Estimation Method for Roof‐damaged Buildings from Aero-Photo Images During Earthquakes Using Deep Learning

2023 | Information Systems Frontiers | Citations: 0

Authors: Fujita, Shono; Hatayama, Michinori

Abstract: Issuing a disaster certificate, which is used to decide the contents of a victim ... Expand

Abstract: Issuing a disaster certificate, which is used to decide the contents of a victim’s support, requires accuracy and rapidity. However, in Japan at large, issuing of damage certificates has taken a long time in past earthquake disasters. Hence, the government needs a more efficient mechanism for issuing damage certificates. This study developed an estimation system of roof-damaged buildings to obtain an overview of earthquake damage based on aero-photo images using deep learning. To provide speedy estimation, this system utilized the trimming algorithm, which automatically generates roof image data using the location information of building polygons on GIS (Geographic Information System). Consequently, the proposed system can estimate, if a house is covered with a blue sheet with 97.57 % accuracy and also detect whether a house is damaged, with 93.51 % accuracy. It would therefore be worth considering the development of an image recognition model and a method of collecting aero-photo data to operate this system during a real earthquake. Collapse

Topics: earthquake database system geographic information system

Methods: computational algorithm deep learning machine learning experiment survey

Multi-Channel Convolutional Neural Network for the Identification of Eyewitness Tweets of Disaster

2023 | Information Systems Frontiers | Citations: 0

Authors: Kumar, Abhinav; Singh, Jyoti Prakash; Rana, Nripendra P.; Dwivedi, Yogesh K.

Abstract: During a disaster, a large number of disaster-related social media posts are wid ... Expand

Abstract: During a disaster, a large number of disaster-related social media posts are widely disseminated. Only a small percentage of disaster-related information is posted by eyewitnesses. The post of a disaster eyewitness offers an accurate depiction of the disaster. Therefore, the information posted by the eyewitness is preferred over the other source of information as it is more effective at helping organize rescue and relief operations and potentially saving lives. In this work, we propose a multi-channel convolutional neural network (MCNN) that uses three different word-embedding vectors together to classify disaster-related tweets into eyewitness, non-eyewitness, and don’t know classes. We compared the performance of the proposed multi-channel convolutional neural network with several attention-based deep-learning models and conventional machine learning-models such as recurrent neural network, gated recurrent unit, Long-Short-Term-Memory, convolutional neural network, logistic regression, support vector machine, and gradient boosting. The proposed multi-channel convolutional neural network achieved an F1-score of 0.84, 0.88, 0.84, and 0.86 with four disaster-related datasets of floods, earthquakes, hurricanes, and wildfires, respectively. The experimental results show that the training MCNN model with different word embedding together performs better than the conventional machine-learning models and several other deep-learning models. Collapse

Topics: Twitter earthquake hurricane crowdsourcing social media

Methods: machine learning deep learning convolutional neural network experiment GloVe

The strategic value of IT-enabled self-organised collectives during crises

2023 | Journal of Strategic Information Systems | Citations: 0

Authors: Morton, Josh; Zorina, Aljona; Kudaravalli, Sri

Abstract: There is a promising body of work pertaining to the strategic value of IT-enable ... Expand

Abstract: There is a promising body of work pertaining to the strategic value of IT-enabled self-organised collectives in times of crisis. This area is of significant theoretical and practical importance. Yet, we still have little systematic knowledge about precisely how self-organised collectives contribute during crises and how the value of their contributions might be leveraged strategically. To address this, we develop a model to demonstrate four dimensions across which self-organised collectives create strategic value: (i) information sharing value; (ii) collective resourcemobilisation value; (iii) network value; and (iv) generative value. In doing so, we reveal more about the specific capabilities of self-organised collectives, and we use these insights to develop implications for theory. We conclude by outlining an agenda to encourage and accelerate future research on the role of IT-enabled self-organised collectives during crises. Collapse

Topics: information exchange database system emergency management unintended consequence problem solving

Methods: theory development literature sample literature study synthesis

Digital Interoperability: In-Situ Adaptation in Natural Crisis Responses

2023 | International Conference on Information Systems | Citations: 0

Authors: Sandhyaduhita, Puspa; Tan, Chuan Hoo; Sutanto, Juliana

Abstract: Essential to effective and efficient collaboration among natural crisis respond ... Expand

Abstract: Essential to effective and efficient collaboration among natural crisis responders is the fast and ample crisis-related data, including victims' data (e.g., their locations and needs). However, the reality often falls short of it because the responders deployed by different crisis response agencies using various digital forms result in an incomplete and delayed view of crisis information. Attempts to enforce a unified digital form proposed by a leading agency or the pre-developed one co-created by several agencies had been made but failed. This research, based mainly on qualitative data collected, proposes an adaptability-by-bricolage approach of a digital interoperability solution for immediate digital collaboration among crisis responders during the crisis response. Preliminary findings that holistically define the solution are discussed. Collapse

Topics: sensemaking user experience computer supported cooperative work logistics management WhatsApp

Methods: qualitative interview design science design artifact constant comparative analysis personal interview

Theories: theory of affordance

Institutional Disruptions and the Philanthropy of Multinational Firms

2022 | Organization Science | Citations: 0

Authors: Ballesteros, Luis; Magelssen, Catherine

Abstract: This paper studies philanthropy by multinational enterprises (MNEs) during insti ... Expand

Abstract: This paper studies philanthropy by multinational enterprises (MNEs) during institutional disruptions—the sudden and unexpected, temporary, and systemic breakdowns in market-oriented institutions. The central argument is that, under institutional disruptions, MNEs aim to restore factors that are essential for the market to function, such as infrastructure and labor markets, and the strength of the market restoration motive is positively associated with the economic importance of the affected country to the MNE. Analyses of donations from 2,000 MNEs headquartered in 63 countries in the aftermath of 265 major epidemics, natural disasters, and terrorist attacks affecting 129 countries suggest that the economic importance of the country to the firm strongly explains donations. Country market concentration, public aid, and the country’s regulatory quality moderate this effect. These associations are robust to a matching method; a vector of firm-, country-, and event-specific time-varying and -constant variables; and alternative motives, such as reputation, altruism, media salience, market standing, and poverty-gap avoidance. They offer evidence that company philanthropy in the aftermath of institutional disruptions may deviate from predicted behavior under stable conditions. Particularly, the findings contest the expectation that philanthropy rises in market competition. Monopolistic firms are comparatively large donors and may act as an economic stop-loss mechanism during large disruptions. Collapse

Topics: database system terrorist incident pandemic missing data earthquake

Methods: qualitative interview descriptive statistic natural language processing theory development robustness check

Theories: theory of economic fluctuations

A simulation-based decision support tool for dynamic post-disaster pedestrian evacuation

2022 | Decision Support Systems | Citations: 0

Authors: Chang, Kuo-Hao; Wu, Ying-Zheng; Ke, Siao-Syun

Abstract: Taiwan, located in the Pacific Ring of Fire, is highly vulnerable to the destruc ... Expand

Abstract: Taiwan, located in the Pacific Ring of Fire, is highly vulnerable to the destructive impact of powerful earth­ quakes. When a massive earthquake occurs, failure to take proper measures can lead to massive casualties, collapse of public facilities, and disruption to traffic networks. Among the many post-disaster management strategies, efficient evacuation is absolutely critical as it can potentially reduce the number of casualties sub­ stantially. At present, most post-disaster evacuation decisions are made based on past experience, but the rarity of high-magnitude earthquakes impedes the rate at which the quality of the decision-making process can improve. As such, this study primarily aims to develop an efficient and credible evacuation simulation modeling framework which can be used as a powerful tool to bolster evacuation strategies. The simulation evacuation framework we propose is known as the Stochastic Pedestrian Cell Transmission Model (SPCTM). The model is built based on real data of the mapping of roads and emergency shelters in an urban environment, as well as predictive models of pedestrian flow, the number of people needed to be evacuated after an earthquake, and the impact of earthquakes on urban infrastructure. Much of the data is provided by the Taiwan Earthquake Impact Research and Information Application platform (TERIA) developed by the National Science and Technology Center for Disaster Reduction (NCDR). Applying this data, the model divides the traffic network into a cellular structure, applies the concepts of inflow and outflow to represent population movement and uses random var­ iables to simulate the selection behavior of pedestrian agents. In addition to SPCTM, we propose an alternative model which makes slight modifications to SPCTM to offer users a complementary framework in which evacuees are armed with less ideal information about the evacuation situation. An empirical study is run in a district of Taipei, Taiwan based on a simulated earthquake of magnitude 6.5 in which the overall and moment-by-moment simulation evacuation process is presented. The use of SPCTM as a simulation evacuation model is compared to the current government evacuation policy in Taiwan. Further potential benefits of using the proposed simulation evacuation tool are numerous. For example, the frameworks proposed in this study can offer valuable insights to policy-makers on infrastructure design decisions and evacuation strategies before an earthquake occurs, including the best placement of relief centers, to potentially significantly reduce the number of casualties. Also, simulation results can be utilized after a disaster to assist in crucial decisions related to road restoration prior­ ities, distribution of supplies to shelters, etc. Collapse

Topics: earthquake mobile system broadband cellular network decision support system decision support

Methods: simulation parametric test descriptive statistic computational algorithm agent based simulation

Beyond Spatial Proximity: The Impact of Enhanced Spatial Connectedness from New Bridges on Entrepreneurship

2022 | Organization Science | Citations: 0

Authors: Dutta, Sunasir; Armanios, Daniel Erian; Desai, Jaison D.

Abstract: Various strands of work have explored how spatial proximity helps (metaphoricall ... Expand

Abstract: Various strands of work have explored how spatial proximity helps (metaphorically) bridge barriers to resource mobilization and foster knowledge transfer. However, much of that work takes spatial connectedness as a given. We argue that spatial connectedness is a distinct construct that affects the extent to which spaces are not just proximate but are actually able to link people, ideas, resources, and knowledge together. We explore one such source of connectedness—physical (not metaphorical) bridges. We find that the opening of newly built bridges enhances startup founding in the local geographic community. Beyond their impact on startup founding, newly built bridges also influence the organizing process for such ventures. This includes a positive impact on the entry of prospective founders into entrepreneurship and an increase in the number of early-stage investors. The subsequently founded ventures are also more likely to engage in recombination and to cross industry boundaries. We explore scope conditions around industry and connective heterogeneity. We also test for robustness to various modeling approaches. The discussion highlights contributions of these findings to the study of entrepreneurship, as well as of organizations and the institutional fields in which they operate. Collapse

Topics: entrepreneurship innovation management knowledge sharing knowledge spillover economic surplus

Methods: robustness check hierarchical linear modeling archival research statistical hypothesis test instrumental variables estimation

Theories: institutional theory sociomaterialism theory organizational theory theory of economic booms

The Role of Information Technologies in Crises: A Review and Conceptual Development of IT-Enabled Agile Crisis Management

2022 | Communications of the Association for Information Systems | Citations: 0

Authors: Lee, One-Ki (Daniel); Jiang, Shan; Hyun, Youyung; Jeong, Hyein

Abstract: There has been a growing concern about crises such as natural disasters and epi ... Expand

Abstract: There has been a growing concern about crises such as natural disasters and epidemics that cause severe damage to the society and economy. For effective management of such crises, agility has been discussed as a vital capability to enable the responding organizations to react to the crises with speed and flexibility. Although IT has received great attention as a media and infrastructure during crises, our understanding of the role of IT in agile crisis management remains very limited. To fill this gap, we first conducted a systematic literature review on the role of IT in crises. We identified a total of 11,390 published journal articles relevant to natural disasters and epidemics during the last 20 years using text mining techniques and analyzed which categories of IT have been used in crisis management and how their relative importance has evolved. Next, based on the conceptual foundation built through our literature review and the theoretical perspective of agility, we propose a framework of IT-enable agile crisis management that conceptualizes how various information technologies facilitate the agile crisis management processes. Based on our systematic literature review and the theoretical development, this study suggests future research directions and approaches to IS literature. Volume 5010.17705/1CAIS.05038 Paper 38terms and relevant articles that directly discuss the role of IT in various crisis events. In this qualitative review process, we form our conceptual foundation to categorize the information technologies that are relevant to crisis management and to determine the relevant keywords for each IT category. Based on the conceptual foundation and the keywords for each IT category, i.e., seed keywords, we conduct a quantitative literature review. From a public journal database, in particular, we access a large body of journal articles relating to disasters and epidemics published during 2000-2019 and identify the articles directly involving the role of specific information technologies in either natural disasters or epidemics using text mining techniques Liu et al., 2008). The articles are analyzed using quantitative approaches, and the results are discussed from various angles such as IT category, yearly trend, and involvement of IS research.Next, based on our qualitative and quantitative literature review results as well as the theoretical perspective of organizational agilitya dynamic capability to sense and respond to environmental changes with speed and flexibility (Dove, 1992;Lee et al., 2015;Overby et al., 2006;Sambamurthy et al., 2003), we develop a theoretical framework of IT-enabled agile crisis management, which consists of two agile processessensing and respondingand the time horizon of short-term and long-term. Our framework conceptualizes the distinct roles of IT in the different crisis management processes such as emergent detection and action in the short-term, and anticipation and strategic implementation with plans in the long-term. For example, the real-time data sensing and analysis from the pre-installed surveillance sensor network or IoT devices will be a key capability of IT-enabled agile crisis management for the short term. In addition, instant social feeding and sharing will be another crucial component for communitybased disaster response in the short term. On the other hand, continuous data generation, accumulation, and predictive data analytics would be the key capabilities for the long term. Our theoretical framework is then validated using two prior crisis cases. Collapse

Topics: emergency management pandemic information system use natural hazard social media

Methods: literature study structured literature research term frequency–inverse document frequency theory development natural language processing

Theories: dynamic capabilities theory

Towards a Model for Building Information Awareness in Crisis Situations

2022 | Americas Conference on Information Systems | Citations: 0

Authors: Meesters, Kenny; Ou, Carol; Alexiou, Andreas

Abstract: In crisis situations access to information is key to reduce uncertainty and ena ... Expand

Abstract: In crisis situations access to information is key to reduce uncertainty and enable effective decision making. With the advent of modern information technologies there is an abundance of possibilities to obtain, process, and share information. The number of actors that can potentially provide information has grown concomitantly. The challenge therefore is no longer the availability of information but rather the ability to find and connect with actors providing information in a volatile and dynamic environment. This requires of organizations to be aware of the actors and their information potential, and actively build informational awareness. In this paper we propose a model for the development of the awareness of organizations of the information landscape during critical events. We validate this model using two case studies and extract key factors that contribute to the challenges and success of leveraging information potential of actors in a crisis. Collapse

Topics: information management earthquake covid 19 decision making information exchange

Methods: qualitative interview case study archival research conceptual modelling maturity model

Developing an Adaptive Building Evacuation Simulation and Decision Support Framework using Cognitive Agent-Based Modelling

2022 | HICSS | Citations: 0

Authors: Rollan, Therese Anne; Marquez, Leorey; Chua, Caslon

Abstract: Preparing for an unprecedented event involving the movement of populations could ... Expand

Abstract: Preparing for an unprecedented event involving the movement of populations could take up large amounts of resources if done conventionally. The main motivation of this study is the behavioural modification approach which is an underexplored potential in evacuation dynamics, offering new possibilities in terms of practicality and ease of implementation. This paper tackles an adaptive building evacuation simulation and decision support framework that will serve as a guide to evaluate and propose evacuation strategies for disaster management researchers and decision-making authorities. The framework mainly involves the formulation of the cognitive agent model, the evacuation simulation, and the decision support. The timeliness in the Philippine context of the long-overdue “Big One” earthquake, the vulnerability of the case study, and the capability of the framework to be a standard guide where components can be customized by users based on the disaster type and site-specific requirements make this research a significant undertaking. Collapse

Topics: decision support earthquake decision making personality emergency management

Methods: simulation survey structural equation modeling case study cluster analysis