Elements: Cyberinfrastructure Service for IoT-Based Construction Research and Applications

从5G到物联网，无线基础设施正在稳步发展为所有人和大多数设备的无线接入。这种广泛的访问产生了从个人网络到骨干网络的自定义和自适应服务的期望。此外，跨网络、应用程序和服务存在规模和互操作性方面的挑战，这两者都需要有效的无线网络管理基础设施。与此同时，越来越迫切需要利用当前的技术进步来解决围绕建筑和建筑环境的最紧迫问题，以增加健康和安全；生产力;和可持续性。该项目结合了计算机科学、电气工程、建筑和建筑等领域，为建筑研究开发了一个强大的网络基础设施（CI）服务，以及利用最先进的新兴技术和软件来解决建筑行业当前面临的挑战的应用程序。该项目的主要贡献是开发物联网应用建设研究和教育服务（iot - acre）系统，这是一个可互操作的中央框架枢纽，可以整合各种异构传感器、技术和软件，由软件定义的网络基础设施管理，并通过机器学习和人工智能技术进行优化。该原型系统将有助于增强工程和/或安全管理人员检测危险的能力，从而提高施工中的安全性能，这是建筑行业面临的最大挑战之一。此外，该框架还可用于在需要同时跟踪多个实体（人、车辆、设备等）、检测多个感兴趣对象、分析实时生物特征数据和做出自主决策的应用程序中增加自主性。研究结果将通过出版物、研讨会演讲、培训课程和在线专业认证项目传播给工业界和研究界。该项目还将被用作研究、教育和培训工具，以(1)指导和教授K-12学生有关STEM的知识，以及(2)开发和加强课程，向当前和下一代学生、用户和工人传授最新技术和最新网络安全技术方法。该项目开发了一个强大的网络基础设施（CI）系统和服务，用于建筑研究和应用，以解决当前建筑行业面临的挑战。本提案旨在提供的成果和服务是：1)一个分布式sdn管理和人工智能辅助的基于物联网的系统，该系统可以根据研究和应用的需求进行调整和扩展；2)识别应对建筑行业挑战所需的数据和数据安全要求，以及可以提供这些数据的潜在技术；3)评估在动态建筑环境中部署的基于物联网组件的可靠实时多传感器融合技术的坚固性、可用性和局限性；4)基于物联网系统框架的鲁棒安全实时监控原型系统；5)推荐系统的潜在配置，采用适当的技术和传感器，以满足应用的需要。由此产生的经验数据将通过年度NSF进展和发现报告、学术价值和科学发现的期刊出版物以及讨论更广泛影响和未来研究目标的会议记录提供。还将出版硬件和软件的框架，包括一份指导手册。该软件将通过项目网站、开放源代码帖子以及会议和讲习班的传播请求提供。该项目将探索各种交付机制的使用，例如NSF的极限科学与工程发现环境（XSEDE）。IoT- acres将利用IBM物联网持续工程和云计算服务器云（例如亚马逊AWS）进行数据分析和性能指标。这一新颖的融合研究项目将最终推动可持续CI社区的发展和可持续CI服务的管理，从而提高生产力并加速科学和工程领域的创新。这项工作将通过开发一种用于建筑工地安全监测的工具来推进安全控制实践，该工具将通过可视化和实时报告安全隐患的界面呈现给安全管理人员。值得注意的是，它将解决计算机视觉和施工管理方面的基础研究挑战：改进基于上下文的物体识别和跟踪；并将整合视觉、文本和生物特征数据的规则正规化，以主动识别安全隐患。该奖项反映了美国国家科学基金会的法定使命，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。

Wireless infrastructure is steadily evolving into wireless access for all humans and most devices, from 5G to Internet-of-Things. This widespread access creates the expectation of custom and adaptive services from the personal network to the backbone network. In addition, challenges of scale and interoperability exist across networks, applications and services, both requiring an effective wireless network management infrastructure. At the same time, there has been a rising imperative to capitalize on the current technological advancements to address to the most pressing issues surrounding construction and the built environment to increase health and safety; productivity; and sustainability. This Elements project combines the areas of computer science, electrical engineering, and construction and building to develop a robust cyberinfrastructure (CI) service for construction research, as well as applications that utilize state-of-the-art emerging technologies and software to address the current challenges faced by the construction industry. The major contribution of the project is the development of the IoT-ACRES (IoT-Applied Construction Research and Education Services) system, a central, interoperable framework hub that can incorporate a variety of heterogeneous sensors, technology, software, managed by a software-defined network infrastructure and optimized by machine learning and artificial intelligence techniques. The prototype system will help to augment the works and/or safety manager's ability to detect hazards and subsequently improve safety performance in construction, which is one of the greatest challenges faced by the construction industry. In addition, the framework can be used to increase autonomy in applications that require simultaneous tracking of multiple entities (people, vehicles, equipment, etc.), detecting multiple objects of interests, analyzing real-time biometric data, and making autonomous decisions. Results will be disseminated to industry and research communities through publications and presentations at workshops, training courses and online professional certification programs. The project will also be used as a research, education, and training tool to (1) mentor and teach K-12 students about STEM, and (2) to develop and enhance courses to educate the current and next generations of students, users, and workers, on the latest technology and the latest approaches to cyber security techniques. This project develops a robust cyberinfrastructure (CI) system and service for construction research and applications to address the current challenges faced in the construction industry. The outcomes and services that this proposal aims to provide are 1) a distributed SDN-managed and AI-assisted IoT-based system that can be adapted and extended based on needs of the research and application; 2) identification of the data and data security requirements needed to address the challenges in the construction industry and potential technologies that can provide those data; 3) evaluation of reliable real-time multi-sensor fusion techniques for ruggedness, usability, and limitations of IoT-based components deployed in the dynamic construction environments; 4) robust prototype system for real-time safety monitoring based on the IoT system framework; and 5) recommendations of potential configurations of the system with the appropriate technology and sensors to meet the needs of the application. The empirical data resulting will be delivered through yearly NSF reports on the progress and findings, journal publications of the intellectual merit and scientific findings, and conference proceedings discussing the broader impacts and future research objectives. The framework of the hardware and software, including an instructional manual will also be published. The software will be made available through request via a project website, open source posts, and conference and workshop dissemination. The project will explore the use of various delivery mechanisms, such as NSF's eXtreme Science and Engineering Discovery Environment (XSEDE). The IoT-ACRES will utilize IBM IoT Continuous Engineering and Cloud Computing Servers Cloud (e.g. Amazon AWS) for the data analysis and performance metrics. This novel convergence research project will ultimately advance the development of sustainable CI communities and stewardships of sustainable CI services that can enhance productivity and accelerate innovation in science and engineering. This work will advance practices of safety controls by developing a tool for safety monitoring on construction sites, presented to safety managers with interfaces that visualize, and report real-time safety hazards. Significantly, it will address fundamental research challenges in computer vision and construction management: improving context-based object recognition and tracking; and formalizing rules for integrating visual, textual, biometric data to proactively recognize safety hazards.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.