Convergence Accelerator Phase I(RAISE): Smart Platform of Personalized Learning, Assessment and Prediction for Future Career Training of Skilled Workers

融合加速器第一期（RAISE）：技能工人未来职业培训个性化学习、评估和预测的智能平台

• 批准号: 1937010
• 负责人: Aidong Lu
• 金额: $ 99.99万
• 依托单位: University of North Carolina at Charlotte
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-09-01 至 2022-05-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1937010&HistoricalAwards=false
• 关键词: Convergence; Accelerator; Phase; RAISE; Smart

The NSF Convergence Accelerator supports team-based, multidisciplinary efforts that address challenges of national importance and show potential for deliverables in the near future. The broader impact/potential benefit of this Convergence Accelerator Phase I project is to address the critical needs for developing and sustaining skilled technical workforce, which are a key component of the U.S. economy. This project proposes to develop a smart training platform through digitalizing the training processes and embedding advanced techniques of big data, (Artificial Intelligence) AI, smart sensing, mixed reality, kinesiology and fire engineering. The results could accelerate the changes of traditional training programs to new types of training and certification related to the latest technology advances. Specifically, this project will benefit firefighters with a new training platform that reduces injuries, shortens training process, and prepares more people as future firefighters with virtual training programs. This will save lives and reduce costs of both property damage and human casualty in fires. With the developed platform that will be made publicly available, firefighters will learn STEM skills and achieve an easy transition into new positions that require similar skills in later in their careers. The platform could be extended to a variety of skilled worker occupations such as health care and smart manufacturing. This project will also strengthen college and online programs of fire safety and train minority students at two participating universities.This Convergence Accelerator Phase I project proposes to innovate the training of skilled workers through a smart, personalized and augmented training platform that coordinates training across organizations. The platform will integrate data-centric techniques to serve multiple purposes of various participants and provide a comprehensive suite of training functions. Specifically, this project will investigate several research tasks: intelligent wireless sensing system for simultaneous user tracking, action recognition, and user identification; smart and adaptive sensing for comprehensive evaluation of user actions and impacts on environments; new data-driven methods for injury assessment and prediction; deep learning based recommendation models for personalized training activity and future jobs; and collaborative augmenting methods for creating various training environments and immersive analytics for analyzing large-scale data provenance. These methods form a holistic environment for adaptive training of the future workforce. As a special case, the investigators will evaluate and demonstrate the application of the developed system on training of firefighters through close collaborations among university fire engineering programs, fire departments and a training academy, and a nationwide firefighter association.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.

NSF融合加速器支持以团队为基础的多学科努力，以应对国家重要性的挑战，并在不久的将来展示可交付成果的潜力。 这个融合加速器第一阶段项目的更广泛的影响/潜在利益是解决发展和维持熟练技术劳动力的关键需求，这是美国经济的关键组成部分。该项目建议通过数字化培训过程并嵌入大数据，（人工智能）AI，智能传感，混合现实，人体工学和消防工程的先进技术来开发智能培训平台。研究结果可以加速传统培训计划向与最新技术进步相关的新型培训和认证的转变。具体来说，该项目将通过一个新的培训平台使消防员受益，该平台可以减少受伤，缩短培训过程，并通过虚拟培训计划为更多的未来消防员做好准备。这将拯救生命，减少火灾中财产损失和人员伤亡的成本。通过将公开提供的开发平台，消防员将学习STEM技能，并在职业生涯后期轻松过渡到需要类似技能的新职位。该平台可以扩展到各种技术工人职业，如医疗保健和智能制造。该项目还将加强大学和在线消防安全项目，并在两所参与大学培训少数民族学生。该融合加速器第一阶段项目提出通过智能，个性化和增强的培训平台来创新技术工人的培训，协调跨组织的培训。该平台将整合以数据为中心的技术，为各种参与者的多种目的服务，并提供一套全面的培训功能。具体而言，该项目将研究几个研究任务：用于同时跟踪用户，动作识别和用户识别的智能无线传感系统;用于全面评估用户动作和对环境影响的智能和自适应传感;用于伤害评估和预测的新数据驱动方法;基于深度学习的个性化培训活动和未来工作的推荐模型;以及用于创建各种培训环境的协作增强方法和用于分析大规模数据来源的沉浸式分析。这些方法形成了一个整体环境，为未来的劳动力进行适应性培训。作为一个特殊的案例，调查人员将通过大学消防工程项目、消防部门和培训学院以及全国消防员协会之间的密切合作，评估和展示开发的消防员培训系统的应用。该奖项反映了NSF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。

项目成果

Privacy-Preserving Participant Grouping for Mobile Social Sensing Over Edge Clouds

边缘云上移动社交感知的隐私保护参与者分组

• DOI: 10.1109/tnse.2020.3020159
• 发表时间: 2021
• 期刊: IEEE Transactions on Network Science and Engineering
• 影响因子: 6.6
• 作者: Li, Ting;Qiu, Zhijin;Cao, Lijuan;Cheng, Dazhao;Wang, Weichao;Shi, Xinghua;Wang, Yu
• 通讯作者: Wang, Yu

Exploring the SenseMaking Process through Interactions and fNIRS in Immersive Visualization

• DOI: 10.1109/tvcg.2021.3067693
• 发表时间: 2021-05-01
• 期刊: IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
• 影响因子: 5.2
• 作者: Galati, Alexia;Schoppa, Riley;Lu, Aidong
• 通讯作者: Lu, Aidong

Fairness-aware Bandit-based Recommendation

基于公平意识的强盗推荐

• DOI: 10.1109/bigdata52589.2021.9671959
• 发表时间: 2021
• 期刊: 2021 IEEE International Conference on Big Data (Big Data
• 作者: Huang, Wen;Labille, Kevin;Wu, Xintao;Lee, Dongwon;Heffernan, Neil
• 通讯作者: Heffernan, Neil

Deep CSI Learning for Gait Recognition At-Scale

用于大规模步态识别的深度 CSI 学习

• 发表时间: 2019
• 期刊: Proc. of BalkanCom'19
• 作者: K. Jakkala, A. Bhuyan

Towards AI-Assisted Smart Training Platform for Future Manufacturing Workforce

面向未来制造业劳动力的人工智能辅助智能培训平台

• 发表时间: 2020
• 期刊: AI in Manufacturing
• 作者: Wang, Weichao;Wu, Xintao;Wang, Pu;Maybury, Mark;Lu, Aidong
• 通讯作者: Lu, Aidong