Adaptive and Cost-Effective Collection of High-Quality Data for Critical Infrastructure and Emergency Management in Smart Cities—Framework and Challenges
Adaptive and Cost-Effective Collection of High-Quality Data for Critical Infrastructure and Emergency Management in Smart Cities—Framework and Challenges
复制标题
智慧城市关键基础设施和应急管理的高质量数据的适应性和成本效益收集——框架和挑战
DOI：
10.1145/3190579
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Jahanshahi, Mohammad R.
中科院分区：
文献类型：
--
作者：
Bertino, Elisa;Jahanshahi, Mohammad R.
在未来的智慧城市中，关键基础设施和应急管理的许多决策过程将基于机器学习技术。一个特定的应用将是处理用于缺陷评估的视觉图像的大数据集，其中数据由一群移动的传感代理（例如，无人驾驶飞行器）收集。在这种情况下，缺陷区域的例子是建筑物和设施的腐蚀和裂缝[1]，以及道路上的坑洞。这种评估过程成功的关键要求是缺陷区域的可靠检测、定量和定位。此外，在这样的应用中，实时评估通常是至关重要的，以便群可以决定在未知环境中有效收集数据的最佳策略和相应行动（例如，将用于地震侦察和救援的机器人，其中它们进入机器人未知计划的建筑物）。另一方面，评估的可靠性需要高质量的数据，因为差的数据可能对分类和预测的准确性产生负面影响，从而可能带来额外的费用和时间开销。一般而言，获取此类数据并确保数据具有高质量，特别是对于实时决策而言，由于难以到达感兴趣物体所在的区域以及需要进行人力密集型评估，因此成本很高。然而，今天我们有许多技术可以用来设计有效和廉价的解决方案，包括：用于图像分析的深度神经网络;图像处理技术;移动的图像数据采集这项工作部分得到了NSF奖IIS-1636891“BD Spokes：规划：中西部：网络基础设施，以提高数据质量和支持传感器起源大数据的可再现结果”的支持。作者地址：E。Bertino，CS部门，普渡大学，西拉斐特，印第安纳州，47907;电子邮件：bertino@ purdue。edu; MR Jahannshahi，土木工程学院，普渡大学，西拉斐特，IN，47907;电子邮件：jahansha@ purdue. edu.
In future smart cities, many decision processes in critical infrastructure and emergency management will be based on machine learning techniques. One particular application will be the processing of large datasets of visual images for defect assessment where the data is collected by a swarm of mobile sensing agents (eg, unmanned aerial vehicles). In this context, examples of defective regions are corrosion and cracks in buildings and facilities [1], and potholes on roads. A critical requirement for the success of such assessment processes is the reliable detection, quantification, and localization of defective regions. Furthermore, in such applications, the real-time assessment is often critical so that the swarm can decide regarding the optimum strategy and corresponding actions for effective data collection in unknown environments (eg, robots that will be used for earthquake reconnaissance and rescue where they enter buildings whose plan is unknown to the robot). On the other hand, the reliability of the assessments requires data of good quality, since poor data may negatively affect the accuracy of classification and predictions, and consequently, may introduce additional costs and time overhead. In general, acquiring such data and making sure that the data is of high quality, especially for real-time decisions, is expensive due to difficulty of reaching the regions where the objects of interest are located and the need for human-intensive assessment. However, today we have many technologies that can be leveraged to devise effective and inexpensive solutions, including: deep neural networks for image analysis; image processing techniques; mobile image data acquisitionThis work was partially supported by the NSF Award IIS-1636891 “BD Spokes: Planning: MIDWEST: Cyberinfrastructure to Enhance Data Quality and Support Reproducible Results in Sensor Originated Big Data.” Authors’ addresses: E. Bertino, CS Dept., Purdue University, West Lafayette, IN, 47907; email: bertino@ purdue. edu; MR Jahannshahi, Civil Engineering School, Purdue University, West Lafayette, IN, 47907; email: jahansha@ purdue. edu.
用于领土应急响应行动中自适应风险管理的时空贝叶斯网络
DOI：
--
发表时间：
2012
期刊：
影响因子：
--
作者：
A. Giretti;A. Carbonari;B. Naticchia
通讯作者：
B. Naticchia
使用机器学习进行实时模拟的灾害管理
DOI：
--
发表时间：
2011
期刊：
Canadian Conference on Electrical and Computer Engineering
影响因子：
--
作者：
Mohammed Talat Khouj;C. Castellanos;Sarbjit S. Sarkaria;J. Martí
通讯作者：
J. Martí