IUCRC Phase II UMBC: Center for Accelerated Real time Analytics (CARTA)

加速和实时数据分析是智能数据革命的前沿，一方面是互联网连接的传感器硬件的进步，另一方面是加速的AI/ML分析。这些技术包括机器学习、认知、量子、神经形态和边缘计算，结合了新的传感和可编程硬件组件、主动存储、高级FPGA处理器、内存云系统和嵌入式传感器。在IUCRC/CARTA第二阶段，我们开发了新的加速和实时方法，以解决与我们的合作伙伴相关的这些先进技术及其集成。我们利用AI/ML和可编程网络系统的前沿研究来开展CARTA合作研究。我们的研究领域包括加速医学图像分析，用于医学和视觉/语言模型的可解释和可解释的AI/ML，用于真实的时间动态系统的数字双胞胎，以及用于改善理解的物理信息AI/ML建模。我们的研究将主要是“应用中立”，即，这些技术可以在多个学科中进行修改，包括网络安全，医疗保健和医疗，动态系统，环境和商业智能。我们的探索将包括深度学习，半/无监督学习，联邦学习，架构，实时模拟，数据合规性和区块链。在这种情况下，CARTA/UMBC网站将专注于开发下一代自学系统，该系统将利用高性能计算（HPC）平台来促进实时关键决策。我们的项目将通过提供更大的高技能多样化劳动力资源库而使企业受益。我们通过在适当的期刊和会议上发表文章，与业界广泛传播我们合作研究的结果;与其他想要复制这种方法的非CARTA机构分享我们的研究成果。我们利用UMBC的专业项目，例如我们国家认可的多元化Meyerhoff和技术女性中心（CWIT）学者项目，扩大学生的参与，特别是来自代表性不足的群体。该奖项反映了NSF的法定使命，并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，被认为值得支持。

Accelerated and real-time data analytics is a leading edge of the smart data revolution, pushed by advances in internet-connected sensor hardware on one side and accelerated AI/ML analytics on the other. These technologies include machine learning, cognitive, quantum, neuromorphic, and edge computing combined with new classes of sensory and programmable hardware components, active storage, advanced FPGA processors, in-memory cloud systems, and embedded sensors. They address many pursuits of national defense and cybersecurity, weather and climate prediction, health/disease monitoring, Industrial IoT, etc. In IUCRC/CARTA Phase II, we develop new accelerated and real-time approaches to address these advanced technologies and their integration relevant to our partners.We leverage cutting-edge research in AI/ML and programmable cyber-systems to conduct collaborative CARTA research. Our research areas include accelerated medical image analytics, explainable and interpretable AI/ML for medical and vision/language models, digital twins for real time dynamical systems, and physics-informed AI/ML modeling for improved understanding. Our research will be primarily “application neutral,” i.e., techniques that can be applied with modifications across multiple disciplines, including cyber security, healthcare and medical, dynamic systems, environment, and business intelligence. Our exploration will include deep learning, semi/unsupervised learning, federated learning, architectures, real-time simulations, data compliance, and Blockchains. In this context, the CARTA/UMBC site will focus on developing next generation self-learning systems that will leverage High Performance Computing (HPC) platforms to facilitate real-time critical decision-making.Our projects will benefit businesses by providing a larger pool of a highly skilled diverse workforce. We disseminate results from our collaborative research widely with industry by publishing in appropriate journals and conferences; share our research outputs with other non-CARTA institutions that want to duplicate this approach. We leverage specialized programs at UMBC, such as our nationally recognized diverse Meyerhoff and Center for Women in Technology (CWIT) scholars programs, to broaden student participation, especially from underrepresented groups.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.