首页> 外文学位 >Un outil d'evaluation neurocognitive des interactions humain-machine.
【24h】

Un outil d'evaluation neurocognitive des interactions humain-machine.

机译:用于人机交互的神经认知评估的工具。

获取原文
获取原文并翻译 | 示例

摘要

More and more researches on Human-Computer Interactions (HCI) are trying to perform detailed analyses of interaction to determine its influence on users' behaviours. A particular emphasis is now put on emotional reactions during the interaction, whether it's from the perspective of user experience evaluation or user performance. Standard qualitative approaches are limited because they are based on observations and interviews after the interaction, therefore limiting the precision of the diagnosis. User experience and emotional reactions being, by nature, highly dynamic and contextualized, evaluation approaches should be the same to accurately diagnose the quality of interaction. This thesis presents an evaluation approach, both dynamic and quantitative, which allows contextualising users' emotional reactions to help identify their causes during the interaction with a system. To this end, our work focuses on three main axes: 1) automatic task recognition using machine learning modeling of eye tracking and interaction data; 2) automatic inference of psychological constructs (emotional activation, emotional valence, and cognitive load) through physiological signals analysis; and 3) diagnosis of users' reactions during interaction based on the coupling of the two previous operations. The ideas and development of our approach are illustrated using two experimental contexts: e-commerce and simulation-based training. We also present the tool we implemented in order to allow HCI professionals (e.g.: user experience expert, training supervisor, or game designer) to use our evaluation approach to assess interaction. This tool is designed to facilitate the triangulation of measuring instruments and the integration with more classical Human-Computer Interaction methods (ex.: surveys and observation coding).
机译:关于人机交互(HCI)的越来越多的研究试图对交互进行详细的分析,以确定其对用户行为的影响。现在,无论是从用户体验评估还是从用户性能的角度,都特别着重于交互过程中的情绪反应。标准的定性方法是有限的,因为它们基于交互后的观察和访谈,因此限制了诊断的准确性。从本质上讲,用户体验和情感反应具有高度的动态性和相关性,评估方法应该相同,以准确地诊断交互的质量。本文提出了一种动态和定量的评估方法,该方法可以根据用户的情绪反应来进行情境评估,以帮助确定与系统交互期间的原因。为此,我们的工作集中在三个主要方面:1)使用机器学习的眼动追踪和交互数据建模技术自动进行任务识别; 2)通过生理信号分析自动推断心理构造(情绪激活,情绪价和认知负荷);和3)基于前两个操作的耦合来诊断用户在交互过程中的反应。我们使用两种实验环境说明了我们方法的思想和发展:电子商务和基于模拟的培训。我们还介绍了我们实施的工具,以允许HCI专业人员(例如:用户体验专家,培训主管或游戏设计师)使用我们的评估方法来评估互动。该工具旨在促进测量仪器的三角测量以及与更经典的人机交互方法(例如:调查和观察编码)的集成。

著录项

  • 作者

    Courtemanche, Francois.;

  • 作者单位

    Universite de Montreal (Canada).;

  • 授予单位 Universite de Montreal (Canada).;
  • 学科 Computer Science.
  • 学位 Ph.D.
  • 年度 2013
  • 页码 267 p.
  • 总页数 267
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类 肿瘤学;
  • 关键词

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号