Skip to main content

Über dieses Buch

This contributed volume discusses essential topics and the fundamentals for Big Data Emergency Management and primarily focusses on the application of Big Data for Emergency Management. It walks the reader through the state of the art, in different facets of the big disaster data field. This includes many elements that are important for these technologies to have real-world impact. This book brings together different computational techniques from: machine learning, communication network analysis, natural language processing, knowledge graphs, data mining, and information visualization, aiming at methods that are typically used for processing big emergency data. This book also provides authoritative insights and highlights valuable lessons by distinguished authors, who are leaders in this field.
Emergencies are severe, large-scale, non-routine events that disrupt the normal functioning of a community or a society, causing widespread and overwhelming losses and impacts. Emergency Management is the process of planning and taking actions to minimize the social and physical impact of emergencies and reduces the community’s vulnerability to the consequences of emergencies. Information exchange before, during and after the disaster periods can greatly reduce the losses caused by the emergency. This allows people to make better use of the available resources, such as relief materials and medical supplies. It also provides a channel through which reports on casualties and losses in each affected area, can be delivered expeditiously. Big Data-Driven Emergency Management refers to applying advanced data collection and analysis technologies to achieve more effective and responsive decision-making during emergencies.
Researchers, engineers and computer scientists working in Big Data Emergency Management, who need to deal with large and complex sets of data will want to purchase this book. Advanced-level students interested in data-driven emergency/crisis/disaster management will also want to purchase this book as a study guide.



Introduction to Emergency Management

The term emergency management is used in this book to encompass all of the activities carried out by the federal state and local agencies that are referred to as emergency services. These activities have the primary goal of managing hazards, risks, and emergencies of all types. The advances in information and communication technology have a profound impact on emergency management by making unprecedented volumes of data available to decision makers. This has resulted in new challenges related to an effective management of large volumes of data. In this chapter, we examine basic concepts of emergency management and provide its brief history.
Rajendra Akerkar, Minsung Hong

Big Data

The Internet of Things, crowdsourcing, social media, public authorities, and other sources generate bigger and bigger data sets. Big and open data offers many benefits for emergency management, but also pose new challenges. This chapter will review the sources of big data and their characteristics. We then discuss potential benefits of big data for emergency management along with the technological and the societal challenges it poses. We review central technologies for big-data storage and processing in general, before presenting the Spark big-data engine in more detail. Finally, we review ethical and societal threats that big data pose.
Andreas L. Opdahl, Vimala Nunavath

Learning Algorithms for Emergency Management

Machine learning techniques can help authorities and decision makers more accurately answer urgent questions. Machine learning can be used to refine strategies over time, getting smarter about planning and response. This chapter discusses the application of fundamental learning techniques to support the decision making processes for emergency management. The chapter also presents exercises based on the learning techniques using emergency relevant tweeter datasets.
Minsung Hong, Rajendra Akerkar

Knowledge Graphs and Natural-Language Processing

Emergency-relevant data comes in many varieties. It can be high volume and high velocity, and reaction times are critical, calling for efficient and powerful techniques for data analysis and management. Knowledge graphs represent data in a rich, flexible, and uniform way that is well matched with the needs of emergency management. They build on existing standards, resources, techniques, and tools for semantic data and computing. This chapter explains the most important semantic technologies and how they support knowledge graphs. We proceed to discuss their benefits and challenges and give examples of relevant semantic data sources and vocabularies. Natural-language texts—in particular those collected from social media such as Twitter—is a type of data source that poses particular analysis challenges. We therefore include an overview of techniques for processing natural-language texts.
Andreas L. Opdahl

Social Media Mining for Disaster Management and Community Resilience

Social media, mobile technologies, and Internet have become an integral part of our daily life. This chapter describes the role of social media during disasters as how platforms like Twitter and Facebook facilitate communication for both the public and response agencies during the time-critical events. Specifically, we introduce the concepts of social media mining for disaster events, provide the use-cases to mine social media for helping public and emergency services, and describe various methods of user, content, network, context, and visual analytics to process and analyze social media data for disaster management and community resilience.
Hemant Purohit, Steve Peterson

Big Data-Driven Citywide Human Mobility Modeling for Emergency Management

Human mobility modeling for emergency management plays an critical role in guaranteeing people safety and saving people’s life. However, many traditional methods for regular human mobility modeling fail on emergency management, because human mobility differs significantly from routines. In this chapter, we elaborate the challenges and review the state-of-the-art technologies to cope with the three fundamental tasks of human mobility modeling for emergency management: (1) Analyzing a rare event in the past, (2) Predicting the human mobility during a rare event, and (3) Simulating an imaginary rare event. In the end, we conclude with a summarization of this chapter and future directions on this topic.
Zipei Fan, Xuan Song, Ryosuke Shibasaki

Smartphone Based Emergency Communication

Emergency communication networks (ECNs) are designed to provide reliable communications under emergent scenarios. Recently, smartphone based networks have attracted remarkable attentions on the management of ECNs. In this topic, we first review the state-of-the-art research efforts devoted to the establishment and management of smartphone based ECNs. The related key techniques and their significant roles for disaster-relief in ECNs are discussed. We also present several real-world applications and case studies. Finally, we summarize the open issues and future research directions.
Huawei Huang, Song Guo

Emergency Information Visualisation

In data-intensive decision making, how to visualize huge, multi-dimension data become an important challenge. In an emergency situation, providing timely information is critical for efficient search and rescue operations. This chapter aims to give an understanding in how information can be designed and presented to give efficient and effective knowledge transfer and decision making. The focus of this chapter is on providing essential comprehension about visualising emergency information. The chapter presents visualisation design objectives and summarises various visualising techniques for content-based, geospatial, and temporal information along with specifics of dashboards. The chapter further introduces some pertinent research issues and finally provides some exercises.
Hoang Long Nguyen, Rajendra Akerkar
Weitere Informationen