CRII: HCC: Sustaining Cognitive Flow in Physical Making

进入“状态”，无论是沉浸式的电子游戏、运动还是织毛衣，都是大脑的自然反应，可以让人们完全集中精力，处理困难、乏味和经常重复的任务。这种反应被称为进入心流的认知状态，在手工艺和制作社区中有许多已知的好处，包括减少失败的影响，扭曲的时间感，以及通常与“制作的乐趣”相关的自我意识的消失。该项目通过开发一种可穿戴传感器技术检测流状态的方法，促进了科学的进步。通过更好地理解任务、环境和个人特征是如何影响心流的，本项目将为设计和评估创造性技术提供原则，以支持新手制造者发展积极的应对机制。该团队还将创建工具和教程，允许研究人员和设计师在制作和相关领域采用这些方法。对于交互设计来说，“心流”是一个被充分研究过的有价值的概念，但研究人员和设计师都局限于将“心流”作为一种定性评估的形式。通过将流动视为一个活动识别问题，该项目将研究如何使用现成的生理和活动传感来不显眼地识别每时每刻的流动。通过用户完成等效流密集型任务的文档，这项工作将开发(1)第一个开放访问的此类流活动数据集，(2)流的基准深度学习模型，以及(3)提供实时流表征的开源定性分析工具。这项研究将产生知识来加强和扩展我们对身体对心流状态的反应的理解；与此同时，案例研究将产生设计范例，以操作如何使用流作为设计变量来诱导或维持创造性技术中的流状态。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

Getting "in the zone," whether it be from an immersive video game, playing a sport, or knitting a sweater, is a natural response of the mind that allows people to fully concentrate and cope with difficult, tedious, and often repetitive tasks. This response, known as entering a cognitive state of flow, has many known benefits within craft and making communities, including a lessened impact of failure, a distorted sense of time, and a disappearance of self-consciousness that are often associated with the "joy of making." This project promotes the progress of science by developing a method of detecting flow states from wearable sensor technologies. By better understanding how tasks, environments, and individual characteristics influence flow, this project will provide principles for designing and evaluating creative technologies that support novice makers in developing positive coping mechanisms. The team will also create tools and tutorials that will allow the methods to be taken up by researchers and designers in making and related domains.Flow is a well-studied and valuable concept to interaction design, yet researchers and designers are limited to using flow as a form of qualitative assessment. By treating flow as an activity recognition problem, this project will investigate how off-the-shelf physiological and activity sensing can be used to unobtrusively recognize flow on a moment-by-moment scale. Through documentation of users completing equivalent flow-intensive tasks, this work will develop (1) the first open-access flow activity dataset of its kind, (2) a benchmark deep learning model of flow, and (3) an open-source qualitative analysis tool that provides real-time flow characterization. This research will produce knowledge to reinforce and extend our understanding of the body's response to flow states; in conjunction, case studies will produce design exemplars to operationalize how flow can be used as a design variable to induce or sustain flow states within creative technologies.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.