Use of an Extended Premise Condition Index for detection of priority areas for vector control actions

Barbosa, Gerson Laurindo; Lage, Mariana de Oliveira; Andrade, Valmir Roberto; Gomes, Antonio Henrique Alves; Quintanilha, José Alberto; Neto, Francisco Chiaravalloti

doi:10.1016/j.actatropica.2020.105543

“…The strong positive correlation and dependency relationship between the facade conditions and building and backyard conditions, not found in other studies on the topic, together with the positive correlation with backyard paving and shading, shows that the higher the facade condition level, the higher the PCI value, considering its original definition with three categories [26] and its extended version proposed by Barbosa et al [31]. With this, it is possible to say that from the facade PCI, we could infer the general PCI of a building.…”

Section: Discussionmentioning

confidence: 85%

“…This approach may be valuable for categorizing areas with a higher presence of vector breeding sites because previous studies using PCI have demonstrated that elevated PCI values are associated with a higher likelihood of Ae. aegypti breeding sites [31, 83]. Based on the findings of this study, it is believed that the employed methodology can be implemented into the routine of the vector control program.…”

Section: Discussionmentioning

confidence: 99%

Automatic mapping of high-risk urban areas forAedes aegyptiinfestation based on building facade image analysis

Laranjeira,

Pereira,

Vitor Ferreira de Oliveira

et al. 2023

Preprint

Self Cite

0

View full text Add to dashboard Cite

BackgroundDengue, Zika, and chikungunya, whose viruses are transmitted mainly byAedes aegypti, significantly impact human health worldwide. Despite the recent development of promising vaccines against the dengue virus, controlling these arbovirus diseases still depends on mosquito surveillance and control. Nonetheless, several studies have shown that these measures are not sufficiently effective or ineffective. Identifying higher-risk areas in a municipality and directing control efforts towards them could improve it. One tool for this is the premise condition index (PCI); however, its measure requires visiting all buildings. We propose a novel approach capable of predicting the PCI based on facade street-level images, which we call PCINet.MethodologyOur study was conducted in Campinas, a one million-inhabitant city in São Paulo, Brazil. We surveyed 200 blocks, visited their buildings, and measured the three traditional PCI components (building and backyard conditions and shading), the facade conditions (taking pictures of them), and other characteristics. We trained a deep neural network with the pictures taken, creating a computational model that can predict buildings’ conditions based on the view of their facades. We evaluated PCINet in a scenario emulating a real large-scale situation, where the model could be deployed to automatically monitor four regions of Campinas to identify risk areas.Principal findingsPCINet produced reasonable results in differentiating the facade condition into three levels, and it is a scalable strategy to triage large areas. The entire process can be automated through data collection from facade data sources and inferences through PCINet. The facade conditions correlated highly with the building and backyard conditions and reasonably well with shading and backyard conditions. The use of street-level images and PCINet could help to optimizeAe. aegyptisurveillance and control, reducing the number of in-person visits necessary to identify buildings, blocks, and neighborhoods at higher risk from mosquito and arbovirus diseases.Author SummaryThe strategies to controlAe. aegyptirequire intensive work and considerable financial resources, are time-consuming, and are commonly affected by operational problems requiring urgent improvement. The PCI is a good tool for identifying higher-risk areas; however, its measure requires a high amount of human and material resources, and the aforementioned issues remain. In this paper, we propose a novel approach capable of predicting the PCI of buildings based on street-level images. This first work combines deep learning-based methods with street-level data to predict facade conditions.Considering the good results obtained with PCINet and the good correlations of facade conditions with PCI components, we could use this methodology to classify building conditions without visiting them physically. With this, we intend to overcome the high cost of identifying high-risk areas. Although we have a long road ahead, our results show that PCINet could help to optimizeAe. aegyptiand arbovirus surveillance and control, reducing the number of in-person visits necessary to identify buildings or areas at risk.

show abstract

“…Studies have presented several ways to identify key properties of a region for the presence of breeding sites [ 41 , 54 – 57 ]. The main issue with these methods is the necessity of visiting the places to classify them as key or not.…”

Section: Discussionmentioning

confidence: 99%

“…Four areas were selected ( Fig 2 ) with different socioeconomic levels [ 41 ], which were characterized using the information of the demographic census of 2010 made available by the Brazilian Institute of Geography and Statistics (IBGE). Area 1 had the best socioeconomic level, with an average income per household of 1,807 Reais (the Brazilian currency) and 3.0 inhabitants per household; Area 4 had the worst socioeconomic level, with an average income per household of 755 Reais and 3.5 inhabitants per household.…”

Section: Methodsmentioning

confidence: 99%

Water tank and swimming pool detection based on remote sensing and deep learning: Relationship with socioeconomic level and applications in dengue control

Cunha

¹

,

Sclauser

²

,

Wildemberg

³

et al. 2021

Self Cite

View full text Add to dashboard Cite

Studies have shown that areas with lower socioeconomic standings are often more vulnerable to dengue and similar deadly diseases that can be spread through mosquitoes. This study aims to detect water tanks installed on rooftops and swimming pools in digital images to identify and classify areas based on the socioeconomic index, in order to assist public health programs in the control of diseases linked to the Aedes aegypti mosquito. This study covers four regions of Campinas, São Paulo, characterized by different socioeconomic contexts. With mosaics of images obtained by a 12.1 MP Canon PowerShot S100 (5.2 mm focal length) carried by unmanned aerial vehicles, we developed deep learning algorithms in the scope of computer vision for the detection of water tanks and swimming pools. An object detection model, which was initially created for areas of Belo Horizonte, Minas Gerais, was enhanced using the transfer learning technique, and allowed us to detect objects in Campinas with fewer samples and more efficiency. With the detection of objects in digital images, the proportions of objects per square kilometer for each region studied were estimated by adopting a Chi-square distribution model. Thus, we found that regions with low socioeconomic status had more exposed water tanks, while regions with high socioeconomic levels had more exposed pools. Using deep learning approaches, we created a useful tool for Ae. aegypti control programs to utilize and direct disease prevention efforts. Therefore, we concluded that it is possible to detect objects directly related to the socioeconomic level of a given region from digital images, which encourages the practicality of this approach for studies aimed towards public health.

show abstract

“…To evaluate the PCI, the model by Tun-Lin et al [26] and the extended model by Barbosa et al [31] were used, adding other variables to improve the classification of the building and expanding the score (1 to 5, instead of 1 to 3). We used the following characteristics: building type, facade, building and backyard conditions, shading, backyard paving, roofing, and potential breeding sites.…”

Section: Field Data Collection and Databasementioning

confidence: 99%

Automatic mapping of high-risk urban areas for Aedes aegypti infestation based on building facade image analysis

Laranjeira,

Pereira,

Oliveira

et al. 2024

PLoS Negl Trop Dis

0

View full text Add to dashboard Cite

Background Dengue, Zika, and chikungunya, whose viruses are transmitted mainly by Aedes aegypti, significantly impact human health worldwide. Despite the recent development of promising vaccines against the dengue virus, controlling these arbovirus diseases still depends on mosquito surveillance and control. Nonetheless, several studies have shown that these measures are not sufficiently effective or ineffective. Identifying higher-risk areas in a municipality and directing control efforts towards them could improve it. One tool for this is the premise condition index (PCI); however, its measure requires visiting all buildings. We propose a novel approach capable of predicting the PCI based on facade street-level images, which we call PCINet. Methodology Our study was conducted in Campinas, a one million-inhabitant city in São Paulo, Brazil. We surveyed 200 blocks, visited their buildings, and measured the three traditional PCI components (building and backyard conditions and shading), the facade conditions (taking pictures of them), and other characteristics. We trained a deep neural network with the pictures taken, creating a computational model that can predict buildings’ conditions based on the view of their facades. We evaluated PCINet in a scenario emulating a real large-scale situation, where the model could be deployed to automatically monitor four regions of Campinas to identify risk areas. Principal findings PCINet produced reasonable results in differentiating the facade condition into three levels, and it is a scalable strategy to triage large areas. The entire process can be automated through data collection from facade data sources and inferences through PCINet. The facade conditions correlated highly with the building and backyard conditions and reasonably well with shading and backyard conditions. The use of street-level images and PCINet could help to optimize Ae. aegypti surveillance and control, reducing the number of in-person visits necessary to identify buildings, blocks, and neighborhoods at higher risk from mosquito and arbovirus diseases.

show abstract

Use of an Extended Premise Condition Index for detection of priority areas for vector control actions

Cited by 4 publications

References 34 publications

Automatic mapping of high-risk urban areas forAedes aegyptiinfestation based on building facade image analysis

Automatic mapping of high-risk urban areas forAedes aegyptiinfestation based on building facade image analysis

Water tank and swimming pool detection based on remote sensing and deep learning: Relationship with socioeconomic level and applications in dengue control

Automatic mapping of high-risk urban areas for Aedes aegypti infestation based on building facade image analysis

Contact Info

Product

Resources

About