Dataset Information

Deep learning for bridge load capacity estimation in post-disaster and -conflict zones.

ABSTRACT: Many post-disaster and post-conflict regions do not have sufficient data on their transportation infrastructure assets, hindering both mobility and reconstruction. In particular, as the number of ageing and deteriorating bridges increases, it is necessary to quantify their load characteristics in order to inform maintenance and asset databases. The load carrying capacity and the design load are considered as the main aspects of any civil structures. Human examination can be costly and slow when expertise is lacking in challenging scenarios. In this paper, we propose to employ deep learning as a method to estimate the load carrying capacity from crowdsourced images. A convolutional neural network architecture is trained on data from over 6000 bridges, which will benefit future research and applications. We observe significant variations in the dataset (e.g. class interval, image completion, image colour) and quantify their impact on the prediction accuracy, precision, recall and F1 score. Finally, practical optimization is performed by converting multiclass classification into binary classification to achieve a promising field use performance.

SUBMITTER: Pamuncak A

PROVIDER: S-EPMC6936281 | biostudies-literature | 2019 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep learning for bridge load capacity estimation in post-disaster and -conflict zones.

Pamuncak Arya A Guo Weisi W Soliman Khaled Ahmed A Laory Irwanda I

Royal Society open science 20191204 12

Many post-disaster and post-conflict regions do not have sufficient data on their transportation infrastructure assets, hindering both mobility and reconstruction. In particular, as the number of ageing and deteriorating bridges increases, it is necessary to quantify their load characteristics in order to inform maintenance and asset databases. The load carrying capacity and the design load are considered as the main aspects of any civil structures. Human examination can be costly and slow when ...[more]

PMID: 31903194

Similar Datasets

Project description:In the context of the 2016 Peace Agreement signed between the Colombian government and the FARC-EP (Fuerzas Armadas Revolucionarias de Colombia-Ejército del Pueblo), several challenges for society and academia have emerged: (1) overcoming the gap between the rural and urban settings, which has been one of the roots of the Colombian armed conflict, and (2) training psychologists and transforming traditional educational practices, which have not been designed to fulfill community needs in a post-conflict setting. One of the strategies from academia to overcome these difficulties is to create alliances with rural communities where students learn key competences to foster a horizontal approach while actively working with the community. In the region of Caquetá, Colombia, two Territorial Spaces for Training and Reincorporation (ETCR) were created in order to provide a space for former guerrilla members' reintegration to civil society. In the ETCR Héctor Ramírez, 27 students and two faculty participated in a service-learning project (2 weeks in December 2018 and two in June 2019) where they engaged in local daily practices and social projects based on the community's prioritized needs. The aim of this study was to analyze the learning process of undergraduate psychology students in this community psychology service-learning project in the context of peacebuilding in Colombia. This study is grounded in a Participatory Action Research (PAR) approach and data collected include reflective narratives and video diaries by students before and during the course, and two focus groups after the experience. Findings suggest that students who participated in the experience are in the process of developing cultural humility, through affective understandings and the consolidation of communities of practice that include the former guerrilla members and their knowledges. Preparing psychologists to lead peacebuilding and reconciliation processes is of importance to the field because the professional competencies gained in this context surpass the professional practice as they become part of the students' abilities as citizens. The social impact is twofold: the students learn to create partnerships where purposes are co-constructed and trust-based, while the community takes the lead of their processes creating alliances with an academia that recognizes their knowledge and practices.

Dataset Information

Deep learning for bridge load capacity estimation in post-disaster and -conflict zones.

Publications

Deep learning for bridge load capacity estimation in post-disaster and -conflict zones.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure