CIF: Small: Collaborative Research: Distributed Detection Algorithms and Stochastic Modeling for Large Monitoring Sensor Networks

建筑环境的运营和安全目标要求对基础设施系统进行强大、可扩展和可靠的大规模监控。高性能的实时事件检测和决策需要模型和算法来处理来自密集传感器网络的大量数据。尽管在这类网络的检测算法的发展方面取得了进展，但存在两个被广泛认可且相互冲突的障碍：检测规则需要足够复杂以适应环境中的时空变化，需要共享数据;但是规则受到网络所强加的统计性能保证、计算和通信预算的约束。这个项目通过开发一个全新的该研究开发了一个框架，该框架将底层网络基础设施的分布式计算和通信约束与灵活的随机建模和时空数据学习算法相结合。建模和算法使同时和顺序决策在许多地方的网站，通过借用信息在网络中的统计一致性和计算效率的方式。该项目结合顺序变化点检测、非参数和概率图模型以及时空统计的形式化方法，开发了分布式和顺序消息传递算法，用于检测生成网络数据的底层分布的变化。所开发的模型还提供了对统计模型复杂性、分布式计算效率、这种跨学科的研究汇集了来自不同领域的学生和研究人员，利用和发展计算机科学，统计学，信号处理和土木工程领域的知识和跨学科技能。

Operational and safety goals for the built environment demand robust, scalable and reliable largescale monitoring for infrastructure systems. High performance real-time event detection and decision makingrequires models and algorithms to process large amounts of data from dense sensor networks deployedin these systems. Despite advances in the development of detection algorithms for such networks, there aretwo widely recognized and conflicting obstacles: detection rules need to be sufficiently complex to adapt tothe spatiotemporal changes in the environment, requiring the sharing of data; but rules are constrained bystatistical performance guarantees and computation and communicational budgets imposed by the network.This project addresses these challenges by developing a fundamentally new approach that jointly accountsfor statistical detection, communication constraints and distributed computation.This research develops a framework that integrates the distributed computation and communication constraintsof the underlying network infrastructure with flexible stochastic modeling and learning algorithmswith spatiotemporal data. The modeling and algorithms enable simultaneous and sequential decision makingat many local sites, by borrowing information across the network in a statistically coherent and computationallyefficient manner. Combining the formalism of sequential change point detection, nonparametric andprobabilistic graphical models and spatiotemporal statistics, the project develops distributed and sequentialmessage-passing algorithms for detecting changes in the underlying distributions generating network data.The models developed also offer new theoretical understanding of the trade-offs between statistical modelcomplexity, distributed computation efficiency, and structure of communication constraints within the network.This interdisciplinary research brings together students and researchers from different areas, utilizingand developing knowledge and cross-disciplinary skills in the fields of computer science, statistics, signalprocessing and civil engineering.