Neuro-Fuzzy Modeling: A Promising Alternative for Risk Analysis in Urban Afforestation Management

Bressane, Adriano; Bagatini, João Augusto; Biagolini, Carlos Humberto; Roveda, José Arnaldo Frutuoso; Roveda, Sandra Regina Monteiro Masalskiene; Fengler, Felipe Hashimoto; Longo, Regina Márcia

doi:10.1590/1806-90882018000100006

Cited by 4 publications

(4 citation statements)

References 15 publications

(11 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Urbanization is a global trend that oftentimes leads to soil sealing, deforestation and habitat fragmentation, requiring integrated management of anthropic and natural issues to achieve healthy and sustainable cities (Adler & Tanner 2015, Aronson et al 2017, Bressane et al 2017b, Ribeiro et al 2018. It is widely acknowledged that green areas not only contribute to biodiversity conservation but that they also provide environmental quality in urban landscapes (Zhou & Wang 2011, Sperandelli et al 2013, Andersson et al 2014, Kabisch & Haase 2014, Gavrilidis et al 2017, Meerow & Newell 2017, Bressane et al 2018b, Rocha & Mussury 2020.…”

Section: Introductionmentioning

confidence: 99%

A fuzzy-based methodological proposal for analysing green areas in urban neighborhoods

Mota¹,

Galvão

Bressane³

et al. 2022

An. Acad. Bras. Ciênc.

View full text Add to dashboard Cite

The reduction of the green areas due to the growth of the built-up areas has affected the environmental quality in cities. Nevertheless, some uncertainties remain about the adequate amount of such areas in the urban landscape. This study aims at introducing a methodology to support analysis of green areas in urban neighborhoods.The methodological proposal was based on a fuzzy expert system (FES), a soft computing approach capable of dealing with uncertainties in complex multiple-criteria decisionmaking. As empirical research, some case studies to introduce and validate the proposed methodology were performed. An agglomerative hierarchical clustering, followed by a Kruskal-Wallis test and multiple pairwise comparisons using the Conover-Iman procedure (significance 0.05), demonstrated that the FES was able to provide outcomes consistent with hypothetical situations, simulated as ideal and critical conditions of green areas. In conclusion, our findings indicate that the methodological proposal based on FES is a promising tool for complex case-by-case analysis in urban neighborhoods.

show abstract

Section: Introductionmentioning

confidence: 99%

A fuzzy-based methodological proposal for analysing green areas in urban neighborhoods

Mota¹,

Galvão

Bressane³

et al. 2022

An. Acad. Bras. Ciênc.

View full text Add to dashboard Cite

show abstract

“…Apesar da importância da floresta para a qualidade de vida, o planeamento e a gestão inadequados podem promover riscos para a população e resultar em perdas materiais ou mesmo fatalidades (Bressane et al 2018). O aumento da ocorrencias de quedas de árvores nos centros urbanos tem se intensificado nos últimos anos, causada por condicionantes, como: chuvas fortes e longas, podas irregulares, rajadas de vento e raiz instável (Sampaio et al 2010).…”

Section: Introductionunclassified

Diagnóstico sobre a queda de árvores urbanas em Belo Horizonte-MG

2020

View full text Add to dashboard Cite

As árvores urbanas proporcionam inúmeros benefícios para a população, contribuindo significativamente para a melhoria da qualidade de vida. Contudo, tem sido frequente os transtornos ocasionados por queda de árvores nas grandes cidades. Desta forma, o objetivo da presente pesquisa foi realizar um diagnóstico sobre a queda de árvores urbanas em Belo Horizonte-MG. Para isso, os dados foram coletados por meio de amostragem aleatória após a ocorrência das quedas, entre os anos de 2015 e 2018. Sempre após o registro da queda, no local de ocorrência foram coletas as seguintes informações: identificação botânica, porte, condição de plantio, local de ruptura; qualidade da copa, troco e colo; presença de pragas ou sinais de doença. A análise, realizada em 69 exemplares arbóreos indicou a queda de 24 espécies pertencentes a 10 famílias botânicas. Sete espécies foram responsáveis por aproximadamente 60% das quedas registradas, destas, destacaramse as espécies Pachira aquatica e Libidibia ferrea var. leiostachya responsáveis por 10,1% das ocorrências cada uma e Poincianella pluviosa (8,7%). Apenas 20,3% das árvores apresentaram problemas fitossanitários, desencadeados principalmente pelo ataque do besouro metálico e por cupins nas raízes. A maioria foram plantadas em calçadas e apresentavam grande porte (76,8%), com boas condições de copa (88%), tronco (88%) e colo (95%), não evidenciando problemas, sendo a ruptura ocorrida principalmente nas raízes (82,6%). Conclui-se, a condição de plantio onde houve falta de espaço ou dificuldade de enraizamento no solo urbano, teve relação direta com a queda, evidenciando a dificuldade de ancoragem em árvores de grande porte.

show abstract

“…Thus, by affording a convenient formalism for integrating different kinds of variables, by means of an user-friendly structure with transparency and interpretability, the usage of fuzzy modeling is becoming more and more common, with several applications in the environmental sciences over the years (e.g. [7], [8], [9], [22], [23], [21], [4], [2], [28]).…”

Section: Introductionmentioning

confidence: 99%

Arboreal Identification Supported by Fuzzy Modeling for Trunk Texture Recognition

Bressane

Fengler²,

Roveda³

et al. 2018

Tend. Mat. Apl. Comput.

Self Cite

View full text Add to dashboard Cite

Due to the natural variability of the arboreal bark there are texture patterns in trunk images with values belonging to more than one species. Thus, the present study analyzed the usage of fuzzy modeling as an alternative to handle the uncertainty in the trunk texture recognition, in comparison with other machine learning algorithms. A total of 2160 samples, belonging to 20 tree species from the Brazilian native deciduous forest, were used in the experimental analyzes. After transforming the images from RGB to HSV, 70 texture patterns have been extracted based on first and second order statistics. Secondly, an exploratory factor analysis was performed for dealing with redundant information and optimizing the computational effort. Then, only the first dimensions with higher cumulative variability were selected as input variables in the predictive modeling. As a result, fuzzy modeling reached a generalization ability that outperformed algorithms widely used in classification tasks, besides of obtaining an almost perfect agreement with the classifier with the best accuracy in the validation tests. Therefore, the fuzzy modeling can be considered as a competitive approach, with reliable performance in arboreal trunk texture recognition.

show abstract

Neuro-Fuzzy Modeling: A Promising Alternative for Risk Analysis in Urban Afforestation Management

Cited by 4 publications

References 15 publications

A fuzzy-based methodological proposal for analysing green areas in urban neighborhoods

A fuzzy-based methodological proposal for analysing green areas in urban neighborhoods

Diagnóstico sobre a queda de árvores urbanas em Belo Horizonte-MG

Arboreal Identification Supported by Fuzzy Modeling for Trunk Texture Recognition

Contact Info

Product

Resources

About