Enhancing Undergraduate Learning About Biomechanics and Data Science Through Augmented Reality and Self-motion Data

通过增强现实和自运动数据加强本科生对生物力学和数据科学的学习

• 批准号: 2013451
• 负责人: Xu Xu
• 金额: $ 60万
• 依托单位: North Carolina State University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-09-01 至 2024-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2013451&HistoricalAwards=false
• 关键词: Enhancing; Undergraduate; Learning; About; Biomechanics

This project aims to combine learning about biomechanics with learning about data science. Biomechanics is the study of the structure and movement of living things. Biomechanics uses data about motion and the science of mechanics to answer questions such as how birds fly and how people walk. This knowledge can then be used for many purposes, such as designing artificial joints and helping workers avoid injuries. Data science applies methods such as artificial intelligence and algorithms to analyze data from any source, including data about human motion. These analyses can lead to new insights and new discoveries about the source of the data. This project will enable biomechanics students to become the source of the movement data that they will analyze using data science methods. Students will use computer vision and machine learning to create datasets from their own movements. They will then use these personally relevant datasets to learn both biomechanics and data science, and to gain a comprehensive understanding of human motion. To support the data collection and analysis, the project will develop a platform for augmented learning and associated curriculum modules for both in-class and out-of-class learning.This project will develop and implement an augmented learning platform that will enable undergraduate students in different STEM paths to "be the dataset" and interactively acquire formal concepts and feedback in biomechanics and data science. The project has the potential to advance learning sciences and education technology by expanding the understanding of students' interactions with self-generated motion data, as well as the effectiveness of the specific instructional technologies and strategies. The project includes an educational research project that will employ a two-phase design-based approach. Questionnaires will be used to collect data about student demographics, and semi-structured interviews will be used to learn more about student experiences with analyzing self-motion data and using augmented reality technologies, as well as their interests and self-efficacy in biomechanics or data science. Descriptive statistics will be used to acquire an overall understanding of the student sample. Repeated measures ANOVA and ANCOVA will be used to analyze changes in student interests and self-efficacy over time. This project is supported by the NSF Improving Undergraduate STEM Education Program: Education and Human Resources. The IUSE: EHR program supports research and development projects to improve the effectiveness of STEM education for all students. This project is in the Engaged Student Learning track, through which the program supports the creation, exploration, and implementation of promising practices and tools.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.

该项目旨在将联合收割机学习生物力学与学习数据科学相结合。 生物力学是研究生物的结构和运动的学科。 生物力学使用有关运动和力学科学的数据来回答诸如鸟类如何飞行和人类如何行走等问题。 这些知识可以用于许多目的，例如设计人工关节和帮助工人避免受伤。 数据科学应用人工智能和算法等方法来分析来自任何来源的数据，包括有关人体运动的数据。 这些分析可以带来关于数据来源的新见解和新发现。 该项目将使生物力学学生成为他们将使用数据科学方法分析的运动数据的来源。学生将使用计算机视觉和机器学习来创建自己的运动数据集。然后，他们将使用这些与个人相关的数据集来学习生物力学和数据科学，并全面了解人体运动。为了支持数据收集和分析，该项目将开发一个增强学习平台和相关的课程模块，用于课堂和课外学习。该项目将开发和实施一个增强学习平台，使不同STEM路径的本科生能够“成为数据集”，并以交互方式获得生物力学和数据科学的正式概念和反馈。该项目有可能通过扩大对学生与自我生成的运动数据的交互的理解，以及特定教学技术和策略的有效性，来推进学习科学和教育技术。该项目包括一个教育研究项目，将采用两个阶段的设计为基础的方法。问卷将用于收集有关学生人口统计数据，半结构化访谈将用于更多地了解学生在分析自我运动数据和使用增强现实技术方面的经验，以及他们在生物力学或数据科学方面的兴趣和自我效能。描述性统计将被用来获得学生样本的整体理解。重复测量方差分析和协方差分析将被用来分析学生的兴趣和自我效能随着时间的推移变化。 该项目由NSF改善本科STEM教育计划：教育和人力资源支持。IUSE：EHR计划支持研究和开发项目，以提高所有学生STEM教育的有效性。该项目是在学生学习的轨道，通过该计划支持的创建，探索和实施有前途的做法和工具。这个奖项反映了NSF的法定使命，并已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。

项目成果

PaCa-ViT: Learning Patch-to-Cluster Attention in Vision Transformers

• DOI: 10.1109/cvpr52729.2023.01781
• 发表时间: 2022-03
• 期刊: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
• 作者: Ryan Grainger;Thomas Paniagua;Xi Song;Naresh P. Cuntoor;Mun Wai Lee;Tianfu Wu

Attentive Normalization

• DOI: 10.1007/978-3-030-58520-4_5
• 发表时间: 2019-08
• 作者: Xilai Li;Wei Sun-;Tianfu Wu

NOPE-SAC: Neural One-Plane RANSAC for Sparse-View Planar 3D Reconstruction

• DOI: 10.1109/tpami.2023.3314745
• 发表时间: 2022-11
• 期刊: IEEE Transactions on Pattern Analysis and Machine Intelligence
• 影响因子: 23.6
• 作者: Bin Tan;Nan Xue;Tianfu Wu;Guisong Xia

Learning Local-Global Contextual Adaptation for Multi-Person Pose Estimation

• DOI: 10.1109/cvpr52688.2022.01272
• 发表时间: 2021-09
• 期刊: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
• 作者: Nan Xue;Tianfu Wu;Gui-Song Xia;L. Zhang

CGBA: Curvature-aware Geometric Black-box Attack

• DOI: 10.1109/iccv51070.2023.00018
• 发表时间: 2023-08
• 期刊: 2023 IEEE/CVF International Conference on Computer Vision (ICCV)
• 作者: Md. Farhamdur Reza;A. Rahmati;Tianfu Wu;H. Dai