Alan Aipe, Asif Ekbal, Mukuntha NS, & Sadao Kurohashi. (2018). Linguistic Feature Assisted Deep Learning Approach towards Multi-label Classification of Crisis Related Tweets. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (pp. 705–717). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: Micro-blogging site like Twitter, over the last decade, has evolved into a proactive communication channel during mass convergence and emergency events, especially in crisis stricken scenarios. Extracting multiple levels of information associated with the overwhelming amount of social media data generated during such situations remains a great challenge to disaster-affected communities and professional emergency responders. These valuable data, segregated into different informative categories, can be leveraged by the government agencies, humanitarian communities as well as citizens to bring about faster response in areas of necessity. In this paper, we address the above scenario by developing a deep Convolutional Neural Network (CNN) for multi-label classification of crisis related tweets.We augment deep CNN by several linguistic features extracted from Tweet, and investigate their usage in classification. Evaluation on a benchmark dataset show that our proposed approach attains the state-of-the-art performance.
|
Alessandro Farasin, Luca Colomba, Giulio Palomba, & Giovanni Nini. (2020). Supervised Burned Areas Delineation by Means of Sentinel-2 Imagery and Convolutional Neural Networks. In Amanda Hughes, Fiona McNeill, & Christopher W. Zobel (Eds.), ISCRAM 2020 Conference Proceedings – 17th International Conference on Information Systems for Crisis Response and Management (pp. 1060–1071). Blacksburg, VA (USA): Virginia Tech.
Abstract: Wildfire events are increasingly threatening our lands, cities, and lives. To contrast this phenomenon and to limit its damages, governments around the globe are trying to find proper counter-measures, identifying prevention and monitoring as two key factors to reduce wildfires impact worldwide. In this work, we propose two deep convolutional neural networks to automatically detect and delineate burned areas from satellite acquisitions, assessing their performances at scale using validated maps of burned areas of historical wildfires. We demonstrate that the proposed networks substantially improve the burned area delineation accuracy over conventional methods.
|
Bo Andersson, & Jonas Hedman. (2006). Issues in the development of a mobile based communication platform for the swedish police force and appointed security guards. In M. T. B. Van de Walle (Ed.), Proceedings of ISCRAM 2006 – 3rd International Conference on Information Systems for Crisis Response and Management (pp. 181–187). Newark, NJ: Royal Flemish Academy of Belgium.
Abstract: This paper presents the learning experiences from the development of a mobile-based communication platform, called OrdningsVaktsCentralen (OVC). OVC can be translated to Security Guard Central. OVC is designed to enable the Swedish Police Force (SPF) to comply with new legal requirements and enhance their collaboration with Appointed Security Guards (ASG). The focus of this paper is on the early phases of development; in particular on the specific technical issues such as interoperability and standards used in the development of mobile based systems. The learning experiences are as follows: firstly, when developing mobile based systems we suggest and recommend that the analysis phase should be enhanced and it should address the interoperability between mobile phones on one hand and operators on the other hand. Secondly, global and national standards, such as the MMS7 for sending multi-media messages, are not always standardized. It seems that operators and mobile phone manufacturers make minor alterations and interpretations of the standard and thereby some of the benefits found in standards disappear. Thirdly, mobile based communication platforms have a large potential for contributing to the field of emergency management information systems since they can be based on open and nationally accepted standards.
|
Dennis Andersson, & Amy Rankin. (2012). Sharing mission experience in tactical organisations. In Z.Franco J. R. L. Rothkrantz (Ed.), ISCRAM 2012 Conference Proceedings – 9th International Conference on Information Systems for Crisis Response and Management. Vancouver, BC: Simon Fraser University.
Abstract: A tactical organisation can be seen as an adhocracy designed to perform missions in uncertain, ambiguous and complex environments. Flexibility, adaptability, resilience, innovation, creativity and improvisation have all been identified as key skills for successful outcome of these missions. To learn skills associated with such abilities previous research has shown that knowledge acquired through experience plays an important role. It is important that organisations share and learn from experiences to improve their ability to cope with novel situations. In literature there is a lack of consistency in how these abilities are discussed, we therefore propose the FAIRIC model. By unravelling some of the similarities and differences we create a common vocabulary to discuss knowledge gained from experience. This can help classify different experiences and provide a systematic way of gathering and modelling knowledge on situational factors to enable sharing of mission experience over boundaries of time and space. © 2012 ISCRAM.
|
Antone Evans Jr., Yingyuan Yang, & Sunshin Lee. (2021). Towards Predicting COVID-19 Trends: Feature Engineering on Social Media Responses. In Anouck Adrot, Rob Grace, Kathleen Moore, & Christopher W. Zobel (Eds.), ISCRAM 2021 Conference Proceedings – 18th International Conference on Information Systems for Crisis Response and Management (pp. 792–807). Blacksburg, VA (USA): Virginia Tech.
Abstract: During the course of this pandemic, the use of social media and virtual networks has been at an all-time high. Individuals have used social media to express their thoughts on matters related to this pandemic. It is difficult to predict current trends based on historic case data because trends are more connected to social activities which can lead to the spread of coronavirus. So, it's important for us to derive meaningful information from social media as it is widely used. Therefore, we grouped tweets by common keywords, found correlations between keywords and daily COVID-19 statistics and built predictive modeling. The features correlation analysis was very effective, so trends were predicted very well. A RMSE score of 0.0425504, MAE of 0.03295105 and RSQ of 0.5237014 in relation to daily deaths. In addition, we found a RMSE score of 0.07346836, MAE of 0.0491152 and RSQ 0.374529 in relation to daily cases.
|
Berggren, P., Ryrberg, T., Lindhagen, A., & Johansson, B. (2023). Building capacity – conceptualizing Training of Trainers. In Jaziar Radianti, Ioannis Dokas, Nicolas Lalone, & Deepak Khazanchi (Eds.), Proceedings of the 20th International ISCRAM Conference (pp. 701–710). Omaha, USA: University of Nebraska at Omaha.
Abstract: Many organizations train and educate their staff to prepare for crisis. One approach is train-the-trainer (ToT; Training of trainers) concept. It is based on the idea that someone can be trained as a trainer, who in turn train their colleagues. The philosophy resembles a pyramid scheme that allows for a fast and efficient spread of knowledge and skills. This study focused on perceptions of the ToT concept through interviews with ToT trainers. Two learning theories, organizational learning (4I) and experiential learning theory (ELT) were used to conceptualize the ToT-concept. It was found that the ToT-concept can be used as the method to conduct ELT to achieve organizational learning and knowledge (4I). Furthermore, the study also presents how participants perceives ToT using thematic analysis. This resulted in four themes: Common understanding of ToT, Learn-by doing, No grounding in ToT, and Difficult to ensure quality.
|
Björn J E Johansson. (2020). Boundary Stories – A Systems Perspective on Inter-organizational Learning from Crisis Response Exercises. In Amanda Hughes, Fiona McNeill, & Christopher W. Zobel (Eds.), ISCRAM 2020 Conference Proceedings – 17th International Conference on Information Systems for Crisis Response and Management (pp. 427–434). Blacksburg, VA (USA): Virginia Tech.
Abstract: Inter-organizational exercises are commonly conducted with the aim to improve overall crisis response system performance. However, there are challenges associated with establishing learning goals for, designing and evaluating inter-organizational exercises. This work-in-progress paper applies a systems science perspective on the Swedish crisis response system with the aim to understand (1) what kind of a system it is (2) what properties or mechanisms enable good system performance?, and, (3) what are desirable training goals for improving the crisis response capability of the Swedish crisis response system? The author suggests that (1) the Swedish crisis response system can be seen as a Complex Adaptive System, and (2) that the focus must shift from exercising organizations' intra-organizational capabilities to adaptive capabilities. The latter can be achieved by designing exercises comprising boundary-crossing activities with the purpose to support the buildup of boundary-crossing competence. Cross-organizational learning can be achieved by identifying, documenting and disseminating boundary stories.
|
Cornelia Caragea, Nathan McNeese, Anuj Jaiswal, Greg Traylor, Hyun-Woo Kim, Prasenjit Mitra, et al. (2011). Classifying text messages for the haiti earthquake. In E. Portela L. S. M.A. Santos (Ed.), 8th International Conference on Information Systems for Crisis Response and Management: From Early-Warning Systems to Preparedness and Training, ISCRAM 2011. Lisbon: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: In case of emergencies (e.g., earthquakes, flooding), rapid responses are needed in order to address victims' requests for help. Social media used around crises involves self-organizing behavior that can produce accurate results, often in advance of official communications. This allows affected population to send tweets or text messages, and hence, make them heard. The ability to classify tweets and text messages automatically, together with the ability to deliver the relevant information to the appropriate personnel are essential for enabling the personnel to timely and efficiently work to address the most urgent needs, and to understand the emergency situation better. In this study, we developed a reusable information technology infrastructure, called Enhanced Messaging for the Emergency Response Sector (EMERSE), which classifies and aggregates tweets and text messages about the Haiti disaster relief so that non-governmental organizations, relief workers, people in Haiti, and their friends and families can easily access them.
|
Cheng Wang, Benjamin Bowes, Arash Tavakoli, Stephen Adams, Jonathan Goodall, & Peter Beling. (2020). Smart Stormwater Control Systems: A Reinforcement Learning Approach. In Amanda Hughes, Fiona McNeill, & Christopher W. Zobel (Eds.), ISCRAM 2020 Conference Proceedings – 17th International Conference on Information Systems for Crisis Response and Management (pp. 2–13). Blacksburg, VA (USA): Virginia Tech.
Abstract: Flooding poses a significant and growing risk for many urban areas. Stormwater systems are typically used to control flooding, but are traditionally passive (i.e. have no controllable components). However, if stormwater systems are retrofitted with valves and pumps, policies for controlling them in real-time could be implemented to enhance system performance over a wider range of conditions than originally designed for. In this paper, we propose an autonomous, reinforcement learning (RL) based, stormwater control system that aims to minimize flooding during storms. With this approach, an optimal control policy can be learned by letting an RL agent interact with the system in response to received reward signals. In comparison with a set of static control rules, RL shows superior performance on a wide range of artificial storm events. This demonstrates RL's ability to learn control actions based on observation and interaction, a key benefit for dynamic and ever-changing urban areas.
|
Christian Iasio, Ingrid Canovas, Elie Chevillot-Miot, & Tendry Randramialala. (2022). A New Approach to Structured Processing of Feedback for Discovering and Investigating Interconnections, Cascading Events and Disaster Chains. In Rob Grace, & Hossein Baharmand (Eds.), ISCRAM 2022 Conference Proceedings – 19th International Conference on Information Systems for Crisis Response and Management (pp. 285–298). Tarbes, France.
Abstract: Post-disaster information processing is relevant for the continuous improvement of operations and the reductionof risks. The current methodologies for post-disaster review suffer from several limitations, which reduce their use as a way of translating narrative in data for qualitative and quantitative analysis. Learning or effective knowledge sharing need a common formalism and method. Ontologies are the reference tool for structuring information in a “coded” data structure. Using the investigation of disaster management during the 2017 hurricane season in the French West Indies within the scope of the ANR “APRIL” project, this contribution introduces a methodology and a tool for providing a graphical representation of experiences for post-disaster review and lessons learning, based on a novel approach to case-based ontology development.
|
Christine Adler, Werner Sauter, Jona Meyer, Maria Hagl, & Margit Raich. (2015). First Steps in the Development of an Internet-based Learning Platform for Strategic Crisis Managers. In L. Palen, M. Buscher, T. Comes, & A. Hughes (Eds.), ISCRAM 2015 Conference Proceedings ? 12th International Conference on Information Systems for Crisis Response and Management. Kristiansand, Norway: University of Agder (UiA).
Abstract: Based on interviews with European crisis managers and other stakeholders, we identified specific learning requirements regarding psycho-social support in disaster management. This paper describes the process of developing a learning environment specifically for disaster managers with strategic responsibilities. Focusing on competence development, the underlying concept emphasizes peer-like exchanges and self-directed learning rather than passive, externally organized training methods. For that purpose a web-based learning platform is being developed in combination with competence development modules tailored to the needs of crisis managers. The envisioned learning platform utilizes blended learning and social learning concepts and technologies to facilitate knowledge building, adapted and customized to the needs of the crisis managers. End-user requirements will be individually assessed in order to generate up-to-date content while considering the wider EU-context.
|
Daniel Link, Bernd Hellingrath, & Jie Ling. (2016). A Human-is-the-Loop Approach for Semi-Automated Content Moderation. In A. Tapia, P. Antunes, V.A. Bañuls, K. Moore, & J. Porto (Eds.), ISCRAM 2016 Conference Proceedings ? 13th International Conference on Information Systems for Crisis Response and Management. Rio de Janeiro, Brasil: Federal University of Rio de Janeiro.
Abstract: Online social media has been recognized as a valuable information source for disaster management whose volume, velocity and variety exceed manual processing capacity. Current machine learning systems that support the processing of such data generally follow a human-in-the-loop approach, which has several inherent limitations. This work applies the human-is-the-loop concept from visual analytics to semi-automate a manual content moderation workflow, wherein human moderators take the dominant role. The workflow is instantiated with a supervised machine learning system that supports moderators with suggestions regarding the relevance and categorization of content. The instantiated workflow has been evaluated using in-depth interviews with practitioners and serious games. which suggest that it offers good compatibility with work practices in humanitarian assessment as well as improved moderation quality and higher flexibility than common approaches.
|
Simone De Kleermaeker, Annette Zijderveld, & Bart Thonus. (2011). Training for crisis response with serious games based on early warning systems. In E. Portela L. S. M.A. Santos (Ed.), 8th International Conference on Information Systems for Crisis Response and Management: From Early-Warning Systems to Preparedness and Training, ISCRAM 2011. Lisbon: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: This paper discusses serious games developed as part of a training program developed for a Dutch crisis response group, which acts during a (potential) flooding crisis. Training in general contributes to a wide range of learning objectives and can address different target audiences. For each combination of learning objective and target audience, the proper form of education has to be selected, ranging from self-tuition to large scale multi-party training and exercises. Serious games can be a useful and educational addition to the set of existing training tools. For operational crisis response groups a high match with real-time warning systems is essential. Our approach shows how to integrate both serious games and early warning systems for effective training and exercises. We end with our lessons learned in designing serious games based on early warning systems, in the context of a training program for a crisis response group.
|
Denis Havlik, Jasmin Pielorz, & Adam Widera. (2016). Interaction with citizens experiments: from context-aware alerting to crowdtasking. In A. Tapia, P. Antunes, V.A. Bañuls, K. Moore, & J. Porto (Eds.), ISCRAM 2016 Conference Proceedings ? 13th International Conference on Information Systems for Crisis Response and Management. Rio de Janeiro, Brasil: Federal University of Rio de Janeiro.
Abstract: The EU FP7 project DRIVER is conducting a number of experiments to assess the feasibility of addressing known deficiencies in crisis management. In this paper, we introduce experiments that investigate two-way communication solutions between crisis managers and citizens or unaffiliated volunteers. In the so-called ?Interaction with Citizens? experiments we are testing the usability and acceptance of the various methods and tools that facilitate crisis communication at several levels. This includes: informing and alerting of citizens; micro-tasking of volunteers; gathering of situational information about the crisis incident from volunteers; and usage of this information to improve situation awareness. At the time of writing this paper, our ?Interaction with Citizens? experiments are still under way. Therefore, this paper reports the lessons learned in the first two experiments along with the experimental setup and expectations for the final experiment.
|
Diana C. Arce Cuesta, Gilbert J. Huber, Jose Orlando Gomes, & Paulo V. R. Carvalho. (2015). A Framework to Capture Incidents during Emergency Situations. In L. Palen, M. Buscher, T. Comes, & A. Hughes (Eds.), ISCRAM 2015 Conference Proceedings ? 12th International Conference on Information Systems for Crisis Response and Management. Kristiansand, Norway: University of Agder (UiA).
Abstract: Emergency organizations have contingency plans, which define responsibilities, resources, and actions to be performed in an emergency situation. However, unexpected incidents may arise and cause additional difficulty in the emergency control process. The knowledge that team members develop to deal with these incidents and keep the system ?functioning? improves resilience and response and is very valuable for such organizations. This research addresses the problem of how to capture the incidents and knowledge generated during the emergency response through a conceptual framework. The framework defines a structured process for preparation and capture of incidents during an emergency through direct observations, to assist in the capture and proper representation of the incidents to produce knowledge within other practitioners.
|
Dipak Singh, Shayan Shams, Joohyun Kim, Seung-jong Park, & Seungwon Yang. (2020). Fighting for Information Credibility: AnEnd-to-End Framework to Identify FakeNews during Natural Disasters. In Amanda Hughes, Fiona McNeill, & Christopher W. Zobel (Eds.), ISCRAM 2020 Conference Proceedings – 17th International Conference on Information Systems for Crisis Response and Management (pp. 90–99). Blacksburg, VA (USA): Virginia Tech.
Abstract: Fast-spreading fake news has become an epidemic in the post-truth world of politics, the stock market, or even during natural disasters. A large amount of unverified information may reach a vast audience quickly via social media. The effect of misinformation (false) and disinformation (deliberately false) is more severe during the critical time of natural disasters such as flooding, hurricanes, or earthquakes. This can lead to disruptions in rescue missions and recovery activities, costing human lives and delaying the time needed for affected communities to return to normal. In this paper, we designed a comprehensive framework which is capable of developing a training set and trains a deep learning model for detecting fake news events occurring during disasters. Our proposed framework includes infrastructure to collect Twitter posts which spread false information. In our model implementation, we utilized the Transfer Learning scheme to transfer knowledge gained from a large and general fake news dataset to relatively smaller fake news events occurring during disasters as a means of overcoming the limited size of our training dataset. Our detection model was able to achieve an accuracy of 91.47\% and F1 score of 90.89 when it was trained with the first 28 hours of Twitter data. Our vision for this study is to help emergency managers during disaster response with our framework so that they may perform their rescue and recovery actions effectively and efficiently without being distracted by false information.
|
Julie Dugdale, Bernard Pavard, Nico Pallamin, Mehdi El Jed, & Laurent Maugan. (2004). Emergency fire incident training in a virtual world. In B. C. B. Van de Walle (Ed.), Proceedings of ISCRAM 2004 – 1st International Workshop on Information Systems for Crisis Response and Management (pp. 167–172). Brussels: Royal Flemish Academy of Belgium.
Abstract: The effectiveness of 'close to reality' training simulations is due to the fact that they provide a sense of immersion and allow several participants to interact naturally. However, they are expensive, time-consuming, difficult to organise and have a limited scope. We present a virtual reality training simulator which overcomes these disadvantages. We describe the approach and methodology and conclude with a discussion of the most crucial challenges when developing such a system. In this paper we would like to introduce the notion of cultural technologies which produce a sense of social as well as cultural immersion. We will discuss the main ingredients of such an immersion, in particular the notion of situated virtual interaction (how interactions in a virtual world can be comparable with human interactions in real situations). We also discuss on the role of interfaces (real time motion capture) and emotional expression in the design of such environments. © Proceedings ISCRAM 2004.
|
Federico Angaramo, & Claudio Rossi. (2018). Online clustering and classification for real-time event detection in Twitter. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (pp. 1098–1107). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: Event detection from social media is a challenging task due to the volume, the velocity and the variety of user-generated data requiring real-time processing. Despite recent works on this subject, a generalized and scalable approach that could be applied across languages and topics has not been consolidated, yet. In this paper, we propose a methodology for real-time event detection from Twitter data that allows users to select a topic of interest by defining a simple set of keywords and a matching rule. We implement the proposed methodology and evaluate it with real data to detect different types of events.
|
Soraia Felicio, Viviane S. R. Silva, André Dargains, Paulo Roberto Azevedo Souza, Felippe Sampaio, Paulo V. R. Carvalho, et al. (2014). Stop disasters game experiment with elementary school students in Rio de Janeiro: Building safety culture. In and P.C. Shih. L. Plotnick M. S. P. S.R. Hiltz (Ed.), ISCRAM 2014 Conference Proceedings – 11th International Conference on Information Systems for Crisis Response and Management (pp. 585–591). University Park, PA: The Pennsylvania State University.
Abstract: Currently, the city of Rio de Janeiro is is in total evidence, hosting important events such as the Pope's Francis' visit in 2013, the World Cup in 2014 and the Olympic Games in 2016. In order to make the population aware, of some environmental problems this article was produced to analyze what factors people consider dangerous. In 2011, Rio de Janeiro went through difficult times, caused by one of the biggest floods seen in the city which ended up partly destroying cities of the state's the mountain region. Kids from aged 10 to 13 years from a high school in Rio were invited to participate in a study and they had to answer questionnaires before and after playing the game. From the results obtained, we analyzed how the game “Stop Disasters” developed by the by the UN can help create awareness and learning on how to behave in flooding situations at an accelerated rate.
|
Ferda Ofli, Firoj Alam, & Muhammad Imran. (2020). Analysis of Social Media Data using Multimodal Deep Learning for Disaster Response. In Amanda Hughes, Fiona McNeill, & Christopher W. Zobel (Eds.), ISCRAM 2020 Conference Proceedings – 17th International Conference on Information Systems for Crisis Response and Management (pp. 802–811). Blacksburg, VA (USA): Virginia Tech.
Abstract: Multimedia content in social media platforms provides significant information during disaster events. The types of information shared include reports of injured or deceased people, infrastructure damage, and missing or found people, among others. Although many studies have shown the usefulness of both text and image content for disaster response purposes, the research has been mostly focused on analyzing only the text modality in the past. In this paper, we propose to use both text and image modalities of social media data to learn a joint representation using state-of-the-art deep learning techniques. Specifically, we utilize convolutional neural networks to define a multimodal deep learning architecture with a modality-agnostic shared representation. Extensive experiments on real-world disaster datasets show that the proposed multimodal architecture yields better performance than models trained using a single modality (e.g., either text or image).
|
Joris Field, Arjan Lemmers, Amy Rankin, & Michael Morin. (2012). Instructor tools for virtual training systems. In Z.Franco J. R. L. Rothkrantz (Ed.), ISCRAM 2012 Conference Proceedings – 9th International Conference on Information Systems for Crisis Response and Management. Vancouver, BC: Simon Fraser University.
Abstract: Crisis management exercises require a lot of preparation and planning to ensure that the training objectives are met. This is often a time consuming and expensive process and can be a major barrier to setting up frequent crisis management training sessions. The introduction of virtual training environments to supplement the live exercises enables the development of tools to support the instructors in their planning, management, observation and analysis of training exercises. This can simplify the planning process, and give instructors control over the configuration of the exercises to tailor them to the needs of individual trainees. In this paper we present a tool that supports instructors in the planning of virtual exercises, and can be used to provide templates for live exercises. This tool has been developed with ongoing feedback from instructors and crisis management personnel and forms part of a crisis management virtual training system. © 2012 ISCRAM.
|
Florian Vandecasteele, Krishna Kumar, Kenzo Milleville, & Steven Verstockt. (2019). Video Summarization And Video Highlight Selection Tools To Facilitate Fire Incident Management. In Z. Franco, J. J. González, & J. H. Canós (Eds.), Proceedings of the 16th International Conference on Information Systems for Crisis Response And Management. Valencia, Spain: Iscram.
Abstract: This paper reports on the added value of combining different types of sensor data and geographic information for fire incident management. A survey was launched within the Belgian fire community to explore the need of added value and the use of new types of sensor data during a fire incident. This evaluation revealed that people are visually-oriented and that video footages and images are of great value to gain insights in a particular problem. However, due to the limited available time (i.e., fast decisions need to be taken) and the large amount of cameras it is not feasible to analyze all video footages sequentially. To solve this problem we propose a video summarization mechanism and a video highlight selection tool based on the automatic generated image and video tags.
|
Giulio Palomba, Alessandro Farasin, & Claudio Rossi. (2020). Sentinel-1 Flood Delineation with Supervised Machine Learning. In Amanda Hughes, Fiona McNeill, & Christopher W. Zobel (Eds.), ISCRAM 2020 Conference Proceedings – 17th International Conference on Information Systems for Crisis Response and Management (pp. 1072–1083). Blacksburg, VA (USA): Virginia Tech.
Abstract: Floods are one of the major natural hazards in terms of affected people and economic damages. The increasing and often uncontrolled urban sprawl together with climate change effects will make future floods more frequent and impacting. An accurate flood mapping is of paramount importance in order to update hazard and risk maps and to plan prevention measures. In this paper, we propose the use of a supervised machine learning approach for flood delineation from satellite data. We train and evaluate the proposed algorithm using Sentinel-1 acquisition and certified flood delineation maps produced by the Copernicus Emergency Management Service across different geographical regions in Europe, achieving increased performances against previously proposed supervised machine learning approaches for flood mapping.
|
Gkika, I., Pattas, D., Konstantoudakis, K., & Zarpalas, D. (2023). Object detection and augmented reality annotations for increased situational awareness in light smoke conditions. In Jaziar Radianti, Ioannis Dokas, Nicolas Lalone, & Deepak Khazanchi (Eds.), Proceedings of the 20th International ISCRAM Conference (pp. 231–241). Omaha, USA: University of Nebraska at Omaha.
Abstract: Innovative technologies powered by Computer Vision algorithms can aid first responders, increasing their situ ational awareness. However, adverse conditions, such as smoke, can reduce the efficacy of such algorithms by degrading the input images. This paper presents a pipeline of image de-smoking, object detection, and augmented reality display that aims to enhance situational awareness in smoky conditions. A novel smoke-reducing deep learning algorithm is applied as a preprocessing step, before state-of-the-art object detection. The detected objects and persons are highlighted in the user’s augmented reality display. The proposed method is shown to increase detection accuracy and confidence. Testing in realistic environments provides an initial evaluation of the method, both in terms of image processing and of usefulness to first responders.
|
Grégoire Burel, & Harith Alani. (2018). Crisis Event Extraction Service (CREES) – Automatic Detection and Classification of Crisis-related Content on Social Media. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (pp. 597–608). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: Social media posts tend to provide valuable reports during crises. However, this information can be hidden in large amounts of unrelated documents. Providing tools that automatically identify relevant posts, event types (e.g., hurricane, floods, etc.) and information categories (e.g., reports on affected individuals, donations and volunteering, etc.) in social media posts is vital for their efficient handling and consumption. We introduce the Crisis Event Extraction Service (CREES), an open-source web API that automatically classifies posts during crisis situations. The API provides annotations for crisis-related documents, event types and information categories through an easily deployable and accessible web API that can be integrated into multiple platform and tools. The annotation service is backed by Convolutional Neural Networks (CNNs) and validated against traditional machine learning models. Results show that the CNN-based API results can be relied upon when dealing with specific crises with the benefits associated with the usage word embeddings.
|