Drones are increasingly being introduced to support healthcare delivery around the world. Most Drones for Health projects are currently in the pilot phase, where frontline staff are testing the feasibility of implementing drones into their healthcare system. Many of these projects are happening in remote localities where populations have been historically under-served within national healthcare systems. Currently, there exists limited drone-specific guidance on best practices for engaging individuals in decision-making about drone use in their communities. Towards supporting the development of such guidance, this paper focuses on the issue of obtaining community and individual consent for implementing Drones for Health projects. This paper is based on original qualitative research involving semi-structured interviews (N = 16) with program managers and implementation staff hired to work on health-related projects using drone technologies. In this paper, we introduce a scenario described by one participant to highlight the ethical and practical challenges associated with the implementation and use of drones for health-related purposes. We explore the ethical and practical complexities of obtaining informed consent from individuals who reside in communities where Drones for Health projects are implemented.

Unmanned aerial vehicles (UAVs), also known as drones, have significant potential in the healthcare field. Ethical and practical concerns, challenges, and complexities of using drones for specific and diverse healthcare purposes have been minimally explored to date. This paper aims to document and advance awareness of diverse context-specific concerns, challenges, and complexities encountered by individuals working on the front lines of drones for health. It draws on original qualitative research and data from semi-structured interviews (N = 16) with drones for health program managers and field staff in nine countries. Directed thematic analysis was used to analyze interviews and identify key ethical and practical concerns, challenges, and complexities experienced by participants in their work with drones for health projects. While some concerns, challenges, and complexities described by study participants were more technical in nature, for example, those related to drone technology and approval processes, the majority were not. The bulk of context-specific concerns and challenges identified by participants, we propose, could be mitigated through community engagement initiatives.

Efficient analysis of aerial imagery has great potential to assist in disaster response efforts. In this paper we develop methods based on active learning to detect objects of interest. We formulate an approach based on fine-tuning deep networks for object recognition based on labels obtained from a human user. We demonstrate that this approach can effectively adapt features to recognize objects in aerial images taken after a disaster strikes.

In response to the growing HIV/AIDS and other health-related issues, UNICEF through their U-Report platform receives thousands of messages (SMS) every day to provide prevention strategies, health case advice, and counsel- ing support to vulnerable population. Due to a rapid increase in U-Report usage (up to 300% in last 3 years), plus approximately 1,000 new registrations each day, the volume of messages has thus continued to increase, which made it impossible for the team at UNICEF to process them in a timely manner. In this paper, we present a platform designed to perform automatic classification of short messages (SMS) in real-time to help UNICEF categorize and prioritize health-related messages as they arrive. We employ a hybrid approach, which combines human and machine intelligence that seeks to resolve the information overload issue by introducing processing of large-scale data at high-speed while maintaining a high classification accuracy. The system has recently been tested in conjunction with UNICEF in Zambia to classify short messages received via the U-Report platform on various health related issues. The system is designed to enable UNICEF make sense of a large volume of short messages in a timely manner. In terms of evaluation, we report design choices, challenges, and performance of the system observed during the deployment to validate its effectiveness.

Crowdsourcing technologies represent a paradigm shift in the way certain tasks are performed. Linux, Wikipedia or OpenStreetMap represent massive achievements that are changing our access to open software technology, knowledge and geoservices. These changes have also reached humanitarian response in front of man-made or natural disasters: digital humanitarians (DH) are given the chance to remotely help out those in urgent need, by accomplishing thousands of microtasks that augment the information about the disaster for those who work on the ground. However, the organisers and designers of these complex technological platforms need also to consider how to achieve larger, better, faster humanitarian reaction; as well as how to build, expand and maintain a volunteer community. This paper studies the temporal and geographical patterns of past online humanitarian response, and attempts to find clues that optimize the potentialities of a DH platform. Our findings suggest that the volunteers are strongly committed to the tasks: their contributions are submitted at a very fast pace, and they contribute repeatedly over time; also, such contribution is heavily driven by mass media coverage of the disaster: an increase in the media coverage is closely followed by an increase in the volunteers response. On the geographic side, there are large asymmetries regarding the origin of contributions, with a clear skew towards English-speaking areas. All these analysis outcomes inform us about human activity temporal and temporal patterns in very specific, unexplored context-time-constrained task accomplishing; additionally, such outcomes should rigorously inform future humanitarian technologies, and associated activities. (C) 2016 The Authors. Published by Elsevier Ltd.

Aerial imagery captured via unmanned aerial vehicles (UAVs) is playing an increasingly important role in disaster response. Unlike satellite imagery, aerial imagery can be captured and processed within hours rather than days. In addition, the spatial resolution of aerial imagery is an order of magnitude higher than the imagery produced by the most sophisticated commercial satellites today. Both the United States Federal Emergency Management Agency (FEMA) and the European Commission's Joint Research Center (JRC) have noted that aerial imagery will inevitably present a big data challenge. The purpose of this article is to get ahead of this future challenge by proposing a hybrid crowdsourcing and real-time machine learning solution to rapidly process large volumes of aerial data for disaster response in a time-sensitive manner. Crowdsourcing can be used to annotate features of interest in aerial images (such as damaged shelters and roads blocked by debris). These human-annotated features can then be used to train a supervised machine learning system to learn to recognize such features in new unseen images. In this article, we describe how this hybrid solution for image analysis can be implemented as a module (i.e., Aerial Clicker) to extend an existing platform called Artificial Intelligence for Disaster Response (AIDR), which has already been deployed to classify microblog messages during disasters using its Text Clicker module and in response to Cyclone Pam, a category 5 cyclone that devastated Vanuatu in March 2015. The hybrid solution we present can be applied to both aerial and satellite imagery and has applications beyond disaster response such as wildlife protection, human rights, and archeological exploration. As a proof of concept, we recently piloted this solution using very high-resolution aerial photographs of a wildlife reserve in Namibia to support rangers with their wildlife conservation efforts (SAVMAP project, http://lasig.epfl.ch/savmap ). The results suggest that the platform we have developed to combine crowdsourcing and machine learning to make sense of large volumes of aerial images can be used for disaster response.

With the reactive nature of disaster relief efforts, the response time of NGO's and humanitarian organizations is critical. Organizations cannot predict the next crisis, nor can they build a catch all solution for any future problem. Consequently, the quicker a system is in place following a crisis, the more data can be collected to improve the relief efforts. Data is vital in assessing the severity of a crisis, informing organizations on how to prepare or give aid, and informing the community about an event. Mobile phones in general, and smartphones in particular, are an ideal tool for the collection of this valuable data.The development effort required to create smartphone applications is usually substantial. There are technical barriers to entry, and usually lengthy development times. Because of this, traditional mobile application development has been limited in its ability to help disaster relief. The Punya framework, presented in this paper, drastically shortens the development time required for Android applications, while supporting the communication and sensor features needed to acquire data during a crisis scenario. Punya's advanced sensor functionality, as well as its data capture and reporting components, allow organizations to build mobile applications quickly that can gather both user and context data as well as visualize results. (C) 2015 Published by Elsevier Ltd.

The overflow of information generated during disasters can be as paralyzing to humanitarian response as the lack of information. Making sense of this information--Big Data--is proving an impossible challenge for traditional humanitarian organizations, which is precisely why they're turning to Digital Humanitarians. This new humanitarians mobilize online to make sense of vast volumes of data--social media and text messages; satellite and aerial imagery--in direct support of relief efforts worldwide. How? They craft ingenious crowdsourcing solutions with trail-blazing insights from artificial intelligence. This book charts the spectacular rise of Digital Humanitarians, highlighting how their humanity coupled with innovative Big Data solutions is changing humanitarian relief for forever. Praise for the book: ...examines how new uses of technology and vast quantities of digital data are transforming the way societies prepare for, respond to, cope with, and ultimately understand humanitarian disasters. --Dr. Enzo Bollettino, Executive Director, The Harvard Humanitarian Initiative, Harvard University ...explains the strengths and potential weaknesses of using big data and crowdsourced analytics in crisis situations. It is at once a deeply personal and intellectually satisfying book.--Professor Steven Livingston, Professor of Media & Public and International Affairs, Elliott School of International Affairs, George Washington University

During sudden onset crisis events, the presence of spam, rumors and fake content on Twitter reduces the value of information contained on its messages (or "tweets"). A possible solution to this problem is to use machine learning to automatically evaluate the credibility of a tweet, i.e. whether a person would deem the tweet believable or trustworthy. This has been often framed and studied as a supervised classification problem in an off-line (post-hoc) setting.In this paper, we present a semi-supervised ranking model for scoring tweets according to their credibility. This model is used in TweetCred, a real-time system that assigns a credibility score to tweets in a user's timeline. TweetCred, available as a browser plug-in, was installed and used by 1,127 Twitter users within a span of three months. During this period, the credibility score for about 5.4 million tweets was computed, allowing us to evaluate TweetCred in terms of response time, effectiveness and usability. To the best of our knowledge, this is the first research work to develop a real-time system for credibility on Twitter, and to evaluate it on a user base of this size.

We present AIDR (Artificial Intelligence for Disaster Response), a platform designed to perform automatic classification of crisis-related microblog communications. AIDR enables humans and machines to work together to apply human intelligence to large-scale data at high speed. The objective of AIDR is to classify messages that people post during disasters into a set of user-defined categories of information (e.g., "needs", "damage", etc.) For this purpose, the system continuously ingests data from Twitter, processes it (i.e., using machine learning classification techniques) and leverages human-participation (through crowdsourcing) in real-time. AIDR has been successfully tested to classify informative vs. non-informative tweets posted during the 2013 Pakistan Earthquake. Overall, we achieved a classification quality (measured using AUC) of 80%. AIDR is available at http://aidr.qcri.org/.

Disaster affected communities are increasingly turning to social media for communication and coordination. This includes reports on needs (demands) and offers (supplies) of resources required during emergency situations. Identifying and matching such requests with potential responders can substantially accelerate emergency relief efforts. Current work of disaster management agencies is labor intensive, and there is substantial interest in automated tools.We present machine–learning methods to automatically identify and match needs and offers communicated via social media for items and services such as shelter, money, clothing, etc. For instance, a message such as “we are coordinating a clothing/food drive for families affected by Hurricane Sandy. If you would like to donate, DM us” can be matched with a message such as “I got a bunch of clothes I’d like to donate to hurricane sandy victims. Anyone know where/how I can do that?” Compared to traditional search, our results can significantly improve the matchmaking efforts of disaster response agencies.

An emerging paradigm for the processing of data streams involves human and machine computation working together, allowing human intelligence to process large-scale data. We apply this approach to the classification of crisis-related messages in microblog streams. We begin by describing the platform AIDR (Artificial Intelligence for Disaster Response), which collects human annotations over time to create and maintain automatic supervised classifiers for social media messages. Next, we study two significant challenges in its design: (1) identifying which elements must be labeled by humans, and (2) determining when to ask for such annotations to be done. The first challenge is selecting the items to be labeled by crowdsourcing workers to maximize the productivity of their work. The second challenge is to schedule the work in order to reliably maintain high classification accuracy over time. We provide and validate answers to these challenges by extensive experimentation on realworld datasets.