IoT Flows: A Network Flow Model Application to Building Evacuation

Arbib, Claudio; Moghaddam, Mahyar Tourchi; Muccini, Henry

doi:10.1007/978-3-030-25842-9_9

Cited by 11 publications

(6 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• the definition of the GisToGraph algorithm to generate an enriched underlining network of any location, specifically tailored to include useful information for disaster management, especially in the preparedness, response and reconstruction phases. • the adaptation and validation of the optimization model developed by [10] to a real outdoor case study, i.e, the historical city centre of L'Aquila in Italy, for emergency evacuation purposes. • Reconstruction planning of damaged buildings and physical dependencies during post-disaster situation in damaged area by using double deep Q-network (DDQN) learning algorithm.…”

Section: Discussionmentioning

confidence: 99%

“…Different from other similar algorithms, we are able to manage additional information, needed for evacuation planning and reconstruction, added as attributes to network nodes and arcs. Concerning the evacuation planning model, we adapted the linear optimization model originally developed by Arbib et al [10] for the evacuation of the interior of a building. The model had to be customized with respect to several parameters, and re-scaled to the network of several orders of magnitude.…”

Section: Discussionmentioning

confidence: 99%

“…To generate the emergency evacuation plan that minimizes the total evacuation time while maximizing the number of evacuees evacuated to safety, we adapted the linear optimization model originally developed by [10] for building evacuation. The model was then calibrated with respect to several parameters and re-scaled to the network of several orders of magnitude.…”

Section: B Evacuation Planningmentioning

confidence: 99%

“…With reference to the earlier works of [13], [10] and [25] where a discrete-time network stock-and-flow model is devised to find, at increasing time slots τ , the maximum amount of people that can be evacuated within τ to a given set of safe areas. The model starts with a static oriented network G = (N, A) obtained from the graph G D generated by the GisToGraph algorithm by suitably embedding the city streets into a set N of elementary cells; the arcs in A connect geometrically adjacent cells in both directions.…”

Section: ) Dynamic Maximum Flow Modelingmentioning

confidence: 99%

“…Political priority is associated with every reconstruction unit, it describes political importance for a specific strategy, and it is modeled as an integer in the interval [1,10]. If the maximum integer is associated with any building, it represents that the building is the most important concerning political strategies.…”

Section: ) Social Benefitsmentioning

confidence: 99%

See 4 more Smart Citations

Toward Effective Response to Natural Disasters: A Data Science Approach

et al. 2021

Self Cite

View full text Add to dashboard Cite

Natural disasters can cause widespread damage to buildings and infrastructures and kill thousands of living beings. These events are difficult to be overcome both by the populations and by government authorities. Two challenging issues require in particular to be addressed: find an effective way to evacuate people first, and later to rebuild houses and other infrastructures. An adequate recovery strategy to evacuate people and start reconstructing damaged areas on a priority basis can then be a game changer allowing to overcome effectively those terrible circumstances. In this perspective, we here present DiReCT, an approach based on i) a dynamic optimization model designed to timely formulate an evacuation plan of an area struck by an earthquake, and ii) a decision support system, based on double deep Q Network, able to guide efficiently the reconstruction the affected areas. The latter works by considering both the resources available and the needs of the various stakeholders involved (e.g., residents social benefits and political priorities). The ground on which both the above solutions stand was a dedicated geographical data extraction algorithm, called "GisToGraph", especially developed for this purpose. To check applicability of the whole approach, we dovetailed it on the real use-case of the historical city center of L'Aquila (Italy) using detailed GIS data and information on urban land structure and buildings vulnerability. Several simulations were run on the underlining network generated. First, we ran experiments to safely evacuate in the shortest possible time as many people as possible from an endangered area towards a set of safe places. Then, using DDQN, we generated different reconstruction plans and selected the best ones considering both social benefits and political priorities of the building units. The described approaches are comprised in a more general data science framework delved to produce an effective response to natural disasters.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: B Evacuation Planningmentioning

confidence: 99%

Section: ) Dynamic Maximum Flow Modelingmentioning

confidence: 99%

Section: ) Social Benefitsmentioning

confidence: 99%

See 3 more Smart Citations