens d'action. Pour cela, nous identifons le rôle clef que jouent les stratégies de dialogue et de présentation : 1) La stratégie de dialogue pour des systèmes coopératifs définit la tâche dialogique qui oriente la suite du dialogue et conditionne, voire contraint, le choix du contenu, comme la relaxation, la présentation ou la restriction. 2) La stratégie de présentation définit une configuration multimodale des unités informationnelles à rendre perceptibles par l'utilisateur. Nous prônons le choix concerté de la stratégie de dialogue avec celle de présentation et nous proposons un composant logiciel dédié au choix conjoint des stratégies de dialogue et de présentation au sein de l'architecture logicielle de référence Arch. Ce nouveau composant, intermédiaire entre le contrôleur de dialogue et les composants de présentation concrète, prend en compte les contraintes de présentation, qu'elle soient définies par l'utilisateur ou issues du contexte d'utilisation et/ou d'études ergonomiques et cognitives, pour déterminer la réaction multimodale du système interactif. Outre la réalisation logicielle du composant au sein de deux systèmes, nous proposons un outil de conception destiné à des non-informaticiens qui permet la conception incrémentale et la génération d'un composant de choix pour un système donné grâce à une interface graphique. L'outil est associé à une plate-forme de simulation pour des expérimentations magicien d'Oz.
5
Callupe, Luna Jhedmar Jhonathan. "Étude du fauteuil roulant Volting : interaction, commande et assistance." Electronic Thesis or Diss., université Paris-Saclay, 2023. http://www.theses.fr/2023UPASG050.
Full textAbstract:
Une grande partie des solutions de mobilité pour les fauteuils roulants se concentre sur l'aide au déplacement de l'utilisateur.La plupart des fauteuils roulants visent à offrir une solution adaptée pour assurer la conduite adaptée et la stabilité pour l'utilisateur.Le projet Volting, développé au LISV depuis 2020, propose une nouvel axe d'étude. Il s'agit du développement d'un fauteuil roulant capable d'offrir une plus grande mobilité posturale pour l'utilisateur basée sur une inclinaison latérale.L'objectif suivi dans le projet Volting est de proposer une réappropriation de son corps avec ce déséquilibre. Dans cette optique, une première proposition a été réalisée. Elle consiste en un fauteuil roulant capable de basculer latéralement proportionnellement à l'inclinaison de l'utilisateur. Cette liberté de mouvement supplémentaire donne à l'utilisateur une plus grande capacité de gestes corporels. C'est dans ce contexte que la danse en fauteuil roulant a été choisie comme domaine d'application.Dans cette thèse, le prototype Volting a été étudié sous trois points de vue : l'interaction, la commande et l'assistance.Tout d'abord, l'interaction entre l'utilisateur et Volting fait référence à la relation entre d'inclinaison du tronc de l'utilisateur et d'inclinaison de Volting. Elle a été analysée afin de rechercher un comportement approprié. Ainsi, une analyse du modèle a été réalisée pour étudier les paramètres impliquées dans cette interaction. Des expériences ont montré que l'utilisation de notre modèle fournit les paramètres appropriés pour une cinématique correcte.Le deuxième axe d'étude porte sur le contrôle du Volting par son usager. Ainsi, l'utilisation d'un dispositif multi-capteurs, appelé WISP, a été proposée. Ce dispositif prend comme entrées de commande la posture du tronc de la personne ou la position de ses mains afin de contrôler le Volting. La logique de contrôle mise en œuvre permet à l'utilisateur de contrôler le fauteuil roulant avec une plus grande liberté dans l'exécution de gestes. WISP a été testé par une professionnelle et une amatrice de la danse en fauteuil roulant. Cela montre leur adaptation rapide dans l'utilisation du dispositif. Cela montre aussi leur motivation envers la pratique de sa danse.Le troisième axe d'étude porte sur l'utilisation de l'assistant à l'inclinaison, nommé "Glissiere" dans Volting. Ce dispositif repose sur le décalage de l'assise de l'utilisateur pour favoriser ou contrer l'inclinaison latérale de Volting et donc du corps de l'usager. Pour pré-évaluer cette solution, des expériences ont ainsi montré que des utilisateurs présentant différentes morphologies, qui n'arrivaient pas à utiliser Volting à sa pleine capacité, pouvaient utiliser Volting grâce à cet assistantA significant portion of mobility solutions for wheelchairs focuses on assisting the user's movement. Most wheelchairs aim to provide a tailored solution that ensures appropriate driving and stability for the user. The Volting project, developed at LISV since 2020, introduces a new research direction: the development of a wheelchair capable of offering enhanced postural mobility for the user based on lateral tilting.The main objective pursued in the Volting project is to propose a reappropriation of the user's body with the imbalance caused by the tilting. In this regard, an initial proposition was made, consisting of a wheelchair capable of tilting laterally in proportion to the user's inclination. This additional freedom of movement provides the user with a greater capacity for bodily gestures, and it is in this context that wheelchair dancing was chosen as the application domain.In this thesis, the Volting prototype was studied from three perspectives: interaction, control, and assistance.Firstly, the interaction between the user and Volting refers to the relationship between the user's trunk inclination and the tilt of the Volting wheelchair. It was analyzed to find an appropriate behavior. Consequently, a model analysis was conducted to study the parameters involved in this interaction. Experiments demonstrated that the use of our model provided the appropriate parameters for correct kinematics.The second focus of this study is on the user's control of the Volting wheelchair. For this purpose, the use of a multi-sensor device called WISP was proposed. This device takes the user's trunk posture or hand position as input commands to control Volting. The implemented control logic allows the user to control the wheelchair with greater freedom in executing gestures. WISP was tested by a professional and an amateur wheelchair dancer, showing their quick adaptation to the device's use and their motivation towards dance practice.The third area of investigation concerns the use of the incline assistant, named "Glissiere" in Volting. This device relies on shifting the user's seat to promote or counteract the lateral tilt of the Volting wheelchair and, consequently, the user's body tilt. To pre-evaluate this solution, experiments showed that users with different morphologies, who were unable to use Volting to its full capacity, could use Volting with the assistance of "Glissiere."
6
Avril, Eugénie. "Automatisation de l'information et fiabilité : effets sur le comportement humain." Electronic Thesis or Diss., Toulouse 2, 2020. http://www.theses.fr/2020TOU20073.
Full textAbstract:
Face à la présence de plus en plus prépondérante des systèmes automatisés dans notre vie quotidienne, étudier les conséquences de problèmes de fiabilité de ces derniers sur le comportement humain est devenu une nécessité pour le domaine des facteurs humains. Cette thèse a pour objectif d’étudier les effets de systèmes automatisés imparfaits, dont la fiabilité n’est pas irréprochable, sur le comportement humain. Elle se focalise plus précisément sur les systèmes automatisés prenant en charge la fonction information comme présentée dans le modèle de Parasuraman, Sheridan et Wickens (2000). Ces effets sont étudiés à travers deux secteurs : le secteur aéronautique et le secteur du transport routier de marchandises. Croiser ces deux secteurs permet de mettre en place des méthodes complémentaires. Plus précisément, à travers une tâche de simulation de pilotage d’avion et une tâche d’évaluation de scénarios de planification, deux types de prise en charge de la fonction information présentant des problèmes de fiabilité ont été investigués. Ces études ont permis d’une part (1) d’approfondir les connaissances sur la fiabilité des systèmes automatisés selon les fonctions prises en charge et (2) d’apporter de nouvelles connaissances sur l’implémentation de nouveaux systèmes automatisés soutenant l’activité de planification où les études sur la fiabilité d’un système prenant en charge l’information sont inexistantesIn our daily life, it is easy to notice the overwhelming increase of automated systems. Studying the consequences of reliability problems of these systems on human behavior has become a necessity for different fields and especially for the human factors. The purpose of this thesis is to study the effects of imperfect automated systems on human behavior, knowing that their reliability is not perfect. More specifically, it focuses on automated systems that support the information function as presented in the model of Parasuraman, Sheridan and Wickens (2000). These effects are studied across two mains sectors: the aeronautical sector and the road freight transport sector. Using these two sectors allow to implement complementary methods. More precisely two types of support of the information function with reliability problems have been investigated. One is through an aircraft piloting simulation task and the second on a planning scenario evaluation task. These studies allowed on one hand (1) to deepen the knowledge on the reliability of automated systems according to the functions supported and (2) on another hand to bring new knowledge on the implementation of new automated systems supporting the planning activity where studies on the reliability of a system supporting information are non-existent
7
Bailly, Gilles. "Techniques de menus : caractérisation, conception et évaluation." Grenoble 1, 2009. http://www.theses.fr/2009GRE10062.
Full textAbstract:
Les menus permettent d'explorer et de sélectionner les commandes d'une application. Ils sont présents dans la plupart des applications et concernent un large public. Les menus sont donc au cœur de l'Interaction Homme-Machine (IHM). Aussi, cet enjeu a motivé de nombreux travaux en IHM : face au foisonnement de nouvelles techniques de menus, il n'est pas facile d'appréhender les avancées et de cerner les différences et similitudes entre les techniques de menus conçues. Dans ce contexte, cette thèse en IHM propose un espace de conception des techniques de menus, appelé MenUA. Cet espace repose sur une liste de critères utiles pour structurer les travaux sur les menus et permettre aux concepteurs d'applications de faire des choix informés. MenUA facilite aussi l'exploration de l'espace des possibilités lors de la conception : il a été à l'origine de quatre nouvelles techniques de menus que nous avons conçues, développées et évaluées : les Wave menus, les Flower menus, les Leaf menus et les Multi-Touch Menus. Les Wave menus améliorent le mode novice des Marking menus en favorisant la navigation dans la hiérarchie de commandes. En considérant la courbure des gestes de l'utilisateur, les Flower menus augmentent le nombre de commandes disponibles et améliorent l'apprentissage du mode expert des Marking menus. Les Leaf Menus sont quant à eux des menus linéaires enrichis de raccourcis gestuels et conçus pour être utilisés sur des dispositifs mobiles. Enfin, les Multi-Touch Menus exploitent la technologie multi-points des surfaces tactiles afin de naviguer et sélectionner des commandes avec les cinq doigts de la mainMenus are used for exploring and selecting commands in interactive applications. They are widespread in current applications and used by a large variety of users. As a consequence, menus are at the heart of Human-Computer Interaction (HCI) and motivate many studies in HCI. Facing the large variety of designed menu techniques, it is however difficult to have a clear understanding of the design possibilities, to understand the advances as well as to compare existing menu techniques. In this context, this thesis in HCI proposes a design space of menu techniques called MenUA. MenUA is based on a list of criteria that define a coherent framework of design issues for menus. MenUA also helps application designers to make informed design choices and is a support for exploring design alternatives. Stemming from MenUA, we designed, developed and evaluated four menu techniques: Wave menus, Flower menus, Leaf menus and Multi-Touch Menus. Wave menus improve the novice mode of Marking menus by making the navigation within the hierarchy of commands easier. Flower menus increase the menu breadth of Marking menus while supporting good learning performance of the expert mode. Leaf menus are linear menus enriched by stroke shortcuts to facilitate the selection of commands on small handheld touch-screen devices. Finally, Multi-Touch Menus exploit the recent capabilities of multi-touch surfaces in order to allow the users to explore and select commands using the five fingers of the hands
8
Clodic, Aurélie. "Supervision pour un robot interactif : action et interaction pour un robot autonome en environnement humain." Toulouse 3, 2007. http://www.theses.fr/2007TOU30248.
Full textAbstract:
Nos travaux portent sur la supervision d'un robot autonome en environnement humain et plus particulièrement sur la prise en compte de l'interaction homme-robot au niveau décisionnel. Dans ce cadre, l'homme et le robot constituent un système dans lequel ils partagent un espace commun et échangent des informations à travers différentes modalités. L'interaction peut intervenir soit sur une requête explicite de l'homme, soit parce que le robot l'a estimée utile et en a pris l'initiative. Dans les deux cas le robot doit agir afin de satisfaire un but en prenant en compte de manière explicite la présence et les préferences de son partenaire humain. Pour cela, nous avons conçu et développé un système de supervision nommé Shary qui permet de gérer des tâches individuelles (où seul le robot est impliqué) et des tâches jointes (où le robot et un autre agent sont impliqués). Ce système se compose d'une mécanique d'exécution de tâches gérant d'une part la communication nécessaire au sein d'une tâche et d'autre part l'affinement de la tâche en sous-tâches. Pour cela chaque tâche est définie par un plan de communication et un plan de réalisation auxquels sont associés des moniteurs de suivi. Nous avons développé ce système sur le robot Rackham dans le cadre d'une tâche de "Guide de musée". Nous avons également utilisé ce système dans le cadre d'une tâche du type : "apporter quelque chose à quelqu'un" sur le robot Jido pour montrer la généricité du systèmeHuman-robot collaborative task achievement requires specific task supervision and execution. In order to close the loop with their human partners robots must maintain an interaction stream in order to communicate their own intentions and beliefs and to monitor the activity of their human partner. In this work we introduce SHARY, a supervisor dedicated to collaborative task achievement in the human robot interaction context. The system deals for one part with task refinement and on the other part with communication needed in the human-robot interaction context. To this end, each task is defined at a communication level and at an execution level. This system has been developped on the robot Rackham for a tour-guide demonstration and has then be used on the robot Jido for a task of fetch and carry to demonstrate system genericity
9
He, Ruan. "Architecture et mécanismes de sécurité pour l'auto-protection des systèmes pervasifs." Paris, Télécom ParisTech, 2010. https://pastel.hal.science/pastel-00579773.
Full textAbstract:
Un système pervasif est un environnement dans lequel l'homme peut interagir avec des équipements qui ont des capacités de calcul et de communication. Dans cette thèse, un système pervasif correspond à un réseau (composé de terminaux) qui est :1- distribué et décentralisé: les terminaux sont physiquement distribués dans une région et sont reliés entre eux par des connexions sans fil. Quelque soit leur localisation physique, la communication sans fil les rend connectés entre eux. En plus, cette architecture distribuée demande souvent une coordination décentralisée des terminaux. 2- dynamique et ouvert : les terminaux, en particulier les terminaux mobiles, peuvent rejoindre et quitter un réseau pervasif à tout moment. Cette ouverture rend l’architecture du système dynamique : c'est-à-dire que la topologie du système évolue au cours du temps pendent l’exécution. Ce caractère dynamique de l'architecture nécessite une modélisation du système très flexible pour décrire les topologies variantes du système. 3 - complexe et de grande taille : l’échelle de ces systèmes peut atteindre des centaines voire des milliers de terminaux. La coordination de ces terminaux qui gère non seulement ces terminaux, mai également leurs connexions est d’un niveau de complexité élevé. Au lieu de solutions traditionnellement centralisées qui gèrent un petit nombre de terminaux, les systèmes pervasifs à grande échelle devraient appliquer une solution plus efficaceIn this thesis, we propose: - A three-layer abstract architecture: a three-layer self-protection architecture is applied to the framework. A lower execution space provides running environment for applications, a control plane controls the execution space, and an autonomic plane guides the control behavior of the control plane in taking into account system status, context evolution, administrator strategy and user preferences. - An attribute-based access control model: the proposed model (Generic Attribute-Based Access Control) is an attribute-based access control model which improves both the policy-neutrality to specify other access control policies and exibility to enable fine-grain manipulations on one policy. - A policy-based framework for authorization integrating autonomic computing: the policy-based approach has shown its advantages when handling complex and dynamic systems. In integrating autonomic functions into this approach, an Autonomic Security Policy Framework provides a consistent and decentralized solution to administer G-ABAC policies in large-scale distributed pervasive systems. Moreover, the integration of autonomic functions enhances user-friendliness and context-awareness. - A terminal-side access control enforcement OS: the distributed authorization policies are then enforced by an OS level authorization architecture. It is an effcient OS kernel which controls resource access through a dynamic manner to reduce authorization overhead. On the other hand, this dynamic mechanism improves the integrability of di_erent authorization policies. - An adaptation policy specifcation Domain Speci_c Language (DSL) for adaptation policy specification
10
Vo, Dong-Bach. "Conception et évaluation de nouvelles techniques d'interaction dans le contexte de la télévision interactive." Thesis, Paris, ENST, 2013. http://www.theses.fr/2013ENST0053/document.
Full textAbstract:
La télévision n’a cessé de se populariser et d’évoluer en proposant de nouveaux services. Ces services de plus en plus interactifs rendent les téléspectateurs plus engagés dans l’activité télévisuelle. Contrairement à l’usage d’un ordinateur, ils interagissent sur un écran distant avec une télécommande et des applications depuis leur canapé peu propice à l’usage d’un clavier et d’une souris. Ce dispositif et les techniques d’interaction actuelles qui lui sont associées peinent à répondre correctement à leurs attentes. Afin de répondre à cette problématique, les travaux de cette thèse explorent les possibilités offertes par la modalité gestuelle pour concevoir de nouvelles techniques d’interaction pour la télévision interactive en tenant compte de son contexte d’usage. Dans un premier temps, nous présentons le contexte singulier de l’activité télévisuelle. Puis, nous proposons un espace de caractérisation des travaux de la littérature cherchant à améliorer la télécommande pour, finalement, nous focaliser sur l’interaction gestuelle. Nous introduisons un espace de caractérisation qui tente d’unifier l’interaction gestuelle contrainte par une surface, mains libres, et instrumentée ou non afin de guider la conception de nouvelles techniques. Nous avons conçu et évalué diverses techniques d’interaction gestuelle selon deux axes de recherche : les techniques d’interaction gestuelle instrumentées permettant d’améliorer l’expressivité interactionnelle de la télécommande traditionnelle, et les techniques d’interaction gestuelles mains libres en explorant la possibilité de réaliser des gestes sur la surface du ventre pour contrôler sa télévisionTelevision has never stopped being popularized and offering new services to the viewers. These interactive services make viewers more engaged in television activities. Unlike the use of a computer, they interact on a remote screen with a remote control from their sofa which is not convenient for using a keyboard and a mouse. The remote control and the current interaction techniques associated with it are struggling to meet viewers’ expectations. To address this problem, the work of this thesis explores the possibilities offered by the gestural modality to design new interaction techniques for interactive television, taking into account its context of use. More specifically, in a first step, we present the specific context of the television usage. Then, we propose a litterature review of research trying to improve the remote control. Finally we focus on gestural interaction. To guide the design of interaction techniques based on gestural modality, we introduce a taxonomy that attempts to unify gesture interaction constrained by a surface and hand-free gesture interaction. Therefore, we propose various techniques for gestural interaction in two scopes of research : gestural instrumented interaction techniques, which improves the traditional remote control expressiveness, and hand-free gestural interaction by exploring the possibility o performing gestures on the surface of the belly to control the television set
Books on the topic "Interaction humain et machine"
1
Jahn, Robert G. Consciousness and the source of reality: The PEAR odyssey. Princeton, New Jersey: ICRL Press, 2011.
Find full text
2
Céline, Paganelli, ed. IHM et recherche d'information. Paris: Hermès science publications, 2002.
Find full text
3
David, Ermann M., Williams Mary B, and Gutiérrez Carranza Claudio 1930-, eds. Computers, ethics, and society. New York: Oxford University Press, 1990.
Find full text
4
Sylvain, Missonnier, and Stora Michael, eds. L'enfant au risque du virtuel. Paris: Dunod, 2006.
Find full text
5
Norman, Donald A. She ji & wei lai sheng huo. Taibei Shi: Yuan liu chu ban shi ye gu fen you xian gong si, 2008.
Find full text
6
Adams, Annette. Notre corps, cette prodigieuse machine: Pour en savoir plus sur notre organisme et pénétrer le miracle de la vie. Montréal: Sélection Reader's Digest, 1998.
Find full text
7
Adams, Annette. Notre corps, cette prodigieuse machine: Pour en savoir plus sur notre organisme et pénétrer le miracle de la vie. Montréal: Sélection Reader's Digest, 1998.
Find full text
8
Ontario. Esquisse de cours 12e année: Géographie mondiale: le milieu humain cgu4u cours préuniversitaire. Vanier, Ont: CFORP, 2002.
Find full text
9
Leopoldina, Fortunati, Katz James Everett, and Riccini Raimonda, eds. Mediating the human body: Technology, communication, and fashion. Mahwah, N.J: Lawrence Erlbaum Associates, Publishers, 2003.
Find full text
10
missing], [name. Mediating the human body: Technology, communication, and fashion. Mahwah, NJ: Lawrence Erlbaum Associates, 2003.
Find full textBook chapters on the topic "Interaction humain et machine"
1
Trambaiolli, Lucas R., Claudinei E. Biazoli, and João R. Sato. "Brain Imaging Methods in Social and Affective Neuroscience: A Machine Learning Perspective." In Social and Affective Neuroscience of Everyday Human Interaction, 213–30. Cham: Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-031-08651-9_13.
Full textAbstract:
AbstractMachine learning (ML) is a subarea of artificial intelligence which uses the induction approach to learn based on previous experiences and make conclusions about new inputs (Mitchell, Machine learning. McGraw Hill, 1997). In the last decades, the use of ML approaches to analyze neuroimaging data has attracted widening attention (Pereira et al., Neuroimage 45(1):S199–S209, 2009; Lemm et al., Neuroimage 56(2):387–399, 2011). Particularly interesting recent applications to affective and social neuroscience include affective state decoding, exploring potential biomarkers of neurological and psychiatric disorders, predicting treatment response, and developing real-time neurofeedback and brain-computer interface protocols. In this chapter, we review the bases of the most common neuroimaging techniques, the basic concepts of ML, and how it can be applied to neuroimaging data. We also describe some recent examples of applications of ML-based analysis of neuroimaging data to social and affective neuroscience issues. Finally, we discuss the main ethical aspects and future perspectives for these emerging approaches.
2
Skadiņa, Inguna, Ilze Auziņa, Baiba Valkovska, and Normunds Grūzītis. "Language Report Latvian." In European Language Equality, 171–74. Cham: Springer International Publishing, 2023. http://dx.doi.org/10.1007/978-3-031-28819-7_24.
Full textAbstract:
AbstractTen years ago, when META-NET conducted a study on Language Technology support for Europe’s languages, Latvian was assessed as a language with little or no support (Skadiņa et al. 2012). During the last decade, progress has been made in the development of language resources and tools for Latvian, particularly with respect to advanced datasets and language models, machine translation solutions, speech technologies, and technologies for natural language understanding and human-computer interaction. This chapter provides a summary of the current state of the Latvian language, the only official language of Latvia, in the digital environment and highlights the most important activities in the language technology field.
3
Osęka, Laura, Grzegorz Pochwatko, and Justyna Świdrak. "Polish Adaptation of the Cybersickness Susceptibility Questionnaire (CSSQ-PL)." In Digital Interaction and Machine Intelligence, 222–30. Cham: Springer Nature Switzerland, 2023. http://dx.doi.org/10.1007/978-3-031-37649-8_22.
Full textAbstract:
AbstractWe present the Polish adaptation of the Cybersickness Susceptibility Questionnaire (CSSQ) by Freiwald et al. [4] and its short version. To validate the scale, we analyzed the results of 85 participants of the VR artistic experience “Nightsss” in versions with 3 and 6 degrees of freedom. Both long and short versions are characterized by high internal consistency. The validity was analyzed by evaluating the difference between the scores obtained in the CSSQ-PL and the level of experienced cybersickness measured with the Simulator Sickness Questionnaire. The scale is suitable for screening participants in research conducted with the use of immersive virtual reality (VR). Further studies are necessary to confirm the predictive power of the scale.
4
Bellagamba, Ugo. "Isabot 2050, ou l’histoire de l’avocat augmenté qui comptait trop sur son IA." In Transhumanisme : de nouveaux droits ?, 127–35. Aix-en-Provznce: DICE Éditions, 2024. http://dx.doi.org/10.4000/11zb1.
Full textAbstract:
En 2050, dans un monde où l’usage des intelligences artificielles s’est généralisé, au point de les voir investir tous les domaines de la vie privée et professionnelle, les fonctions de l’avocat sont restées étrangement semblables : il consulte, et il plaide. Mais, sous les apparences d’une belle symbiose entre la machine et l’être humain, se dessinent les contours d’une société qui, sans s’en rendre compte, a tourné le dos à certains de ses repères juridiques les mieux ancrés. Demain, la pluie est programmée, mais qu’en est-il de la défense ?
5
Seta, Kazuhisa. "Task Ontology-Based Human-Computer Interaction." In Human Computer Interaction, 950–60. IGI Global, 2009. http://dx.doi.org/10.4018/978-1-87828-991-9.ch058.
Full textAbstract:
In ontological engineering research field, the concept of “task ontology” is well-known as a useful technology to systemize and accumulate the knowledge to perform problem-solving tasks (e.g., diagnosis, design, scheduling, and so on). A task ontology refers to a system of a vocabulary/ concepts used as building blocks to perform a problem-solving task in a machine readable manner, so that the system and humans can collaboratively solve a problem based on it. The concept of task ontology was proposed by Mizoguchi (Mizoguchi, Tijerino, & Ikeda, 1992, 1995) and its validity is substantiated by development of many practical knowledge-based systems (Hori & Yoshida, 1998; Ikeda, Seta, & Mizoguchi, 1997; Izumi &Yamaguchi, 2002; Schreiber et al., 2000; Seta, Ikeda, Kakusho, & Mizoguchi, 1997). He stated: …task ontology characterizes the computational architecture of a knowledge-based system which performs a task. The idea of task ontology which serves as a system of the vocabulary/concepts used as building blocks for knowledge-based systems might provide an effective methodology and vocabulary for both analyzing and synthesizing knowledge-based systems. It is useful for describing inherent problem-solving structure of the existing tasks domain-independently. It is obtained by analyzing task structures of real world problem. ... The ultimate goal of task ontology research is to provide a theory of all the vocabulary/concepts necessary for building a model of human problem solving processes. (Mizoguchi, 2003) We can also recognize task ontology as a static user model (Seta et al., 1997), which captures the meaning of problem-solving processes, that is, the input/output relation of each activity in a problem-solving task and its effects on the real world as well as on the humans’ mind.
6
Seta, Kazuhisa. "Task Ontology-Based Human-Computer Interaction." In Encyclopedia of Human Computer Interaction, 588–96. IGI Global, 2006. http://dx.doi.org/10.4018/978-1-59140-562-7.ch087.
Full textAbstract:
In ontological engineering research field, the concept of “task ontology” is well-known as a useful technology to systemize and accumulate the knowledge to perform problem-solving tasks (e.g., diagnosis, design, scheduling, and so on). A task ontology refers to a system of a vocabulary/concepts used as building blocks to perform a problem-solving task in a machine readable manner, so that the system and humans can collaboratively solve a problem based on it. The concept of task ontology was proposed by Mizoguchi (Mizoguchi, Tijerino, & Ikeda, 1992, 1995) and its validity is substantiated by development of many practical knowledge-based systems (Hori & Yoshida, 1998; Ikeda, Seta, & Mizoguchi, 1997; Izumi &Yamaguchi, 2002; Schreiber et al., 2000; Seta, Ikeda, Kakusho, & Mizoguchi, 1997). He stated: …task ontology characterizes the computational architecture of a knowledge-based system which performs a task. The idea of task ontology which serves as a system of the vocabulary/concepts used as building blocks for knowledge-based systems might provide an effective methodology and vocabulary for both analyzing and synthesizing knowledge-based systems. It is useful for describing inherent problem-solving structure of the existing tasks domain-independently. It is obtained by analyzing task structures of real world problem. ... The ultimate goal of task ontology research is to provide a theory of all the vocabulary/concepts necessary for building a model of human problem solving processes. (Mizoguchi, 2003) We can also recognize task ontology as a static user model (Seta et al., 1997), which captures the meaning of problem-solving processes, that is, the input/output relation of each activity in a problem-solving task and its effects on the real world as well as on the humans’ mind.
7
Gruszauskas, Nicholas P., Karen Drukker, and Maryellen L. Giger. "Robustness Studies of Ultrasound CADx in Breast Cancer Diagnosis." In Machine Learning in Computer-Aided Diagnosis, 1–22. IGI Global, 2012. http://dx.doi.org/10.4018/978-1-4666-0059-1.ch001.
Full textAbstract:
This chapter will focus on the robustness, or reliability, of computer-aided diagnosis, abbreviated as CADx. In CADx, computerized analysis is used to characterize abnormalities identified by a human user (e.g., a radiologist). CADx is part of the broader area of quantitative imaging (Giger, Chan, & Boone, 2008). Other examples of quantitative imaging applications include computer-aided detection (Drukker, et al., 2002; Drukker, Giger, & Mendelson, 2003), computer-aided prognosis (Bhooshan, et al., 2010), and computer-aided assessment of response to therapy (Shi, et al., 2009; Shiraishi, Li, Appelbaum, Pu, & Doi, 2007). The task of primary interest in this chapter is the diagnosis of breast cancer using sonographic images(i.e., the distinction between benign and malignant breast lesions). The only steps that require human interaction are the identification of suspicious abnormalities prior to the computerized analysis by the CADx system and the interpretation of the CADx results. It is important to note that CADx only provides the radiologist with additional information. The final decision as to whether or not a given abnormality is worrisome lies with the radiologist. In order for CADx to be of potential help it is required that a CADx system demonstrates not only good but also consistent performance. The latter aspect is the focus of this chapter in which the authors will explore causes of variability and investigate CADx performance under different realistic scenarios.
8
Sofo, Giuseppe. "La traduction à l’ère numérique : Histoire, évolution et perspectives de la rencontre entre la traduction et l’intelligence artificielle." In Human Translation and Natural Language Processing Towards a New Consensus? Venice: Fondazione Università Ca’ Foscari, 2023. http://dx.doi.org/10.30687/978-88-6969-762-3/002.
Full textAbstract:
This article analyses the long history of the relationship between translation and digital technologies, from the first attempts to build machine translation systems to the evolution of language and translation in the digital age. The deep relationship between translation and digital technologies has been fruitful and has generated fascinating perspectives for linguistics, and it is also due to the fact that the questions at the heart of translation practice and theory have much in common with those posed by research into Artificial Intelligence. The current evolution of translation is directly linked to that of digital tools, computing, and Artificial intelligence, and this will be all the more true in the future, and although most attempts to predict the results of this interaction have failed in the past, this article will try to trace a few lines of research that are beginning to emerge, or that could be envisaged for the future.
9
Wendrich, Robert E. "Cyber-Physical Systems, Blended Tool Environments, and Playful Creativity." In Advances in Computers and Information in Engineering Research, Volume 2, 589–619. ASME, 2021. http://dx.doi.org/10.1115/1.862025_ch19.
Full textAbstract:
All tools humanity uses are extensions of their physical and/or virtual reach, towards a specific purpose or to fulfill a particular, specified, or dedicated task. The tool is handled, initiated and actively guided to participate in interaction, perception, and/or interpretation of the world around us. Tools mediate in action and interaction, like handling a toothbrush to gain a fresh set of cleaned teeth or to use a hammer to pound nails in a material. The real physicality of these human interactions convey a lot of information and creates knowledge in various levels of insight and understanding. Not only in terms of feeling satisfied in the accomplishment of a task, but also in the experience of tool use and succesful interaction. Furthermore, metacognitive aspects of tool use occur when human beings and tools work together and can be seen as an action-based method of advancing knowledge. In the quotidian, a mixture of tools (i.e. used, embedded) and tool activities occur to directly or indirectly interact with our physical and virtual surroundings, things, or systems. Analogue tools, like e.g. knives, pens, chairs and cars have different complexities, but through communicated ’meaning’ (Dewey, 2005) [9], these artifacts possess a distinct quality and intrinsic interaction of use. Some of these tools have very simple but effective use qualities and therefore are most of the time easy to understand in function and use. Other more sophisticated tools imply more study and demand lots of exercise (i.e. high learning threshold) in order to get the full benefit, function and gain in user experience (UX) and results. In the digital and virtual realms many varieties of computational tools are encountered. As a consequence, many categories and levels of tool use, usage through interaction, usability, user-skills and UX happen. The last decades showed a plethora of tool applications and tool interactions that eluded many users, consequently leading to misinterpretation, misguidance, frustration, reduction and inert mediocrity. Not to speculate that digital innovations and tools are defunct gadgets or not worthy of inclusion in daily life. On the contrary, digital technology plays a crucial role in our understanding of the physical and virtual worlds that co-exists and give us much broader boundless experiences and perspectives than ever before. The problem with most digital tools is, the constructed user interface (UI) and user interaction (UA) between a user and machine, as shown in, for example; Carroll, 1991 [5], Carroll, 2002 [6], Dix, 2009 [10], Hartson, 2003 [16], Piumsomboon et al., 2017 [31], Wendrich, 2016 [44], Rogers, 2011 [33]. This in turn has lead to more study and research being conducted on this subject over the last decades, what somehow lead to more confusion and misapprehension. Incremental improvements in UI have been explored and became a sort of standard, new approaches to UIs and UAs have appeared and wiped others, in some cases e.g. multi-touch sensing surfaces became a next step in interacting with the digital-virtual realms. This in turn lead to a leap in applications software (app) design to create tools that were easy to manipulate and use by swiping fingers across high-definition interactive icons to work the tool. However, how feebly, fleetly or superficial this type of mediated interactions may seem, somehow it became a prefered way of ’doing things.’ Gradually this kind of interaction became the standard, encroached with instant gratification and satisfaction. Eventually, everything is an approximation with human frailty, so is tool use and are tools, Figure 19.1.
10
VAZ-CERNIGLIA, Célia. "Vulnérabilité et Intelligences Artificielles." In Intelligence(s) artificielle(s) et Vulnérabilité(s) : kaléidoscope, 23–28. Editions des archives contemporaines, 2020. http://dx.doi.org/10.17184/eac.3632.
Full textAbstract:
Cet écrit relate une série d’interrogations sur ce qui relève spécifiquement du sujet humain et de sa complexité, à savoir sa singularité et qui ne peut être vécu par une machine, une intelligence artificielle, si sophistiquée soit-elle.
Conference papers on the topic "Interaction humain et machine"
1
Probst, Alice, Gary Perelman, Emmanuel Dubois, and Marcos Serrano. "Acquisition visuelle en réalité mixte, depuis et vers une table interactive : Analyse de la transition entre un écran virtuel et un écran physique." In IHM '22: 33e conférence internationale francophone sur l'Interaction Humain-Machine. New York, NY, USA: ACM, 2022. http://dx.doi.org/10.1145/3500866.3516377.
Full text
2
Barile, Paolo, Sergio Barile, Clara Bassano, Paolo Piciocchi, Marialuisa Saviano, and James Clinton Spohrer. "T-Shaped Professional (T-SP) Model to support Human-Machine Interaction." In 14th International Conference on Applied Human Factors and Ergonomics (AHFE 2023). AHFE International, 2023. http://dx.doi.org/10.54941/ahfe1003110.
Full textAbstract:
Researches and studies did not investigate in deep the importance to develop T-shaped skills and techniques for aligning human machine learning (Spohrer, Banavar, 2015) and to design more intuitive machine interfaces. Recently, in this direction, we can find some efforts with regards to the introduction of innovative approaches in education programs inspired by the T-Shaped Model (Barile and Saviano 2021; Saviano et al., 2017a; 2017b; Barile et al., 2015; 2015a). Thus, the aim of the paper is to explore the interpretative contribution of the VSA proposal of the T-Shaped Professional (T-SP) representation, to reconceive human-machine interaction in order to understand the characteristics that people must have to interact effectively (Barile et al., 2019; 2021; Bassano et al., 2020; 2021). Given our purpose, we refer to the trans-disciplinary approach based on Service Science (SS) and Viable Systems Approach (VSA) as methodological frameworks for highlighting the VSA contribution to frame the use of the revised T-Shaped Professionals (T-SP) Model – in which vertical expertise is combined with horizontal and cross-sectional knowledge (Maglio & Spohrer, 2008; Demirkan & Spohrer, 2015; Freund 2018; Moghaddam, Demirkan, and Spohrer 2018; Gardner & Maietta 2020) –, in the emerging context of the digital transformation where workforce’s personal and intellectual habits are challenged (Piciocchi et al., 2017; 2018; 2019). The paper could offer interesting insights for debating on the need for an actualized T-SP model that should be characterized by a proactive attitude, creativity and change management orientation. This assumption is coherent with the increasing demand for workers whose social emotional learning skills are crucial and not yet susceptible to computerization (Frey, C.B. and Osborne, 2017). This implies the need to understand why and how each person can access the rapidly growing digital workforce by reconfiguring own professional shape.
3
Gonzalez, Sergio. "Generative Humane-Machine Interaction in Oil & Gas." In Offshore Technology Conference. OTC, 2024. http://dx.doi.org/10.4043/35168-ms.
Full textAbstract:
Abstract From the Acheulean stone tools in prehistory first made by the homo ergaster around 250.000 BCE (V. Smil, 2017) to the wooden plows in Mesopotamia enabling first steps to enabling machine-assisted agriculture around 4.000 BCE (V. Smil, 2017) and then the scaling of waterwheels in Greece and Rome civilizations from 100 BCE to 600 CE (V. Smil, 2017) along with following developments of windmills and blast furnaces that preceded the revolutions of steam, mechanical, combustion and electrical machines in recent history, there is one common aspect that has remained true across all civilizations: how humans interact with machines for greater efficiency, effectiveness and ultimately better quality of life. The arrival of information technology in the 20th century transformed that interaction in many ways, starting with a dream of a small shop in Redmond, WA, which vision at its foundation in 1974 was to have a personal computer in every single household of the world and later a company from California bringing mobile phones into everyone's hands, to name a few examples out of many. This citizen-based change quickly expanded to industrial operations and machines that used to be "dumb" for ages suddenly start speaking and telling humans how they feel through basic arrangements of measurement sensors, data historians and visualization technologies. At the moment of development of this paper we are at the end of the first quarter of the 21st century and looking back and reflecting on what has been the most significant development during this period affecting human-machine interaction, it is the author's belief that it is in the field of artificial intelligence. Artificial intelligence (AI) refers to the theory and development of computer systems capable of performing tasks that normally require human intelligence, such as visual perception, speech recognition, decision-making, and translation between languages (H.A. Simon, 1996). The goal of AI is to create machines that can perform tasks that would normally require human intelligence. (S. Russell et al., 2016) The power of cognitive and machine learning services, together with rapid advancements in robotics and autonomous systems, will significantly change the way humans interact with machines and subsequently drive impact inflection points on productivity and efficiency. Within the artificial intelligence realm, probably one of the most exciting technological developments of today lies around generative AI, which could be briefly defined as a form of artificial intelligence in which models are trained to generate new original content based on natural language input (learn.microsoft.com). This paper focuses on how artificial intelligence in general and particularly generative AI could transform the human-machine interaction in the oil and gas industry, covering specific examples in the fields of artificial lift and power generation.
4
Jefferson, Brett, and Jessica Baweja. "Human Factors in Discovery Phase of TRLs and HRLs." In 14th International Conference on Applied Human Factors and Ergonomics (AHFE 2023). AHFE International, 2023. http://dx.doi.org/10.54941/ahfe1003582.
Full textAbstract:
With rapid growth in technology, there has been a corresponding growth in research focused on the ways that human-machine interactions can be improved. As part of that work, researchers have explored how human expertise can inform technology design and evaluation. For example, interaction with subject matter experts (SMEs) or end users can help to design and enhance a machine. The human factors of technology release can be divided into five steps: discovery, planning, development, evaluation, and deployment. This framework is a higher-level abstraction of the Human Readiness Levels for technology use and adoption (See et al. 2018). In this exposition, we discuss how human factors methodologies, principles, and practices can be realized in the first phase, Discovery, of the technology development process.
5
Wirtz, Lena, Emirhan Sever, and Lutz Eckstein. "Adaptive Human-Machine Interfaces and Inclusivity in the Automotive Field: A Review." In 15th International Conference on Applied Human Factors and Ergonomics (AHFE 2024). AHFE International, 2024. http://dx.doi.org/10.54941/ahfe1004613.
Full textAbstract:
With advances in automated driving, the importance of the vehicle interior continues to grow. However, the growing number of functions leads to a large amount of information on automation or infotainment systems. To create an individual customer experience and not to overwhelm the driver with the growing amount of information, an adaptive human-machine interface (HMI) can be a solution. (Amditis et al., 2011) With the help of adaptive HMI, it is possible to display contextual and user-specific information and to adapt the interaction with the vehicle. Inclusion is a form of adaptation focusing the needs of the respective users. Thereby, adaptive HMI addresses, among other things, the enhancement of driving safety and empathy in the vehicle. (Rittger et al., 2022) This paper provides an overview of the current state of the art with respect to adaptive and inclusive HMI in the automotive context and facilitates the identification of open research questions. A systematic literature search was conducted to facilitate this scoping review.
6
Giugliano, Giovanna, Sonia Capece, and Mario Buono. "Multidimensional, Intuitive and Augmented Interaction Models for Robotic Surgery." In 13th International Conference on Applied Human Factors and Ergonomics (AHFE 2022). AHFE International, 2022. http://dx.doi.org/10.54941/ahfe1002320.
Full textAbstract:
Surgical robotics in operating rooms is an innovative and rapidly evolving field, and performance levels need to be improved. Despite technological advances, there are still many limitations in surgeon-robot interaction, such as the lack of tactile feedback from the surgeon and visualization issues arising from the surgeon's position relative to the operating table. Therefore, among the challenges of robotic surgery is the design of efficient and ergonomic human-machine interaction systems that can improve and enhance the capabilities of the surgeon and the robot (Boyraz et al., 2019) while ensuring risk reduction and high levels of ergonomics and safety. This will improve the surgeon's perception and eliminate possible accidental contact with tissues and injuries. In this scenario, the contribution illustrates the reconnaissance and analysis activities carried out to identify the limitations and advantages of the current interfaces and visualization technologies applied to robotic surgery to verify their usability and the ways of surgeon-robot interaction.
7
Erik Mørkrid, Odd, Kay Fjørtoft, Marianne Hagaseth, and Even Holte. "Assessment of resilience in a maritime autonomous transport system." In 15th International Conference on Applied Human Factors and Ergonomics (AHFE 2024). AHFE International, 2024. http://dx.doi.org/10.54941/ahfe1005262.
Full textAbstract:
Resilience attributes are turned upside down when introducing autonomous maritime transport systems, as technology replaces or assists human functions. We enter an unknown world where we need to rely on autonomous functions and the collaboration between humans and technology. Since less human interaction might cause challenges and effects not yet uncovered, Kaber (2018)[1] discussed levels of autonomy in the context of human automation interaction (HAI). The paper particularly looks at the use of levels of autonomy as taxonomies to structure and improve analysis of human performance, workload, but also situational awareness as well as some of the problems that this may cause. The introduction of increasing automation changes the way human and machine interact in many ways. As such, to ensure resilience in autonomous transport systems, these human and machine interaction challenges must be addressed and systemized, and in this paper the different awareness categories humans, technology and external (Fjørtoft, K.E., 2021), are revisited and linked to resilience. Also, as an extension on how to utilize integrated planning for autonomous transport systems (IPA), as presented by Fjørtoft, et al. (2023), this paper further details emerging issues related to human and machine interface by presenting a framework for how to secure resilience during the design, plan and follow up autonomous ship operations. In other words, the ability to assess and ensure resilience when planning operations in autonomous maritime transport system, while accounting for the interaction between humans and technology. This is of particular relevance due to the likelihood of vessels sailing with different degrees of autonomy, depending on the ongoing operation and its surroundings. Described as operational envelopes in "Towards approval of autonomous ship systems by their operational envelope" (Rødseth 2021), the overall operation must be broken down into sub-operations such as sailing in open seas, berthing, cargo loading/unloading (crane operation), etc.The framework is exemplified through a case study, by combining research results from the Norwegian project MARMAN and EU projects like AUTOSHIP and AEGIS.
8
Cîrcu, Sorina-Silvia, and Chu-Yin Chen. "How Digital Anthropomorphism Enhances Creativity in Human-to-Robot Dance Interactivity." In 28th International Symposium on Electronic Art. Paris: Ecole des arts decoratifs - PSL, 2024. http://dx.doi.org/10.69564/isea2023-47-full-circu-et-al-human-to-robot-dance.
Full textAbstract:
Through our research-creation experiments, we imagine movement sequences that challenge the concept of anthropomorphism in digital twin robots. While considering the term of interactivity to better define their interaction, we observe how different movement material is stimulating creativity through a hybridization process between human and machine. From this perspective, we determine how users experience qualia while learning through imitation a dance sequence consecutively demonstrated by a humanoid robot, an industrial arm and a human. Their feedback and our own practical experimentation allow us to better understand the impact of digital anthropomorphism in the making of a sustainable human-to-robot interaction.
9
Ech Chafai, Nicolas, Magalie Ochs, Christopher Peters, Maurizio Mancini, Elisabetta Bevacqua, and Catherine Pelachaud. "Des agents virtuels sociaux et émotionnels pour l'interaction humain-machine." In the 19th International Conference of the Association Francophone d'Interaction Homme-Machine. New York, New York, USA: ACM Press, 2007. http://dx.doi.org/10.1145/1541436.1541475.
Full text
10
Gerges, Nader, Gennady Makarychev, Luisa Ana Barillas, Alaa Maarouf, Midhun Madhavan, Sonal Gore, Lulwa Almarzooqi, Sylvain Wlodarczyk, Chakib Kada Kloucha, and Hussein Mustapha. "Machine-Learning-Assisted Well-Log Data Quality Control and Preprocessing Lab." In ADIPEC. SPE, 2022. http://dx.doi.org/10.2118/211719-ms.
Full textAbstract:
Abstract Log and core data has been collected in the mature supergiant fields of the Middle East over many decades with variable data quality and vintages. These data could be affected by artifacts created by borehole conditions, different logging tools, water- or oil-based mud systems, and different processing parameters. The data are frequently lacking traceability to borehole/experiment conditions required to apply appropriate and consistent corrections for further modeling workflows. As a result, petrophysicists must perform substantial log, core quality control (QC) and editing prior to interpreting logs or using core data. The purpose of this paper is to discuss machine-learning (ML) applications grouped in the solution to automatically QC and process core and log data for hundreds of wells. The goal was to detect poor data and outliers to apply corrections that mimic human-led interpretation for at least 80 to 90% of the data processed. For several data sets and cases, ML was successfully used to various aspects of log editing. (Akkurt et al. 2018; Liang et al. 2019; Mawlod et al. 2019; Singh et al. 2020). However, as a result of our 2020 study, we discovered numerous lessons that are addressed in this work: Geological and geospatial information are potentially as valuable as well data and cannot be overlooked by any ML algorithm working with well data at the field scale.ML algorithms are more efficient than human-led data processing and can produce more accurate and consistent outcomes. However, the parameter selection and QC of outcomes require an expert assessment. Thus, ML-based applications cannot be "black boxes" and must include a user-interaction toolbox for efficient workflow control.To deliver a more efficient solution in terms of performance over large data sets, the full capacity of cloud-based technologies should be utilized, thereby enabling the parallelization of operations while simultaneously constructing and analyzing multiple solution scenarios. In the current work, we developed an ML application to QC core and well log data to perform log editing (artifact correction) and missing log prediction using other available data. The ML application is guided by petrophysical domain expertise and advanced data-driven algorithms to perform complex data homogenization and predictions for hundreds of wells using a cloud-based environment. The application may communicate with a wellbore platform project and read data from separate files in the log ASCII standard (LAS) and digital log interchange standard (DLIS) formats. The methodology is as follows: Data liberation from wellbore platform projectIntegration of geospatial and geological data with available core and log data in a single data frameOutlier detection of petrophysical logs and core dataFeatures selection for log editingClustering–prediction–validation of training data sets using a variable number of clusters to select the best model for a targeted variable predictionResults transfer to a wellbore platform project The proposed ML application integrates geological and geospatial information to provide a quality homogenized data set to be used in rock-typing, permeability, and saturation modeling. The ML application will significantly save time and effort to eliminate repetitive human tasks. The cloud-based implementation, when combined with existing petrophysical platforms, enables the highest performance and data exchange between the different software platforms. Interactive and user-friendly dashboards will provide the geoscientists with complete control over each step of the ML data-driven workflow.
Reports on the topic "Interaction humain et machine"
1
Jocelyn, Sabrina, Élise Ledoux, Damien Burlet-Vienney, Isabelle Berger, Isvieysys Armas Marrero, Chun Hong Law, Yuvin Chinniah, et al. Identification en laboratoire des éléments essentiels au processus d’intégration sécuritaire de cellules cobotiques. IRSST, August 2024. http://dx.doi.org/10.70010/qkwy4060.
Full textAbstract:
Les cobots sont apparus vers 2010 en industrie et les accidents sont très peu documentés. La gestion des risques en cobotique représente un réel défi. La littérature scientifique montre l’existence de divers modèles, méthodes et outils pour gérer les risques en cobotique, en mettant l’opérateur humain au cœur de l’intégration des applications collaboratives. Cependant, un autre humain clé de la mise en œuvre de ces applications est négligé la plupart du temps. Il s’agit de l’intégrateur, celui qui doit concevoir la cellule cobotique. À notre connaissance, deux études portant sur un même projet de conception d’un logiciel aidant à mettre en œuvre des cellules cobotiques sont les seules mettant l’intégrateur au cœur de leur invention. Cependant, cette prise en compte de l’intégrateur se base sur un retour d’expérience relatif à leurs intégrations passées. Le présent rapport se démarque en plaçant l’intégrateur au cœur de sa méthodologie et en exploitant l’analyse de l’entièreté du processus d’intégration au fur et à mesure qu’il se déroule. En effet, l’objectif de ce rapport est d’identifier, en laboratoire, les éléments essentiels au processus d’intégration sécuritaire de cellules cobotiques, en considérant les variabilités inhérentes à la tâche à cobotiser et à l’intégrateur. Pour y parvenir, l’étude passe par trois étapes principales : 1) la caractérisation des tâches cobotisées en industrie et des interactions humain-cobot à partir de matériels visuels issus d’études de cas et de visites en entreprise ; 2) l’intégration, en laboratoire, de quatre cellules cobotiques, à savoir deux tâches industrielles implantées chacune par deux intégrateurs (chaque intégrateur doit mettre en œuvre les cellules cobotiques relatives aux deux tâches industrielles) ; 3) l’analyse des éléments de prises de décisions des intégrateurs pour chacun des quatre processus d’intégration. La caractérisation à l’étape 1 du projet permet de proposer cinq classes d’applications collaboratives : 1) la collaboration directe en alternance ; 2) la collaboration directe d’assistance ; 3) la collaboration indirecte séquentielle ; 4) la collaboration indirecte parallèle ; 5) le partage d’espace occasionnel sans collaboration. La définition de ces classes est utile à tout intégrateur voulant démarrer son analyse des risques d’une installation cobotique. L’analyse des risques commence avec la détermination des limites de l’installation à mettre en œuvre, au sens de la norme en robotique ISO 10218 et, plus généralement, au sens de la norme ISO 12100 en sécurité des machines. À la lumière des résultats des trois étapes de l’étude, ce rapport propose un outil de détermination des limites d’une installation cobotique. Ces limites sont les variabilités inhérentes à la tâche à cobotiser, notées au fil de la réalisation des intégrations et des différentes étapes de la méthodologie. Nous avons constaté que, parmi tous les éléments de variabilité influençant les quatre processus d’intégration étudiés, les trois premiers éléments suivants liés à la tâche à cobotiser et les deux derniers éléments suivants associés à l’intégrateur étaient essentiels dans ces processus : 1) le choix du cobot ; 2) le type de pièce à manipuler et le type d’outil robotique ; 3) les contraintes de temps de cycle et de productivité ; 4) la formation de l’intégrateur en sécurité des machines en général et en sécurité en cobotique plus précisément ; 5) les informations, relatives à la sécurité ou la productivité, qu’il reçoit de son entourage, puisqu’elles le poussent à remettre en question ses choix initiaux et les corriger s’il y a lieu (il s’agit de rétroactions). Des pistes de réflexion relatives à ces éléments de variabilité sont énoncées à la fin du rapport.