scholarly journals Deep-learning Coupled with Novel Classification Method to Classify the Urban Environment of the Developing World

2021 ◽  
Author(s):  
Qianwei Cheng ◽  
AKM Mahbubur Rahman ◽  
Anis Sarker ◽  
Abu Bakar Siddik Nayem ◽  
Ovi Paul ◽  
...  
Keyword(s):  
Urban Environment ◽  
Urban Area ◽  
Urban Space ◽  
Developing World ◽  
Google Earth ◽  
The State ◽  
Classification Method ◽  
Small Scale ◽  
Surrounding Environment

Rapid globalization and the interdependence of the countries have engendered tremendous in-flow of human migration towards the urban spaces. With the advent of high definition satellite images, high-resolution data, computational methods such as deep neural network analysis, and hardware capable of high-speed analysis; urban planning is seeing a paradigm shift. Legacy data on urban environments are now being complemented with high-volume, high-frequency data. However, the first step of understanding the urban area lies in the useful classification of the urban environment that is usable for data collection, analysis, and visualization. In this paper, we propose a novel classification method that is readily usable for machine analysis and it shows the applicability of the methodology in a developing world setting. However, the state-of-the-art is mostly dominated by the classification of building structures, building types, etc., and largely represents the developed world. Hence, these methods and models are not sufficient for developing countries such as Bangladesh where the surrounding environment is crucial for the classification. Moreover, the traditional classifications propose small-scale classifications, which give limited information, have poor scalability and are slow to compute in real-time. We categorize the urban area in terms of informal and formal spaces and take the surrounding environment into account. 50 km × 50 km Google Earth image of Dhaka, Bangladesh was visually annotated and categorized by an expert and consequently, a map was drawn. The classification is based broadly on two dimensions the state of urbanization and the architectural form of the urban environment. Consequently, the urban space is divided into four classifications: 1) highly informal area 2) moderately informal area 3) moderately formal area and 4) highly formal area. For semantic segmentation and automatic classification, Google’s DeeplabV3+ model was used. The model uses the Atrous convolution operation to analyze different layers of texture and shape. This allows us to enlarge the field of view of the filters to incorporate a larger context. Image encompassing 70% of the urban space was used to train the model and the remaining 30% was used for testing and validation. The model can segment with 75% accuracy and 60% Mean Intersection over Union (mIoU).

scholarly journals Integrated Strategies for the Control of Leishmaniasis in the Municipality of Teodoro Sampaio, SP, from a Geographical Perspective, Supported by Geoprocessing

2014 ◽  
Author(s):  
Elivelton Da Silva Fonseca
Keyword(s):  
Urban Area ◽  
Population Based ◽  
Sao Paulo ◽  
The State ◽  
Small Scale ◽  
São Paulo ◽  
Spatial Transformation ◽  
Mato Grosso ◽  
General Terms

Introduction: This study is justified since very little is known of the relationship between Leishmaniasis and the spatial transformation process. In the past, the municipality of Teodoro Sampaio has spread ACL and recently cases of visceral Leishmaniasis have been found in dogs in the urban area, making the municipality a likely area for the convergence of both manifestations of the disease. The overall aim is to relate recent spatial transformations with the pattern of spatial distribution of the infection’s vectors and hosts, keeping in mind the integrated geographic distribution of ACL and AVL.  Methods:  The study has two levels of aggregation: (a) a population-based case study of the municipality of Teodoro Sampaio, Pontal do Paranapanema, in the state of São Paulo, designed to be quantitative, descriptive and cross-sectional, and (b) population-based across the municipalities of São Paulo state, designed to be retrospective, quantitative, observational and descriptive. The choice of two approaches to the study is justified by a consideration of the articulations which enable the formation of production circuits for Leishmaniasis in the region. The gathering of data for the Teodoro Sampaio case study underwent two phases: field study and by means of secondary official data sources. Data concerning the state of São Paulo comes from secondary sources.  Conclusion: As it is a focal disease, the data presented allows us to infer that AVL spreads from Sector 1 of the urban area to Sector 3, because the vector relevant to transmission is within the former. The ACL pattern in Teodoro Sampaio is thought to be based in the woodlands surrounding the urban area, in general terms, based in the Parque Estadual do Morro do Diabo (PEMD), the edge of which is five kilometres from the centre of the district. Exchanges take place between the urban area of the municipality, the PEMD, the settlement of Ribeirão Bonito, which forms part of the transect making up the geosystem of Teodoro Sampaio, and Pontal do Paranapanema. Human intervention can be seen as the main agent in promoting these exchanges between environments due to the transit of people between subgeosystems and the interrelationship with other municipalities encouraging the spread of the disease. The only municipalities to be among those with a high incidence of AVL are Araçatuba and Presidente Prudente, although the number of cases is growing and becoming more concentrated. The state presents a circumscribed hub of AVL cases in the region of Campinas and Piracicaba, and another in Pontal do Paranapanema. This interaction borders on Mato Grosso do Sul, giving rise to the main circuit AVL instances of the Southeast. ACL has a hub at Itapetininga, which is next to Vale do Paraiba Paulista, also leading to interactions across the border with the state of Rio de Janeiro and its principal circumscribed centres of transmission of ACL. This will be Brazil’s next ACL production circuit. It was possible to identify areas in the state of São Paulo particularly vulnerable to Leishmaniasis with particular distributions for each of the two types of the disease, sometimes existing together. Outbreaks of canine VL do not depend on distribution rules on a small scale, although the effect of many outbreaks together clarifies a spatial pattern, as seen in the state of São Paulo. Patterns of transmission of Leishmaniasis are established in the state of São Paulo and the data analyzed helps to verify these patterns.

scholarly journals Confirmed cases of malaria in Brazil between 2011 and 2015

2020 ◽  
pp. 05-16
Author(s):  
Hellen Karine Santos Almeida ◽  
Amanda Alves Fecury ◽  
Euzébio Oliveira ◽  
Carla Viana Dendasck ◽  
Claudio Alberto Gellis de Mattos Dias
Keyword(s):  
Higher Education ◽  
High School ◽  
Urban Environment ◽  
Urban Area ◽  
The State ◽  
Age Group ◽  
Breeding Sites ◽  
Genus Plasmodium ◽  
It Department ◽  
Southeastern Region

Malaria is a worldwide disease that causes a high number of deaths. It is caused by the bite of the Anopholes mosquito infected by the parasitic protozoan of the genus Plasmodium. The purpose of this article is to show the numbers of confirmed cases of malaria in Brazil, regarding the years of confirmation, the age group and the notification region, between the years 2011 to 2015. Data taken from the SUS IT department, DATASUS and from articles. There was a decline in the number of the period cited, people between the age group of 20 to 39 years, followed by the group between 49 and 59 years, the largest number of cases occurred with male people, the largest number of cases occurred with people of white race followed by browns, the highest number of cases per schooling is unknown where schooling is known, the highest numbers are with people from complete high school, followed by people with complete higher education, most cases occurred in an urban area , the southeastern region has the highest number of confirmed cases of malaria in the period, the highest number of cases occurred in the state of Rondônia. It is concluded that campaigns had an influence on society and collaborated with the reduction of the number of communicable diseases like malaria. Men work in areas with a higher risk of contamination and in places of vector proliferation, so they are more exposed to areas of mosquito proliferation and contagion. In Brazil the majority of the population is recognized as being white and brown, respectively, so the numbers show these ethnicities as the most infected. The mosquito seems to proliferate more easily in places where there have been man-made changes. The urban environment, as it is an extremely modified place, causes a greater number of cases due to the greater availability of breeding sites. It is believed that for this reason the southeastern region has a greater number of cases and because it is also one of the regions of the country that has suffered the most changes by man. The opening of highways and the increase in settlements facilitate contact between mosquitoes and humans. The state of Rondônia has a large number of settlements and deforestation to accommodate progress.

Research on Assessment and Classification for Major Hazard Installation of Dangerous Chemicals

2012 ◽  
Vol 610-613 ◽  
pp. 904-909
Author(s):  
Ze Min Luo
Keyword(s):  
Research Result ◽  
Reference Value ◽  
Classification Method ◽  
Real Situation ◽  
Probability Summation ◽  
The Real ◽  
Surrounding Environment ◽  
Property Losses ◽  
Principle Of Maximum

Based on death radius classification method for major hazard installation, this assay utilize “the principle of maximum danger” and “the principle of probability summation” as the principles to calculate property losses and casualties, and use the Classification Standards of Major Hazard Installation (exposure draft) as the standard, to classify the major hazard installation of dangerous chemicals. Thus, it could take property losses and casualties of surrounding environment into consideration, which ensure the considered factors of major hazard installation classification of dangerous chemicals more comprehensive, and ensure the classification results more closely with the real situation. The research result of this essay would provide certain reference value on major hazard installation assessment and classification of dangerous chemicals.

‘Useful’ and ‘Earning’ Citizens? Gender, state, and the market in post-colonial Delhi

2019 ◽  
Vol 53 (06) ◽  
pp. 1924-1955
Author(s):  
ANJALI BHARDWAJ DATTA
Keyword(s):  
Urban Space ◽  
The State ◽  
Small Scale ◽  
Post Colonial ◽  
Colonial India ◽  
Refugee Women ◽  
Point Of Entry ◽  
Indian State ◽  
History Of ◽  
National Disaster

AbstractThe Indian state treated the partition of Punjab as a ‘national disaster’ and training for refugee women was deemed essential to restore the social landscape; yet the kind of help it offered to refugee women rested on its clear assumptions and biases about the kind of work that was appropriate for them: women were offered training in embroidery, stitching, tailoring, and weaving, as these are associated with feminine and household-based skills. This article will reveal that the state rehabilitation enterprise was primarily masculine in focus. The state treated women refugees as secondary earners and as guardians of hearth, kith, and kin; it did not see them playing a definitive role in nation-building in post-colonial India. In the absence of state supportive policies, refugee women were compelled to take up informal jobs like petty trading, domestic service, and labouring work. This article suggests that refugee women were handicapped in the labour market at their very point of entry. It traces the history of women's informalities in Delhi. In doing so, it investigates the feminization and commercialization of urban space in twentieth-century Delhi. It urges that women made space in more than one way: identifying fragmentary livelihoods, producing small-scale capitalism, and creating informal markets.

scholarly journals Food availability and food insecurity in households in the state of Tocantins, Northern Brazil

2020 ◽  
Vol 33 ◽  
Author(s):  
Eloise SCHOTT ◽  
Silvia Eloiza PRIORE ◽  
Andréia Queiroz RIBEIRO ◽  
Fabiane Aparecida Canaan REZENDE ◽  
Sylvia do Carmo Castro FRANCESCHINI
Keyword(s):  
Food Insecurity ◽  
Urban Area ◽  
Food Availability ◽  
Population Based ◽  
Cross Sectional Study ◽  
The State ◽  
Cross Sectional ◽  
Socioeconomic Vulnerability ◽  
Northern Brazil

ABSTRACT Objective To assess the relationship between food availability, food insecurity and socioeconomic and demographic characteristics of households in the urban area of the state of Tocantins. Methods Population-based, cross-sectional study conducted in 594 households in the urban area of 22 municipalities in the state of Tocantins. A survey was carried out in the households, to collect socioeconomic and data, and assess food insecurity using the Brazilian Food Insecurity Scale. Further a food availability questionnaire was applied by the interviewer with the head of the family, who reported on the food and drinks available at home in the last 30 days. The description of the food available in the households resulted in a total of 142 food items that were grouped according to the NOVA classification of foods. demographic Results It was found that 63.3% of households were in a situation of food insecurity. The median caloric availability found was 2,771.4kcal/per capita/day, with the largest caloric contribution coming from fresh and minimally processed foods, regardless of the degree of food insecurity. Food availability was affected by socioeconomic vulnerability and the situation of food insecurity in the families.

scholarly journals Applying State-of-the-Art Deep-Learning Methods to Classify Urban Cities of the Developing World

Sensors ◽  
2021 ◽  
Vol 21 (22) ◽  
pp. 7469
Author(s):  
A. K. M. Mahbubur Rahman ◽  
Moinul Zaber ◽  
Qianwei Cheng ◽  
Abu Bakar Siddik Nayem ◽  
Anis Sarker ◽  
...  
Keyword(s):  
Deep Learning ◽  
Urban Space ◽  
Urban Areas ◽  
Developing World ◽  
State Of The Art ◽  
Google Earth ◽  
Two Dimensions ◽  
Urban Spaces ◽  
Convolutional Network ◽  
Architectural Form

This paper shows the efficacy of a novel urban categorization framework based on deep learning, and a novel categorization method customized for cities in the global south. The proposed categorization method assesses urban space broadly on two dimensions—the states of urbanization and the architectural form of the units observed. This paper shows how the sixteen sub-categories can be used by state-of-the-art deep learning modules (fully convolutional network FCN-8, U-Net, and DeepLabv3+) to categorize formal and informal urban areas in seven urban cities in the developing world—Dhaka, Nairobi, Jakarta, Guangzhou, Mumbai, Cairo, and Lima. Firstly, an expert visually annotated and categorized 50 × 50 km Google Earth images of the cities. Each urban space was divided into four socioeconomic categories: (1) highly informal area; (2) moderately informal area; (3) moderately formal area, and (4) highly formal area. Then, three models mentioned above were used to categorize urban spaces. Image encompassing 70% of the urban space was used to train the models, and the remaining 30% was used for testing and validation of each city. The DeepLabv3+ model can segment the test part with an average accuracy of 90.0% for Dhaka, 91.5% for Nairobi, 94.75% for Jakarta, 82.0% for Guangzhou city, 94.25% for Mumbai, 91.75% for Cairo, and 96.75% for Lima. These results are the best for the DeepLabv3+ model among all. Thus, DeepLabv3+ shows an overall high accuracy level for most of the measuring parameters for all cities, making it highly scalable, readily usable to understand the cities’ current conditions, forecast land use growth, and other computational modeling tasks. Therefore, the proposed categorization method is also suited for real-time socioeconomic comparative analysis among cities, making it an essential tool for the policymakers to plan future sustainable urban spaces.

Sign in / Sign up

Export Citation Format

Share Document