Dataset Information

Interpreting the socio-technical interactions within a wind damage-artificial neural network model for community resilience.

ABSTRACT: The use of machine learning has grown in popularity in various disciplines. Despite the popularity, the apparent 'black box' nature of such tools continues to be an area of concern. In this article, we attempt to unravel the complexity of this black box by exploring the use of artificial neural networks (ANNs), coupled with graph theory, to model and interpret the spatial distribution of building damage from extreme wind events at a community level. Structural wind damage is a topic that is mostly well understood for how wind pressure translates to extreme loading on a structure, how debris can affect that loading and how specific social characteristics contribute to the overall population vulnerability. While these themes are widely accepted, they have proven difficult to model in a cohesive manner, which has led primarily to physical damage models considering wind loading only as it relates to structural capacity. We take advantage of this modelling difficulty to reflect on two different ANN models for predicting the spatial distribution of structural damage due to wind loading. Through graph theory analysis, we study the internal patterns of the apparent black box of artificial intelligence of the models and show that social parameters are key to predict structural damage.

SUBMITTER: Pilkington SF

PROVIDER: S-EPMC7735332 | biostudies-literature | 2020 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Interpreting the socio-technical interactions within a wind damage-artificial neural network model for community resilience.

Pilkington Stephanie F SF Mahmoud Hussam N HN

Royal Society open science 20201118 11

The use of machine learning has grown in popularity in various disciplines. Despite the popularity, the apparent 'black box' nature of such tools continues to be an area of concern. In this article, we attempt to unravel the complexity of this black box by exploring the use of artificial neural networks (ANNs), coupled with graph theory, to model and interpret the spatial distribution of building damage from extreme wind events at a community level. Structural wind damage is a topic that is most ...[more]

PMID: 33391792

Similar Datasets

Project description:Anode-associated multispecies exoelectrogenic biofilms are essential for the function of bioelectrochemical systems (BESs). The individual activities of anode-associated organisms and physiological responses resulting from coculturing are often hard to assess due to the high microbial diversity in these systems. Therefore, we developed a model multispecies biofilm comprising three exoelectrogenic proteobacteria, Shewanella oneidensis, Geobacter sulfurreducens, and Geobacter metallireducens, with the aim to study in detail the biofilm formation dynamics, the interactions between the organisms, and the overall activity of an exoelectrogenic biofilm as a consequence of the applied anode potential. The experiments revealed that the organisms build a stable biofilm on an electrode surface that is rather resilient to changes in the redox potential of the anode. The community operated at maximum electron transfer rates at electrode potentials that were higher than 0.04 V versus a normal hydrogen electrode. Current densities decreased gradually with lower potentials and reached half-maximal values at -0.08 V. Transcriptomic results point toward a positive interaction among the individual strains. S. oneidensis and G. sulfurreducens upregulated their central metabolisms as a response to cultivation under mixed-species conditions. G. sulfurreducens was detected in the planktonic phase of the bioelectrochemical reactors in mixed-culture experiments but not when it was grown in the absence of the other two organisms.IMPORTANCE In many cases, multispecies communities can convert organic substrates into electric power more efficiently than axenic cultures, a phenomenon that remains unresolved. In this study, we aimed to elucidate the potential mutual effects of multispecies communities in bioelectrochemical systems to understand how microbes interact in the coculture anodic network and to improve the community's conversion efficiency for organic substrates into electrical energy. The results reveal positive interactions that might lead to accelerated electron transfer in mixed-species anode communities. The observations made within this model biofilm might be applicable to a variety of nonaxenic systems in the field.

Project description:BackgroundThe introduction of a new method of transmitting prescriptions from general practices to community pharmacies in England (Electronic Prescription Service Release 2 (EPS2)) has generated debate on how it will change work practice. As EPS2 will be a key technical element in dispensing, we reviewed the literature to find that there were no studies on how social and technical elements come together to form work practice in community pharmacies. This means the debate has little point of reference. Our aim therefore was to study the ways social and technical elements of a community pharmacy are used to achieve dispensing through the development of a conceptual model on pharmacy work practice, and to consider how a core technical element such the EPS2 could change work practice.MethodWe used ethnographic methods inclusive of case-study observations and interviews to collect qualitative data from 15 community pharmacies that were in the process of adopting or were soon to adopt EPS2. We analysed the case studies thematically and used rigorous multi-dimensional and multi-disciplinary interpretive validation techniques to cross analyse findings.ResultsIn practice, dispensing procedures were not designed to take into account variations in human and technical integration, and assumed that repetitive and collective use of socio-technical elements were at a constant. Variables such as availability of social and technical resources, and technical know-how of staff were not taken into account in formalised procedures. Yet community pharmacies were found to adapt their dispensing in relation to the balance of social and technical elements available, and how much of the social and technical elements they were willing to integrate into dispensing. While some integrated as few technical elements as possible, some depended entirely on technical artefacts. This pattern also applied to the social elements of dispensing. Through the conceptual model development process, we identified three approaches community pharmacies used to appropriate procedures in practice. These were 'technically oriented', 'improvising' or 'socially oriented'.ConclusionWe offer a model of different work approaches community pharmacies use to dispense, which suggests that when adopting a core technical element such as the EPS2 system of dispensing there could be variations in its successful adoption. Technically oriented pharmacies might find it easiest to integrate a similar artefact into work practice although needs EPS2 to synchronise effectively with existing technologies. Pharmacies adopting an improvising-approach have the potential to improve how they organise dispensing through EPS2 although they will need to improve how they apply their operating procedures. Socially oriented pharmacies will need to dramatically adapt their approach to dispensing since they usually rely on few technical tools.

Dataset Information

Interpreting the socio-technical interactions within a wind damage-artificial neural network model for community resilience.

Publications

Interpreting the socio-technical interactions within a wind damage-artificial neural network model for community resilience.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets