Exploring convolutional neural networks and spatial video for on-the-ground mapping in informal settlements.
Exploring convolutional neural networks and spatial video for on-the-ground mapping in informal settlements.
复制标题
探索卷积神经网络和空间视频，用于非正规住区的实地测绘。
DOI：
10.1186/s12942-021-00259-z
复制
发表时间：
2021-01-25
影响因子：
4.9
通讯作者：
Morris JG
中科院分区：
文献类型：
--
作者：
Ajayakumar J;Curtis AJ;Rouzier V;Pape JW;Bempah S;Alam MT;Alam MM;Rashid MH;Ali A;Morris JG
发展中国家非正规住区的健康负担往往与缺乏可用于指导干预战略的空间数据相吻合。空间视频（SV）已被证明是一个有用的工具，以收集环境和社会数据在一个粒度级，虽然需要的努力，把这些空间编码的视频帧到地图限制了可持续性和可扩展性。在本文中，我们探索使用卷积神经网络（CNN）来解决这个问题，通过自动识别从海地收集的一系列SV中与疾病相关的环境风险。我们的目标是通过评估在充分训练所需分类模型时所面临的挑战，确定机器学习在这些环境中健康风险映射中的潜力。我们表明，SV可以成为使用机器学习自动识别和提取健康风险特征的合适来源。虽然诸如排水管、水桶、轮胎和动物等明确的物体可以有效地分类，但诸如垃圾或积水等更无定形的物质难以分类。我们的研究结果进一步表明，选择的图像帧的数量，图像分辨率，以及这些组合的变化可以用来提高整体模型的性能。机器学习与空间视频相结合，可用于自动识别与非正规住区常见健康问题相关的环境风险，尽管根据位置进行培训所需的数据类型可能会有所不同。基于所确定的风险类型的成功也可能因地域而异。然而，我们有信心在这些环境中确定一系列数据收集，模型训练和性能的最佳实践。我们还讨论了在其他环境中测试这些发现的下一步，以及如何添加同时收集的地理数据可以用来创建一个自动健康风险映射工具。
The health burden in developing world informal settlements often coincides with a lack of spatial data that could be used to guide intervention strategies. Spatial video (SV) has proven to be a useful tool to collect environmental and social data at a granular scale, though the effort required to turn these spatially encoded video frames into maps limits sustainability and scalability. In this paper we explore the use of convolution neural networks (CNN) to solve this problem by automatically identifying disease related environmental risks in a series of SV collected from Haiti. Our objective is to determine the potential of machine learning in health risk mapping for these environments by assessing the challenges faced in adequately training the required classification models. We show that SV can be a suitable source for automatically identifying and extracting health risk features using machine learning. While well-defined objects such as drains, buckets, tires and animals can be efficiently classified, more amorphous masses such as trash or standing water are difficult to classify. Our results further show that variations in the number of image frames selected, the image resolution, and combinations of these can be used to improve the overall model performance. Machine learning in combination with spatial video can be used to automatically identify environmental risks associated with common health problems in informal settlements, though there are likely to be variations in the type of data needed for training based on location. Success based on the risk type being identified are also likely to vary geographically. However, we are confident in identifying a series of best practices for data collection, model training and performance in these settings. We also discuss the next step of testing these findings in other environments, and how adding in the simultaneously collected geographic data could be used to create an automatic health risk mapping tool.
登录
查看更多内容
影响因子：
4.9
作者：
Curtis A;Blackburn JK;Widmer JM;Morris JG Jr
通讯作者：
Morris JG Jr
影响因子：
5
作者：
Liu, Ruoyun;Kuffer, Monika;Persello, Claudio
通讯作者：
Persello, Claudio
贫民窟的卫生和肯尼亚内罗毕妇女健康的社会决定因素。
影响因子：
--
作者：
Corburn J;Hildebrand C
通讯作者：
Hildebrand C
DOI：
10.3390/ijerph13020187
发表时间：
2016-02-01
影响因子：
--
作者：
Curtis, Andrew;Blackburn, Jason K.;Morris, J. Glenn, Jr.
通讯作者：
Morris, J. Glenn, Jr.
DOI：
10.1016/j.compenvurbsys.2019.03.005
发表时间：
2019-07-01
影响因子：
6.8
作者：
Ibrahim, Mohamed R.;Titheridge, Helena;Haworth, James
通讯作者：
Haworth, James