Exploring the role of deep neural networks for post-disaster decision support

2020 | Decision Support Systems | Citations: 0

Authors: Chaudhuri, Neha; Bose, Indranil

Abstract: Disaster management operations are information intensive activities due to high ... Expand

Abstract: Disaster management operations are information intensive activities due to high uncertainty and complex information needs. Emergency response planners need to effectively plan response activities with limited resources and assign rescue teams to specific disaster sites with high probability of survivors swiftly. Decision making becomes tougher since the limited information available is heterogenous, untimely and often fragmented. We address the problem of lack of insightful information of the disaster sites by utilizing image data obtained from smart infrastructures. We collect geo-tagged images from earthquake-hit regions and apply deep learning method for classification of these images to identify survivors in debris. We find that deep learning method is able to classify the images with significantly higher accuracy than the conventionally used machine learning methods for image classification and utilizes significantly lesser time and computational resources. The novel application of image analytics and the resultant findings from our models have valuable implications for effective disaster response operations, especially in smart urban settlements. Collapse

Topics: earthquake emergency management natural hazard database system decision support system

Methods: support vector machine machine learning deep learning literature study robustness check

Application of Image Analytics for Disaster Response in Smart Cities

2019 | HICSS | Citations: 1

Authors: Chaudhuri, Neha; Bose, Indranil

Abstract: Post-disaster, city planners need to effectively plan response activities and as ... Expand

Abstract: Post-disaster, city planners need to effectively plan response activities and assign rescue teams to specific disaster zones quickly. We address the problem of lack of accurate information of the disaster zones and existence of human survivors in debris using image analytics from smart city data. Innovative usage of smart city infrastructure is proposed as a potential solution to this issue. We collected images from earthquake-hit smart urban environments and implemented a CNN model for classification of these images to identify human body parts out of the debris. TensorFlow backend (using Keras) was utilized for this classification. We were able to achieve 83.2% accuracy from our model. The novel application of image data from smart city infrastructure and the resultant findings from our model has significant implications for effective disaster response operations, especially in smart cities. Collapse

Topics: smart city earthquake emergency management Google+ database system

Methods: machine learning TensorFlow Keras convolutional neural network deep learning

An IoT Software Architecture for an Evacuable Building Architecture

2019 | HICSS | Citations: 0

Authors: Muccini, Henry; Arbib, Claudio; Davidsson, Paul; Moghaddam, Mahyar T

Abstract: This paper presents a computational component designed to improve and evaluate e ... Expand

Abstract: This paper presents a computational component designed to improve and evaluate emergency handling plans. In real-time, the component operates as the core of an Internet of Things (IoT) infrastructure aimed at crowd monitoring and optimum evacuation paths planning. In this case, a software architecture facilitates achieving the minimum time necessary to evacuate people from a building. In design-time, the component helps discovering the optimal building dimensions for a safe emergency evacuation, even before (re-) construction of a building. The space and time dimension are discretized according to metrics and models in literature. The component formulates and solves a linearized, time-indexed flow problem on a network that represents feasible movements of people at a suitable frequency. The CPU time to solve the model is compliant with real-time use. The application of the model to a real location with real data testifies the model capability to optimize the safety standards by small changes in the building dimensions, and guarantees an optimal emergency evacuation performance. Collapse

Topics: mobile system internet of things Microsoft Windows earthquake radio frequency identification

Methods: simulation computational algorithm experiment case study

An Embedding Based IR Model for Disaster Situations

2018 | Information Systems Frontiers | Citations: 4

Authors: Bandyopadhyay, Ayan; Ganguly, Debasis; Mitra, Mandar; Saha, Sanjoy Kumar; Jones, Gareth J.F.

Abstract: Twitter (http://twitter.com) is one of the most popular social networking platfo ... Expand

Abstract: Twitter (http://twitter.com) is one of the most popular social networking platforms. Twitter users can easily broadcast disaster-specific information, which, if effectively mined, can assist in relief operations. However, the brevity and informal nature of tweets pose a challenge to Information Retrieval (IR) researchers. In this paper, we successfully use word embedding techniques to improve ranking for ad-hoc queries on microblog data. Our experiments with the ‘Social Media for Emergency Relief and Preparedness’ (SMERP) dataset provided at an ECIR 2017 workshop show that these techniques outperform conventional term-matching based IR models. In addition, we show that, for the SMERP task, our word embedding based method is more effective if the embeddings are generated from the disaster specific SMERP data, than when they are trained on the large social media collection provided for the TREC (http://trec.nist.gov/) 2011 Microblog track dataset. Collapse

Topics: Twitter information retrieval microblog social media earthquake

Methods: word embedding word2vec Okapi BM25 experiment language model

CrisMap: a Big Data Crisis Mapping System Based on Damage Detection and Geoparsing

2018 | Information Systems Frontiers | Citations: 9

Authors: Avvenuti, Marco; Cresci, Stefano; Del Vigna, Fabio; Fagni, Tiziano; Tesconi, Maurizio

Abstract: Natural disasters, as well as human-made disasters, can have a deep impact on wi ... Expand

Abstract: Natural disasters, as well as human-made disasters, can have a deep impact on wide geographic areas, and emergency responders can benefit from the early estimation of emergency consequences. This work presents CrisMap, a Big Data crisis mapping system capable of quickly collecting and analyzing social media data. CrisMap extracts potential crisis-related actionable information from tweets by adopting a classification technique based on word embeddings and by exploiting a combination of readily-available semantic annotators to geoparse tweets. The enriched tweets are then visualized in customizable, Web-based dashboards, also leveraging ad-hoc quantitative visualizations like choropleth maps. The maps produced by our system help to estimate the impact of the emergency in its early phases, to identify areas that have been severely struck, and to acquire a greater situational awareness. We extensively benchmark the performance of our system on two Italian natural disasters by validating our maps against authoritative data. Finally, we perform a qualitative case-study on a recent devastating earthquake occurred in Central Italy. Collapse

Topics: Twitter earthquake Wikipedia natural hazard big data

Methods: natural language processing word embedding case study support vector machine experiment

Effective Use of Twitter Data in Crisis Management: The Challenge of Harnessing Geospatial Data

2018 | Americas Conference on Information Systems | Citations: 0

Authors: Bonaretti, Dario

Abstract: Could a Tweet save a life? The attention that public agencies and IS research ha ... Expand

Abstract: Could a Tweet save a life? The attention that public agencies and IS research have been dedicating to social media analysis in the last ten years seem to assume it could. Not only IS research in crisis-management is deeply oriented to harness the power of social media analysis, but public agencies are also following on this wave of enthusiasm for information extraction from social media (Twitter in particular). Our paper is an attempt to challenge some of the assumptions behind the ability to use crisis-related information on social media effectively, in particular, geospatial data. In particular, we suggest that current estimates about the volume of georeferenced data might be overoptimistic and ~35% of the georeferenced might not be precise enough to be used effectively in crises response initiatives such as localizing victims in the aftermath of an earthquake. Collapse

Topics: Twitter social network emergency management earthquake geographic information system

Methods: literature study literature sample

Theories: representation theory

On Combining Partial and Incompatible Information in E-negotiation and E-arbitration

2008 | Group Decision and Negotiation | Citations: 0

Authors: Andrýsek, Josef; Bodini, Antonella; Kárný, Miroslav; Kracík, Jan; Ruggeri, Fabrizio

Abstract: The complexity of the problems to be addressed in an e-democracy framework and t ... Expand

Abstract: The complexity of the problems to be addressed in an e-democracy framework and the variety of involved stakeholders, with different backgrounds, views and access to information sources, lead us to consider the case in which an e-negotiation should be performed among subjects who have partial, sometimes incompatible, information and can hardly gather to discuss issues together, under the supervision of a facilitator. We propose a statistical method which addresses the issue of partial and incompatible information, merging it and then using it to get a final decision, possibly in an automatic way, through processes of e-negotiation and e-arbitration. Collapse

Topics: negotiation support system earthquake internet technology

Methods: computational algorithm experiment