Sebastian Schmitz, Lennart Landsberg, Tim Brüstle, Johannes Weinem, & Ompe Aimé Mudimu. (2018). Evaluation of a flying localization system for the rescue of buried victims – A scenario based training approach. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (pp. 1143–1147). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: The objective of this study was to develop various scenarios for evaluating an unmanned aerial vehicle that is developed for the localization of buried people after a building collapse. To test their concept of implementing this system into the command structure of organized first response the authors plan to carry out a tabletop exercise in laboratory scale and a large-scale exercise. Scenario based training is used as methodic approach for these exercises. To develop realistic scenarios, relevant national and international organizations and their requirements have been identified. Also, the requirements of the localization system have been taken into account. Furthermore, real incidents have been analyzed and their match with the requirements has been verified. As result one national and one international scenario, based on real incidents, are developed.
|
Shada Alsalamah, Hessah Alsalamah, Jaziar Radianti, Sakher Alqahtani, Thamer Adnan Nouh, Mohamed Abomhara, et al. (2018). Information Requirements for Disaster Victim Identification and Emergency Medical Services:Hajj Crowd Disaster Case Study. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (pp. 861–873). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: Disturbing crowd disaster incidents have been witnessed in every corner of the planet, which often lead to extensive difficulties, especially when they involve mass multi-nation casualties. When conducting Disaster Victim Identification (DVI) tasks, starting from finding the missing, curing the injured, and identifying the deceased, the challenge in such disasters is the lack of information to provide Emergency Medical Services (EMS) and conduct DVI in a timely manner. The literature presents fragmented solutions that can equip either post-mortem DVI or EMS with solutions to facilitate data collection and dissemination, but they do not consider a holistic solution that allows access to the victims' right information when needed. In this paper, we analyze information needs across multi-disciplines, as well as the requirements for technical support that can help manage the identification process. Recommendations should lay a sound foundation for future multi-disciplinary research in the areas of DVI, EMS, crowd disaster, health informatics, information security and software engineering in the health sphere.
|
Shane Errol Halse, Aurélie Montarnal, Andrea Tapia, & Frederick Benaben. (2018). Bad Weather Coming: Linking social media and weather sensor data. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (pp. 507–515). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: In this paper we leverage the power of citizen supplied data. We examined how both physical weather sensor data (obtained from the weather underground API) and social media data (obtained from Twitter) can serve to improve local community awareness during a severe weather event. A local tornado warning was selected due to its small scale and isolated geographic area, and only Twitter data found from within this geo-locational area was used. Our results indicate that during a severe weather event, an increase in weather activity obtained from the local weather sensors does correlate with an increase in local social media usage. The data found on social media also contains additional information from, and about the community of interest during the event. While this study focuses on a small scale event, it provides the groundwork for use during a much larger weather event.
|
Shane Halse, Jess Kropczynski, & Andrea Tapia. (2018). Using Metrics of Stability to Identify Points of Failure and Support in Online Information Distribution during a Disaster. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (p. 1121). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: We utilize the 2012 Hurricane Sandy dataset to investigate methods to measure network stability during a crisis. While previous research on information distribution has focused on individuals that are most connected, or most willing to share information, we examined this dataset for indicators of network stability. The value of this measure is to identify the points of failure within the network. The findings in this paper provide support for the use of social network analysis within the realm of crisis response to identify the points of failure within the network.
|
Shane Halse, Jomara Binda, & Samantha Weirman. (2018). It's what's outside that counts: Finding credibility metrics through non-message related Twitter features. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (pp. 516–528). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: Social media data, such as Twitter, enables crisis response personnel and civilians to share information during a crisis situation. However, a lack of information gatekeeping processes also translates into concerns about both content and source credibility. This research aims to identify Twitter metrics which could assist with the latter. A 2 (average number of hashtags used) x 2 (ratio of tweets/retweets posted) x 2 (ratio of follower/followee) between-subjects experiment was conducted to evaluate the level of influence of Twitter broker metrics on behavioral intention and the perception of source credibility. The findings indicate that follower/followee ratio in conjunction with hashtag usage approached a significant effect on perceived source credibility. In addition, both Twitter awareness metrics and dispositional trust played an important role in determining behavioral intentions and perceived source credibility. Implications and limitations are also discussed.
|
Shuji Nishikawa, Osamu Uchida, & Keisuke Utsu. (2018). Introduction of a Tracking Map to a Web Application for Location Recording and Rescue Request. In Kristin Stock, & Deborah Bunker (Eds.), Proceedings of ISCRAM Asia Pacific 2018: Innovating for Resilience – 1st International Conference on Information Systems for Crisis Response and Management Asia Pacific. (pp. 459–468). Albany, Auckland, New Zealand: Massey Univeristy.
Abstract: We developed a web application for location recording and rescue request using Twitter (T-Pl@ce). This application helps supported users (e.g., older adults, persons with disabilities, and children) who require support to share their location coordinates via Twitter. Supporting users (e.g., families, relatives, or neighbors) of the supported user can then check the location coordinates of the supported user when required. When the supported user needs to be rescued, he/she can post a rescue request on Twitter by pressing the “Rescue request” button on the application. In this study, we introduce the e-mail notification function to reliably notify a rescue request to the system administrator. In addition, to track the location of the supported user, we introduce a location tracking function. Then, the administrator, the emergency assistance employees (e.g., rescue experts or social workers), or the supporting user can refer to the request and the location tracking page and execute the support and rescue activities.
|
Sofia Eleni Spatharioti, Sara Wylie, & Seth Cooper. (2018). Does Flight Path Context Matter? Impact on Worker Performance in Crowdsourced Aerial Imagery Analysis. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (pp. 621–628). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: Natural disasters result in billions of dollars in damages annually and communities left struggling with the difficult task of response and recovery. To this end, small private aircraft and drones have been deployed to gather images along flight paths over the affected areas, for analyzing aerial photography through crowdsourcing. However, due to the volume of raw data, the context and order of these images is often lost when reaching workers. In this work, we explored the effect of contextualizing a labeling task on Amazon Mechanical Turk, by serving workers images in the order they were collected on the flight and showing them the location of the current image on a map. We did not find a negative impact from the loss of contextual information, and found map context had a negative impact on worker performance. This may indicate that ordering images based on other criteria may be more effective.
|
Sofia Eleni Spatharioti, Sara Wylie, & Seth Cooper. (2018). Identifying and Assessing Points of Interest through Crowdsourced Image Analysis. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (pp. 1123–1125). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: During a natural disaster, major damages to critical structures such as bridges or power lines can severely disrupt community functions for long periods of time, making the task of swiftly identifying this type of damage vital for response and recovery. However, survey flight paths are often designed with a main focus of complete and quick coverage of affected areas through aerial photography, which is then assigned to volunteers to aid in damage report and labeling. We designed a crowdsourcing interface that focuses on locating points of interest and assessing damage using images from survey flights. We tested our design using a disaster and a non-disaster application by recruiting volunteers on Amazon Mechanical Turk. We found that the type of structure may cause difficulties for crowd workers in providing accurate assessments and that designing flights to also target structures may provide higher quality imagery for this type of task.
|
Songhui Yue, Jyothsna Kondari, Aibek Musaev, Songqing Yue, & Randy Smith. (2018). Using Twitter Data to Determine Hurricane Category: An Experiment. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (pp. 718–726). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: Social media posts contain an abundant amount of information about public opinion on major events, especially natural disasters such as hurricanes. Posts related to an event, are usually published by the users who live near the place of the event at the time of the event. Special correlation between the social media data and the events can be obtained using data mining approaches. This paper presents research work to find the mappings between social media data and the severity level of a disaster. Specifically, we have investigated the Twitter data posted during hurricanes Harvey and Irma, and attempted to find the correlation between the Twitter data of a specific area and the hurricane level in that area. Our experimental results indicate a positive correlation between them. We also present a method to predict the hurricane category for a specific area using relevant Twitter data.
|
Sonia Gul, Nurul Sarkar, Jairo Gutierrez, & Edmund Lai. (2018). RESILICOMM: A Framework for Resilient Communication System. In Kristin Stock, & Deborah Bunker (Eds.), Proceedings of ISCRAM Asia Pacific 2018: Innovating for Resilience – 1st International Conference on Information Systems for Crisis Response and Management Asia Pacific. (pp. 83–88). Albany, Auckland, New Zealand: Massey Univeristy.
Abstract: Disasters, when they strike hard, may cause the disruption of many vital services. 'Telecommunications' is being considered one of the vital lifeline services as many disaster relief operations rely on it. Effective communication is dependent on a telecommunication network infrastructure that is working properly. Unfortunately, the infrastructure may be damaged during a disaster causing no-coverage and/or congested network traffic in the disaster-affected areas. In this paper we propose a conceptual framework for building a resilient communication system that not only considers the communications infrastructure but also other driving factors which are necessary for its success. The proposed framework is based on five key pillars, namely: robustness, redundancy, adaptability, agility, and readiness to build capability for developing a resilient communication system. The findings reported in this paper provide some insights into resilient communications that may help network researchers/engineers to contribute further towards developing a robust and resilient communication system capable of coping with disasters.
|
Stefan Schauer, Stefan Rass, Sandra König, Thomas Grafenauer, & Martin Latzenhofer. (2018). Analyzing Cascading Effects among Critical Infrastructures. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (pp. 428–437). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: In this article, we present a novel approach, which allows not only to identify potential cascading effects within a network of interrelated critical infrastructures but also supports the assessment of these cascading effects. Based on percolation theory and Markov chains, our method models the interdependencies among various infrastructures and evaluates the possible consequences if an infrastructure has to reduce its capacity or is failing completely, by simulating the effects over time. Additionally, our approach is designed to take the intrinsic uncertainty into account, which resides in the description of potential consequences a failing critical infrastructure might cause, by using probabilistic state transitions. In this way, not only the critical infrastructure's risk and security managers are able to evaluate the consequences of an incident anywhere in the network but also the emergency services can use this information to improve their operation in case of a crisis and anticipate potential trouble spots.
|
Steve Peterson, Chris Thompson, & Cat Graham. (2018). Getting Disaster Data Right: A Call for Real-time Research in Disaster Response. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (pp. 851–859). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: In the response phase of disasters, minimal research has been conducted on the near real-time operational usage of social media. Research findings during this phase could provide evidence to the emergency management community that social media content can be retrieved, verified, and ultimately utilized in decision-making. This paper discusses potential strategies for conducting future research in near real-time during disasters to gain insightful knowledge rarely captured. Following the April 25, 2015, magnitude 7.8 Nepal earthquake, a team of 20 digital volunteers were virtually activated for 48 hours to extract medical-related information from multiple social media platforms and Internet sources. This practitioner insight paper examines methods applied to filter, classify, analyze, verify, and distribute the medical-related information in a timely manner. Association of past research studies are applied to the digital volunteer's experience within a case study framework, calling attention to the feasibility of digital volunteers as an information source in future research.
|
Steve Peterson, & Denis Gusty. (2018). Incorporating Digital Volunteers into Exercises: A Case Study on CAUSE V. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (pp. 1126–1129). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: The U.S. Department of Homeland Security (DHS) Science and Technology Directorate (S&T) and Canada Department of National Defence's Centre for Security Science conducted its fifth Canada-U.S. Enhanced Resiliency Experiment (CAUSE V) on November 15 – 16, 2017 along the border between the Canadian province of British Columbia and the state of Washington. The experiment tested emerging technologies to promote more effective communication and information sharing for emergency management officials and first responder agencies on both sides of the border in response to a Mt. Baker volcanic eruption and lahar mudflow scenario. The CAUSE V experiment explored the use of trained digital volunteers to provide operational and public information support to emergency management professionals. These digital volunteers were assigned to monitor simulated social media platforms, identifying information according to pre-assigned mission assignments, including misinformation and rumor control, and reporting this information to emergency management officials and first responder agencies. Researchers from the University of Washington were in attendance to specifically observe the efforts of the digital volunteers during the experiment. Research observations, and the benefits of integrating the research and practitioner communities, will be highlighted on the poster.
|
Sultan A. Alharthi, Nick LaLone, Ahmed S. Khalaf, Ruth Torres, Lennart Nacke, Igor Dolgov, et al. (2018). Practical Insights into the Design of Future Disaster Response Training Simulations. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (pp. 818–830). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: A primary component of disaster response is training. These educational exercises provide responders with the knowledge and skills needed to be prepared when disasters happen. However, traditional training methods, such as high-fidelity simulations (e.g., real-life drills) and classroom courses, may fall short of providing effective and cost-efficient training that is needed for today's challenges. Advances in technology open a wide range of opportunities for training using computer-mediated simulations and exercises. These exercises include the use of mixed reality games and wearable computers. Existing studies report on the usefulness of these technologies for training purposes. This review paper synthesizes prior research and development of disaster response simulations and identifies challenges, opportunities, and lessons learned. Through this review, we provide researchers and designers with an overview of current practices in designing training simulations and contribute practical insights into the design of future disaster response training.
|
Takuya Oki. (2018). Possibility of Using Tweets to Detect Crowd Congestion: A Case Study Using Tweets just before/after the Great East Japan Earthquake. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (pp. 584–596). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: During large earthquakes, it is critical to safely guide evacuation efforts and to prevent accidents caused by congestion. In this paper, we focus on detecting the degree of crowd congestion following an earthquake based on information posted to Social Networking Services (SNSs). This research uses text data posted to Twitter just before/after the occurrence of the Great East Japan Earthquake (11 March 2011 at 02:46 PM JST). First, we extract co-occurring place names, proper nouns, and time-series information from tweets about congestion in the Tokyo metropolitan area (TMA). Next, using these extracted data, we analyze the frequency and spatiotemporal characteristics of these tweets. Finally, we identify expressions that describe the degree of crowd congestion and discuss methods to quantify these expressions based on a questionnaire survey and tweets that contain a photograph.
|
Tayler Ruggero, & Brian Tomaszewski. (2018). Geographic Information Capacity (GIC) Across International Scales: Comparing Institutional Structures of Germany to the United States. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (pp. 1153–1155). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: Over the last three decades, the number and severity of natural disasters all across the world has been increasing exponentially (Basher, 2006). This paper intends to consider geographic information capacity (GIC) as it relates to government, government regulated organizations, and international organizations, including the United Nations, and their involvement in disaster risk reduction and management. Specifically, the paper aims to understand similarities and differences and the connection between two governmental disaster management organizations, FEMA in the United States and BBK and THW in Germany. We present a comparative analysis on the two countries in terms of their organizational structures, how their structures affect geographic information capacity and how geographic information capacity is related to disaster risk reduction and disaster response. Future work can make comparisons across more countries, including developing countries, to see what structural changes can be made in government entities to help increase GIC when disaster strikes.
|
Teresa Gordon, Hamish Keith, & Todd Velvin. (2018). Insight into the Emergency Mobile Alert system and Public Information Management in New Zealand Insight into the Emergency Mobile Alert system and Public Information Management in New Zealand. In Kristin Stock, & Deborah Bunker (Eds.), Proceedings of ISCRAM Asia Pacific 2018: Innovating for Resilience – 1st International Conference on Information Systems for Crisis Response and Management Asia Pacific. (pp. 103–109). Albany, Auckland, New Zealand: Massey Univeristy.
Abstract: New Plymouth city's water supply infrastructure suffered major damage as Ex-Tropical Cyclone Gita passed over New Zealand on 20 February 2018. By 1950 hours a State of Local Emergency had been declared due to the disruption of the drinking water supply in New Plymouth and power supply across the region. This report focuses on the feedback received by the Taranaki CDEM Group Public Information Management team following activation of the Emergency Mobile Alert (EMA) system on the evening of Wednesday 21 February 2018, to warn people in New Plymouth District that tap water must be boiled. The report gives a practitioner's insight into making the decision to send one of New Zealand's first EMAs and the subsequent handset issues experienced by members of the public with this new system, including various misunderstandings about how the EMA system works.
|
Terje Gjøsæter, Jaziar Radianti, & Weiqin Chen. (2018). Universal Design of ICT for Emergency Management: A Research Agenda. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (pp. 1148–1152). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: Information and communication technologies (ICT) are becoming increasingly important in emergency management and crisis communication. ICT tools are developed and adopted in all phases of the emergency management cycle. On the one hand, these tools contribute to better disaster preparedness and effective response. On the other hand, the lack of consideration of universal design in these tools also creates new barriers for different stakeholders, particularly the elderly and people with disabilities. The primary objective of this paper is to give an overview of the current state of the emerging research field of Universal Design of ICT for emergency management and provide a Research Agenda to highlight ways to uncover how the increasing introduction of ICT in emergency management can contribute to removing barriers instead of adding more barriers.
|
Thomas Huggins, Stephen Hill, Robin Peace, & David Johnston. (2018). Extending Ecological Rationality: Catching the High Balls of Disaster Management. In Kristin Stock, & Deborah Bunker (Eds.), Proceedings of ISCRAM Asia Pacific 2018: Innovating for Resilience – 1st International Conference on Information Systems for Crisis Response and Management Asia Pacific. (pp. 295–309). Albany, Auckland, New Zealand: Massey Univeristy.
Abstract: The contemporary world is characterized by several large-scale hazards to human societies and the environments we live in, including the impacts of climate change. This paper outlines theories concerning cognitive psychology and complexity dynamics that help explain the challenges of responding to these hazards and the complex systems which create them. These theories are illustrated with a baseball metaphor, to highlight the need for decision-making strategies which do not rely on comprehensive information where comprehensive information is not available. The importance of tools which can support more efficient uses of limited information is also outlined, as is the way that these tools help combine the computational resources and acquired experience of several minds. Existing research has been used to investigate many of the concepts outlined. However, further research is required to coalesce cognitive theories with complexity theories and the analysis of group-level interactions, towards improving important disaster management decisions.
|
Tim Grant. (2018). Common Topics in C2 Doctrine for Emergency Management. In Kristin Stock, & Deborah Bunker (Eds.), Proceedings of ISCRAM Asia Pacific 2018: Innovating for Resilience – 1st International Conference on Information Systems for Crisis Response and Management Asia Pacific. (pp. 56–68). Albany, Auckland, New Zealand: Massey Univeristy.
Abstract: A set of publications from the online, English-language, Emergency Management (EM) doctrine has been surveyed to identify common topics in Command & Control (C2) at the tactical and operational levels. Jackson's (2013) ontological and epistemological review of the evolution of military doctrine serves as the analytic lens, enabling a link to be made to resilience and agility. The topics identified were mapped to scientific disciplines in C2. The results could be used to draw up a recommended table of contents for comprehensive EM doctrine, to guide the development of curricula for training emergency managers, and to define the user requirements for supporting information systems. In further research, the results should be compared to a similar, ongoing survey of military C2 doctrine.
|
Toshihiro Osaragi. (2018). Crowding of Various Facilities Relevant to Supporting People Who Have Difficulty Returning Home after a Large Earthquake. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (pp. 45–59). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: When a large earthquake occurs, many people are presumed to have difficulty in returning home. However, no research has been achieved yet to discuss the congestion of supporting facilities for stranded people in terms of site, the number and spatial distribution. In this study, we construct a simulation model, which describes people's behavior such as returning home or going to other facilities after an earthquake occurs. Using the model, we estimate the congestion of facilities which varies according to day of the week or the time when the event occurs, and demonstrate the effective methods for reducing the congestion, which include offering information for people and cooperation of private institutions.
|
Tzu-Yin CHANG, Shang-Yu Wu, & Jyun-Yuan Chen. (2018). Mobile Communication Technology and Cell Broadcast Service for Emergency Alerts. In Kristin Stock, & Deborah Bunker (Eds.), Proceedings of ISCRAM Asia Pacific 2018: Innovating for Resilience – 1st International Conference on Information Systems for Crisis Response and Management Asia Pacific. (pp. 97–102). Albany, Auckland, New Zealand: Massey Univeristy.
Abstract: Taiwan is located in the collision zones between two continental plates collide. From the perspective of plate tectonics, the paleo-tectonic environment of the Taiwan and its surrounding areas are rather complex and active due to the tectonic compression of the Eurasian Plate and Philippine Sea Plate. This has resulted in frequent earthquakes in Taiwan. In addition, the tropical and subtropical climate drives not only weathering and erosion of surface rocks, but also typhoon or monsoon triggered torrential and heavy rains in summer and autumn. For downstream land subsidence areas with poor discharge capacity, it is therefore often to have serious floods and resulted in large-scale disasters that endanger citizens' lives and property. Affected by climate change, high urban density and overexploitation of land resources, Taiwan has a substantial increase in natural disasters over the last couple of years. As the country is confronted by unfavorable environment and climate conditions, how disaster alerts and information are accurately and timely released has become an important topic for facilitating the evacuation of citizens and dispatch of disaster relief personnel. This study has combined the mobile communications technology to enable our government to, with the Cell Broadcast Service (CBS), instantly send messages to all 4G and 3G (WCDMA) mobile users within the coverage of designated base stations and without being affected by the network congestion through independent channels. This will help timely notify citizens to evacuate and reduce casualties.
|
Varsha Hassan Vishwanath, & Brian Tomaszewski. (2018). Flood Hazard, Vulnerability, Risk Assessment for Uttarakhand State in India. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (pp. 362–375). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: The Indian state of Uttarakhand, located in the valleys of the Himalayan Mountains, is severely prone to flash floods. High intense rainfall, slope, river channels are some of the significant factors responsible for flash floods. In this work-in-progress paper, we address these challenges via a geospatial flood risk analysis that utilizes hazard and vulnerability assessments, computed using satellite, hydrologic and demographic data by employing Analytical Hierarchy Process (AHP). The entire analysis was carried out in geosprocesing framework. The resulting maps indicate that flood risk regions have significant correspondence to regions that are highly hazardous and vulnerable. These maps could help in developing better disaster management measures for Uttarakhand. Flash floods still being a globally challenging problem, these methods and results could be used to expand research and improve flash floods prediction and warning systems in many countries.
|
Venkata Kishore Neppalli, Cornelia Caragea, & Doina Caragea. (2018). Deep Neural Networks versus Naive Bayes Classifiers for Identifying Informative Tweets during Disasters. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (pp. 677–686). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: In this paper, we focus on understanding the effectiveness of deep neural networks by comparison with the effectiveness of standard classifiers that use carefully engineered features. Specifically, we design various feature sets (based on tweet content, user details and polarity clues) and use these feature sets individually or in various combinations, with Naïve Bayes classifiers. Furthermore, we develop neural models based on Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) with handcrafted architectures. We compare the two types of approaches in the context of identifying informative tweets posted during disasters, and show that the deep neural networks, in particular the CNN networks, are more effective for the task considered.
|
Vitaveska Lanfranchi, Nadia Noori, & Tudor Sirbu. (2018). GPS-based solution for tracking and protecting humanitarians in conflict zones. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (pp. 334–349). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: The operational environment in which humanitarians operate is unstable and high-risk; when operating in such environments, time becomes a critical factor. Thus, real-time location systems (RTLS) are often deployed in the operational environment to provide awareness of the location of personnel and assets in real-time that would support an informed decision making in the event of responding to emergency. Whilst standard RTLS are very precise, they are not suitable to outdoor spaces; GPS position technology can be used to identify the location of objects and people and to track them. In this paper, first, we present a description of threat scenarios identified based on information from existing security incidents datasets and from interviews with aid workers and security professionals operating in high-risk regions. Second, we describe the implementation of a GPS-based real-time location tracking and alert system for humanitarians operating in conflict zones that supports the identified scenarios.
|