REU Site: TaMaLe - Testing and Machine Learning for Context-Driven Systems: Research Experience for Undergraduates

REU 网站：TaMaLe - 上下文驱动系统的测试和机器学习：本科生的研究经验

• 批准号: 2149969
• 负责人: Renee Bryce
• 金额: $ 40.5万
• 依托单位: University of North Texas
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-03-01 至 2025-02-28
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2149969&HistoricalAwards=false
• 关键词: REU; Site; TaMaLe; Testing; Machine

TaMaLe (Testing and Machine Learning for Context-Driven Systems), a renewal Research Experience for Undergraduates (REU) Site at University of North Texas, engages 10 undergraduate students for 10 weeks with problems in the context-driven system domain. The students explore research problems to improve the reliability and security of context-driven systems. Context-driven systems, such as mobile apps, face constant streams of input from both users and context changes in their environments. Users interact with apps through touch and speech interfaces. These systems also respond to context events that occur in their environments such as changes to network connection, battery level, screen orientation, and more. The combined explosion of possible user events and context event sequences pose new challenges that require cost effective testing solutions. Students and mentors in this REU program work in small teams to develop and empirically evaluate new software testing techniques for context-driven systems using strategies such as reinforcement learning and combinatorial-based techniques. The project's broader significance and importance are that it trains three diverse cohorts heavily recruited from underrepresented groups. Students gain basic research skills to better prepare them for graduate school, including working with researchers and gaining the ability to formulate research questions, design experiments, critically analyze results, and develop written and oral communication skills.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.

TaMaLe（上下文驱动系统的测试和机器学习）是北德克萨斯大学本科生（REU）网站的一个更新研究经验，吸引了10名本科生10周的时间来解决上下文驱动系统领域的问题。学生探索研究问题，以提高上下文驱动系统的可靠性和安全性。上下文驱动的系统，如移动的应用程序，面临着来自用户的持续输入流及其环境中的上下文变化。用户通过触摸和语音界面与应用程序进行交互。这些系统还响应其环境中发生的上下文事件，例如网络连接、电池电量、屏幕方向等的更改。可能的用户事件和上下文事件序列的组合爆炸提出了新的挑战，需要成本有效的测试解决方案。 在这个REU计划的学生和导师在小团队工作，开发和经验评估新的软件测试技术的上下文驱动系统使用的策略，如强化学习和组合为基础的技术。 该项目更广泛的意义和重要性在于，它培训了从代表性不足的群体中大量招募的三个不同群体。学生获得基本的研究技能，以更好地为他们的研究生院做准备，包括与研究人员合作，并获得制定研究问题，设计实验，批判性分析结果，以及发展书面和口头沟通技能的能力。该奖项反映了NSF的法定使命，并被认为是值得通过使用基金会的智力价值和更广泛的影响审查标准进行评估的支持。