On streaming disaster damage assessment in social sensing: A crowd-driven dynamic neural architecture searching approach
On streaming disaster damage assessment in social sensing: A crowd-driven dynamic neural architecture searching approach
复制标题
DOI：
10.1016/j.knosys.2021.107984
复制
发表时间：
2021-12
期刊：
影响因子：
--
通讯作者：
Yang Zhang;Ruohan Zong;Ziyi Kou;Lanyu Shang;Dong Wang
中科院分区：
文献类型：
--
作者：
Yang Zhang;Ruohan Zong;Ziyi Kou;Lanyu Shang;Dong Wang
受互联网和通信技术的最新进展以及在线社交媒体的激增的推动，社会感测已经成为一种新的感测范式，以从“人类传感器”获得对物理世界的及时观察。在这项研究中，我们专注于一个新兴的应用在社会传感流灾害损失评估（DDA），其目的是自动评估受灾地区的损害严重程度，在飞行中的灾害事件，利用流媒体上的灾害图像数据。特别地，我们研究了流DDA应用中的自适应最优神经结构搜索（NAS）问题。我们的目标是动态确定最佳神经网络架构，通过利用众包系统的人类智能，准确估计流中每个新到达图像的损坏严重程度。本研究的动机是观察到当前DDA解决方案中的神经网络架构主要由人工智能（AI）专家设计，鉴于流式DDA应用程序的动态性以及缺乏大量社交媒体数据输入的实时注释，这通常会导致不可忽略的成本和错误。在解决我们的问题时存在两个关键的技术挑战：（i）在不知道其地面真实先验标签的情况下动态识别每个图像的最佳神经网络架构是不平凡的;（ii）有效地利用不完美的群体智能来正确识别每个图像的最佳神经网络架构是具有挑战性的。为了应对上述挑战，我们开发了CD-NAS，这是一个动态的众包AI协作NAS框架，它仔细探索了众包系统中的人类智能，以解决动态优化NAS问题并优化流式DDA应用程序的性能。来自真实流式DDA应用的评估结果表明，CD-NAS始终优于最先进的AI和NAS基线，实现了最高的灾害损失评估准确性，同时保持了最低的计算成本。
Motivated by the recent advances in Internet and communication techniques and the proliferation of online social media, social sensing has emerged as a new sensing paradigm to obtain timely observations of the physical world from “human sensors”. In this study, we focus on an emerging application in social sensing –streaming disaster damage assessment (DDA), which aims to automatically assess the damage severity of affected areas in a disaster event on the fly by leveraging the streaming imagery data about the disaster on social media. In particular, we study adynamic optimal neural architecture searching (NAS)problem in streaming DDA applications. Our goal is to dynamically determine the optimal neural network architecture that accurately estimates the damage severity for each newly arrived image in the stream by leveraging human intelligence from the crowdsourcing systems. The present study is motivated by the observation that the neural network architectures in current DDA solutions are mainly designed by artificial intelligence (AI) experts, which often leads to non-negligible costs and errors given the dynamic nature of the streaming DDA applications and the lack of real-time annotations of the massive social media data inputs. Two critical technical challenges exist in solving our problem: (i) it is non-trivial to dynamically identify the optimal neural network architecture for each image on the fly without knowing its ground-truth labela priori; (ii) it is challenging to effectively leverage the imperfect crowd intelligence to correctly identify the optimal neural network architecture for each image. To address the above challenges, we developed CD-NAS, a dynamic crowd-AI collaborative NAS framework that carefully explores the human intelligence from crowdsourcing systems to solve the dynamic optimal NAS problem and optimize the performance of streaming DDA applications. The evaluation results from a real-world streaming DDA application show that CD-NAS consistently outperforms the state-of-the-art AI and NAS baselines by achieving the highest disaster damage assessment accuracy while maintaining the lowest computational cost.