REU Site: Computational Methods for Discovery Driven by Big Data

REU 网站：大数据驱动的发现计算方法

• 批准号: 1757916
• 负责人: George Karypis
• 金额: $ 36.04万
• 依托单位: University of Minnesota-Twin Cities
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-04-01 至 2022-03-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1757916&HistoricalAwards=false
• 关键词: REU; Site; Computational; Methods; Discovery

The objective of this project is to continue the University of Minnesota (UMN) Research Experiences for Undergraduates (REU) Site in which students engage in research that develops computational methods for scientific discovery across disciplines that are driven by big data. Closely mentored by Computer Science and Engineering (CS&E) faculty, each student will contribute to active research that addresses open questions in computational complexity, machine learning, parallel and distributed computing, mobile and cloud computing, or graphics and visualization. A UMN REU participant might use observation data to simulate crowd behavior, analyze genome sequence data to better understand microbial communities, develop tools to analyze chemical-genetic interaction networks, improve spatial perception in a virtual environment, develop visualization techniques to better understand massive data sets, enhance parallel distributed processing through algorithm development or by harnessing the computational power of a network of mobile devices, or use graph-based approaches to better understand climate change. The diverse research of CS&E faculty represents collaboration across the University with faculty in genetics, chemistry, climate science, neuroscience, architecture, medicine, and biomedical engineering to propel all of these disciplines and computer science towards previously unattainable insights and discoveries. In this 10-week summer program, in addition to immersion in research, students will receive technical training and professional development that encourages and prepares them for a sustained career in the sciences. This includes Big Data Colloquia, Communicating Science workshops, career mentoring, and public dissemination of research findings. Towards an objective of increased participation and broader impacts, this program will bring together nationally recruited students and those from UMN and local institutions to establish a cohort with diverse academic and cultural backgrounds. http://reubigdata.cs.umn.edu/The objectives of the University of Minnesota (UMN) REU Site program are to (i) intellectually engage and excite participants to motivate their commitment to and pursuit of a career in the sciences, specifically to foster academic persistence, (ii) increase participation in and contribution to the sciences by women and underrepresented minorities in computer science, (iii) train students for sustained contribution to the sciences, particularly in computational methods for big data transdisciplinary research, and (iv) professionally prepare and mentor participants for a career in the sciences, i.e., to teach participants to be effective communicators, be career savvy, and versed in the ethics of science. Towards these objectives, in a 10-week summer program students are immersed daily in research addressing open questions in computational methods for big data. Throughout the summer, each student is closely mentored by a faculty member and graduate student. Program activities help students quickly acclimatize to research and independent work, and most importantly, motivate and prepare students for academic persistence and a career in the sciences. Activities include research tutorials, a Big Data Colloquium series, a Communicating Science workshop series, career mentoring, and a poster presentation at a campus-wide research symposium. The program combines a non-resident and resident program to create a cohort of up to 25 students: 2 from local institutions, 8 from a national recruiting effort funded by this grant, and 15 students through other funding mechanisms. This combined program increases diversity, improves program and impact sustainability, and capitalizes on economic efficiencies.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.

该项目的目标是继续明尼苏达大学(UMN)本科生研究体验(REU)网站，在该网站上，学生从事研究，开发由大数据驱动的跨学科科学发现的计算方法。在计算机科学与工程(CS&amp；E)教师的密切指导下，每个学生都将为解决计算复杂性、机器学习、并行和分布式计算、移动和云计算或图形和可视化方面的公开问题的积极研究做出贡献。UMN REU参与者可能会使用观察数据来模拟人群行为，分析基因组序列数据以更好地了解微生物群落，开发工具来分析化学-遗传相互作用网络，改善虚拟环境中的空间感知，开发可视化技术以更好地理解海量数据集，通过算法开发或通过利用移动设备网络的计算能力来增强并行分布式处理，或者使用基于图形的方法来更好地了解气候变化。CS&Amp；E教职员工的多样化研究代表着整个大学与遗传学、化学、气候科学、神经科学、建筑学、医学和生物医学工程方面的教职员工的合作，以推动所有这些学科和计算机科学朝着以前无法实现的见解和发现迈进。在这个为期10周的暑期计划中，除了沉浸在研究中，学生还将接受技术培训和专业发展，以鼓励和准备他们在科学领域的持续职业生涯。这包括大数据研讨会、传播科学研讨会、职业指导和研究成果的公开传播。为了实现更多的参与和更广泛的影响，该计划将把国家招收的学生以及来自曼彻斯特大学和当地机构的学生聚集在一起，建立一个具有不同学术和文化背景的队列。明尼苏达大学REU Site计划的http://reubigdata.cs.umn.edu/The目标是(I)在智力上吸引和激励参与者，以激励他们对科学事业的承诺和追求，特别是培养学术坚持性，(Ii)增加计算机科学领域的女性和未被充分代表的少数群体对科学的参与和贡献，(Iii)培训学生对科学做出持续贡献，特别是在大数据跨学科研究的计算方法方面，以及(Iv)从专业上为参与者在科学领域的职业生涯做准备和指导，即教参与者成为有效的沟通者，成为精通职业的人，精通科学伦理。为了实现这些目标，在为期10周的暑期项目中，学生们每天都沉浸在研究中，解决大数据计算方法中的公开问题。整个暑假，每个学生都由一名教职员工和研究生密切指导。项目活动帮助学生迅速适应研究和独立工作，最重要的是，激励学生并为他们在科学领域的学术坚持和职业生涯做好准备。活动包括研究教程、大数据研讨会系列、传播科学研讨会系列、职业指导，以及在全校研究研讨会上的海报演示。该计划结合了非居民和居民计划，创建了一个最多25名学生的队列：2名来自当地机构，8名来自由该补助金资助的全国招生努力，15名学生通过其他资助机制。这一联合计划增加了多样性，改善了计划和影响的可持续性，并充分利用了经济效率。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

A Virtual Reality Investigation of the Impact of Wallpaper Pattern Scale on Qualitative Spaciousness Judgments and Action-Based Measures of Room Size Perception

虚拟现实研究壁纸图案比例对定性宽敞判断和基于行动的房间尺寸感知测量的影响

• DOI: 10.1007/978-3-030-01790-3_10
• 发表时间: 2018
• 期刊: International Conference on Virtual Reality and Augmented Reality
• 作者: Simpson, Governess;Sinnis-Bourozikas, Ariadne;Zhao, Megan;Aseeri, Sahar;Interrante, Victoria
• 通讯作者: Interrante, Victoria

Facilitating CPAP Adherence with Personalized Recommendations Using Artificial Neural Networks

使用人工神经网络通过个性化建议促进 CPAP 坚持

• DOI: 10.1109/cbms52027.2021.00093
• 发表时间: 2021
• 期刊: IEEE International Symposium on Computer-Based Medical Systems
• 作者: Araujo, Matheus;Pereira, Tara;Srivastava, Jaideep;Iber, Conrad
• 通讯作者: Iber, Conrad

Multi-Touch Querying on Data Physicalizations in Immersive AR

• DOI: 10.1145/3488542
• 发表时间: 2021-11
• 期刊: Proceedings of the ACM on Human-Computer Interaction
• 作者: Bridger Herman;Maxwell Omdal;Stephanie Zeller;Clara A. Richter;F. Samsel;G. Abram;Daniel F. Keefe

Design and Experiments with LoCO AUV: A Low Cost Open-Source Autonomous Underwater Vehicle

LoCO AUV 的设计和实验：低成本开源自主水下航行器

• DOI: 10.1109/iros45743.2020.9341007
• 发表时间: 2021
• 期刊: IEEE/RSJ International Conference on Intelligent Robots and Systems
• 作者: Edge, Chelsey;Sakib Enan, Sadman;Fulton, Michael;Hong, Jungseok;Mo, Jiawei;Barthelemy, Kimberly;Bashaw, Hunter;Kallevig, Berik;Knutson, Corey;Orpen, Kevin
• 通讯作者: Orpen, Kevin

SCARLET: Explainable Attention based Graph Neural Network for Fake News spreader prediction

• DOI: 10.1007/978-3-030-75762-5_56
• 发表时间: 2021-02
• 期刊: Journal of Personality and Social Psychology
• 影响因子: 7.6
• 作者: Bhavtosh Rath;X. Morales;J. Srivastava