Search

Showing total 2 results
2 results

1. Simulating fire-safe cities using a machine learning-based algorithm for the complex urban forms of developing nations: a case of Mumbai India.

Author

Kumar, Vaibhav, Jana, Arnab, and Ramamritham, Krithi

Subjects
DEVELOPING countries, ALGORITHMS, URBAN planning, FIRE detectors, REGRESSION analysis, URBAN health
Abstract

The article addresses the void in developing analytical methods concerning to design urban configurations that could reduce fire risks, and, thus, could help in achieving sustainable goals. A novel algorithm is developed to generate alternative Urban Built Form (UBF) models that could be less susceptible to fire compared to the existing built-form. Fire susceptibility of a generated UBF is predicted using a developed linear regression model. The algorithm considers existing regulations to derive rules and develop scenarios that might be effective in building fire-resilient cities. The outcomes of the simulations showed a significant decrease in the fire susceptibility of the southern region of Mumbai city. Moreover, for a certain simulated scenario the predicted UBF could accommodate twice the current population while being less susceptible than the existing UBF. The proposed techniques and methods can act as a decision-making tool in taking pre-emptive planning measures to develop fire resilient cities. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

2. Satellite image segmentation with Shadowed C-Means

Author

Mitra, Sushmita and Kundu, Partha Pratim

Subjects
*REMOTE-sensing images, *OPTICAL resolution, *LIGHTING, *IMAGE analysis, *ALGORITHMS, *PIXELS, *QUALITATIVE research, *QUANTITATIVE research
Abstract

Abstract: Satellite images often require segmentation in the presence of uncertainty, caused due to factors like environmental conditions, poor resolution and poor illumination. Since any subsequent image analysis depends on the quality of such segmentation, one has to obtain an efficient algorithm for the purpose. Pixel clustering is a popular way of determining the homogeneous image regions, corresponding to the different land cover types, based on their spectral properties. In this paper we map the newly developed shadowed clustering algorithm to the problem of segmenting remotely sensed images. It is observed that shadowed clustering can efficiently handle overlapping among segments while modeling uncertainty among the boundaries. Unlike rough clustering, here the choice of user-defined parameters is fully eliminated. The number of segments is automatically optimized in terms of validity indices. The algorithm is robust in the presence of outliers. The superiority of the system is demonstrated in segmenting a synthetic image, along with land cover types from the Indian Remote Sensing (IRS) images of the cities of Mumbai and Kolkata and the SPOT image around Kolkata. The algorithm is found to efficiently and accurately extract the different homogeneous regions in the presence of uncertainty. The results are analyzed both qualitatively and quantitatively. [Copyright &y& Elsevier]

Published
2011
Full Text
View/download PDF