Example of a pipe-based water point that was added to the training set after the second round

Example of a pipe-based water point that was added to the training set after the second round

Source publication
Article
Full-text available
Background: 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 fram...

Similar publications

Thesis
Full-text available
Over a century ago, citizens migrating abroad has deeply marked Haiti. A significant part of the country’s population moved to other countries, yet, they have kept connections in the distance with their homeland. From 2010 onwards, Brazil has inserted in the group of destinations that are part of the intense Haitian mobility. Haitians, present in h...

Citations

... The resulting information consists of various data types, including textual data, video images, and spatial data (in the form of GPS paths). New ways to automate the digitizing of environmental risks from SV images using machine learning are currently in development [24]. ...
Article
Full-text available
Disease risk associated with contaminated water, poor sanitation, and hygiene in informal settlement environments is conceptually well understood. From an analytical perspective, collecting data at a suitably fine scale spatial and temporal granularity is challenging. Novel mobile methodologies, such as spatial video (SV), can complement more traditional epidemiological field work to address this gap. However, this work then poses additional challenges in terms of analytical visualizations that can be used to both understand sub-neighborhood patterns of risk, and even provide an early warning system. In this paper, we use bespoke spatial programming to create a framework for flexible, fine-scale exploratory investigations of simultaneously-collected water quality and environmental surveys in three different informal settlements of Port-au-Prince, Haiti. We dynamically mine these spatio-temporal epidemiological and environmental data to provide insights not easily achievable using more traditional spatial software, such as Geographic Information System (GIS). The results include sub-neighborhood maps of localized risk that vary monthly. Most interestingly, some of these epidemiological variations might have previously been erroneously explained because of proximate environmental factors and/or meteorological conditions.
... The results achieved using these techniques vary from one geographic area in some cases within a city due to varying physical characteristics of informal settlements. Recent studies on informal settlement detection have tested deep machine learning techniques such as convolutional neural network (CNN) and very high spatial resolution imagery to detect informal settlements (Ajayakumar et al., 2021;Maiya and Babu, 2018). These techniques have the potential of improving the accuracy of informal settlement detection compared to other machine learning techniques such as Support Vector Machine (Gram-Hansen et al., 2019;Maiya and Babu, 2018). ...
Article
Full-text available
The study proposes a ratio of informal settlement land consumption rate to imperviousness growth rate to understand informal settlement growth patterns. To compute this ratio, information on the informal extent and impervious surface within an informal settlement over at least two time periods is required. This ratio can be used to understand the density of building structures within an informal settlement. We investigated this ratio in a densely populated township in Tshwane Metropolitan Municipality over a five-year interval between 2005 and 2020. Informal settlement extent was generated using the object-based image analysis technique which uses asymmetry of image objects to classify informal settlements. The impervious surface was mapped using a ruleset that uses soil adjusted vegetation index, border index and radiometric values of the blue band. The results show that the ratio of land consumption rate of informal settlement to the impervious surface growth rate was 0.70 during the 2005-2010 interval, decreased substantially to − 11.25 during the 2010-2015 interval and increased to 0.85 during the 2015-2020 interval. The results can be used to support the management and planning of informal settlement upgrade projects and to monitor progress made towards achieving sustainable development goals.
... Within the past ten years, the rapid development of deep learning represented by Convolutional Neural Networks (CNNs) [10][11][12] seems to have brought some light to the field of target detection. Region-based CNN (R-CNN) [13] proposed in 2014 was the milestone in target detection based on convolutional neural networks. ...
Article
Full-text available
In the past few decades, target detection from remote sensing images gained from aircraft or satellites has become one of the hottest topics. However, the existing algorithms are still limited by the detection of small remote sensing targets. Benefiting from the great development of computing power, deep learning has also made great breakthroughs. Due to a large number of small targets and complexity of background, the task of remote sensing target detection is still a challenge. In this work, we establish a series of feature enhancement modules for the network based on YOLO (You Only Look Once -V3 to improve the performance of feature extraction. Therefore, we term our proposed network as FE-YOLO. In addition, to realize fast detection, the original Darknet-53 was simplified. Experimental results on remote sensing datasets show that our proposed FE-YOLO performs better than other state-of-the-art target detection models.
... Convolution is the result of two variables multiplied together in a range [15]. In our method, we used convolution operation to extract the features of input information [16]. ...
Article
As the fundamental unit of urban governance, communities are the grassroots for responding to and facing disasters directly, and their resilience to disaster risks has garnered increasing consideration. Despite the large body of community resilience research that now exists, few studies have considered the resilience of informal settlements such as ‘urban villages’. In fact, the high density of building facilities in informal settlements, the diversity and mobility of their populations, their lack of public space and infrastructure and all kinds of managerial problems have become more prominent in the context of the COVID-19 pandemic. This study aimed to analyse the characteristics of the migrant populations and healthy living environments of informal settlements, sum up the pandemic prevention measures and their effects, study the community resilience of informal settlements during the COVID-19 pandemic and summarise the strategies to build resilience. Our research results can be utilised to (1) enrich the content of existing community resilience research and promote the resilience of the whole city system in the face of public health events, and (2) provide a scientific basis for comprehensive management of informal settlements and optimise the living environments of migrant populations from the perspective of resilience.