Machine learning for buildings’ characterization and power-law recovery of urban metrics

Krayem, Alaa; Yeretzian, Aram; Faour, Ghaleb; Najem, Sara

doi:10.1371/journal.pone.0246096

Cited by 7 publications

(7 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The number of floors can be estimated by dividing the building's height by the average story height. In previous studies, values ranging from 2.8 m to 4.5 m, depending on the building's construction period, were attributed to the average story height in Beirut (Krayem et al, 2021;Salameh, 2016). As the average story height in Beirut varies according to different sources, we relied on a linear regression between the heights of the LIB-STAT buildings retrieved from satellite images and the number of floors of these buildings to derive an empirical story height for buildings in Beirut.…”

Section: Estimation Of the Buildings' Number Of Floorsmentioning

confidence: 97%

“…Recently, novel approaches relying on satellite images and/or open-accessible geospatial data have been developed to set up seismic exposure models (Geiß et al, 2017;Gomez-Zapata et al, 2022;Krayem et al, 2021;Nievas et al, 2022;Sousa et al, 2017;Wieland et al, 2012). Particularly, in countries with limited census data and incomplete building datasets, such as Lebanon, volunteered geographic information, such as the data provided by OpenStreetMap (OSM) (https://www.openstreetmap.org/) are valuable resources for the development of up-todate building exposure models (e.g.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Estimating urban seismic damages and debris at the building-level: Application to the city of Beirut, Lebanon

Iskandar

Tfaily

Cornou

et al. 2022

Preprint

View full text Add to dashboard Cite

The estimation of seismic damages and debris at the urban scale - at a precise building-by-building level- is challenging for several reasons. First, commonly used methodologies for seismic damage estimation rarely take into account the local site effects, precisely at the building-level. Second, the available methods for debris estimation fail to estimate at the same time the quantity of debris generated per building according to its damage level and the distribution of the debris (extent and height) around buildings. Finally, the lack of comprehensive data on the building stock and the relevant building properties and their taxonomy further increases the complexity of assessing possible earthquake consequences at an urban scale. This paper addresses these challenges and proposes improvements to the assessment of seismic damages and debris at the building level, along with the development of a 3D building model based on satellite images and heterogeneous data. These developments, applied to the city of Beirut, Lebanon, highlight the control of the site effects on the seismic damage spatial distribution throughout the city and the large volume and extent of debris to be expected in the city for a strong earthquake.

show abstract

Section: Estimation Of the Buildings' Number Of Floorsmentioning

confidence: 97%

mentioning

confidence: 99%

Estimating urban seismic damages and debris at the building-level: Application to the city of Beirut, Lebanon

Iskandar

Tfaily

Cornou

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…4-5). The SMOTE algorithm and Support Vector Machines (SVM) are combined in SVMSMOTE to make fake samples that are less similar to the original minority class instances (Krayem et al, 2021;Nguyen et al, 2011). To use this method, the original minority class samples are used to train an SVM classi er and nd the decision boundary.…”

Section: Svmsmotementioning

confidence: 99%

Exploring Resampling Techniques in Credit Card Default Prediction

Lokanan

2024

Preprint

View full text Add to dashboard Cite

In the field of machine learning, the preparation of data is a pivotal step in optimizing model performance. This paper delves into the crucial role of data cleaning and transformation, with a particular emphasis on resampling techniques tailored for addressing imbalanced datasets. By emphasizing the significance of tailored data preparation methodologies, this study underscores the role of resampling techniques in optimizing model performance, especially when dealing with imbalanced datasets. Through an exploration of both undersampling and oversampling methods, the study delves into their nuanced impacts on classification performance and explores the potential trade-offs inherent in each approach. Focusing on the domain of credit card default prediction, the research leverages the UCI Credit Card dataset to provide a comprehensive analysis. The results demonstrate that NearMiss outperformed other undersampling techniques across all classifiers and evaluation metrics. Similarly, K-MeansSMOTE emerged as the top-performing oversampling technique across all classifiers and evaluation metrics. Among the techniques investigated in the study, K-MeansSMOTE oversampling yielded the highest performance accuracy. The findings from this paper enhance our understanding of the performance of different resampling techniques and contribute to the scholarship on handling imbalanced datasets. The results show the pros and cons of different resampling methods used with different machine learning algorithms. They also show how important customized methods are for getting accurate predictions. While offering valuable insights, the study acknowledges the necessity for further research to refine and generalize these techniques across diverse domains and real-world applications, thereby contributing to the broader landscape of machine learning methodologies.

show abstract

“…The method has low time complexity, but when the current algorithm is used for small feature enhancement of super-resolution images, it cannot feature the details of the images and has the problem of large error in image feature enhancement. In the literature [31], the blocks are divided along the azimuths direction and the continuity of the walls inside each block is sparsely represented using a dictionary matrix of Radonlike transformations, and then the sparse signal vector is recovered using the orthogonal matching tracking (OMP) algorithm, and finally the sparse imaging is obtained by multiplying it with the sparse dictionary. However, the correlation between the front and back sparse coefficient vector elements is not utilized in the signal reconstruction process, so the obtained wall image is a discontinuous strip with inconspicuous contour characteristics and poor focus.…”

Section: Introductionmentioning

confidence: 99%

Study on the application of multi-angle imaging related technology in the construction process

Gao

2023

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

The mufti-angle imaging technique is proposed to address the wall position offset and the side flaps and gate flaps caused by the sparse array in the ultra-wide band through-wall radar building layout imaging, using the characteristic that the azimuth upward distance profile is similar around the main flap but different around the side flap/gate flap. Firstly, after the backward projection algorithm obtains the wall image of each viewpoint, the mufti-directional two-dimensional matching filter is used to enhance the image of each viewpoint and eliminate the effect of side flaps and raster flaps. Then the images of each viewpoint are decomposed by combining the multistage transform, i.e., the non-down sampling contour let transform, and the obtained low-frequency components and high-frequency components are fused using the corresponding fusion rules, respectively. Finally, the final fused building layout image is obtained by non-down sampling contour let inverse transform. The simulation experimental data show that the running time of the method in this paper is 10.99s. It shows that the proposed method enhances the outline and detail information of the building wall, and the final fused image obtained has prominent wall image, clearer edge contours, and good retention of overall detail information. The quality of image fusion is greatly improved than other methods, which paves the way for subsequent fusion methods including chatterers such as construction building corners and windows and doors.

show abstract

Machine learning for buildings’ characterization and power-law recovery of urban metrics

Cited by 7 publications

References 30 publications

Estimating urban seismic damages and debris at the building-level: Application to the city of Beirut, Lebanon

Estimating urban seismic damages and debris at the building-level: Application to the city of Beirut, Lebanon

Exploring Resampling Techniques in Credit Card Default Prediction

Study on the application of multi-angle imaging related technology in the construction process

Contact Info

Product

Resources

About