Big Data education for the masses: MOOCs, modules, & intelligent tutoring systems

面向大众的大数据教育：MOOC、模块、

• 批准号: 8829370
• 负责人: BRIAN Scott CAFFO
• 金额: $ 21.6万
• 依托单位: JOHNS HOPKINS UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2014
• 资助国家: 美国
• 起止时间: 2014-09-29 至 2017-05-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/8829370
• 关键词: Adopted; Amaze; Area; Attention; Automobile Driving; Big Data; Biological; Biology; Brain; Clinical Trials; Communities; Complex; Computer software; Cost Analysis; Data; Data Analyses; Data Collection; Data Set; Databases; Development; Dimensions; Discipline; Drops; Education; Educational Curriculum; Educational Models; Educational process of instructing; Electronic Health Record; Enrollment; Environment; Generations; Genes; Genome; Genomics; Grant; Head; Human; Image; Knowledge; Laboratories; Learning; Learning Module; Machine Learning; Measurement; Measures; Medical; Medicine; Modeling; Molecular Biology; Molecular Medicine; Multivariate Analysis; Persons; Population; Principal Investigator; Proteome; Public Health; Public Health Nurses; Public Health Nursing; Race; Research; Research Personnel; Resolution; Science; Scientist; Series; Services; Solutions; Stream; Students; System; Systems Biology; Techniques; Technology; Testing; Time; TimeLine; Touch sensation; Training; Training Programs; Universities; Work; abstracting; cost; density; flexibility; instructor; lectures; meetings; multidisciplinary; neuroimaging; new technology; novel strategies; open source; operation; process repeatability; programs; public health relevance; research study; skills; statistics; teacher

DESCRIPTION (provided by applicant): Abstract Biomedical science, higher education, software and technology are simultaneously undergoing tectonic shifts. The amazing pace of software and technological development are driving equally amazing advances in the ability to acquire massive data sets in the biomedical sciences. These new Big Biomedical data sets come in the form of complex measurements, such as that of the brain, genome, proteome and human biome or massive databases, such as with electronic health records. Big Data issues, such as reproducibility of processing, measurement and analysis techniques, are increasingly complex, and crucial. Across all domains there is a knowledge gap of researchers to analyze and interpret these new data sets and the current higher education model cannot meet the insatiable demand for this training. We propose to make substantial progress on these issues in two domains. Specifically, we propose to use Massive Open Online Courses (MOOCs) to create two series, one in neuroimaging and one in genomics. These series will allow for flexible, student paced, low cost scalable training for tens of thousands of students. Along with these series, we propose the creation of modular Big Data biostatistical content that can be used by students as well as teachers. This effort will be parallel to work on an intelligent tutoring syste called swirl. This application proposes to use swirl to create rich, gamified learning environments for students. All of the material created from this grant will be open access and free.

摘要生物医学、高等教育、软件和技术正同时发生着结构性的变化。软件和技术发展的惊人步伐同样推动了生物医学科学中获取大量数据集的能力的惊人进步。这些新的大型生物医学数据集以复杂测量的形式出现，如大脑、基因组、蛋白质组和人类生物组的测量，或大型数据库，如电子健康记录。大数据问题，如处理、测量和分析技术的可重复性，正变得越来越复杂和关键。在所有领域，研究人员在分析和解释这些新数据集方面都存在知识缺口，目前的高等教育模式无法满足对这种培训的永不满足的需求。我们建议在两个领域就这些问题取得实质性进展。具体来说，我们建议使用大规模在线开放课程（MOOCs）创建两个系列，一个是神经影像学，一个是基因组学。这些系列将允许灵活的，学生节奏，低成本可扩展的培训数以万计的学生。与这些系列一起，我们建议创建模块化的大数据生物统计学内容，可供学生和教师使用。这项工作将与一个名为swirl的智能辅导系统的工作并行。该应用程序建议使用swirl为学生创建丰富的游戏化学习环境。所有由这项授权创建的材料都将是开放获取和免费的。